system

Abstract

Provide a system. [Solution] means for receiving text data entered by a user; A means for analyzing the received text data using natural language processing technology; A means of correcting and refining the text data based on the analysis results; A means of returning modified and refined text data to the user; 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] Describe the "problem to be solved" and "means for solving the problem."

[0005] When creating text, manually correcting grammatical errors and expressions requires time and effort. This is particularly true for specialized texts or high-quality content, where the quality of the text may decline if the user lacks the necessary knowledge and skills. Furthermore, refining text requires advanced natural language processing technology, which is not practical for users to use directly. Therefore, a system that allows users to easily create high-quality text is needed. [Means for solving the problem]

[0006] This invention provides a system that includes a means for receiving text data entered by a user, a means for analyzing the received text data using natural language processing technology, a means for correcting and refining the text data based on the analysis results, and a means for returning the corrected and refined text data to the user. This system allows users to quickly generate high-quality sentences without much effort. Specifically, the system includes a means for tokenizing the text data and tagging it with parts of speech, as well as a means for correcting grammatical structure, correcting typos, and selecting appropriate vocabulary based on the analysis results. This allows users to create sentences that are natural and free of errors.

[0007] Understood. Below are definitions of important terms included in the claims.

[0008] "User" means an individual or legal entity that uses the System to input and edit documents.

[0009] "Text data" refers to a character string entered by a user, and is an element that constitutes the content of a sentence.

[0010] The "means for receiving" refers to a mechanism that includes a method for transmitting text data entered by a user to a server via a web application or a standalone application.

[0011] The "means of analysis" refers to a method of evaluating and identifying the grammatical structure, vocabulary selection, punctuation placement, etc. of the received text data using natural language processing technology.

[0012] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate human language, and includes, for example, tokenization, part-of-speech tagging, and dependency structure analysis.

[0013] "Methods of correction and refinement" are methods of correcting the grammatical structure of text data based on the analysis results, correcting typos, and selecting appropriate vocabulary.

[0014] The "means of returning" is a mechanism for returning the corrected and refined text data to the user's terminal so that the user can check the results.

[0015] "Tokenization" is the process of breaking down the words and phrases that make up a sentence into individual units (tokens).

[0016] "Part-of-speech tagging" is the process of tagging each word in a sentence with its part of speech (e.g., noun, verb, adjective, etc.). [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, and finally returns it to the user. This section explains the program for realizing this system and its operation.

[0039] System configuration

[0040] The system mainly includes the following components:

[0041] 1. User Interface

[0042] It provides an interface for users to enter text data, and can be implemented as a web application or a standalone application.

[0043] 2. Server Receiving Method

[0044] The server receives the text data entered by the user using an HTTP POST request.

[0045] 3. Natural Language Processing Methods

[0046] The server analyzes the received text data using natural language processing techniques, such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0047] 4. Correction / refinement measures

[0048] The server then uses the analysis results to make grammatical corrections and select vocabulary, for example, correcting typos, improving grammatical structures, and replacing them with appropriate vocabulary.

[0049] 5. Return Method

[0050] The server returns the corrected and refined text data to the user, who can review it and make further corrections if necessary.

[0051] Program processing

[0052] The system program operates as follows.

[0053] 1. User input:

[0054] A user uses the terminal to enter text data into the interface, for example, "This project is very important to me."

[0055] 2. Receiving text data:

[0056] The server receives the text data entered by the user and processes it in JSON format, which is used as input data for analysis.

[0057] 3. Text data analysis:

[0058] The server analyzes the received text data using natural language processing technology. First, it divides the text into tokens and tags each token with a part of speech. Then it analyzes dependencies to understand the grammatical structure.

[0059] 4. Correcting and refining text data:

[0060] The server uses the analysis results to correct the grammatical structure of the input text data and perform lexical substitutions as necessary, for example, replacing "very" with "extremely."

[0061] 5. Corrected and refined text data return:

[0062] The server returns the corrected and refined text data to the user, who can review it and make further corrections if necessary.

[0063] Specific examples

[0064] For example, consider the case where a user enters "This project is very important to me."

[0065] 1. The user enters text into the interface.

[0066] 2. The server receives this input and stores it in JSON format.

[0067] 3. The server uses natural language processing technology to tokenize the input text, dividing it into "this project is very important to me," "is," and "is." It then tags each token with a part of speech tag and analyzes dependencies.

[0068] 4. The server makes corrections, such as replacing "very" with "extremely," and checks for grammatical errors.

[0069] 5. The revised and refined text "This project is extremely important to me" is sent back to the user.

[0070] In this way, the present invention provides a system that allows users to easily create high-quality text.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] A user uses a terminal to enter text data into an interface, for example, "This project is very important to me."

[0074] Step 2:

[0075] The device sends the text data entered by the user to the server via an HTTP POST request.

[0076] Step 3:

[0077] The server receives text data from the user in JSON format, which is then stored in internal memory for analysis.

[0078] Step 4:

[0079] The server uses natural language processing technology to analyze the received text data. First, it divides the text data into tokens (tokenization).

[0080] Step 5:

[0081] The server tags each token with a part-of-speech tag, which identifies whether each word belongs to a noun, verb, adjective, etc.

[0082] Step 6:

[0083] The server performs dependency analysis, identifying how words in a sentence are related and figuring out grammatical structure.

[0084] Step 7:

[0085] The server then corrects and refines the text data based on the analysis results, for example, replacing the word "very" with "extremely" or correcting grammatical errors.

[0086] Step 8:

[0087] The server generates the final corrected and refined text data, which is then ready to be sent back to the user.

[0088] Step 9:

[0089] The server returns the modified and refined text data in JSON format to the user's device as an HTTP response.

[0090] Step 10:

[0091] The user can check the returned text data on the terminal and make additional corrections as necessary.

[0092] In this way, the server performs a series of processes to analyze the input text data, correct and refine it, and then return it to the user.

[0093] Example 1

[0094] 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."

[0095] Conventional text data correction systems often lack sufficient accuracy and automation in correcting grammatical errors and selecting vocabulary in user-entered text data, resulting in the burden of having to manually correct the data. Furthermore, the accuracy of the analysis of the input text data and the correction algorithms are insufficient, and in some cases, the system fails to make appropriate corrections.

[0096] 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.

[0097] In this invention, the server includes means for receiving text data entered by a user, means for analyzing the received text data using natural language processing technology, and means for correcting and refining the text data based on the analysis results, thereby enabling automatic correction and refinement of grammatical errors and vocabulary selection in the text data entered by a user with high accuracy.

[0098] "User" means a user who uses the System to input text data and receive corrected and refined text data.

[0099] A "server" is a device or system that receives text data entered by a user and analyzes, modifies, and refines it using natural language processing techniques.

[0100] "Text data" refers to character string information that a user inputs into a system, such as sentences or documents that require grammar and vocabulary correction.

[0101] "Natural language processing technology" refers to the general technology of processing and analyzing human language using a computer, including tokenization, part-of-speech tagging, dependency analysis, etc.

[0102] "Tokenization" is the process of dividing input text data into the smallest meaningful units.

[0103] "Part-of-speech tagging" is the process of assigning each segmented token its linguistic category (noun, verb, adjective, etc.).

[0104] "Analysis results" refers to data obtained through analysis using natural language processing technology, i.e., the results of tokenization, part-of-speech tagging, and dependency analysis.

[0105] "Revising and refining" is the process of using the analysis results to improve grammatical structure, correct typos, and change to appropriate vocabulary, making the text more accurate and understandable.

[0106] A "web application" is software used over the Internet that provides functionality to users via a browser.

[0107] A "standalone application" is software that functions independently and does not require an internet connection.

[0108] A "prompt" is a sentence that the system outputs to the user as an instruction or guide, especially to prompt the user to confirm corrected or refined text.

[0109] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, and finally returns it to the user. This section describes the program for realizing this system and its details.

[0110] System configuration

[0111] The system includes the following main components:

[0112] 1. User Interface

[0113] It provides an interface for users to enter text data. The interface can be implemented as a web application or a standalone application. A user accesses a web page through a browser, enters text into a text box, and clicks a submit button.

[0114] 2. Server Receiving Method

[0115] The server receives text data entered by the user. The data is received through an HTTP POST request and processed in JSON format. For example, if the user enters "This project is very important to me" and submits it, the data is sent to the server.

[0116] 3. Natural Language Processing Methods

[0117] The server analyzes the received text data using natural language processing technology. For this analysis, it uses spaCy, an open-source natural language processing library. First, it divides the text into tokens, tags each token with a part of speech tag, and analyzes dependencies.

[0118] 4. Correction / refinement measures

[0119] Based on the analysis results, the server makes grammatical corrections and selects vocabulary for the input text data. For example, it replaces the word "very" with "extremely," correcting it to a more appropriate expression while preserving the meaning.

[0120] 5. Return Method

[0121] The server sends the corrected and refined text data back to the user, again via an HTTP response, and the user sees the corrected text in their browser. For example, the corrected text "This project is extremely important to me" is sent back to the user.

[0122] Specific examples

[0123] Here are some examples:

[0124] When a user types "This project is very important to me" into the interface and clicks the submit button, the following happens:

[0125] 1. The user enters text into the interface

[0126] The user types "This project is very important to me" in the text box and clicks the submit button.

[0127] 2. The server receives

[0128] The server receives this input via an HTTP POST request and processes it in JSON format.

[0129] 3. The server analyzes the data

[0130] The server uses the natural language processing library spaCy to tokenize the text data, tag it with part-of-speech tags, and analyze dependencies. "This project is very important to me," "this project is very important to me," and "this project is very important to me" are analyzed.

[0131] 4. Server fixes and refines

[0132] Based on the analysis results, the server makes corrections such as replacing "very" with "extremely" and checks for grammatical errors.

[0133] 5. The server responds

[0134] The server sends the revised and refined text "This project is extremely important to me" back to the user.

[0135] Examples of prompt statements

[0136] Here are some example prompts to input to the generative AI model:

[0137] Analyze "This project is very important to me" and revise it to make it more grammatically correct and appropriate.

[0138] In this way, the present invention provides a system that allows users to easily create high-quality sentences, thereby solving the problems of conventional grammatical structures and vocabulary selection, and ultimately realizing a system that is easy for users to use.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1:

[0141] User input of text

[0142] A user uses a terminal to input text data into an interface. For example, a user opens a web application and types, "This project is very important to me." This is done by typing the sentence into a text box on a browser and clicking a "Submit" button.

[0143] Input: Text data entered by the user

[0144] Output: Text data is sent from the user's device to the server.

[0145] Step 2:

[0146] Receiving text data

[0147] The server receives the text data entered by the user via an HTTP POST request, with the data sent in JSON format, and prepares the data for analysis.

[0148] Input: Text data sent from the user's device (JSON format)

[0149] Output: Stores the text data received by the server in an internal variable.

[0150] Specific behavior: Receives an HTTP POST request and parses the payload as text data.

[0151] Step 3:

[0152] Text data analysis

[0153] The server analyzes the received text data using the natural language processing library spaCy. The server divides the input sentence into tokens and tags each token with a part of speech tag. It then analyzes dependencies to understand the grammatical structure.

[0154] Input: Received text data

[0155] Output: Tokenized data, its part-of-speech tagging results, and dependency analysis results

[0156] Specific operation: Text data is passed to spaCy for analysis, tokenization, part-of-speech tagging, and dependency analysis.

[0157] Step 4:

[0158] Correcting and refining text data

[0159] Based on the analysis results, the server corrects the grammatical structure of the input text data and performs vocabulary replacement as necessary. For example, it replaces "very" with "extremely." During this process, it checks for grammatical errors and corrects them to appropriate expressions.

[0160] Input: Parsed text data, token and part-of-speech tag information, dependencies

[0161] Output: Corrected and refined text data

[0162] Specific operation: Based on the analysis results, grammatical structure correction and vocabulary replacement are performed.

[0163] Step 5:

[0164] Corrected and refined text data return

[0165] The server returns the corrected and refined text data to the user via an HTTP response, where the user can view the corrected text in their browser and make further edits if necessary.

[0166] Input: Corrected and refined text data

[0167] Output: Modified and refined text data that is displayed in the user's browser.

[0168] Specific operation: The corrected text data is returned to the user in JSON format as an HTTP response.

[0169] These are the specific processing steps of the system program, which allows the text data entered by the user to be corrected and refined with high precision and returned to the user.

[0170] (Application example 1)

[0171] 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."

[0172] While conventional text input assistance systems can correct grammatical errors and spelling mistakes in the text entered by the user, they have difficulty generating new text to improve the quality of the content or rewriting it into more natural and fluent sentences. Furthermore, the generated text often does not match the user's intention, which increases the user's workload.

[0173] 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.

[0174] In this invention, the server includes means for receiving text data entered by a user, means for analyzing the received text data using natural language processing technology, means for correcting and refining the text data based on the analysis results, and means for generating corrected and refined text data using a new text generation model. This enables the server to convert the text entered by the user into high-quality, natural-sounding sentences and generate sentences that meet the user's intentions.

[0175] "Text data entered by the user"

[0176] Refers to the string data that the user provides to the system through the interface.

[0177] "Natural language processing technology"

[0178] It refers to a computational technique for analyzing input text data and extracting meaning, and includes tokenization, part-of-speech tagging, dependency structure analysis, etc.

[0179] "Means of correction and refinement"

[0180] This refers to a means of improving the quality of received and analyzed text data by making grammatical corrections and substituting appropriate words.

[0181] "Means to return"

[0182] A mechanism for sending modified and refined text data back to the user, usually with the ability to send the data over a network.

[0183] "New text generation model"

[0184] Refers to algorithms and techniques that use generative AI models to generate new text based on user-entered text data.

[0185] "Prompt Statement"

[0186] Refers to the initial text or instructions that are input to a new text generation model, based on which the model generates new text.

[0187] The present invention relates to a system that receives text data entered by a user, analyzes, corrects, and refines it using natural language processing techniques and a new text generation model, and returns the results to the user.

[0188] System configuration

[0189] The system of the present invention mainly comprises the following components:

[0190] 1. User Interface

[0191] This is an interface for users to input text data. The interface is implemented as a smartphone application, and users can input sentences in a text field.

[0192] 2. Server Receiving Method

[0193] The server receives the text data entered by the user using an HTTP POST request.

[0194] 3. Natural Language Processing Methods

[0195] The server analyzes the received text data using natural language processing techniques, such as tokenization, part-of-speech tagging, and dependency structure analysis. Software such as SpaCy and transformers are used for this purpose.

[0196] 4. Correction / refinement measures

[0197] The server then uses the analysis results to make grammatical corrections and select vocabulary, for example, correcting typos, improving grammatical structures, and replacing them with appropriate vocabulary.

[0198] 5. Generation method using a new text generation model

[0199] The server uses the revised and refined text to generate more fluent and natural-sounding sentences using a new text generation model, the generative AI model GPT-2.

[0200] 6. Return Method

[0201] The server sends the modified and refined text back to the user, which is then displayed on the application screen along with the original text entered by the user.

[0202] Program processing overview

[0203] The system's program works as follows: A user inputs text data using a smartphone application, and the text is sent to the server. The server uses SpaCy to tokenize the text and tag it with parts of speech. It then uses GPT-2 to perform grammatical corrections and vocabulary refinement, generating new text. The new text is then sent back to the user and displayed on the application screen.

[0204] Specific examples

[0205] As a concrete example, the following prompt is input to the generative AI model to be used:

[0206] Example prompt sentence:

[0207] This project is very important to me.

[0208] Based on this prompt, the following sentence is generated as new text:

[0209] This project is extremely important to me and I want it to be a success.

[0210] In this way, the present invention provides a system that converts text data entered by a user into high-quality, natural-sounding sentences and returns them to the user, allowing the user to receive the text in a more refined form and enabling efficient sentence creation.

[0211] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0212] Step 1:

[0213] The user inputs text data.

[0214] A user inputs a sentence into a text field through a smartphone application. At this point, the input is raw text data, such as a string of characters like "This project is very important to me."

[0215] Step 2:

[0216] The text data entered by the user is sent to the server.

[0217] The terminal sends the entered text data in JSON format to the server using an HTTP POST request. At this point, the input is the text entered by the user, and the output is the JSON data sent to the server.

[0218] Step 3:

[0219] The server receives the text data.

[0220] The server receives the HTTP POST request, extracts the text data, and begins processing it. At this point, the input is JSON data, and the output is text data that is processed within the server.

[0221] Step 4:

[0222] The server analyzes the text data using natural language processing technology.

[0223] The server uses SpaCy to tokenize the received text data and tag it with part-of-speech tags. Specifically, it divides the text into words and assigns part-of-speech information to each word. At this point, the input is raw text data, and the output is tokens and their part-of-speech information.

[0224] Step 5:

[0225] The server performs grammatical corrections and vocabulary refinement based on the analyzed tokens and part-of-speech information.

[0226] Based on the analysis results, the server corrects typos, improves grammatical structures, and replaces them with appropriate vocabulary. At this point, the input is tokens and their part-of-speech information, and the output is corrected and refined text data.

[0227] Step 6:

[0228] The server inputs the modified and refined text into a new text generation model.

[0229] The server inputs the corrected and refined text as a prompt to the new text generation model, GPT-2. Specifically, the server inputs a prompt such as "This project is very important to me" to the generative AI model. At this point, the input is the corrected and refined text data, and the output is the prompt input to the generative AI model.

[0230] Step 7:

[0231] The server retrieves the newly generated text from the generative AI model.

[0232] The server gets the new text generated by the GPT-2 model. For example, the generated text might be "This project is extremely important to me and I want it to succeed." The input at this point is the prompt sentence, and the output is the new text generated.

[0233] Step 8:

[0234] The server sends the newly generated text back to the user.

[0235] The server returns the newly generated text in JSON format as a response to the user, who can then view the returned text on the application screen. At this point, the input is the newly generated text, and the output is the JSON data returned to the user.

[0236] Through this series of processes, users can receive high-quality, natural-sounding text converted from their input text.

[0237] 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.

[0238] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, combines it with an emotion engine that recognizes the user's emotions, and finally returns it to the user. This section explains the program for realizing this system and its operation.

[0239] System configuration

[0240] The system mainly includes the following components:

[0241] 1. User Interface

[0242] It provides an interface for users to enter text data, and can be implemented as a web application or a standalone application.

[0243] 2. Server Receiving Method

[0244] The server receives the text data entered by the user using an HTTP POST request.

[0245] 3. Natural Language Processing Methods

[0246] The server analyzes the received text data using natural language processing techniques, such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0247] 4. Emotion Engine

[0248] The server is equipped with an engine for recognizing user emotions from received text data. This emotion engine uses natural language processing technology to identify positive, negative, and neutral emotions from the text data.

[0249] 5. Correction / refinement measures

[0250] The server corrects and refines the text data based on the analysis and emotion recognition results, for example, correcting typos, improving grammatical structure, and replacing with appropriate vocabulary.

[0251] 6. Return Method

[0252] The server returns both the corrected and refined text data and the emotion recognition results to the user, who can review the returned data and make further corrections if necessary.

[0253] Program processing

[0254] The system program operates as follows.

[0255] 1. User input:

[0256] A user uses the terminal to enter text data into the interface, for example, "This project is very important to me."

[0257] 2. Receiving text data:

[0258] The server receives the text data entered by the user and processes it in JSON format, which is used as input data for analysis.

[0259] 3. Text data analysis:

[0260] The server analyzes the received text data using natural language processing technology. First, it divides the text into tokens and tags each token with a part of speech. Then it analyzes dependencies to understand the grammatical structure.

[0261] 4. User Emotion Recognition:

[0262] The server uses an emotion engine to recognize user emotions from text data. Specifically, it identifies positive, negative, and neutral emotions from the text. This emotion recognition result is used for the subsequent correction and refinement process.

[0263] 5. Correcting and refining text data:

[0264] Based on the analysis and emotion recognition results, the server corrects the grammatical structure of the input text data and performs lexical substitutions as necessary, for example, replacing "very" with "extremely."

[0265] 6. Corrected and refined text data return:

[0266] The server returns the corrected and refined text data and the user's emotion recognition results to the user device as an HTTP response.

[0267] 7. User Verification:

[0268] The user can check the returned text data and emotion recognition results on the device, and can make additional corrections as needed.

[0269] Specific examples

[0270] For example, consider the case where a user types "This project is very important to me." After receiving and analyzing this text, the emotion engine recognizes it as "positive." The server then replaces "very" with "extremely," performs corrections and refinements, and returns the final text "This project is extremely important to me" and the emotion recognition result of "positive" to the user.

[0271] In this way, the present invention provides a system that allows users to easily create high-quality text and also analyzes the emotions contained in the text.

[0272] The processing flow will be explained below.

[0273] Step 1:

[0274] A user uses a terminal to enter text data into an interface, for example, "This project is very important to me."

[0275] Step 2:

[0276] The device sends the text data entered by the user to the server via an HTTP POST request.

[0277] Step 3:

[0278] The server receives text data from the user in JSON format, which is then stored in internal memory for analysis.

[0279] Step 4:

[0280] The server uses natural language processing technology to analyze the received text data. First, it divides the text data into tokens (tokenization).

[0281] Step 5:

[0282] The server tags each token with a part-of-speech tag, which identifies whether each word belongs to a noun, verb, adjective, etc.

[0283] Step 6:

[0284] The server performs dependency analysis, identifying how words in a sentence are related and figuring out grammatical structure.

[0285] Step 7:

[0286] The server uses an emotion engine to recognize emotions from the received text data. Specifically, it analyzes the text data and identifies positive, negative, and neutral emotions.

[0287] Step 8:

[0288] The server corrects and refines the text data based on the analysis and emotion recognition results, for example, replacing the word "very" with "extremely" or correcting grammatical errors.

[0289] Step 9:

[0290] The server generates the final corrected and refined text data and emotion recognition results, which are then ready to be sent back to the user.

[0291] Step 10:

[0292] The server returns the corrected and refined text data and emotion recognition results in JSON format to the user device as an HTTP response.

[0293] Step 11:

[0294] The user can check the returned text data and emotion recognition results on the device, and can make additional corrections as needed.

[0295] In this way, the server performs a series of processes: analyzing the input text data, recognizing emotions, correcting and refining them, and then returning them to the user.

[0296] Example 2

[0297] 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."

[0298] Conventional systems can correct and refine text data entered by users, but it is difficult to recognize emotions contained in the text data and correct the text data based on those emotions. Furthermore, the accuracy of generating and correcting text that reflects emotions is not sufficient. This makes it difficult to generate high-quality sentences that can appropriately convey users' emotions.

[0299] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving text data input by a user, means for analyzing the received text data using natural language processing technology, means for recognizing emotions from the analyzed text data, means for correcting and refining the text data based on the recognized emotions, and means for returning the corrected and refined text data to the user. This makes it possible to accurately recognize emotions contained in text data input by a user and generate corrected and refined text data that reflects the emotions.

[0300] "Text data" refers to a collection of sentences or phrases entered by a user that are analyzed and corrected by the system.

[0301] "Natural language processing technology" refers to technology that enables computers to understand, interpret, and generate human language, and includes tokenization, part-of-speech tagging, grammatical analysis, dependency structure analysis, etc.

[0302] "Tokenization" is the process of dividing text data into its smallest units, such as words or phrases.

[0303] "Part-of-speech tagging" is the process of assigning each tokenized word or phrase its part of speech (noun, verb, adjective, etc.).

[0304] "Dependency structure analysis" is a process that analyzes the interrelationships between words in a sentence to understand its grammatical structure.

[0305] An "emotion engine" refers to an algorithm or software that recognizes emotions (positive, negative, neutral, etc.) from text data.

[0306] "Emotion recognition" is the process of identifying emotions contained in text data and classifying the emotional state.

[0307] "Correction and refinement" refers to the process of correcting typos in text data, improving grammatical structure, and replacing vocabulary with appropriate ones, in order to produce higher quality text.

[0308] "User Interface" refers to the operating screen through which a user inputs text data into the system and reviews the corrected and refined text data.

[0309] "Server" refers to the computer system that receives, analyzes, recognizes emotions, modifies and refines text data, and returns the data.

[0310] An "HTTP POST request" is part of a communication protocol for sending data from a user to a server, and is primarily used in web applications.

[0311] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and is a format for organizing data and expressing it simply and lightly.

[0312] MODE FOR CARRYING OUT THE INVENTION

[0313] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, combines it with an emotion engine that recognizes the user's emotions, and finally returns it to the user.

[0314] System configuration

[0315] The system mainly includes the following components:

[0316] 1. User Interface

[0317] It provides an interface for users to input text data. The interface can be implemented as a web application or a standalone application. For example, we will use an application that runs in a web browser.

[0318] 2. Server Receiving Method

[0319] The server receives the text data entered by the user. The method of reception is via HTTP POST request. This ensures that the server receives the data entered by the user.

[0320] 3. Natural Language Processing Methods

[0321] The server analyzes the received text data using natural language processing techniques, such as software like SpaCy or NLTK, to perform tokenization, part-of-speech tagging, and dependency structure analysis.

[0322] 4. Emotion Engine

[0323] The server is equipped with an engine to recognize user emotions from received text data. VADER and TextBlob are used as emotion engines. This allows us to identify positive, negative, and neutral emotions from text data.

[0324] 5. Correction / refinement measures

[0325] Based on the analysis and emotion recognition results, the server corrects the grammatical structure of the input text data and replaces vocabulary as necessary, for example, correcting typos and replacing vocabulary with more appropriate vocabulary.

[0326] 6. Return Method

[0327] The server returns the corrected and refined text data and emotion recognition results to the user via an HTTP response.

[0328] Specific examples of natural language processing

[0329] If the user enters "This project is very important to me," the system behaves as follows:

[0330] 1. User input

[0331] User: Enters the text "This project is very important to me" and presses submit.

[0332] 2. The server receives

[0333] Server: Receives HTTP POST requests from users and processes text data in JSON format.

[0334] 3. The server analyzes

[0335] Server: Uses SpaCy to tokenize and tag the text, then performs dependency analysis to understand the grammatical structure of the sentence.

[0336] 4. The server recognizes emotions

[0337] Server: Uses VADER to recognize the sentiment of the text data and classify it as "positive."

[0338] 5. Server fixes and refinements

[0339] Server: Based on the analysis results and emotion recognition results, replace "very" with "extremely" and make grammatical corrections.

[0340] 6. Server replies

[0341] Server: Returns the modified and refined text data "This project is extremely important to me" and the emotion recognition result "Positive" in the HTTP response.

[0342] Example prompts for generative AI models

[0343] The present invention also provides prompts for emotion recognition and text correction using generative AI models. For example, the following prompts can be used:

[0344] "Please perform a sentiment analysis on the following text: This project is very important to me."

[0345] By feeding this prompt sentence into a generative AI model, it is possible to obtain emotion recognition results and corrected / refined text.

[0346] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0347] Program processing flow

[0348] Step 1: User inputs text

[0349] Subject: User

[0350] Specific behavior:

[0351] The user uses the terminal to input text data into the interface screen, for example, "This project is very important to me."

[0352] The user clicks the "Submit" button to send the text data to the system.

[0353] input:

[0354] Input text data: "This project is very important to me"

[0355] output:

[0356] The send button is clicked and the text data is sent to the server.

[0357] Step 2: Receiving text data

[0358] Subject: Server

[0359] Specific behavior:

[0360] The server receives the text data entered by the user. This is received using an HTTP POST request.

[0361] input:

[0362] Text data sent via HTTP POST request: "This project is very important to me"

[0363] output:

[0364] The received text data is stored in JSON format for internal processing.

[0365] Step 3: Analyzing the text data

[0366] Subject: Server

[0367] Specific behavior:

[0368] The server analyzes the received text data using natural language processing software (e.g., SpaCy).

[0369] It splits text into tokens, tags each token with a part of speech, and then analyzes dependencies to understand grammatical structure.

[0370] input:

[0371] JSON text data: "This project is very important to me"

[0372] output:

[0373] Tokenized text data

[0374] Part-of-speech tagged data

[0375] Dependency structure analysis results

[0376] Step 4: Recognizing user emotions

[0377] Subject: Server

[0378] Specific behavior:

[0379] The server uses an emotion engine (e.g., VADER) to recognize the user's emotion from the text data.

[0380] The content of the text data is analyzed and a positive, negative, or neutral sentiment score is calculated.

[0381] input:

[0382] Analyzed text data (tokenization, part-of-speech tagging, dependency structure analysis results)

[0383] output:

[0384] Emotion recognition result (e.g., "positive")

[0385] Step 5: Correcting and refining the text data

[0386] Subject: Server

[0387] Specific behavior:

[0388] The server corrects and refines the text data based on the analysis and emotion recognition results.

[0389] The revisions include improving grammatical structure, correcting spelling errors, and substituting appropriate vocabulary, for example, replacing "very" with "extremely."

[0390] input:

[0391] Parsed text data

[0392] Emotion recognition results

[0393] output:

[0394] Corrected / Refined Text Data: "This project is extremely important to me."

[0395] Step 6: Returning the corrected and refined text data

[0396] Subject: Server

[0397] Specific behavior:

[0398] The server serializes the corrected and refined text data and emotion recognition results together into JSON format.

[0399] The server sends this data back as an HTTP response.

[0400] input:

[0401] Corrected and refined text data

[0402] Emotion recognition results

[0403] output:

[0404] JSON format data is returned as an HTTP response.

[0405] Step 7: Verify the user

[0406] Subject: User

[0407] Specific behavior:

[0408] The user checks the returned text data and emotion recognition results on the device's interface screen.

[0409] If necessary, the text data can be corrected again and sent again.

[0410] input:

[0411] Corrected and refined text data sent back to the device

[0412] Emotion recognition results

[0413] output:

[0414] The user checks the data, and if further corrections are required, the data is manipulated and resent.

[0415] (Application example 2)

[0416] 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."

[0417] Current content distribution services do not have a system that automatically analyzes the quality of text entered by users and the emotions contained in that text, and provides feedback. This makes it difficult for users to create high-quality text while taking emotions and content into consideration. This could result in a decline in user satisfaction and the quality of content on the platform as a whole.

[0418] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving text data entered by a user, means for analyzing the received text data using natural language processing technology, means for correcting and refining the text data based on the analysis results, and means for returning the corrected text data and emotion recognition results to the user. This enables the user to easily create high-quality text that takes into consideration emotions and content.

[0419] "User-input text data" refers to a sequence of characters or sentences that a user inputs into a system through an interface.

[0420] "Means for receiving" refers to the technology or device that allows the server to obtain the text data sent by the user.

[0421] "Natural language processing technology" is a technology that allows computers to analyze and understand natural language, which is human language.

[0422] "Means for analysis" refers to technology for analyzing received text data and identifying grammatical structure, meaning, sentiment, etc.

[0423] "Means of correction and refinement" refers to techniques for improving the grammar and content of text data based on the analysis results and arranging it into a more appropriate form.

[0424] "Emotion recognition result" is the result of identifying emotions (positive, negative, neutral, etc.) contained in text data.

[0425] "Returning means" refers to the technology used to send the corrected and refined text data and emotion recognition results to the user.

[0426] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, modifies and refines the text data based on the analysis results, recognizes the user's emotions using an emotion engine, and finally returns the modified and refined text data and the emotion recognition results to the user. This section describes the program for realizing this system and its operation.

[0427] System configuration

[0428] The system mainly includes the following components:

[0429] 1. User Interface:

[0430] Users input text data from devices such as smartphones and tablets, and the input data is sent to a server via a web application or a standalone application.

[0431] 2. Server receiving method:

[0432] The server receives text data sent by the user via an HTTP POST request, etc. The received text data is processed as input data for analysis.

[0433] 3. Natural Language Processing Tools:

[0434] The server analyzes the received text data using natural language processing techniques, specifically using Python's TextBlob library to tokenize the text, tag it as a part of speech, and analyze its grammatical structure.

[0435] 4. Emotion Engine:

[0436] The server uses TextBlob's NaiveBayesAnalyzer to recognize user sentiment from the parsed text data. This sentiment engine identifies positive, negative, and neutral sentiments in the text.

[0437] 5. Modification / refinement measures:

[0438] Based on the analysis and emotion recognition results, the server performs grammatical corrections, spelling corrections, and vocabulary optimization on the text data. For example, it corrects "This projekt iz verie important to me" to "This project is very important to me."

[0439] 6. Return Method:

[0440] The server returns the corrected and refined text data and emotion recognition results to the user as an HTTP response, and the user can view the returned data through the interface.

[0441] Detailed explanation of how it works

[0442] Below is a detailed explanation of how the system works.

[0443] 1. User input:

[0444] The user enters text data into the system through the terminal interface, for example, "This project is important to me."

[0445] 2. Receiving text data:

[0446] The server receives the text data entered by the user through the receiving means, and sends the received data to the server in JSON format or the like.

[0447] 3. Text data analysis:

[0448] The server uses natural language processing tools to analyze the received data. It processes the text using the TextBlob library, tagging each token with a part of speech tag and analyzing its grammatical structure.

[0449] 4. Emotion recognition:

[0450] The server uses an emotion engine to identify positive, negative, and neutral emotions from the text data. The emotion recognition results are used for the correction and refinement process.

[0451] 5. Correcting and refining text data:

[0452] The server performs grammatical corrections on the text data based on the analysis results and emotion recognition results, and performs vocabulary replacement as necessary.

[0453] 6. Corrected and refined text data return:

[0454] The server returns the corrected and refined text data and emotion recognition results to the user's device, which are displayed in the user's interface as an HTTP response.

[0455] Examples of concrete examples and prompts

[0456] For example, if a user types "This projekt iz verie important to me":

[0457] 1. The server receives the text.

[0458] 2. Analysis using natural language processing technology.

[0459] 3. Positive emotions and perceptions with the Emotion Engine.

[0460] 4. Revised to be grammatically correct: "This project is very important to me."

[0461] 5. Correct and refine the text and emotion recognition results and return them to the user.

[0462] Prompt Sentence Examples

[0463] text

[0464] User: This projekt iz verie impotant to me

[0465] System analysis results: This project is very important to me

[0466] Emotion recognition result: Positive

[0467] In this way, users can generate high-quality text and at the same time understand the sentiment contained in that text.

[0468] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0469] Step 1:

[0470] A user uses a terminal to input text data into the interface, for example, "This project is important to me." This input data is then prepared for transmission to the server. The input data is in text format.

[0471] Step 2:

[0472] The server receives text data entered by the user via an HTTP POST request. The received data is converted to JSON format and saved on the server as input data for analysis. Here, the input is text data from the user and the output is JSON format data.

[0473] Step 3:

[0474] The server uses the TextBlob library to analyze the received text data using natural language processing techniques. Specifically, it tokenizes the text and tags each token with a part of speech. It also performs dependency analysis to understand the grammatical structure. The input here is text data in JSON format, and the output is the analyzed tokens and part of speech tagging results.

[0475] Step 4:

[0476] The server uses TextBlob's NaiveBayesAnalyzer to recognize emotions from the parsed tokens. The emotion recognition result is identified as positive, negative, or neutral. The input is the parsed tokens and part-of-speech tagging results, and the output is the emotion recognition result.

[0477] Step 5:

[0478] The server integrates the analysis results and emotion recognition results to correct and refine the text data. Specifically, it corrects typos, corrects grammatical errors, and replaces words with appropriate vocabulary. For example, it corrects "projekt" to "project." The input here is the analysis results and emotion recognition results, and the output is the corrected and refined text data.

[0479] Step 6:

[0480] The server returns the corrected and refined text data and the emotion recognition results to the user. This is again done as an HTTP response. The returned data is displayed in the user interface, where the user can check the corrected text and the emotion recognition results. The input is the corrected and refined text data and the emotion recognition results, and the output is the data displayed in the user interface.

[0481] Step 7:

[0482] The user can review the returned corrected and refined text data and emotion recognition results and make additional corrections if necessary. If the user makes additional corrections, the process starts again from one of the steps. The input is the user's feedback, and the output is the final confirmed corrected text.

[0483] 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.

[0484] 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.

[0485] 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.

[0486] [Second embodiment]

[0487] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0488] 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.

[0489] 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).

[0490] 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.

[0491] 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.

[0492] 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).

[0493] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0494] 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.

[0495] 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.

[0496] 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.

[0497] 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.

[0498] 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."

[0499] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, and finally returns it to the user. This section explains the program for realizing this system and its operation.

[0500] System configuration

[0501] The system mainly includes the following components:

[0502] 1. User Interface

[0503] It provides an interface for users to enter text data, and can be implemented as a web application or a standalone application.

[0504] 2. Server Receiving Method

[0505] The server receives the text data entered by the user using an HTTP POST request.

[0506] 3. Natural Language Processing Methods

[0507] The server analyzes the received text data using natural language processing techniques, such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0508] 4. Correction / refinement measures

[0509] The server then uses the analysis results to make grammatical corrections and select vocabulary, for example, correcting typos, improving grammatical structures, and replacing them with appropriate vocabulary.

[0510] 5. Return Method

[0511] The server returns the corrected and refined text data to the user, who can review it and make further corrections if necessary.

[0512] Program processing

[0513] The system program operates as follows.

[0514] 1. User input:

[0515] A user uses the terminal to enter text data into the interface, for example, "This project is very important to me."

[0516] 2. Receiving text data:

[0517] The server receives the text data entered by the user and processes it in JSON format, which is used as input data for analysis.

[0518] 3. Text data analysis:

[0519] The server analyzes the received text data using natural language processing technology. First, it divides the text into tokens and tags each token with a part of speech. Then it analyzes dependencies to understand the grammatical structure.

[0520] 4. Correcting and refining text data:

[0521] The server uses the analysis results to correct the grammatical structure of the input text data and perform lexical substitutions as necessary, for example, replacing "very" with "extremely."

[0522] 5. Corrected and refined text data return:

[0523] The server returns the corrected and refined text data to the user, who can review it and make further corrections if necessary.

[0524] Specific examples

[0525] For example, consider the case where a user enters "This project is very important to me."

[0526] 1. The user enters text into the interface.

[0527] 2. The server receives this input and stores it in JSON format.

[0528] 3. The server uses natural language processing technology to tokenize the input text, dividing it into "this project is very important to me," "is," and "is." It then tags each token with a part of speech tag and analyzes dependencies.

[0529] 4. The server makes corrections, such as replacing "very" with "extremely," and checks for grammatical errors.

[0530] 5. The revised and refined text "This project is extremely important to me" is sent back to the user.

[0531] In this way, the present invention provides a system that allows users to easily create high-quality text.

[0532] The processing flow will be explained below.

[0533] Step 1:

[0534] A user uses a terminal to enter text data into an interface, for example, "This project is very important to me."

[0535] Step 2:

[0536] The device sends the text data entered by the user to the server via an HTTP POST request.

[0537] Step 3:

[0538] The server receives text data from the user in JSON format, which is then stored in internal memory for analysis.

[0539] Step 4:

[0540] The server uses natural language processing technology to analyze the received text data. First, it divides the text data into tokens (tokenization).

[0541] Step 5:

[0542] The server tags each token with a part-of-speech tag, which identifies whether each word belongs to a noun, verb, adjective, etc.

[0543] Step 6:

[0544] The server performs dependency analysis, identifying how words in a sentence are related and figuring out grammatical structure.

[0545] Step 7:

[0546] The server then corrects and refines the text data based on the analysis results, for example, replacing the word "very" with "extremely" or correcting grammatical errors.

[0547] Step 8:

[0548] The server generates the final corrected and refined text data, which is then ready to be sent back to the user.

[0549] Step 9:

[0550] The server returns the modified and refined text data in JSON format to the user's device as an HTTP response.

[0551] Step 10:

[0552] The user can check the returned text data on the terminal and make additional corrections as necessary.

[0553] In this way, the server performs a series of processes to analyze the input text data, correct and refine it, and then return it to the user.

[0554] Example 1

[0555] 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."

[0556] Conventional text data correction systems often lack sufficient accuracy and automation in correcting grammatical errors and selecting vocabulary in user-entered text data, resulting in the burden of having to manually correct the data. Furthermore, the accuracy of the analysis of the input text data and the correction algorithms are insufficient, and in some cases, the system fails to make appropriate corrections.

[0557] 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.

[0558] In this invention, the server includes means for receiving text data entered by a user, means for analyzing the received text data using natural language processing technology, and means for correcting and refining the text data based on the analysis results, thereby enabling automatic correction and refinement of grammatical errors and vocabulary selection in the text data entered by a user with high accuracy.

[0559] "User" means a user who uses the System to input text data and receive corrected and refined text data.

[0560] A "server" is a device or system that receives text data entered by a user and analyzes, modifies, and refines it using natural language processing techniques.

[0561] "Text data" refers to character string information that a user inputs into a system, such as sentences or documents that require grammar and vocabulary correction.

[0562] "Natural language processing technology" refers to the general technology of processing and analyzing human language using a computer, including tokenization, part-of-speech tagging, dependency analysis, etc.

[0563] "Tokenization" is the process of dividing input text data into the smallest meaningful units.

[0564] "Part-of-speech tagging" is the process of assigning each segmented token its linguistic category (noun, verb, adjective, etc.).

[0565] "Analysis results" refers to data obtained through analysis using natural language processing technology, i.e., the results of tokenization, part-of-speech tagging, and dependency analysis.

[0566] "Revising and refining" is the process of using the analysis results to improve grammatical structure, correct typos, and change to appropriate vocabulary, making the text more accurate and understandable.

[0567] A "web application" is software used over the Internet that provides functionality to users via a browser.

[0568] A "standalone application" is software that functions independently and does not require an internet connection.

[0569] A "prompt" is a sentence that the system outputs to the user as an instruction or guide, especially to prompt the user to confirm corrected or refined text.

[0570] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, and finally returns it to the user. This section describes the program for realizing this system and its details.

[0571] System configuration

[0572] The system includes the following main components:

[0573] 1. User Interface

[0574] It provides an interface for users to enter text data. The interface can be implemented as a web application or a standalone application. A user accesses a web page through a browser, enters text into a text box, and clicks a submit button.

[0575] 2. Server Receiving Method

[0576] The server receives text data entered by the user. The data is received through an HTTP POST request and processed in JSON format. For example, if the user enters "This project is very important to me" and submits it, the data is sent to the server.

[0577] 3. Natural Language Processing Methods

[0578] The server analyzes the received text data using natural language processing technology. For this analysis, it uses spaCy, an open-source natural language processing library. First, it divides the text into tokens, tags each token with a part of speech tag, and analyzes dependencies.

[0579] 4. Correction / refinement measures

[0580] Based on the analysis results, the server makes grammatical corrections and selects vocabulary for the input text data. For example, it replaces the word "very" with "extremely," correcting it to a more appropriate expression while preserving the meaning.

[0581] 5. Return Method

[0582] The server sends the corrected and refined text data back to the user, again via an HTTP response, and the user sees the corrected text in their browser. For example, the corrected text "This project is extremely important to me" is sent back to the user.

[0583] Specific examples

[0584] Here are some examples:

[0585] When a user types "This project is very important to me" into the interface and clicks the submit button, the following happens:

[0586] 1. The user enters text into the interface

[0587] The user types "This project is very important to me" in the text box and clicks the submit button.

[0588] 2. The server receives

[0589] The server receives this input via an HTTP POST request and processes it in JSON format.

[0590] 3. The server analyzes the data

[0591] The server uses the natural language processing library spaCy to tokenize the text data, tag it with part-of-speech tags, and analyze dependencies. "This project is very important to me," "this project is very important to me," and "this project is very important to me" are analyzed.

[0592] 4. Server fixes and refines

[0593] Based on the analysis results, the server makes corrections such as replacing "very" with "extremely" and checks for grammatical errors.

[0594] 5. The server responds

[0595] The server sends the revised and refined text "This project is extremely important to me" back to the user.

[0596] Examples of prompt statements

[0597] Here are some example prompts to input to the generative AI model:

[0598] Analyze "This project is very important to me" and revise it to make it more grammatically correct and appropriate.

[0599] In this way, the present invention provides a system that allows users to easily create high-quality sentences, thereby solving the problems of conventional grammatical structures and vocabulary selection, and ultimately realizing a system that is easy for users to use.

[0600] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0601] Step 1:

[0602] User input of text

[0603] A user uses a terminal to input text data into an interface. For example, a user opens a web application and types, "This project is very important to me." This is done by typing the sentence into a text box on a browser and clicking a "Submit" button.

[0604] Input: Text data entered by the user

[0605] Output: Text data is sent from the user's device to the server.

[0606] Step 2:

[0607] Receiving text data

[0608] The server receives the text data entered by the user via an HTTP POST request, with the data sent in JSON format, and prepares the data for analysis.

[0609] Input: Text data sent from the user's device (JSON format)

[0610] Output: Stores the text data received by the server in an internal variable.

[0611] Specific behavior: Receives an HTTP POST request and parses the payload as text data.

[0612] Step 3:

[0613] Text data analysis

[0614] The server analyzes the received text data using the natural language processing library spaCy. The server divides the input sentence into tokens and tags each token with a part of speech tag. It then analyzes dependencies to understand the grammatical structure.

[0615] Input: Received text data

[0616] Output: Tokenized data, its part-of-speech tagging results, and dependency analysis results

[0617] Specific operation: Text data is passed to spaCy for analysis, tokenization, part-of-speech tagging, and dependency analysis.

[0618] Step 4:

[0619] Correcting and refining text data

[0620] Based on the analysis results, the server corrects the grammatical structure of the input text data and performs vocabulary replacement as necessary. For example, it replaces "very" with "extremely." During this process, it checks for grammatical errors and corrects them to appropriate expressions.

[0621] Input: Parsed text data, token and part-of-speech tag information, dependencies

[0622] Output: Corrected and refined text data

[0623] Specific operation: Based on the analysis results, grammatical structure correction and vocabulary replacement are performed.

[0624] Step 5:

[0625] Corrected and refined text data return

[0626] The server returns the corrected and refined text data to the user via an HTTP response, where the user can view the corrected text in their browser and make further edits if necessary.

[0627] Input: Corrected and refined text data

[0628] Output: Modified and refined text data that is displayed in the user's browser.

[0629] Specific operation: The corrected text data is returned to the user in JSON format as an HTTP response.

[0630] These are the specific processing steps of the system program, which allows the text data entered by the user to be corrected and refined with high precision and returned to the user.

[0631] (Application example 1)

[0632] 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."

[0633] While conventional text input assistance systems can correct grammatical errors and spelling mistakes in the text entered by the user, they have difficulty generating new text to improve the quality of the content or rewriting it into more natural and fluent sentences. Furthermore, the generated text often does not match the user's intention, which increases the user's workload.

[0634] 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.

[0635] In this invention, the server includes means for receiving text data entered by a user, means for analyzing the received text data using natural language processing technology, means for correcting and refining the text data based on the analysis results, and means for generating corrected and refined text data using a new text generation model. This enables the server to convert the text entered by the user into high-quality, natural-sounding sentences and generate sentences that meet the user's intentions.

[0636] "Text data entered by the user"

[0637] Refers to the string data that the user provides to the system through the interface.

[0638] "Natural language processing technology"

[0639] It refers to a computational technique for analyzing input text data and extracting meaning, and includes tokenization, part-of-speech tagging, dependency structure analysis, etc.

[0640] "Means of correction and refinement"

[0641] This refers to a means of improving the quality of received and analyzed text data by making grammatical corrections and substituting appropriate words.

[0642] "Means to return"

[0643] A mechanism for sending modified and refined text data back to the user, usually with the ability to send the data over a network.

[0644] "New text generation model"

[0645] Refers to algorithms and techniques that use generative AI models to generate new text based on user-entered text data.

[0646] "Prompt Statement"

[0647] Refers to the initial text or instructions that are input to a new text generation model, based on which the model generates new text.

[0648] The present invention relates to a system that receives text data entered by a user, analyzes, corrects, and refines it using natural language processing techniques and a new text generation model, and returns the results to the user.

[0649] System configuration

[0650] The system of the present invention mainly comprises the following components:

[0651] 1. User Interface

[0652] This is an interface for users to input text data. The interface is implemented as a smartphone application, and users can input sentences in a text field.

[0653] 2. Server Receiving Method

[0654] The server receives the text data entered by the user using an HTTP POST request.

[0655] 3. Natural Language Processing Methods

[0656] The server analyzes the received text data using natural language processing techniques, such as tokenization, part-of-speech tagging, and dependency structure analysis. Software such as SpaCy and transformers are used for this purpose.

[0657] 4. Correction / refinement measures

[0658] The server then uses the analysis results to make grammatical corrections and select vocabulary, for example, correcting typos, improving grammatical structures, and replacing them with appropriate vocabulary.

[0659] 5. Generation method using a new text generation model

[0660] The server uses the revised and refined text to generate more fluent and natural-sounding sentences using a new text generation model, the generative AI model GPT-2.

[0661] 6. Return Method

[0662] The server sends the modified and refined text back to the user, which is then displayed on the application screen along with the original text entered by the user.

[0663] Program processing overview

[0664] The system's program works as follows: A user inputs text data using a smartphone application, and the text is sent to the server. The server uses SpaCy to tokenize the text and tag it with parts of speech. It then uses GPT-2 to perform grammatical corrections and vocabulary refinement, generating new text. The new text is then sent back to the user and displayed on the application screen.

[0665] Specific examples

[0666] As a concrete example, the following prompt is input to the generative AI model to be used:

[0667] Example prompt sentence:

[0668] This project is very important to me.

[0669] Based on this prompt, the following sentence is generated as new text:

[0670] This project is extremely important to me and I want it to be a success.

[0671] In this way, the present invention provides a system that converts text data entered by a user into high-quality, natural-sounding sentences and returns them to the user, allowing the user to receive the text in a more refined form and enabling efficient sentence creation.

[0672] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0673] Step 1:

[0674] The user inputs text data.

[0675] A user inputs a sentence into a text field through a smartphone application. At this point, the input is raw text data, such as a string of characters like "This project is very important to me."

[0676] Step 2:

[0677] The text data entered by the user is sent to the server.

[0678] The terminal sends the entered text data in JSON format to the server using an HTTP POST request. At this point, the input is the text entered by the user, and the output is the JSON data sent to the server.

[0679] Step 3:

[0680] The server receives the text data.

[0681] The server receives the HTTP POST request, extracts the text data, and begins processing it. At this point, the input is JSON data, and the output is text data that is processed within the server.

[0682] Step 4:

[0683] The server analyzes the text data using natural language processing technology.

[0684] The server uses SpaCy to tokenize the received text data and tag it with part-of-speech tags. Specifically, it divides the text into words and assigns part-of-speech information to each word. At this point, the input is raw text data, and the output is tokens and their part-of-speech information.

[0685] Step 5:

[0686] The server performs grammatical corrections and vocabulary refinement based on the analyzed tokens and part-of-speech information.

[0687] Based on the analysis results, the server corrects typos, improves grammatical structures, and replaces them with appropriate vocabulary. At this point, the input is tokens and their part-of-speech information, and the output is corrected and refined text data.

[0688] Step 6:

[0689] The server inputs the modified and refined text into a new text generation model.

[0690] The server inputs the corrected and refined text as a prompt to the new text generation model, GPT-2. Specifically, the server inputs a prompt such as "This project is very important to me" to the generative AI model. At this point, the input is the corrected and refined text data, and the output is the prompt input to the generative AI model.

[0691] Step 7:

[0692] The server retrieves the newly generated text from the generative AI model.

[0693] The server gets the new text generated by the GPT-2 model. For example, the generated text might be "This project is extremely important to me and I want it to succeed." The input at this point is the prompt sentence, and the output is the new text generated.

[0694] Step 8:

[0695] The server sends the newly generated text back to the user.

[0696] The server returns the newly generated text in JSON format as a response to the user, who can then view the returned text on the application screen. At this point, the input is the newly generated text, and the output is the JSON data returned to the user.

[0697] Through this series of processes, users can receive high-quality, natural-sounding text converted from their input text.

[0698] 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.

[0699] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, combines it with an emotion engine that recognizes the user's emotions, and finally returns it to the user. This section explains the program for realizing this system and its operation.

[0700] System configuration

[0701] The system mainly includes the following components:

[0702] 1. User Interface

[0703] It provides an interface for users to enter text data, and can be implemented as a web application or a standalone application.

[0704] 2. Server Receiving Method

[0705] The server receives the text data entered by the user using an HTTP POST request.

[0706] 3. Natural Language Processing Methods

[0707] The server analyzes the received text data using natural language processing techniques, such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0708] 4. Emotion Engine

[0709] The server is equipped with an engine for recognizing user emotions from received text data. This emotion engine uses natural language processing technology to identify positive, negative, and neutral emotions from the text data.

[0710] 5. Correction / refinement measures

[0711] The server corrects and refines the text data based on the analysis and emotion recognition results, for example, correcting typos, improving grammatical structure, and replacing with appropriate vocabulary.

[0712] 6. Return Method

[0713] The server returns both the corrected and refined text data and the emotion recognition results to the user, who can review the returned data and make further corrections if necessary.

[0714] Program processing

[0715] The system program operates as follows.

[0716] 1. User input:

[0717] A user uses the terminal to enter text data into the interface, for example, "This project is very important to me."

[0718] 2. Receiving text data:

[0719] The server receives the text data entered by the user and processes it in JSON format, which is used as input data for analysis.

[0720] 3. Text data analysis:

[0721] The server analyzes the received text data using natural language processing technology. First, it divides the text into tokens and tags each token with a part of speech. Then it analyzes dependencies to understand the grammatical structure.

[0722] 4. User Emotion Recognition:

[0723] The server uses an emotion engine to recognize user emotions from text data. Specifically, it identifies positive, negative, and neutral emotions from the text. This emotion recognition result is used for the subsequent correction and refinement process.

[0724] 5. Correcting and refining text data:

[0725] Based on the analysis and emotion recognition results, the server corrects the grammatical structure of the input text data and performs lexical substitutions as necessary, for example, replacing "very" with "extremely."

[0726] 6. Corrected and refined text data return:

[0727] The server returns the corrected and refined text data and the user's emotion recognition results to the user device as an HTTP response.

[0728] 7. User Verification:

[0729] The user can check the returned text data and emotion recognition results on the device, and can make additional corrections as needed.

[0730] Specific examples

[0731] For example, consider the case where a user types "This project is very important to me." After receiving and analyzing this text, the emotion engine recognizes it as "positive." The server then replaces "very" with "extremely," performs corrections and refinements, and returns the final text "This project is extremely important to me" and the emotion recognition result of "positive" to the user.

[0732] In this way, the present invention provides a system that allows users to easily create high-quality text and also analyzes the emotions contained in the text.

[0733] The processing flow will be explained below.

[0734] Step 1:

[0735] A user uses a terminal to enter text data into an interface, for example, "This project is very important to me."

[0736] Step 2:

[0737] The device sends the text data entered by the user to the server via an HTTP POST request.

[0738] Step 3:

[0739] The server receives text data from the user in JSON format, which is then stored in internal memory for analysis.

[0740] Step 4:

[0741] The server uses natural language processing technology to analyze the received text data. First, it divides the text data into tokens (tokenization).

[0742] Step 5:

[0743] The server tags each token with a part-of-speech tag, which identifies whether each word belongs to a noun, verb, adjective, etc.

[0744] Step 6:

[0745] The server performs dependency analysis, identifying how words in a sentence are related and figuring out grammatical structure.

[0746] Step 7:

[0747] The server uses an emotion engine to recognize emotions from the received text data. Specifically, it analyzes the text data and identifies positive, negative, and neutral emotions.

[0748] Step 8:

[0749] The server corrects and refines the text data based on the analysis and emotion recognition results, for example, replacing the word "very" with "extremely" or correcting grammatical errors.

[0750] Step 9:

[0751] The server generates the final corrected and refined text data and emotion recognition results, which are then ready to be sent back to the user.

[0752] Step 10:

[0753] The server returns the corrected and refined text data and emotion recognition results in JSON format to the user device as an HTTP response.

[0754] Step 11:

[0755] The user can check the returned text data and emotion recognition results on the device, and can make additional corrections as needed.

[0756] In this way, the server performs a series of processes: analyzing the input text data, recognizing emotions, correcting and refining them, and then returning them to the user.

[0757] Example 2

[0758] 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."

[0759] Conventional systems can correct and refine text data entered by users, but it is difficult to recognize emotions contained in the text data and correct the text data based on those emotions. Furthermore, the accuracy of generating and correcting text that reflects emotions is not sufficient. This makes it difficult to generate high-quality sentences that can appropriately convey users' emotions.

[0760] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving text data input by a user, means for analyzing the received text data using natural language processing technology, means for recognizing emotions from the analyzed text data, means for correcting and refining the text data based on the recognized emotions, and means for returning the corrected and refined text data to the user. This makes it possible to accurately recognize emotions contained in text data input by a user and generate corrected and refined text data that reflects the emotions.

[0761] "Text data" refers to a collection of sentences or phrases entered by a user that are analyzed and corrected by the system.

[0762] "Natural language processing technology" refers to technology that enables computers to understand, interpret, and generate human language, and includes tokenization, part-of-speech tagging, grammatical analysis, dependency structure analysis, etc.

[0763] "Tokenization" is the process of dividing text data into its smallest units, such as words or phrases.

[0764] "Part-of-speech tagging" is the process of assigning each tokenized word or phrase its part of speech (noun, verb, adjective, etc.).

[0765] "Dependency structure analysis" is a process that analyzes the interrelationships between words in a sentence to understand its grammatical structure.

[0766] An "emotion engine" refers to an algorithm or software that recognizes emotions (positive, negative, neutral, etc.) from text data.

[0767] "Emotion recognition" is the process of identifying emotions contained in text data and classifying the emotional state.

[0768] "Correction and refinement" refers to the process of correcting typos in text data, improving grammatical structure, and replacing vocabulary with appropriate ones, in order to produce higher quality text.

[0769] "User Interface" refers to the operating screen through which a user inputs text data into the system and reviews the corrected and refined text data.

[0770] "Server" refers to the computer system that receives, analyzes, recognizes emotions, modifies and refines text data, and returns the data.

[0771] An "HTTP POST request" is part of a communication protocol for sending data from a user to a server, and is primarily used in web applications.

[0772] "JSON format" stands for JavaScript Object Notation, and is a format for organizing data and representing it simply and lightweight.

[0773] MODE FOR CARRYING OUT THE INVENTION

[0774] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, combines it with an emotion engine that recognizes the user's emotions, and finally returns it to the user.

[0775] System configuration

[0776] The system mainly includes the following components:

[0777] 1. User Interface

[0778] It provides an interface for users to input text data. The interface can be implemented as a web application or a standalone application. For example, we will use an application that runs in a web browser.

[0779] 2. Server Receiving Method

[0780] The server receives the text data entered by the user. The method of reception is via HTTP POST request. This ensures that the server receives the data entered by the user.

[0781] 3. Natural Language Processing Methods

[0782] The server analyzes the received text data using natural language processing techniques, such as software like SpaCy or NLTK, to perform tokenization, part-of-speech tagging, and dependency structure analysis.

[0783] 4. Emotion Engine

[0784] The server is equipped with an engine to recognize user emotions from received text data. VADER and TextBlob are used as emotion engines. This allows us to identify positive, negative, and neutral emotions from text data.

[0785] 5. Correction / refinement measures

[0786] Based on the analysis and emotion recognition results, the server corrects the grammatical structure of the input text data and replaces vocabulary as necessary, for example, correcting typos and replacing vocabulary with more appropriate vocabulary.

[0787] 6. Return Method

[0788] The server returns the corrected and refined text data and emotion recognition results to the user via an HTTP response.

[0789] Specific examples of natural language processing

[0790] If the user enters "This project is very important to me," the system behaves as follows:

[0791] 1. User input

[0792] User: Enters the text "This project is very important to me" and presses submit.

[0793] 2. The server receives

[0794] Server: Receives HTTP POST requests from users and processes text data in JSON format.

[0795] 3. The server analyzes

[0796] Server: Uses SpaCy to tokenize and tag the text, then performs dependency analysis to understand the grammatical structure of the sentence.

[0797] 4. The server recognizes emotions

[0798] Server: Uses VADER to recognize the sentiment of the text data and classify it as "positive."

[0799] 5. Server fixes and refinements

[0800] Server: Based on the analysis results and emotion recognition results, replace "very" with "extremely" and make grammatical corrections.

[0801] 6. Server replies

[0802] Server: Returns the modified and refined text data "This project is extremely important to me" and the emotion recognition result "Positive" in the HTTP response.

[0803] Example prompts for generative AI models

[0804] The present invention also provides prompts for emotion recognition and text correction using generative AI models. For example, the following prompts can be used:

[0805] "Please perform a sentiment analysis on the following text: This project is very important to me."

[0806] By feeding this prompt sentence into a generative AI model, it is possible to obtain emotion recognition results and corrected / refined text.

[0807] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0808] Program processing flow

[0809] Step 1: User inputs text

[0810] Subject: User

[0811] Specific behavior:

[0812] The user uses the terminal to input text data into the interface screen, for example, "This project is very important to me."

[0813] The user clicks the "Submit" button to send the text data to the system.

[0814] input:

[0815] Input text data: "This project is very important to me"

[0816] output:

[0817] The send button is clicked and the text data is sent to the server.

[0818] Step 2: Receiving text data

[0819] Subject: Server

[0820] Specific behavior:

[0821] The server receives the text data entered by the user. This is received using an HTTP POST request.

[0822] input:

[0823] Text data sent via HTTP POST request: "This project is very important to me"

[0824] output:

[0825] The received text data is stored in JSON format for internal processing.

[0826] Step 3: Analyzing the text data

[0827] Subject: Server

[0828] Specific behavior:

[0829] The server analyzes the received text data using natural language processing software (e.g., SpaCy).

[0830] It splits text into tokens, tags each token with a part of speech, and then analyzes dependencies to understand grammatical structure.

[0831] input:

[0832] JSON text data: "This project is very important to me"

[0833] output:

[0834] Tokenized text data

[0835] Part-of-speech tagged data

[0836] Dependency structure analysis results

[0837] Step 4: Recognizing user emotions

[0838] Subject: Server

[0839] Specific behavior:

[0840] The server uses an emotion engine (e.g., VADER) to recognize the user's emotion from the text data.

[0841] The content of the text data is analyzed and a positive, negative, or neutral sentiment score is calculated.

[0842] input:

[0843] Analyzed text data (tokenization, part-of-speech tagging, dependency structure analysis results)

[0844] output:

[0845] Emotion recognition result (e.g., "positive")

[0846] Step 5: Correcting and refining the text data

[0847] Subject: Server

[0848] Specific behavior:

[0849] The server corrects and refines the text data based on the analysis and emotion recognition results.

[0850] The revisions include improving grammatical structure, correcting spelling errors, and substituting appropriate vocabulary, for example, replacing "very" with "extremely."

[0851] input:

[0852] Parsed text data

[0853] Emotion recognition results

[0854] output:

[0855] Corrected / Refined Text Data: "This project is extremely important to me."

[0856] Step 6: Returning the corrected and refined text data

[0857] Subject: Server

[0858] Specific behavior:

[0859] The server serializes the corrected and refined text data and emotion recognition results together into JSON format.

[0860] The server sends this data back as an HTTP response.

[0861] input:

[0862] Corrected and refined text data

[0863] Emotion recognition results

[0864] output:

[0865] JSON format data is returned as an HTTP response.

[0866] Step 7: Verify the user

[0867] Subject: User

[0868] Specific behavior:

[0869] The user checks the returned text data and emotion recognition results on the device's interface screen.

[0870] If necessary, the text data can be corrected again and sent again.

[0871] input:

[0872] Corrected and refined text data sent back to the device

[0873] Emotion recognition results

[0874] output:

[0875] The user checks the data, and if further corrections are required, the data is manipulated and resent.

[0876] (Application example 2)

[0877] 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."

[0878] Current content distribution services do not have a system that automatically analyzes the quality of text entered by users and the emotions contained in that text, and provides feedback. This makes it difficult for users to create high-quality text while taking emotions and content into consideration. This could result in a decline in user satisfaction and the quality of content on the platform as a whole.

[0879] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving text data entered by a user, means for analyzing the received text data using natural language processing technology, means for correcting and refining the text data based on the analysis results, and means for returning the corrected text data and emotion recognition results to the user. This enables the user to easily create high-quality text that takes into consideration emotions and content.

[0880] "User-input text data" refers to a sequence of characters or sentences that a user inputs into a system through an interface.

[0881] "Means for receiving" refers to the technology or device that allows the server to obtain the text data sent by the user.

[0882] "Natural language processing technology" is a technology that allows computers to analyze and understand natural language, which is human language.

[0883] "Means for analysis" refers to technology for analyzing received text data and identifying grammatical structure, meaning, sentiment, etc.

[0884] "Means of correction and refinement" refers to techniques for improving the grammar and content of text data based on the analysis results and arranging it into a more appropriate form.

[0885] "Emotion recognition result" is the result of identifying emotions (positive, negative, neutral, etc.) contained in text data.

[0886] "Returning means" refers to the technology used to send the corrected and refined text data and emotion recognition results to the user.

[0887] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, modifies and refines the text data based on the analysis results, recognizes the user's emotions using an emotion engine, and finally returns the modified and refined text data and the emotion recognition results to the user. This section describes the program for realizing this system and its operation.

[0888] System configuration

[0889] The system mainly includes the following components:

[0890] 1. User Interface:

[0891] Users input text data from devices such as smartphones and tablets, and the input data is sent to a server via a web application or a standalone application.

[0892] 2. Server receiving method:

[0893] The server receives text data sent by the user via an HTTP POST request, etc. The received text data is processed as input data for analysis.

[0894] 3. Natural Language Processing Tools:

[0895] The server analyzes the received text data using natural language processing techniques, specifically using Python's TextBlob library to tokenize the text, tag it as a part of speech, and analyze its grammatical structure.

[0896] 4. Emotion Engine:

[0897] The server uses TextBlob's NaiveBayesAnalyzer to recognize user sentiment from the parsed text data. This sentiment engine identifies positive, negative, and neutral sentiments in the text.

[0898] 5. Modification / refinement measures:

[0899] Based on the analysis and emotion recognition results, the server performs grammatical corrections, spelling corrections, and vocabulary optimization on the text data. For example, it corrects "This projekt iz verie important to me" to "This project is very important to me."

[0900] 6. Return Method:

[0901] The server returns the corrected and refined text data and emotion recognition results to the user as an HTTP response, and the user can view the returned data through the interface.

[0902] Detailed explanation of how it works

[0903] Below is a detailed explanation of how the system works.

[0904] 1. User input:

[0905] The user enters text data into the system through the terminal interface, for example, "This project is important to me."

[0906] 2. Receiving text data:

[0907] The server receives the text data entered by the user through the receiving means, and sends the received data to the server in JSON format or the like.

[0908] 3. Text data analysis:

[0909] The server uses natural language processing tools to analyze the received data. It processes the text using the TextBlob library, tagging each token with a part of speech tag and analyzing its grammatical structure.

[0910] 4. Emotion recognition:

[0911] The server uses an emotion engine to identify positive, negative, and neutral emotions from the text data. The emotion recognition results are used for the correction and refinement process.

[0912] 5. Correcting and refining text data:

[0913] The server performs grammatical corrections on the text data based on the analysis results and emotion recognition results, and performs vocabulary replacement as necessary.

[0914] 6. Corrected and refined text data return:

[0915] The server returns the corrected and refined text data and emotion recognition results to the user's device, which are displayed in the user's interface as an HTTP response.

[0916] Examples of concrete examples and prompts

[0917] For example, if a user types "This projekt iz verie important to me":

[0918] 1. The server receives the text.

[0919] 2. Analysis using natural language processing technology.

[0920] 3. Positive emotions and perceptions with the Emotion Engine.

[0921] 4. Revised to be grammatically correct: "This project is very important to me."

[0922] 5. Correct and refine the text and emotion recognition results and return them to the user.

[0923] Prompt Sentence Examples

[0924] text

[0925] User: This projekt iz verie impotant to me

[0926] System analysis results: This project is very important to me

[0927] Emotion recognition result: Positive

[0928] In this way, users can generate high-quality text and at the same time understand the sentiment contained in that text.

[0929] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0930] Step 1:

[0931] A user uses a terminal to input text data into the interface, for example, "This project is important to me." This input data is then prepared for transmission to the server. The input data is in text format.

[0932] Step 2:

[0933] The server receives text data entered by the user via an HTTP POST request. The received data is converted to JSON format and saved on the server as input data for analysis. Here, the input is text data from the user and the output is JSON format data.

[0934] Step 3:

[0935] The server uses the TextBlob library to analyze the received text data using natural language processing techniques. Specifically, it tokenizes the text and tags each token with a part of speech. It also performs dependency analysis to understand the grammatical structure. The input here is text data in JSON format, and the output is the analyzed tokens and part of speech tagging results.

[0936] Step 4:

[0937] The server uses TextBlob's NaiveBayesAnalyzer to recognize emotions from the parsed tokens. The emotion recognition result is identified as positive, negative, or neutral. The input is the parsed tokens and part-of-speech tagging results, and the output is the emotion recognition result.

[0938] Step 5:

[0939] The server integrates the analysis results and emotion recognition results to correct and refine the text data. Specifically, it corrects typos, corrects grammatical errors, and replaces words with appropriate vocabulary. For example, it corrects "projekt" to "project." The input here is the analysis results and emotion recognition results, and the output is the corrected and refined text data.

[0940] Step 6:

[0941] The server returns the corrected and refined text data and the emotion recognition results to the user. This is again done as an HTTP response. The returned data is displayed in the user interface, where the user can check the corrected text and the emotion recognition results. The input is the corrected and refined text data and the emotion recognition results, and the output is the data displayed in the user interface.

[0942] Step 7:

[0943] The user can review the returned corrected and refined text data and emotion recognition results and make additional corrections if necessary. If the user makes additional corrections, the process starts again from one of the steps. The input is the user's feedback, and the output is the final confirmed corrected text.

[0944] 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.

[0945] 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.

[0946] 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.

[0947] [Third embodiment]

[0948] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0949] 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.

[0950] 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).

[0951] 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.

[0952] 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.

[0953] 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).

[0954] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0955] 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.

[0956] 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.

[0957] 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.

[0958] 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.

[0959] 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."

[0960] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, and finally returns it to the user. This section explains the program for realizing this system and its operation.

[0961] System configuration

[0962] The system mainly includes the following components:

[0963] 1. User Interface

[0964] It provides an interface for users to enter text data, and can be implemented as a web application or a standalone application.

[0965] 2. Server Receiving Method

[0966] The server receives the text data entered by the user using an HTTP POST request.

[0967] 3. Natural Language Processing Methods

[0968] The server analyzes the received text data using natural language processing techniques, such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0969] 4. Correction / refinement measures

[0970] The server then uses the analysis results to make grammatical corrections and select vocabulary, for example, correcting typos, improving grammatical structures, and replacing them with appropriate vocabulary.

[0971] 5. Return Method

[0972] The server returns the corrected and refined text data to the user, who can review it and make further corrections if necessary.

[0973] Program processing

[0974] The system program operates as follows.

[0975] 1. User input:

[0976] A user uses the terminal to enter text data into the interface, for example, "This project is very important to me."

[0977] 2. Receiving text data:

[0978] The server receives the text data entered by the user and processes it in JSON format, which is used as input data for analysis.

[0979] 3. Text data analysis:

[0980] The server analyzes the received text data using natural language processing technology. First, it divides the text into tokens and tags each token with a part of speech. Then it analyzes dependencies to understand the grammatical structure.

[0981] 4. Correcting and refining text data:

[0982] The server uses the analysis results to correct the grammatical structure of the input text data and perform lexical substitutions as necessary, for example, replacing "very" with "extremely."

[0983] 5. Corrected and refined text data return:

[0984] The server returns the corrected and refined text data to the user, who can review it and make further corrections if necessary.

[0985] Specific examples

[0986] For example, consider the case where a user enters "This project is very important to me."

[0987] 1. The user enters text into the interface.

[0988] 2. The server receives this input and stores it in JSON format.

[0989] 3. The server uses natural language processing technology to tokenize the input text, dividing it into "this project is very important to me," "is," and "is." It then tags each token with a part of speech tag and analyzes dependencies.

[0990] 4. The server makes corrections, such as replacing "very" with "extremely," and checks for grammatical errors.

[0991] 5. The revised and refined text "This project is extremely important to me" is sent back to the user.

[0992] In this way, the present invention provides a system that allows users to easily create high-quality text.

[0993] The processing flow will be explained below.

[0994] Step 1:

[0995] A user uses a terminal to enter text data into an interface, for example, "This project is very important to me."

[0996] Step 2:

[0997] The device sends the text data entered by the user to the server via an HTTP POST request.

[0998] Step 3:

[0999] The server receives text data from the user in JSON format, which is then stored in internal memory for analysis.

[1000] Step 4:

[1001] The server uses natural language processing technology to analyze the received text data. First, it divides the text data into tokens (tokenization).

[1002] Step 5:

[1003] The server tags each token with a part-of-speech tag, which identifies whether each word belongs to a noun, verb, adjective, etc.

[1004] Step 6:

[1005] The server performs dependency analysis, identifying how words in a sentence are related and figuring out grammatical structure.

[1006] Step 7:

[1007] The server then corrects and refines the text data based on the analysis results, for example, replacing the word "very" with "extremely" or correcting grammatical errors.

[1008] Step 8:

[1009] The server generates the final corrected and refined text data, which is then ready to be sent back to the user.

[1010] Step 9:

[1011] The server returns the modified and refined text data in JSON format to the user's device as an HTTP response.

[1012] Step 10:

[1013] The user can check the returned text data on the terminal and make additional corrections as necessary.

[1014] In this way, the server performs a series of processes to analyze the input text data, correct and refine it, and then return it to the user.

[1015] Example 1

[1016] 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."

[1017] Conventional text data correction systems often lack sufficient accuracy and automation in correcting grammatical errors and selecting vocabulary in user-entered text data, resulting in the burden of having to manually correct the data. Furthermore, the accuracy of the analysis of the input text data and the correction algorithms are insufficient, and in some cases, the system fails to make appropriate corrections.

[1018] 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.

[1019] In this invention, the server includes means for receiving text data entered by a user, means for analyzing the received text data using natural language processing technology, and means for correcting and refining the text data based on the analysis results, thereby enabling automatic correction and refinement of grammatical errors and vocabulary selection in the text data entered by a user with high accuracy.

[1020] "User" means a user who uses the System to input text data and receive corrected and refined text data.

[1021] A "server" is a device or system that receives text data entered by a user and analyzes, modifies, and refines it using natural language processing techniques.

[1022] "Text data" refers to character string information that a user inputs into a system, such as sentences or documents that require grammar and vocabulary correction.

[1023] "Natural language processing technology" refers to the general technology of processing and analyzing human language using a computer, including tokenization, part-of-speech tagging, dependency analysis, etc.

[1024] "Tokenization" is the process of dividing input text data into the smallest meaningful units.

[1025] "Part-of-speech tagging" is the process of assigning each segmented token its linguistic category (noun, verb, adjective, etc.).

[1026] "Analysis results" refers to data obtained through analysis using natural language processing technology, i.e., the results of tokenization, part-of-speech tagging, and dependency analysis.

[1027] "Revising and refining" is the process of using the analysis results to improve grammatical structure, correct typos, and change to appropriate vocabulary, making the text more accurate and understandable.

[1028] A "web application" is software used over the Internet that provides functionality to users via a browser.

[1029] A "standalone application" is software that functions independently and does not require an internet connection.

[1030] A "prompt" is a sentence that the system outputs to the user as an instruction or guide, especially to prompt the user to confirm corrected or refined text.

[1031] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, and finally returns it to the user. This section describes the program for realizing this system and its details.

[1032] System configuration

[1033] The system includes the following main components:

[1034] 1. User Interface

[1035] It provides an interface for users to enter text data. The interface can be implemented as a web application or a standalone application. A user accesses a web page through a browser, enters text into a text box, and clicks a submit button.

[1036] 2. Server Receiving Method

[1037] The server receives text data entered by the user. The data is received through an HTTP POST request and processed in JSON format. For example, if the user enters "This project is very important to me" and submits it, the data is sent to the server.

[1038] 3. Natural Language Processing Methods

[1039] The server analyzes the received text data using natural language processing technology. For this analysis, it uses spaCy, an open-source natural language processing library. First, it divides the text into tokens, tags each token with a part of speech tag, and analyzes dependencies.

[1040] 4. Correction / refinement measures

[1041] Based on the analysis results, the server makes grammatical corrections and selects vocabulary for the input text data. For example, it replaces the word "very" with "extremely," correcting it to a more appropriate expression while preserving the meaning.

[1042] 5. Return Method

[1043] The server sends the corrected and refined text data back to the user, again via an HTTP response, and the user sees the corrected text in their browser. For example, the corrected text "This project is extremely important to me" is sent back to the user.

[1044] Specific examples

[1045] Here are some examples:

[1046] When a user types "This project is very important to me" into the interface and clicks the submit button, the following happens:

[1047] 1. The user enters text into the interface

[1048] The user types "This project is very important to me" in the text box and clicks the submit button.

[1049] 2. The server receives

[1050] The server receives this input via an HTTP POST request and processes it in JSON format.

[1051] 3. The server analyzes the data

[1052] The server uses the natural language processing library spaCy to tokenize the text data, tag it with part-of-speech tags, and analyze dependencies. "This project is very important to me," "this project is very important to me," and "this project is very important to me" are analyzed.

[1053] 4. Server fixes and refines

[1054] Based on the analysis results, the server makes corrections such as replacing "very" with "extremely" and checks for grammatical errors.

[1055] 5. The server responds

[1056] The server sends the revised and refined text "This project is extremely important to me" back to the user.

[1057] Examples of prompt statements

[1058] Here are some example prompts to input to the generative AI model:

[1059] Analyze "This project is very important to me" and revise it to make it more grammatically correct and appropriate.

[1060] In this way, the present invention provides a system that allows users to easily create high-quality sentences, thereby solving the problems of conventional grammatical structures and vocabulary selection, and ultimately realizing a system that is easy for users to use.

[1061] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1062] Step 1:

[1063] User input of text

[1064] A user uses a terminal to input text data into an interface. For example, a user opens a web application and types, "This project is very important to me." This is done by typing the sentence into a text box on a browser and clicking a "Submit" button.

[1065] Input: Text data entered by the user

[1066] Output: Text data is sent from the user's device to the server.

[1067] Step 2:

[1068] Receiving text data

[1069] The server receives the text data entered by the user via an HTTP POST request, with the data sent in JSON format, and prepares the data for analysis.

[1070] Input: Text data sent from the user's device (JSON format)

[1071] Output: Stores the text data received by the server in an internal variable.

[1072] Specific behavior: Receives an HTTP POST request and parses the payload as text data.

[1073] Step 3:

[1074] Text data analysis

[1075] The server analyzes the received text data using the natural language processing library spaCy. The server divides the input sentence into tokens and tags each token with a part of speech tag. It then analyzes dependencies to understand the grammatical structure.

[1076] Input: Received text data

[1077] Output: Tokenized data, its part-of-speech tagging results, and dependency analysis results

[1078] Specific operation: Text data is passed to spaCy for analysis, tokenization, part-of-speech tagging, and dependency analysis.

[1079] Step 4:

[1080] Correcting and refining text data

[1081] Based on the analysis results, the server corrects the grammatical structure of the input text data and performs vocabulary replacement as necessary. For example, it replaces "very" with "extremely." During this process, it checks for grammatical errors and corrects them to appropriate expressions.

[1082] Input: Parsed text data, token and part-of-speech tag information, dependencies

[1083] Output: Corrected and refined text data

[1084] Specific operation: Based on the analysis results, grammatical structure correction and vocabulary replacement are performed.

[1085] Step 5:

[1086] Corrected and refined text data return

[1087] The server returns the corrected and refined text data to the user via an HTTP response, where the user can view the corrected text in their browser and make further edits if necessary.

[1088] Input: Corrected and refined text data

[1089] Output: Modified and refined text data that is displayed in the user's browser.

[1090] Specific operation: The corrected text data is returned to the user in JSON format as an HTTP response.

[1091] These are the specific processing steps of the system program, which allows the text data entered by the user to be corrected and refined with high precision and returned to the user.

[1092] (Application example 1)

[1093] 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."

[1094] While conventional text input assistance systems can correct grammatical errors and spelling mistakes in the text entered by the user, they have difficulty generating new text to improve the quality of the content or rewriting it into more natural and fluent sentences. Furthermore, the generated text often does not match the user's intention, which increases the user's workload.

[1095] 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.

[1096] In this invention, the server includes means for receiving text data entered by a user, means for analyzing the received text data using natural language processing technology, means for correcting and refining the text data based on the analysis results, and means for generating corrected and refined text data using a new text generation model. This enables the server to convert the text entered by the user into high-quality, natural-sounding sentences and generate sentences that meet the user's intentions.

[1097] "Text data entered by the user"

[1098] Refers to the string data that the user provides to the system through the interface.

[1099] "Natural language processing technology"

[1100] It refers to a computational technique for analyzing input text data and extracting meaning, and includes tokenization, part-of-speech tagging, dependency structure analysis, etc.

[1101] "Means of correction and refinement"

[1102] This refers to a means of improving the quality of received and analyzed text data by making grammatical corrections and substituting appropriate words.

[1103] "Means to return"

[1104] A mechanism for sending modified and refined text data back to the user, usually with the ability to send the data over a network.

[1105] "New text generation model"

[1106] Refers to algorithms and techniques that use generative AI models to generate new text based on user-entered text data.

[1107] "Prompt Statement"

[1108] Refers to the initial text or instructions that are input to a new text generation model, based on which the model generates new text.

[1109] The present invention relates to a system that receives text data entered by a user, analyzes, corrects, and refines it using natural language processing techniques and a new text generation model, and returns the results to the user.

[1110] System configuration

[1111] The system of the present invention mainly comprises the following components:

[1112] 1. User Interface

[1113] This is an interface for users to input text data. The interface is implemented as a smartphone application, and users can input sentences in a text field.

[1114] 2. Server Receiving Method

[1115] The server receives the text data entered by the user using an HTTP POST request.

[1116] 3. Natural Language Processing Methods

[1117] The server analyzes the received text data using natural language processing techniques, such as tokenization, part-of-speech tagging, and dependency structure analysis. Software such as SpaCy and transformers are used for this purpose.

[1118] 4. Correction / refinement measures

[1119] The server then uses the analysis results to make grammatical corrections and select vocabulary, for example, correcting typos, improving grammatical structures, and replacing them with appropriate vocabulary.

[1120] 5. Generation method using a new text generation model

[1121] The server uses the revised and refined text to generate more fluent and natural-sounding sentences using a new text generation model, the generative AI model GPT-2.

[1122] 6. Return Method

[1123] The server sends the modified and refined text back to the user, which is then displayed on the application screen along with the original text entered by the user.

[1124] Program processing overview

[1125] The system's program works as follows: A user inputs text data using a smartphone application, and the text is sent to the server. The server uses SpaCy to tokenize the text and tag it with parts of speech. It then uses GPT-2 to perform grammatical corrections and vocabulary refinement, generating new text. The new text is then sent back to the user and displayed on the application screen.

[1126] Specific examples

[1127] As a concrete example, the following prompt is input to the generative AI model to be used:

[1128] Example prompt sentence:

[1129] This project is very important to me.

[1130] Based on this prompt, the following sentence is generated as new text:

[1131] This project is extremely important to me and I want it to be a success.

[1132] In this way, the present invention provides a system that converts text data entered by a user into high-quality, natural-sounding sentences and returns them to the user, allowing the user to receive the text in a more refined form and enabling efficient sentence creation.

[1133] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1134] Step 1:

[1135] The user inputs text data.

[1136] A user inputs a sentence into a text field through a smartphone application. At this point, the input is raw text data, such as a string of characters like "This project is very important to me."

[1137] Step 2:

[1138] The text data entered by the user is sent to the server.

[1139] The terminal sends the entered text data in JSON format to the server using an HTTP POST request. At this point, the input is the text entered by the user, and the output is the JSON data sent to the server.

[1140] Step 3:

[1141] The server receives the text data.

[1142] The server receives the HTTP POST request, extracts the text data, and begins processing it. At this point, the input is JSON data, and the output is text data that is processed within the server.

[1143] Step 4:

[1144] The server analyzes the text data using natural language processing technology.

[1145] The server uses SpaCy to tokenize the received text data and tag it with part-of-speech tags. Specifically, it divides the text into words and assigns part-of-speech information to each word. At this point, the input is raw text data, and the output is tokens and their part-of-speech information.

[1146] Step 5:

[1147] The server performs grammatical corrections and vocabulary refinement based on the analyzed tokens and part-of-speech information.

[1148] Based on the analysis results, the server corrects typos, improves grammatical structures, and replaces them with appropriate vocabulary. At this point, the input is tokens and their part-of-speech information, and the output is corrected and refined text data.

[1149] Step 6:

[1150] The server inputs the modified and refined text into a new text generation model.

[1151] The server inputs the corrected and refined text as a prompt to the new text generation model, GPT-2. Specifically, the server inputs a prompt such as "This project is very important to me" to the generative AI model. At this point, the input is the corrected and refined text data, and the output is the prompt input to the generative AI model.

[1152] Step 7:

[1153] The server retrieves the newly generated text from the generative AI model.

[1154] The server gets the new text generated by the GPT-2 model. For example, the generated text might be "This project is extremely important to me and I want it to succeed." The input at this point is the prompt sentence, and the output is the new text generated.

[1155] Step 8:

[1156] The server sends the newly generated text back to the user.

[1157] The server returns the newly generated text in JSON format as a response to the user, who can then view the returned text on the application screen. At this point, the input is the newly generated text, and the output is the JSON data returned to the user.

[1158] Through this series of processes, users can receive high-quality, natural-sounding text converted from their input text.

[1159] 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.

[1160] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, combines it with an emotion engine that recognizes the user's emotions, and finally returns it to the user. This section explains the program for realizing this system and its operation.

[1161] System configuration

[1162] The system mainly includes the following components:

[1163] 1. User Interface

[1164] It provides an interface for users to enter text data, and can be implemented as a web application or a standalone application.

[1165] 2. Server Receiving Method

[1166] The server receives the text data entered by the user using an HTTP POST request.

[1167] 3. Natural Language Processing Methods

[1168] The server analyzes the received text data using natural language processing techniques, such as tokenization, part-of-speech tagging, and dependency structure analysis.

[1169] 4. Emotion Engine

[1170] The server is equipped with an engine for recognizing user emotions from received text data. This emotion engine uses natural language processing technology to identify positive, negative, and neutral emotions from the text data.

[1171] 5. Correction / refinement measures

[1172] The server corrects and refines the text data based on the analysis and emotion recognition results, for example, correcting typos, improving grammatical structure, and replacing with appropriate vocabulary.

[1173] 6. Return Method

[1174] The server returns both the corrected and refined text data and the emotion recognition results to the user, who can review the returned data and make further corrections if necessary.

[1175] Program processing

[1176] The system program operates as follows.

[1177] 1. User input:

[1178] A user uses the terminal to enter text data into the interface, for example, "This project is very important to me."

[1179] 2. Receiving text data:

[1180] The server receives the text data entered by the user and processes it in JSON format, which is used as input data for analysis.

[1181] 3. Text data analysis:

[1182] The server analyzes the received text data using natural language processing technology. First, it divides the text into tokens and tags each token with a part of speech. Then it analyzes dependencies to understand the grammatical structure.

[1183] 4. User Emotion Recognition:

[1184] The server uses an emotion engine to recognize user emotions from text data. Specifically, it identifies positive, negative, and neutral emotions from the text. This emotion recognition result is used for the subsequent correction and refinement process.

[1185] 5. Correcting and refining text data:

[1186] Based on the analysis and emotion recognition results, the server corrects the grammatical structure of the input text data and performs lexical substitutions as necessary, for example, replacing "very" with "extremely."

[1187] 6. Corrected and refined text data return:

[1188] The server returns the corrected and refined text data and the user's emotion recognition results to the user device as an HTTP response.

[1189] 7. User Verification:

[1190] The user can check the returned text data and emotion recognition results on the device, and can make additional corrections as needed.

[1191] Specific examples

[1192] For example, consider the case where a user types "This project is very important to me." After receiving and analyzing this text, the emotion engine recognizes it as "positive." The server then replaces "very" with "extremely," performs corrections and refinements, and returns the final text "This project is extremely important to me" and the emotion recognition result of "positive" to the user.

[1193] In this way, the present invention provides a system that allows users to easily create high-quality text and also analyzes the emotions contained in the text.

[1194] The processing flow will be explained below.

[1195] Step 1:

[1196] A user uses a terminal to enter text data into an interface, for example, "This project is very important to me."

[1197] Step 2:

[1198] The device sends the text data entered by the user to the server via an HTTP POST request.

[1199] Step 3:

[1200] The server receives text data from the user in JSON format, which is then stored in internal memory for analysis.

[1201] Step 4:

[1202] The server uses natural language processing technology to analyze the received text data. First, it divides the text data into tokens (tokenization).

[1203] Step 5:

[1204] The server tags each token with a part-of-speech tag, which identifies whether each word belongs to a noun, verb, adjective, etc.

[1205] Step 6:

[1206] The server performs dependency analysis, identifying how words in a sentence are related and figuring out grammatical structure.

[1207] Step 7:

[1208] The server uses an emotion engine to recognize emotions from the received text data. Specifically, it analyzes the text data and identifies positive, negative, and neutral emotions.

[1209] Step 8:

[1210] The server corrects and refines the text data based on the analysis and emotion recognition results, for example, replacing the word "very" with "extremely" or correcting grammatical errors.

[1211] Step 9:

[1212] The server generates the final corrected and refined text data and emotion recognition results, which are then ready to be sent back to the user.

[1213] Step 10:

[1214] The server returns the corrected and refined text data and emotion recognition results in JSON format to the user device as an HTTP response.

[1215] Step 11:

[1216] The user can check the returned text data and emotion recognition results on the device, and can make additional corrections as needed.

[1217] In this way, the server performs a series of processes: analyzing the input text data, recognizing emotions, correcting and refining them, and then returning them to the user.

[1218] Example 2

[1219] 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."

[1220] Conventional systems can correct and refine text data entered by users, but it is difficult to recognize emotions contained in the text data and correct the text data based on those emotions. Furthermore, the accuracy of generating and correcting text that reflects emotions is not sufficient. This makes it difficult to generate high-quality sentences that can appropriately convey users' emotions.

[1221] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving text data input by a user, means for analyzing the received text data using natural language processing technology, means for recognizing emotions from the analyzed text data, means for correcting and refining the text data based on the recognized emotions, and means for returning the corrected and refined text data to the user. This makes it possible to accurately recognize emotions contained in text data input by a user and generate corrected and refined text data that reflects the emotions.

[1222] "Text data" refers to a collection of sentences or phrases entered by a user that are analyzed and corrected by the system.

[1223] "Natural language processing technology" refers to technology that enables computers to understand, interpret, and generate human language, and includes tokenization, part-of-speech tagging, grammatical analysis, dependency structure analysis, etc.

[1224] "Tokenization" is the process of dividing text data into its smallest units, such as words or phrases.

[1225] "Part-of-speech tagging" is the process of assigning each tokenized word or phrase its part of speech (noun, verb, adjective, etc.).

[1226] "Dependency structure analysis" is a process that analyzes the interrelationships between words in a sentence to understand its grammatical structure.

[1227] An "emotion engine" refers to an algorithm or software that recognizes emotions (positive, negative, neutral, etc.) from text data.

[1228] "Emotion recognition" is the process of identifying emotions contained in text data and classifying the emotional state.

[1229] "Correction and refinement" refers to the process of correcting typos in text data, improving grammatical structure, and replacing vocabulary with appropriate ones, in order to produce higher quality text.

[1230] "User Interface" refers to the operating screen through which a user inputs text data into the system and reviews the corrected and refined text data.

[1231] "Server" refers to the computer system that receives, analyzes, recognizes emotions, modifies and refines text data, and returns the data.

[1232] An "HTTP POST request" is part of a communication protocol for sending data from a user to a server, and is primarily used in web applications.

[1233] "JSON format" stands for JavaScript Object Notation, and is a format for organizing data and representing it simply and lightweight.

[1234] MODE FOR CARRYING OUT THE INVENTION

[1235] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, combines it with an emotion engine that recognizes the user's emotions, and finally returns it to the user.

[1236] System configuration

[1237] The system mainly includes the following components:

[1238] 1. User Interface

[1239] It provides an interface for users to input text data. The interface can be implemented as a web application or a standalone application. For example, we will use an application that runs in a web browser.

[1240] 2. Server Receiving Method

[1241] The server receives the text data entered by the user. The method of reception is via HTTP POST request. This ensures that the server receives the data entered by the user.

[1242] 3. Natural Language Processing Methods

[1243] The server analyzes the received text data using natural language processing techniques, such as software like SpaCy or NLTK, to perform tokenization, part-of-speech tagging, and dependency structure analysis.

[1244] 4. Emotion Engine

[1245] The server is equipped with an engine to recognize user emotions from received text data. VADER and TextBlob are used as emotion engines. This allows us to identify positive, negative, and neutral emotions from text data.

[1246] 5. Correction / refinement measures

[1247] Based on the analysis and emotion recognition results, the server corrects the grammatical structure of the input text data and replaces vocabulary as necessary, for example, correcting typos and replacing vocabulary with more appropriate vocabulary.

[1248] 6. Return Method

[1249] The server returns the corrected and refined text data and emotion recognition results to the user via an HTTP response.

[1250] Specific examples of natural language processing

[1251] If the user enters "This project is very important to me," the system behaves as follows:

[1252] 1. User input

[1253] User: Enters the text "This project is very important to me" and presses submit.

[1254] 2. The server receives

[1255] Server: Receives HTTP POST requests from users and processes text data in JSON format.

[1256] 3. The server analyzes

[1257] Server: Uses SpaCy to tokenize and tag the text, then performs dependency analysis to understand the grammatical structure of the sentence.

[1258] 4. The server recognizes emotions

[1259] Server: Uses VADER to recognize the sentiment of the text data and classify it as "positive."

[1260] 5. Server fixes and refinements

[1261] Server: Based on the analysis results and emotion recognition results, replace "very" with "extremely" and make grammatical corrections.

[1262] 6. Server replies

[1263] Server: Returns the modified and refined text data "This project is extremely important to me" and the emotion recognition result "Positive" in the HTTP response.

[1264] Example prompts for generative AI models

[1265] The present invention also provides prompts for emotion recognition and text correction using generative AI models. For example, the following prompts can be used:

[1266] "Please perform a sentiment analysis on the following text: This project is very important to me."

[1267] By feeding this prompt sentence into a generative AI model, it is possible to obtain emotion recognition results and corrected / refined text.

[1268] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1269] Program processing flow

[1270] Step 1: User inputs text

[1271] Subject: User

[1272] Specific behavior:

[1273] The user uses the terminal to input text data into the interface screen, for example, "This project is very important to me."

[1274] The user clicks the "Submit" button to send the text data to the system.

[1275] input:

[1276] Input text data: "This project is very important to me"

[1277] output:

[1278] The send button is clicked and the text data is sent to the server.

[1279] Step 2: Receiving text data

[1280] Subject: Server

[1281] Specific behavior:

[1282] The server receives the text data entered by the user. This is received using an HTTP POST request.

[1283] input:

[1284] Text data sent via HTTP POST request: "This project is very important to me"

[1285] output:

[1286] The received text data is stored in JSON format for internal processing.

[1287] Step 3: Analyzing the text data

[1288] Subject: Server

[1289] Specific behavior:

[1290] The server analyzes the received text data using natural language processing software (e.g., SpaCy).

[1291] It splits text into tokens, tags each token with a part of speech, and then analyzes dependencies to understand grammatical structure.

[1292] input:

[1293] JSON text data: "This project is very important to me"

[1294] output:

[1295] Tokenized text data

[1296] Part-of-speech tagged data

[1297] Dependency structure analysis results

[1298] Step 4: Recognizing user emotions

[1299] Subject: Server

[1300] Specific behavior:

[1301] The server uses an emotion engine (e.g., VADER) to recognize the user's emotion from the text data.

[1302] The content of the text data is analyzed and a positive, negative, or neutral sentiment score is calculated.

[1303] input:

[1304] Analyzed text data (tokenization, part-of-speech tagging, dependency structure analysis results)

[1305] output:

[1306] Emotion recognition result (e.g., "positive")

[1307] Step 5: Correcting and refining the text data

[1308] Subject: Server

[1309] Specific behavior:

[1310] The server corrects and refines the text data based on the analysis and emotion recognition results.

[1311] The revisions include improving grammatical structure, correcting spelling errors, and substituting appropriate vocabulary, for example, replacing "very" with "extremely."

[1312] input:

[1313] Parsed text data

[1314] Emotion recognition results

[1315] output:

[1316] Corrected / Refined Text Data: "This project is extremely important to me."

[1317] Step 6: Returning the corrected and refined text data

[1318] Subject: Server

[1319] Specific behavior:

[1320] The server serializes the corrected and refined text data and emotion recognition results together into JSON format.

[1321] The server sends this data back as an HTTP response.

[1322] input:

[1323] Corrected and refined text data

[1324] Emotion recognition results

[1325] output:

[1326] JSON format data is returned as an HTTP response.

[1327] Step 7: Verify the user

[1328] Subject: User

[1329] Specific behavior:

[1330] The user checks the returned text data and emotion recognition results on the device's interface screen.

[1331] If necessary, the text data can be corrected again and sent again.

[1332] input:

[1333] Corrected and refined text data sent back to the device

[1334] Emotion recognition results

[1335] output:

[1336] The user checks the data, and if further corrections are required, the data is manipulated and resent.

[1337] (Application example 2)

[1338] 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."

[1339] Current content distribution services do not have a system that automatically analyzes the quality of text entered by users and the emotions contained in that text, and provides feedback. This makes it difficult for users to create high-quality text while taking emotions and content into consideration. This could result in a decline in user satisfaction and the quality of content on the platform as a whole.

[1340] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving text data entered by a user, means for analyzing the received text data using natural language processing technology, means for correcting and refining the text data based on the analysis results, and means for returning the corrected text data and emotion recognition results to the user. This enables the user to easily create high-quality text that takes into consideration emotions and content.

[1341] "User-input text data" refers to a sequence of characters or sentences that a user inputs into a system through an interface.

[1342] "Means for receiving" refers to the technology or device that allows the server to obtain the text data sent by the user.

[1343] "Natural language processing technology" is a technology that allows computers to analyze and understand natural language, which is human language.

[1344] "Means for analysis" refers to technology for analyzing received text data and identifying grammatical structure, meaning, sentiment, etc.

[1345] "Means of correction and refinement" refers to techniques for improving the grammar and content of text data based on the analysis results and arranging it into a more appropriate form.

[1346] "Emotion recognition result" is the result of identifying emotions (positive, negative, neutral, etc.) contained in text data.

[1347] "Returning means" refers to the technology used to send the corrected and refined text data and emotion recognition results to the user.

[1348] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, modifies and refines the text data based on the analysis results, recognizes the user's emotions using an emotion engine, and finally returns the modified and refined text data and the emotion recognition results to the user. This section describes the program for realizing this system and its operation.

[1349] System configuration

[1350] The system mainly includes the following components:

[1351] 1. User Interface:

[1352] Users input text data from devices such as smartphones and tablets, and the input data is sent to a server via a web application or a standalone application.

[1353] 2. Server receiving method:

[1354] The server receives text data sent by the user via an HTTP POST request, etc. The received text data is processed as input data for analysis.

[1355] 3. Natural Language Processing Tools:

[1356] The server analyzes the received text data using natural language processing techniques, specifically using Python's TextBlob library to tokenize the text, tag it as a part of speech, and analyze its grammatical structure.

[1357] 4. Emotion Engine:

[1358] The server uses TextBlob's NaiveBayesAnalyzer to recognize user sentiment from the parsed text data. This sentiment engine identifies positive, negative, and neutral sentiments in the text.

[1359] 5. Modification / refinement measures:

[1360] Based on the analysis and emotion recognition results, the server performs grammatical corrections, spelling corrections, and vocabulary optimization on the text data. For example, it corrects "This projekt iz verie important to me" to "This project is very important to me."

[1361] 6. Return Method:

[1362] The server returns the corrected and refined text data and emotion recognition results to the user as an HTTP response, and the user can view the returned data through the interface.

[1363] Detailed explanation of how it works

[1364] Below is a detailed explanation of how the system works.

[1365] 1. User input:

[1366] The user enters text data into the system through the terminal interface, for example, "This project is important to me."

[1367] 2. Receiving text data:

[1368] The server receives the text data entered by the user through the receiving means, and sends the received data to the server in JSON format or the like.

[1369] 3. Text data analysis:

[1370] The server uses natural language processing tools to analyze the received data. It processes the text using the TextBlob library, tagging each token with a part of speech tag and analyzing its grammatical structure.

[1371] 4. Emotion recognition:

[1372] The server uses an emotion engine to identify positive, negative, and neutral emotions from the text data. The emotion recognition results are used for the correction and refinement process.

[1373] 5. Correcting and refining text data:

[1374] The server performs grammatical corrections on the text data based on the analysis results and emotion recognition results, and performs vocabulary replacement as necessary.

[1375] 6. Corrected and refined text data return:

[1376] The server returns the corrected and refined text data and emotion recognition results to the user's device, which are displayed in the user's interface as an HTTP response.

[1377] Examples of concrete examples and prompts

[1378] For example, if a user types "This projekt iz verie important to me":

[1379] 1. The server receives the text.

[1380] 2. Analysis using natural language processing technology.

[1381] 3. Positive emotions and perceptions with the Emotion Engine.

[1382] 4. Revised to be grammatically correct: "This project is very important to me."

[1383] 5. Correct and refine the text and emotion recognition results and return them to the user.

[1384] Prompt Sentence Examples

[1385] text

[1386] User: This projekt iz verie impotant to me

[1387] System analysis results: This project is very important to me

[1388] Emotion recognition result: Positive

[1389] In this way, users can generate high-quality text and at the same time understand the sentiment contained in that text.

[1390] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1391] Step 1:

[1392] A user uses a terminal to input text data into the interface, for example, "This project is important to me." This input data is then prepared for transmission to the server. The input data is in text format.

[1393] Step 2:

[1394] The server receives text data entered by the user via an HTTP POST request. The received data is converted to JSON format and saved on the server as input data for analysis. Here, the input is text data from the user and the output is JSON format data.

[1395] Step 3:

[1396] The server uses the TextBlob library to analyze the received text data using natural language processing techniques. Specifically, it tokenizes the text and tags each token with a part of speech. It also performs dependency analysis to understand the grammatical structure. The input here is text data in JSON format, and the output is the analyzed tokens and part of speech tagging results.

[1397] Step 4:

[1398] The server uses TextBlob's NaiveBayesAnalyzer to recognize emotions from the parsed tokens. The emotion recognition result is identified as positive, negative, or neutral. The input is the parsed tokens and part-of-speech tagging results, and the output is the emotion recognition result.

[1399] Step 5:

[1400] The server integrates the analysis results and emotion recognition results to correct and refine the text data. Specifically, it corrects typos, corrects grammatical errors, and replaces words with appropriate vocabulary. For example, it corrects "projekt" to "project." The input here is the analysis results and emotion recognition results, and the output is the corrected and refined text data.

[1401] Step 6:

[1402] The server returns the corrected and refined text data and the emotion recognition results to the user. This is again done as an HTTP response. The returned data is displayed in the user interface, where the user can check the corrected text and the emotion recognition results. The input is the corrected and refined text data and the emotion recognition results, and the output is the data displayed in the user interface.

[1403] Step 7:

[1404] The user can review the returned corrected and refined text data and emotion recognition results and make additional corrections if necessary. If the user makes additional corrections, the process starts again from one of the steps. The input is the user's feedback, and the output is the final confirmed corrected text.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] [Fourth embodiment]

[1409] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1410] 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.

[1411] 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).

[1412] 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.

[1413] 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.

[1414] 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).

[1415] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1416] 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.

[1417] 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.

[1418] 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.

[1419] 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.

[1420] 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.

[1421] 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."

[1422] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, and finally returns it to the user. This section explains the program for realizing this system and its operation.

[1423] System configuration

[1424] The system mainly includes the following components:

[1425] 1. User Interface

[1426] It provides an interface for users to enter text data, and can be implemented as a web application or a standalone application.

[1427] 2. Server Receiving Method

[1428] The server receives the text data entered by the user using an HTTP POST request.

[1429] 3. Natural Language Processing Methods

[1430] The server analyzes the received text data using natural language processing techniques, such as tokenization, part-of-speech tagging, and dependency structure analysis.

[1431] 4. Correction / refinement measures

[1432] The server then uses the analysis results to make grammatical corrections and select vocabulary, for example, correcting typos, improving grammatical structures, and replacing them with appropriate vocabulary.

[1433] 5. Return Method

[1434] The server returns the corrected and refined text data to the user, who can review it and make further corrections if necessary.

[1435] Program processing

[1436] The system program operates as follows.

[1437] 1. User input:

[1438] A user uses the terminal to enter text data into the interface, for example, "This project is very important to me."

[1439] 2. Receiving text data:

[1440] The server receives the text data entered by the user and processes it in JSON format, which is used as input data for analysis.

[1441] 3. Text data analysis:

[1442] The server analyzes the received text data using natural language processing technology. First, it divides the text into tokens and tags each token with a part of speech. Then it analyzes dependencies to understand the grammatical structure.

[1443] 4. Correcting and refining text data:

[1444] The server uses the analysis results to correct the grammatical structure of the input text data and perform lexical substitutions as necessary, for example, replacing "very" with "extremely."

[1445] 5. Corrected and refined text data return:

[1446] The server returns the corrected and refined text data to the user, who can review it and make further corrections if necessary.

[1447] Specific examples

[1448] For example, consider the case where a user enters "This project is very important to me."

[1449] 1. The user enters text into the interface.

[1450] 2. The server receives this input and stores it in JSON format.

[1451] 3. The server uses natural language processing technology to tokenize the input text, dividing it into "this project is very important to me," "is," and "is." It then tags each token with a part of speech tag and analyzes dependencies.

[1452] 4. The server makes corrections, such as replacing "very" with "extremely," and checks for grammatical errors.

[1453] 5. The revised and refined text "This project is extremely important to me" is sent back to the user.

[1454] In this way, the present invention provides a system that allows users to easily create high-quality text.

[1455] The processing flow will be explained below.

[1456] Step 1:

[1457] A user uses a terminal to enter text data into an interface, for example, "This project is very important to me."

[1458] Step 2:

[1459] The device sends the text data entered by the user to the server via an HTTP POST request.

[1460] Step 3:

[1461] The server receives text data from the user in JSON format, which is then stored in internal memory for analysis.

[1462] Step 4:

[1463] The server uses natural language processing technology to analyze the received text data. First, it divides the text data into tokens (tokenization).

[1464] Step 5:

[1465] The server tags each token with a part-of-speech tag, which identifies whether each word belongs to a noun, verb, adjective, etc.

[1466] Step 6:

[1467] The server performs dependency analysis, identifying how words in a sentence are related and figuring out grammatical structure.

[1468] Step 7:

[1469] The server then corrects and refines the text data based on the analysis results, for example, replacing the word "very" with "extremely" or correcting grammatical errors.

[1470] Step 8:

[1471] The server generates the final corrected and refined text data, which is then ready to be sent back to the user.

[1472] Step 9:

[1473] The server returns the modified and refined text data in JSON format to the user's device as an HTTP response.

[1474] Step 10:

[1475] The user can check the returned text data on the terminal and make additional corrections as necessary.

[1476] In this way, the server performs a series of processes to analyze the input text data, correct and refine it, and then return it to the user.

[1477] Example 1

[1478] 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."

[1479] Conventional text data correction systems often lack sufficient accuracy and automation in correcting grammatical errors and selecting vocabulary in user-entered text data, resulting in the burden of having to manually correct the data. Furthermore, the accuracy of the analysis of the input text data and the correction algorithms are insufficient, and in some cases, the system fails to make appropriate corrections.

[1480] 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.

[1481] In this invention, the server includes means for receiving text data entered by a user, means for analyzing the received text data using natural language processing technology, and means for correcting and refining the text data based on the analysis results, thereby enabling automatic correction and refinement of grammatical errors and vocabulary selection in the text data entered by a user with high accuracy.

[1482] "User" means a user who uses the System to input text data and receive corrected and refined text data.

[1483] A "server" is a device or system that receives text data entered by a user and analyzes, modifies, and refines it using natural language processing techniques.

[1484] "Text data" refers to character string information that a user inputs into a system, such as sentences or documents that require grammar and vocabulary correction.

[1485] "Natural language processing technology" refers to the general technology of processing and analyzing human language using a computer, including tokenization, part-of-speech tagging, dependency analysis, etc.

[1486] "Tokenization" is the process of dividing input text data into the smallest meaningful units.

[1487] "Part-of-speech tagging" is the process of assigning each segmented token its linguistic category (noun, verb, adjective, etc.).

[1488] "Analysis results" refers to data obtained through analysis using natural language processing technology, i.e., the results of tokenization, part-of-speech tagging, and dependency analysis.

[1489] "Revising and refining" is the process of using the analysis results to improve grammatical structure, correct typos, and change to appropriate vocabulary, making the text more accurate and understandable.

[1490] A "web application" is software used over the Internet that provides functionality to users via a browser.

[1491] A "standalone application" is software that functions independently and does not require an internet connection.

[1492] A "prompt" is a sentence that the system outputs to the user as an instruction or guide, especially to prompt the user to confirm corrected or refined text.

[1493] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, and finally returns it to the user. This section describes the program for realizing this system and its details.

[1494] System configuration

[1495] The system includes the following main components:

[1496] 1. User Interface

[1497] It provides an interface for users to enter text data. The interface can be implemented as a web application or a standalone application. A user accesses a web page through a browser, enters text into a text box, and clicks a submit button.

[1498] 2. Server Receiving Method

[1499] The server receives text data entered by the user. The data is received through an HTTP POST request and processed in JSON format. For example, if the user enters "This project is very important to me" and submits it, the data is sent to the server.

[1500] 3. Natural Language Processing Methods

[1501] The server analyzes the received text data using natural language processing technology. For this analysis, it uses spaCy, an open-source natural language processing library. First, it divides the text into tokens, tags each token with a part of speech tag, and analyzes dependencies.

[1502] 4. Correction / refinement measures

[1503] Based on the analysis results, the server makes grammatical corrections and selects vocabulary for the input text data. For example, it replaces the word "very" with "extremely," correcting it to a more appropriate expression while preserving the meaning.

[1504] 5. Return Method

[1505] The server sends the corrected and refined text data back to the user, again via an HTTP response, and the user sees the corrected text in their browser. For example, the corrected text "This project is extremely important to me" is sent back to the user.

[1506] Specific examples

[1507] Here are some examples:

[1508] When a user types "This project is very important to me" into the interface and clicks the submit button, the following happens:

[1509] 1. The user enters text into the interface

[1510] The user types "This project is very important to me" in the text box and clicks the submit button.

[1511] 2. The server receives

[1512] The server receives this input via an HTTP POST request and processes it in JSON format.

[1513] 3. The server analyzes the data

[1514] The server uses the natural language processing library spaCy to tokenize the text data, tag it with part-of-speech tags, and analyze dependencies. "This project is very important to me," "this project is very important to me," and "this project is very important to me" are analyzed.

[1515] 4. Server fixes and refines

[1516] Based on the analysis results, the server makes corrections such as replacing "very" with "extremely" and checks for grammatical errors.

[1517] 5. The server responds

[1518] The server sends the revised and refined text "This project is extremely important to me" back to the user.

[1519] Examples of prompt statements

[1520] Here are some example prompts to input to the generative AI model:

[1521] Analyze "This project is very important to me" and revise it to make it more grammatically correct and appropriate.

[1522] In this way, the present invention provides a system that allows users to easily create high-quality sentences, thereby solving the problems of conventional grammatical structures and vocabulary selection, and ultimately realizing a system that is easy for users to use.

[1523] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1524] Step 1:

[1525] User input of text

[1526] A user uses a terminal to input text data into an interface. For example, a user opens a web application and types, "This project is very important to me." This is done by typing the sentence into a text box on a browser and clicking a "Submit" button.

[1527] Input: Text data entered by the user

[1528] Output: Text data is sent from the user's device to the server.

[1529] Step 2:

[1530] Receiving text data

[1531] The server receives the text data entered by the user via an HTTP POST request, with the data sent in JSON format, and prepares the data for analysis.

[1532] Input: Text data sent from the user's device (JSON format)

[1533] Output: Stores the text data received by the server in an internal variable.

[1534] Specific behavior: Receives an HTTP POST request and parses the payload as text data.

[1535] Step 3:

[1536] Text data analysis

[1537] The server analyzes the received text data using the natural language processing library spaCy. The server divides the input sentence into tokens and tags each token with a part of speech tag. It then analyzes dependencies to understand the grammatical structure.

[1538] Input: Received text data

[1539] Output: Tokenized data, its part-of-speech tagging results, and dependency analysis results

[1540] Specific operation: Text data is passed to spaCy for analysis, tokenization, part-of-speech tagging, and dependency analysis.

[1541] Step 4:

[1542] Correcting and refining text data

[1543] Based on the analysis results, the server corrects the grammatical structure of the input text data and performs vocabulary replacement as necessary. For example, it replaces "very" with "extremely." During this process, it checks for grammatical errors and corrects them to appropriate expressions.

[1544] Input: Parsed text data, token and part-of-speech tag information, dependencies

[1545] Output: Corrected and refined text data

[1546] Specific operation: Based on the analysis results, grammatical structure correction and vocabulary replacement are performed.

[1547] Step 5:

[1548] Corrected and refined text data return

[1549] The server returns the corrected and refined text data to the user via an HTTP response, where the user can view the corrected text in their browser and make further edits if necessary.

[1550] Input: Corrected and refined text data

[1551] Output: Modified and refined text data that is displayed in the user's browser.

[1552] Specific operation: The corrected text data is returned to the user in JSON format as an HTTP response.

[1553] These are the specific processing steps of the system program, which allows the text data entered by the user to be corrected and refined with high precision and returned to the user.

[1554] (Application example 1)

[1555] 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."

[1556] While conventional text input assistance systems can correct grammatical errors and spelling mistakes in the text entered by the user, they have difficulty generating new text to improve the quality of the content or rewriting it into more natural and fluent sentences. Furthermore, the generated text often does not match the user's intention, which increases the user's workload.

[1557] 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.

[1558] In this invention, the server includes means for receiving text data entered by a user, means for analyzing the received text data using natural language processing technology, means for correcting and refining the text data based on the analysis results, and means for generating corrected and refined text data using a new text generation model. This enables the server to convert the text entered by the user into high-quality, natural-sounding sentences and generate sentences that meet the user's intentions.

[1559] "Text data entered by the user"

[1560] Refers to the string data that the user provides to the system through the interface.

[1561] "Natural language processing technology"

[1562] It refers to a computational technique for analyzing input text data and extracting meaning, and includes tokenization, part-of-speech tagging, dependency structure analysis, etc.

[1563] "Means of correction and refinement"

[1564] This refers to a means of improving the quality of received and analyzed text data by making grammatical corrections and substituting appropriate words.

[1565] "Means to return"

[1566] A mechanism for sending modified and refined text data back to the user, usually with the ability to send the data over a network.

[1567] "New text generation model"

[1568] Refers to algorithms and techniques that use generative AI models to generate new text based on user-entered text data.

[1569] "Prompt Statement"

[1570] Refers to the initial text or instructions that are input to a new text generation model, based on which the model generates new text.

[1571] The present invention relates to a system that receives text data entered by a user, analyzes, corrects, and refines it using natural language processing techniques and a new text generation model, and returns the results to the user.

[1572] System configuration

[1573] The system of the present invention mainly comprises the following components:

[1574] 1. User Interface

[1575] This is an interface for users to input text data. The interface is implemented as a smartphone application, and users can input sentences in a text field.

[1576] 2. Server Receiving Method

[1577] The server receives the text data entered by the user using an HTTP POST request.

[1578] 3. Natural Language Processing Methods

[1579] The server analyzes the received text data using natural language processing techniques, such as tokenization, part-of-speech tagging, and dependency structure analysis. Software such as SpaCy and transformers are used for this purpose.

[1580] 4. Correction / refinement measures

[1581] The server then uses the analysis results to make grammatical corrections and select vocabulary, for example, correcting typos, improving grammatical structures, and replacing them with appropriate vocabulary.

[1582] 5. Generation method using a new text generation model

[1583] The server uses the revised and refined text to generate more fluent and natural-sounding sentences using a new text generation model, the generative AI model GPT-2.

[1584] 6. Return Method

[1585] The server sends the modified and refined text back to the user, which is then displayed on the application screen along with the original text entered by the user.

[1586] Program processing overview

[1587] The system's program works as follows: A user inputs text data using a smartphone application, and the text is sent to the server. The server uses SpaCy to tokenize the text and tag it with parts of speech. It then uses GPT-2 to perform grammatical corrections and vocabulary refinement, generating new text. The new text is then sent back to the user and displayed on the application screen.

[1588] Specific examples

[1589] As a concrete example, the following prompt is input to the generative AI model to be used:

[1590] Example prompt sentence:

[1591] This project is very important to me.

[1592] Based on this prompt, the following sentence is generated as new text:

[1593] This project is extremely important to me and I want it to be a success.

[1594] In this way, the present invention provides a system that converts text data entered by a user into high-quality, natural-sounding sentences and returns them to the user, allowing the user to receive the text in a more refined form and enabling efficient sentence creation.

[1595] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1596] Step 1:

[1597] The user inputs text data.

[1598] A user inputs a sentence into a text field through a smartphone application. At this point, the input is raw text data, such as a string of characters like "This project is very important to me."

[1599] Step 2:

[1600] The text data entered by the user is sent to the server.

[1601] The terminal sends the entered text data in JSON format to the server using an HTTP POST request. At this point, the input is the text entered by the user, and the output is the JSON data sent to the server.

[1602] Step 3:

[1603] The server receives the text data.

[1604] The server receives the HTTP POST request, extracts the text data, and begins processing it. At this point, the input is JSON data, and the output is text data that is processed within the server.

[1605] Step 4:

[1606] The server analyzes the text data using natural language processing technology.

[1607] The server uses SpaCy to tokenize the received text data and tag it with part-of-speech tags. Specifically, it divides the text into words and assigns part-of-speech information to each word. At this point, the input is raw text data, and the output is tokens and their part-of-speech information.

[1608] Step 5:

[1609] The server performs grammatical corrections and vocabulary refinement based on the analyzed tokens and part-of-speech information.

[1610] Based on the analysis results, the server corrects typos, improves grammatical structures, and replaces them with appropriate vocabulary. At this point, the input is tokens and their part-of-speech information, and the output is corrected and refined text data.

[1611] Step 6:

[1612] The server inputs the modified and refined text into a new text generation model.

[1613] The server inputs the corrected and refined text as a prompt to the new text generation model, GPT-2. Specifically, the server inputs a prompt such as "This project is very important to me" to the generative AI model. At this point, the input is the corrected and refined text data, and the output is the prompt input to the generative AI model.

[1614] Step 7:

[1615] The server retrieves the newly generated text from the generative AI model.

[1616] The server gets the new text generated by the GPT-2 model. For example, the generated text might be "This project is extremely important to me and I want it to succeed." The input at this point is the prompt sentence, and the output is the new text generated.

[1617] Step 8:

[1618] The server sends the newly generated text back to the user.

[1619] The server returns the newly generated text in JSON format as a response to the user, who can then view the returned text on the application screen. At this point, the input is the newly generated text, and the output is the JSON data returned to the user.

[1620] Through this series of processes, users can receive high-quality, natural-sounding text converted from their input text.

[1621] 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.

[1622] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, combines it with an emotion engine that recognizes the user's emotions, and finally returns it to the user. This section explains the program for realizing this system and its operation.

[1623] System configuration

[1624] The system mainly includes the following components:

[1625] 1. User Interface

[1626] It provides an interface for users to enter text data, and can be implemented as a web application or a standalone application.

[1627] 2. Server Receiving Method

[1628] The server receives the text data entered by the user using an HTTP POST request.

[1629] 3. Natural Language Processing Methods

[1630] The server analyzes the received text data using natural language processing techniques, such as tokenization, part-of-speech tagging, and dependency structure analysis.

[1631] 4. Emotion Engine

[1632] The server is equipped with an engine for recognizing user emotions from received text data. This emotion engine uses natural language processing technology to identify positive, negative, and neutral emotions from the text data.

[1633] 5. Correction / refinement measures

[1634] The server corrects and refines the text data based on the analysis and emotion recognition results, for example, correcting typos, improving grammatical structure, and replacing with appropriate vocabulary.

[1635] 6. Return Method

[1636] The server returns both the corrected and refined text data and the emotion recognition results to the user, who can review the returned data and make further corrections if necessary.

[1637] Program processing

[1638] The system program operates as follows.

[1639] 1. User input:

[1640] A user uses the terminal to enter text data into the interface, for example, "This project is very important to me."

[1641] 2. Receiving text data:

[1642] The server receives the text data entered by the user and processes it in JSON format, which is used as input data for analysis.

[1643] 3. Text data analysis:

[1644] The server analyzes the received text data using natural language processing technology. First, it divides the text into tokens and tags each token with a part of speech. Then it analyzes dependencies to understand the grammatical structure.

[1645] 4. User Emotion Recognition:

[1646] The server uses an emotion engine to recognize user emotions from text data. Specifically, it identifies positive, negative, and neutral emotions from the text. This emotion recognition result is used for the subsequent correction and refinement process.

[1647] 5. Correcting and refining text data:

[1648] Based on the analysis and emotion recognition results, the server corrects the grammatical structure of the input text data and performs lexical substitutions as necessary, for example, replacing "very" with "extremely."

[1649] 6. Corrected and refined text data return:

[1650] The server returns the corrected and refined text data and the user's emotion recognition results to the user device as an HTTP response.

[1651] 7. User Verification:

[1652] The user can check the returned text data and emotion recognition results on the device, and can make additional corrections as needed.

[1653] Specific examples

[1654] For example, consider the case where a user types "This project is very important to me." After receiving and analyzing this text, the emotion engine recognizes it as "positive." The server then replaces "very" with "extremely," performs corrections and refinements, and returns the final text "This project is extremely important to me" and the emotion recognition result of "positive" to the user.

[1655] In this way, the present invention provides a system that allows users to easily create high-quality text and also analyzes the emotions contained in the text.

[1656] The processing flow will be explained below.

[1657] Step 1:

[1658] A user uses a terminal to enter text data into an interface, for example, "This project is very important to me."

[1659] Step 2:

[1660] The device sends the text data entered by the user to the server via an HTTP POST request.

[1661] Step 3:

[1662] The server receives text data from the user in JSON format, which is then stored in internal memory for analysis.

[1663] Step 4:

[1664] The server uses natural language processing technology to analyze the received text data. First, it divides the text data into tokens (tokenization).

[1665] Step 5:

[1666] The server tags each token with a part-of-speech tag, which identifies whether each word belongs to a noun, verb, adjective, etc.

[1667] Step 6:

[1668] The server performs dependency analysis, identifying how words in a sentence are related and figuring out grammatical structure.

[1669] Step 7:

[1670] The server uses an emotion engine to recognize emotions from the received text data. Specifically, it analyzes the text data and identifies positive, negative, and neutral emotions.

[1671] Step 8:

[1672] The server corrects and refines the text data based on the analysis and emotion recognition results, for example, replacing the word "very" with "extremely" or correcting grammatical errors.

[1673] Step 9:

[1674] The server generates the final corrected and refined text data and emotion recognition results, which are then ready to be sent back to the user.

[1675] Step 10:

[1676] The server returns the corrected and refined text data and emotion recognition results in JSON format to the user device as an HTTP response.

[1677] Step 11:

[1678] The user can check the returned text data and emotion recognition results on the device, and can make additional corrections as needed.

[1679] In this way, the server performs a series of processes: analyzing the input text data, recognizing emotions, correcting and refining them, and then returning them to the user.

[1680] Example 2

[1681] 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."

[1682] Conventional systems can correct and refine text data entered by users, but it is difficult to recognize emotions contained in the text data and correct the text data based on those emotions. Furthermore, the accuracy of generating and correcting text that reflects emotions is not sufficient. This makes it difficult to generate high-quality sentences that can appropriately convey users' emotions.

[1683] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving text data input by a user, means for analyzing the received text data using natural language processing technology, means for recognizing emotions from the analyzed text data, means for correcting and refining the text data based on the recognized emotions, and means for returning the corrected and refined text data to the user. This makes it possible to accurately recognize emotions contained in text data input by a user and generate corrected and refined text data that reflects the emotions.

[1684] "Text data" refers to a collection of sentences or phrases entered by a user that are analyzed and corrected by the system.

[1685] "Natural language processing technology" refers to technology that enables computers to understand, interpret, and generate human language, and includes tokenization, part-of-speech tagging, grammatical analysis, dependency structure analysis, etc.

[1686] "Tokenization" is the process of dividing text data into its smallest units, such as words or phrases.

[1687] "Part-of-speech tagging" is the process of assigning each tokenized word or phrase its part of speech (noun, verb, adjective, etc.).

[1688] "Dependency structure analysis" is a process that analyzes the interrelationships between words in a sentence to understand its grammatical structure.

[1689] An "emotion engine" refers to an algorithm or software that recognizes emotions (positive, negative, neutral, etc.) from text data.

[1690] "Emotion recognition" is the process of identifying emotions contained in text data and classifying the emotional state.

[1691] "Correction and refinement" refers to the process of correcting typos in text data, improving grammatical structure, and replacing vocabulary with appropriate ones, in order to produce higher quality text.

[1692] "User Interface" refers to the operating screen through which a user inputs text data into the system and reviews the corrected and refined text data.

[1693] "Server" refers to the computer system that receives, analyzes, recognizes emotions, modifies and refines text data, and returns the data.

[1694] An "HTTP POST request" is part of a communication protocol for sending data from a user to a server, and is primarily used in web applications.

[1695] "JSON format" stands for JavaScript Object Notation, and is a format for organizing data and representing it simply and lightweight.

[1696] MODE FOR CARRYING OUT THE INVENTION

[1697] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, corrects and refines the text data based on the analysis results, combines it with an emotion engine that recognizes the user's emotions, and finally returns it to the user.

[1698] System configuration

[1699] The system mainly includes the following components:

[1700] 1. User Interface

[1701] It provides an interface for users to input text data. The interface can be implemented as a web application or a standalone application. For example, we will use an application that runs in a web browser.

[1702] 2. Server Receiving Method

[1703] The server receives the text data entered by the user. The method of reception is via HTTP POST request. This ensures that the server receives the data entered by the user.

[1704] 3. Natural Language Processing Methods

[1705] The server analyzes the received text data using natural language processing techniques, such as software like SpaCy or NLTK, to perform tokenization, part-of-speech tagging, and dependency structure analysis.

[1706] 4. Emotion Engine

[1707] The server is equipped with an engine to recognize user emotions from received text data. VADER and TextBlob are used as emotion engines. This allows us to identify positive, negative, and neutral emotions from text data.

[1708] 5. Correction / refinement measures

[1709] Based on the analysis and emotion recognition results, the server corrects the grammatical structure of the input text data and replaces vocabulary as necessary, for example, correcting typos and replacing vocabulary with more appropriate vocabulary.

[1710] 6. Return Method

[1711] The server returns the corrected and refined text data and emotion recognition results to the user via an HTTP response.

[1712] Specific examples of natural language processing

[1713] If the user enters "This project is very important to me," the system behaves as follows:

[1714] 1. User input

[1715] User: Enters the text "This project is very important to me" and presses submit.

[1716] 2. The server receives

[1717] Server: Receives HTTP POST requests from users and processes text data in JSON format.

[1718] 3. The server analyzes

[1719] Server: Uses SpaCy to tokenize and tag the text, then performs dependency analysis to understand the grammatical structure of the sentence.

[1720] 4. The server recognizes emotions

[1721] Server: Uses VADER to recognize the sentiment of the text data and classify it as "positive."

[1722] 5. Server fixes and refinements

[1723] Server: Based on the analysis results and emotion recognition results, replace "very" with "extremely" and make grammatical corrections.

[1724] 6. Server replies

[1725] Server: Returns the modified and refined text data "This project is extremely important to me" and the emotion recognition result "Positive" in the HTTP response.

[1726] Example prompts for generative AI models

[1727] The present invention also provides prompts for emotion recognition and text correction using generative AI models. For example, the following prompts can be used:

[1728] "Please perform a sentiment analysis on the following text: This project is very important to me."

[1729] By feeding this prompt sentence into a generative AI model, it is possible to obtain emotion recognition results and corrected / refined text.

[1730] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1731] Program processing flow

[1732] Step 1: User inputs text

[1733] Subject: User

[1734] Specific behavior:

[1735] The user uses the terminal to input text data into the interface screen, for example, "This project is very important to me."

[1736] The user clicks the "Submit" button to send the text data to the system.

[1737] input:

[1738] Input text data: "This project is very important to me"

[1739] output:

[1740] The send button is clicked and the text data is sent to the server.

[1741] Step 2: Receiving text data

[1742] Subject: Server

[1743] Specific behavior:

[1744] The server receives the text data entered by the user. This is received using an HTTP POST request.

[1745] input:

[1746] Text data sent via HTTP POST request: "This project is very important to me"

[1747] output:

[1748] The received text data is stored in JSON format for internal processing.

[1749] Step 3: Analyzing the text data

[1750] Subject: Server

[1751] Specific behavior:

[1752] The server analyzes the received text data using natural language processing software (e.g., SpaCy).

[1753] It splits text into tokens, tags each token with a part of speech, and then analyzes dependencies to understand grammatical structure.

[1754] input:

[1755] JSON text data: "This project is very important to me"

[1756] output:

[1757] Tokenized text data

[1758] Part-of-speech tagged data

[1759] Dependency structure analysis results

[1760] Step 4: Recognizing user emotions

[1761] Subject: Server

[1762] Specific behavior:

[1763] The server uses an emotion engine (e.g., VADER) to recognize the user's emotion from the text data.

[1764] The content of the text data is analyzed and a positive, negative, or neutral sentiment score is calculated.

[1765] input:

[1766] Analyzed text data (tokenization, part-of-speech tagging, dependency structure analysis results)

[1767] output:

[1768] Emotion recognition result (e.g., "positive")

[1769] Step 5: Correcting and refining the text data

[1770] Subject: Server

[1771] Specific behavior:

[1772] The server corrects and refines the text data based on the analysis and emotion recognition results.

[1773] The revisions include improving grammatical structure, correcting spelling errors, and substituting appropriate vocabulary, for example, replacing "very" with "extremely."

[1774] input:

[1775] Parsed text data

[1776] Emotion recognition results

[1777] output:

[1778] Corrected / Refined Text Data: "This project is extremely important to me."

[1779] Step 6: Returning the corrected and refined text data

[1780] Subject: Server

[1781] Specific behavior:

[1782] The server serializes the corrected and refined text data and emotion recognition results together into JSON format.

[1783] The server sends this data back as an HTTP response.

[1784] input:

[1785] Corrected and refined text data

[1786] Emotion recognition results

[1787] output:

[1788] JSON format data is returned as an HTTP response.

[1789] Step 7: Verify the user

[1790] Subject: User

[1791] Specific behavior:

[1792] The user checks the returned text data and emotion recognition results on the device's interface screen.

[1793] If necessary, the text data can be corrected again and sent again.

[1794] input:

[1795] Corrected and refined text data sent back to the device

[1796] Emotion recognition results

[1797] output:

[1798] The user checks the data, and if further corrections are required, the data is manipulated and resent.

[1799] (Application example 2)

[1800] 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."

[1801] Current content distribution services do not have a system that automatically analyzes the quality of text entered by users and the emotions contained in that text, and provides feedback. This makes it difficult for users to create high-quality text while taking emotions and content into consideration. This could result in a decline in user satisfaction and the quality of content on the platform as a whole.

[1802] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving text data entered by a user, means for analyzing the received text data using natural language processing technology, means for correcting and refining the text data based on the analysis results, and means for returning the corrected text data and emotion recognition results to the user. This enables the user to easily create high-quality text that takes into consideration emotions and content.

[1803] "User-input text data" refers to a sequence of characters or sentences that a user inputs into a system through an interface.

[1804] "Means for receiving" refers to the technology or device that allows the server to obtain the text data sent by the user.

[1805] "Natural language processing technology" is a technology that allows computers to analyze and understand natural language, which is human language.

[1806] "Means for analysis" refers to technology for analyzing received text data and identifying grammatical structure, meaning, sentiment, etc.

[1807] "Means of correction and refinement" refers to techniques for improving the grammar and content of text data based on the analysis results and arranging it into a more appropriate form.

[1808] "Emotion recognition result" is the result of identifying emotions (positive, negative, neutral, etc.) contained in text data.

[1809] "Returning means" refers to the technology used to send the corrected and refined text data and emotion recognition results to the user.

[1810] This invention relates to a system that receives text data entered by a user, analyzes it using natural language processing technology, modifies and refines the text data based on the analysis results, recognizes the user's emotions using an emotion engine, and finally returns the modified and refined text data and the emotion recognition results to the user. This section describes the program for realizing this system and its operation.

[1811] System configuration

[1812] The system mainly includes the following components:

[1813] 1. User Interface:

[1814] Users input text data from devices such as smartphones and tablets, and the input data is sent to a server via a web application or a standalone application.

[1815] 2. Server receiving method:

[1816] The server receives text data sent by the user via an HTTP POST request, etc. The received text data is processed as input data for analysis.

[1817] 3. Natural Language Processing Tools:

[1818] The server analyzes the received text data using natural language processing techniques, specifically using Python's TextBlob library to tokenize the text, tag it as a part of speech, and analyze its grammatical structure.

[1819] 4. Emotion Engine:

[1820] The server uses TextBlob's NaiveBayesAnalyzer to recognize user sentiment from the parsed text data. This sentiment engine identifies positive, negative, and neutral sentiments in the text.

[1821] 5. Modification / refinement measures:

[1822] Based on the analysis and emotion recognition results, the server performs grammatical corrections, spelling corrections, and vocabulary optimization on the text data. For example, it corrects "This projekt iz verie important to me" to "This project is very important to me."

[1823] 6. Return Method:

[1824] The server returns the corrected and refined text data and emotion recognition results to the user as an HTTP response, and the user can view the returned data through the interface.

[1825] Detailed explanation of how it works

[1826] Below is a detailed explanation of how the system works.

[1827] 1. User input:

[1828] The user enters text data into the system through the terminal interface, for example, "This project is important to me."

[1829] 2. Receiving text data:

[1830] The server receives the text data entered by the user through the receiving means, and sends the received data to the server in JSON format or the like.

[1831] 3. Text data analysis:

[1832] The server uses natural language processing tools to analyze the received data. It processes the text using the TextBlob library, tagging each token with a part of speech tag and analyzing its grammatical structure.

[1833] 4. Emotion recognition:

[1834] The server uses an emotion engine to identify positive, negative, and neutral emotions from the text data. The emotion recognition results are used for the correction and refinement process.

[1835] 5. Correcting and refining text data:

[1836] The server performs grammatical corrections on the text data based on the analysis results and emotion recognition results, and performs vocabulary replacement as necessary.

[1837] 6. Corrected and refined text data return:

[1838] The server returns the corrected and refined text data and emotion recognition results to the user's device, which are displayed in the user's interface as an HTTP response.

[1839] Examples of concrete examples and prompts

[1840] For example, if a user types "This projekt iz verie important to me":

[1841] 1. The server receives the text.

[1842] 2. Analysis using natural language processing technology.

[1843] 3. Positive emotions and perceptions with the Emotion Engine.

[1844] 4. Revised to be grammatically correct: "This project is very important to me."

[1845] 5. Correct and refine the text and emotion recognition results and return them to the user.

[1846] Prompt Sentence Examples

[1847] text

[1848] User: This projekt iz verie impotant to me

[1849] System analysis results: This project is very important to me

[1850] Emotion recognition result: Positive

[1851] In this way, users can generate high-quality text and at the same time understand the sentiment contained in that text.

[1852] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1853] Step 1:

[1854] A user uses a terminal to input text data into the interface, for example, "This project is important to me." This input data is then prepared for transmission to the server. The input data is in text format.

[1855] Step 2:

[1856] The server receives text data entered by the user via an HTTP POST request. The received data is converted to JSON format and saved on the server as input data for analysis. Here, the input is text data from the user and the output is JSON format data.

[1857] Step 3:

[1858] The server uses the TextBlob library to analyze the received text data using natural language processing techniques. Specifically, it tokenizes the text and tags each token with a part of speech. It also performs dependency analysis to understand the grammatical structure. The input here is text data in JSON format, and the output is the analyzed tokens and part of speech tagging results.

[1859] Step 4:

[1860] The server uses TextBlob's NaiveBayesAnalyzer to recognize emotions from the parsed tokens. The emotion recognition result is identified as positive, negative, or neutral. The input is the parsed tokens and part-of-speech tagging results, and the output is the emotion recognition result.

[1861] Step 5:

[1862] The server integrates the analysis results and emotion recognition results to correct and refine the text data. Specifically, it corrects typos, corrects grammatical errors, and replaces words with appropriate vocabulary. For example, it corrects "projekt" to "project." The input here is the analysis results and emotion recognition results, and the output is the corrected and refined text data.

[1863] Step 6:

[1864] The server returns the corrected and refined text data and the emotion recognition results to the user. This is again done as an HTTP response. The returned data is displayed in the user interface, where the user can check the corrected text and the emotion recognition results. The input is the corrected and refined text data and the emotion recognition results, and the output is the data displayed in the user interface.

[1865] Step 7:

[1866] The user can review the returned corrected and refined text data and emotion recognition results and make additional corrections if necessary. If the user makes additional corrections, the process starts again from one of the steps. The input is the user's feedback, and the output is the final confirmed corrected text.

[1867] 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.

[1868] 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.

[1869] 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.

[1870] 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.

[1871] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1872] 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.

[1873] 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).

[1874] 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.

[1875] 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."

[1876] 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.

[1877] 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).

[1878] 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.

[1879] 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.

[1880] 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.

[1881] 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.

[1882] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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 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.

[1883] 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.

[1884] 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.

[1885] 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.

[1886] 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.

[1887] 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.

[1888] The following is further disclosed regarding the above embodiment.

[1889] I understand. I propose the following draft claims:

[1890] (Claim 1)

[1891] means for receiving text data entered by a user;

[1892] A means for analyzing the received text data using natural language processing technology;

[1893] A means of correcting and refining the text data based on the analysis results;

[1894] A means of returning modified and refined text data to the user;

[1895] A system including:

[1896] (Claim 2)

[1897] 10. The system of claim 1, further comprising means for using natural language processing techniques to tokenize and tag part-of-speech text data entered by a user.

[1898] (Claim 3)

[1899] 10. The system of claim 1, further comprising means for correcting grammatical structures, correcting typos, and selecting appropriate vocabulary based on the analysis results.

[1900] "Example 1"

[1901] (Claim 1)

[1902] means for receiving text data entered by a user;

[1903] A means for analyzing the received text data using natural language processing technology;

[1904] A means of correcting and refining the text data based on the analysis results;

[1905] A means of returning modified and refined text data to the user;

[1906] means for providing the interface as a web application or a standalone application;

[1907] A means of tokenizing and part-of-speech tagging the data prior to analysis;

[1908] A means for correcting grammatical structures, selecting appropriate vocabulary, and replacing words based on the analysis results;

[1909] A system including:

[1910] (Claim 2)

[1911] 10. The system of claim 1, further comprising: means for using a natural language processing library to parse the tokenized text data and understand dependencies.

[1912] (Claim 3)

[1913] 10. The system of claim 1, further comprising: means for outputting a prompt sentence to check for errors in the generated sentence when returning the corrected and refined text data.

[1914] "Application Example 1"

[1915] (Claim 1)

[1916] means for receiving text data entered by a user;

[1917] A means for analyzing the received text data using natural language processing technology;

[1918] A means of correcting and refining the text data based on the analysis results;

[1919] A means of returning modified and refined text data to the user;

[1920] A means for generating modified and refined text data using a novel text generation model;

[1921] A system including:

[1922] (Claim 2)

[1923] 10. The system of claim 1, further comprising means for using natural language processing techniques to tokenize and tag part-of-speech text data entered by a user.

[1924] (Claim 3)

[1925] 10. The system of claim 1, further comprising means for correcting grammatical structures, correcting typos, and selecting appropriate vocabulary based on the analysis results.

[1926] (Claim 4)

[1927] 10. The system of claim 1, further comprising means for inputting a prompt sentence to the novel text generation model and using the generated text to generate text to be sent back to the user.

[1928] "Example 2: Combining Emotion Engines"

[1929] (Claim 1)

[1930] means for receiving text data entered by a user;

[1931] A means for analyzing the received text data using natural language processing technology;

[1932] A means of correcting and refining the text data based on the analysis results;

[1933] A means of returning modified and refined text data to the user;

[1934] A means for recognizing emotions from the analyzed text data;

[1935] A means for modifying and refining the text data based on the recognized sentiment;

[1936] A system including:

[1937] (Claim 2)

[1938] 10. The system of claim 1, further comprising means for using natural language processing techniques to tokenize and tag part-of-speech text data entered by a user.

[1939] (Claim 3)

[1940] 10. The system of claim 1, further comprising means for correcting grammatical structures, correcting typos, and selecting appropriate vocabulary based on the analysis results.

[1941] "Application example 2 when combining emotion engines"

[1942] (Claim 1)

[1943] means for receiving text data entered by a user;

[1944] A means for analyzing the received text data using natural language processing technology;

[1945] A means of correcting and refining the text data based on the analysis results;

[1946] means for returning the corrected text data and emotion recognition results to the user;

[1947] A system including:

[1948] (Claim 2)

[1949] 10. The system of claim 1, further comprising means for using natural language processing techniques to tokenize and tag part-of-speech text data entered by a user.

[1950] (Claim 3)

[1951] 10. The system of claim 1, further comprising means for correcting grammatical structures, correcting typos, and selecting appropriate vocabulary based on the analysis results, and for further performing emotion recognition. [Explanation of symbols]

[1952] 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. means for receiving text data entered by a user; A means for analyzing the received text data using natural language processing technology; A means of correcting and refining the text data based on the analysis results; a means for returning the corrected and refined text data to the user; A system including:

2. 10. The system of claim 1, further comprising means for using natural language processing techniques to tokenize and tag parts of speech of user-entered text data.

3. The system according to claim 1, further comprising means for correcting grammatical structures, correcting typos, and selecting appropriate vocabulary based on the analysis results.

Images