system

Abstract

Provide a system. A method for receiving text input from a user includes: means for segmenting the text into words and phrases using a morphological analysis engine; means for extracting words and phrases characteristic of a particular group or generation from among said words and phrases; means for analyzing the extracted words using an artificial intelligence model; means for generating a sentence that is converted into a form that is easy for a user to understand based on the analysis result; means for transmitting the generated sentence to a user terminal; A system including:

Description

[Technical Field]

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

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

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

[0004] In today's world, there has been an increase in words and phrases specific to particular generations or groups used on television programs and in online conversations. This can make communication between different generations or groups difficult and can lead to gaps in understanding. For the elderly and those who do not belong to a particular group, these words are particularly incomprehensible, making it difficult to understand information and communicate smoothly. Therefore, there is a need for a system that can easily understand the meaning of such words and phrases. [Means for solving the problem]

[0005] The present invention relates to a system that receives text entered by a user and divides the text into words and phrases using a morphological analysis engine. The system extracts words specific to a specific group or generation from the divided words and phrases and analyzes them using an artificial intelligence model. Based on the analysis results, the system generates sentences that are converted into a form that is easy for the user to understand and transmits the generated sentences to the user terminal. As a result, the user can easily understand the meaning of specific words and phrases, thereby bridging the communication gap between different generations and groups.

[0006] Furthermore, the morphological analysis engine can perform text normalization as a preprocessing step when dividing words and phrases, achieving even more accurate analysis. Furthermore, when extracting words specific to a particular group or generation, the engine can refer to a database to identify the relevant words, thereby improving analysis accuracy.

[0007] "Text" refers to a character string or sentence entered by a user.

[0008] A "morphological analysis engine" is software that divides input text into words and phrases and analyzes the meaning and parts of speech of each.

[0009] A "word" is the smallest semantic unit in a language, and is an element extracted by morphological analysis.

[0010] A "phrase" is a meaningful word or phrase formed by combining multiple words.

[0011] "Group or generational language" refers to jargon or slang that is unique to a particular age group or community.

[0012] An "artificial intelligence model" refers to a software model that uses machine learning technology to have analytical capabilities similar to human knowledge.

[0013] "Analysis" refers to the process of understanding the internal structure and meaning of input data by breaking it down and examining it.

[0014] A "transformed sentence" is a sentence in which difficult terms or phrases contained in the original text have been replaced with easier-to-understand terms or phrases.

[0015] A "database" refers to a collection of information collected and organized for a specific purpose, and in this system it holds semantic information for specific words and phrases.

[0016] "Text normalization" is the process of arranging text into a unified format before morphological analysis.

[0017] "User terminal" refers to an electronic device that is directly operated by the user, and in this system is mainly used for input and display of results. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] As an embodiment of the present invention, we will specifically explain a system that analyzes and converts words and phrases that are difficult for users to understand. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology to convert words that are unique to a specific group or generation into an easier-to-understand form.

[0040] System program processing

[0041] Input Reception

[0042] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0043] The terminal receives input text from the user and generates a request to send this text to the server.

[0044] Text Preprocessing

[0045] The server receives a text request sent from the device. It uses a morphological analysis engine (e.g., Mecab) to split this text into words and phrases. For example, it could split the text into "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0046] Semantic and Intention Analysis

[0047] The server extracts words specific to a particular group or generation from the segmented words and phrases. For example, it extracts the word "oshikatsu." It then analyzes the meaning of the extracted words using an artificial intelligence model (e.g., BERT or GPT). It verifies that "oshikatsu" refers to the activity of supporting a particular character or artist.

[0048] Transformation and Description Generation

[0049] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it converts it into a form such as, "Oshikatsu is the activity of supporting a favorite artist or character." It also generates an explanatory text that includes additional background information and context as needed. For example, it adds an explanation such as, "It is a term that is particularly popular among young people and is used as part of fan activities."

[0050] Returning and displaying results

[0051] The server generates a request to transmit the generated description to the terminal.

[0052] The device receives the explanation request sent from the server and displays it to the user. For example, it displays something like, "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0053] In this way, users can understand words and phrases that are difficult to understand in an easy-to-understand manner.This invention can bridge the communication gap between different generations and groups.

[0054] The processing flow will be explained below.

[0055] Specific processing steps of the program

[0056] Step 1:

[0057] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0058] Step 2:

[0059] The terminal receives input text from the user and generates a request to send this text to the server.

[0060] Step 3:

[0061] The server receives the text request sent from the terminal.

[0062] Step 4:

[0063] The server uses a morphological analysis engine (e.g., Mecab) to split the received text into words and phrases, such as "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0064] Step 5:

[0065] The server extracts words that are specific to a particular group or generation from the segmented words and phrases. For example, it extracts the word "oshikatsu."

[0066] Step 6:

[0067] The server uses an artificial intelligence model (e.g., BERT or GPT) to analyze the meaning of the extracted words. For example, it confirms that "oshikatsu" refers to the activity of supporting a specific character or artist.

[0068] Step 7:

[0069] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it generates a sentence such as, "'Oshikatsu' is the activity of supporting a favorite artist or character."

[0070] Step 8:

[0071] The server generates a description with additional background information and context as needed, for example, "This term is popular among young people and is used as part of fan activities."

[0072] Step 9:

[0073] The server generates a request to transmit the generated description to the terminal.

[0074] Step 10:

[0075] The terminal receives the explanation request sent from the server.

[0076] Step 11:

[0077] The device then displays the received explanation to the user. For example, it might say, "Oshikatsu is the act of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0078] This concrete step allows users to understand difficult words and phrases in an easy-to-understand and explained way.

[0079] Example 1

[0080] 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."

[0081] Words and phrases used by different generations or specific groups can be difficult to understand, creating a communication gap. In such situations, a means is needed to easily understand the meaning of specific words and phrases, but traditional methods often do not adequately solve this problem. In particular, there is a need for technology that can convert words into a form that is easily understandable to users while understanding related background information and context.

[0082] 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.

[0083] In this invention, the server includes means for receiving text input from a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words specific to a specific group or generation, means for analyzing the extracted words using an artificial intelligence model, means for generating explanatory text in a form that is easy for the user to understand using a generative AI model using a prompt text, means for transmitting the generated explanatory text to a user terminal, and means for displaying the generated explanatory text on a user interface, thereby enabling users to intuitively understand the meanings of words and phrases of different generations or groups.

[0084] "User" refers to an individual or organization that uses the system.

[0085] "Terminal" refers to a device or equipment that allows a user to input information.

[0086] "Text" refers to a character string or sentence entered by a user.

[0087] A "morphological analysis engine" refers to a software tool that breaks text into morphemes (words and phrases).

[0088] A "prompt sentence" refers to an input sentence that gives instructions to a generative AI model for analysis or conversion.

[0089] A "generative AI model" refers to an algorithm or software that uses artificial intelligence techniques to analyze input data and generate an appropriate output.

[0090] "User interface" refers to the screen and operating means that allow a user to interact with a system.

[0091] "Means for splitting" refers to the function of splitting text into words and phrases using a morphological analysis engine.

[0092] "Means of extraction" refers to the function of finding words specific to a particular group or generation within text.

[0093] "Means of analysis" refers to the function of analyzing the meaning and intent of extracted words using an artificial intelligence model.

[0094] "Means for generating" refers to the function of creating an explanation that is easy for the user to understand based on the analysis results.

[0095] The "transmitting means" refers to a communication function for transmitting the generated explanatory text to the user terminal.

[0096] The "display means" refers to a function for displaying the generated explanatory text on the screen of the user terminal.

[0097] As an embodiment of the present invention, a system for analyzing and converting words and phrases that are difficult for users to understand will be specifically described. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology to convert words that are specific to a specific group or generation into an easier-to-understand form.

[0098] The main components of this system are the user terminal, server, morphological analysis engine, and generative AI model.

[0099] First, the user inputs text containing words or phrases that are difficult to understand into the device. For example, they might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." The device receives this input text, creates a request body in JSON format, and sends it to the server as an HTTP request. The specific hardware used by the device could be, for example, a smartphone or a PC.

[0100] The server receives a text request sent from the device. It uses a morphological analysis engine (e.g., Mecab) to break down the received text into words and phrases. For example, it might break down the text into something like, "The other day, I heard the word 'oshikatsu' many times on TV, but I didn't understand what it meant." The software used here is the morphological analysis engine Mecab.

[0101] Next, the server extracts words specific to a particular group or generation (e.g., "oshikatsu") from the segmented words and phrases. A generative AI model (e.g., BERT or GPT) is used to analyze the meaning and intent of the extracted words. The generative AI model receives instructions using prompts and performs the analysis. For example, the prompt might be, "Analyze the meaning of the word oshikatsu, convert it into a general term, and generate an explanatory text including background information."

[0102] The server generates an easy-to-understand explanation for the user based on the analysis results from the AI ​​model. For example, it converts the information into something like, "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0103] The generated explanation is sent from the server to the user's device as an HTTP response. The device receives this response and displays it in a text area or pop-up on the user interface (UI). The user can read and understand the explanation displayed on the screen. A specific example of what is displayed is, "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people, and is used as part of fan activities."

[0104] This allows users to intuitively understand the meaning of words and phrases from different generations and groups, thereby bridging communication gaps. This invention facilitates smooth communication between different generations and groups, and makes it easier to understand the meaning of words.

[0105] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0106] Step 1:

[0107] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, they might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." This input text becomes the input to the system. The device receives this text and temporarily stores it in its internal memory for subsequent processing.

[0108] Step 2:

[0109] The device generates a request to send the text received from the user to the server. This request is usually in JSON format and sent to the server using an HTTP POST request. The request body contains the text entered by the user.

[0110] Step 3:

[0111] The server receives an HTTP POST request sent from the device. It extracts text from the request body and uses a morphological analysis engine (e.g., Mecab) to split the text into words and phrases. The input to this step is the text entered by the user, and the output is a list of words and phrases split by morphological analysis. For example, the phrase might be split as follows: "The other day, I heard the word 'oshikatsu' many times on TV, but I didn't understand what it meant."

[0112] Step 4:

[0113] The server extracts words specific to a particular group or generation from the segmented words and phrases. This extraction can be done by referencing a database. For example, the word "oshikatsu" is extracted. The input of this step is a list of segmented words and phrases, and the output is a specific word (e.g., "oshikatsu").

[0114] Step 5:

[0115] The server uses a generative AI model (such as BERT or GPT) to analyze the meaning of the extracted words. A prompt is used to give instructions to the model and perform the analysis. For example, the prompt could be set as "Analyze the meaning of the word 'oshikatsu,' convert it into a general term, and generate an explanation including background information." The input of this step is the specific extracted words, and the output is the analysis results including the meaning of the words and background information.

[0116] Step 6:

[0117] The server generates an easy-to-understand explanation for the user based on the analysis results from the generative AI model. For example, it generates the explanation, "'Oshikatsu' refers to the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people and is used as part of fan activities." The input of this step is the analysis results, and the output is the generated explanation.

[0118] Step 7:

[0119] The server converts the generated description into a JSON-formatted response body and sends it to the terminal as an HTTP response. The input of this step is the generated description, and the output is the HTTP response.

[0120] Step 8:

[0121] The device receives the HTTP response sent from the server and extracts the description from the response body. The device displays this description in a text area or pop-up on the user interface (UI). For example, it might say, "Oshikatsu is the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people and is used as part of fan activities." The input of this step is the HTTP response, and the output is the description to be displayed.

[0122] Through these steps, users can intuitively understand the meaning of difficult-to-understand words and phrases contained in the input text.

[0123] (Application example 1)

[0124] 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."

[0125] In today's information society, diverse users increasingly use words and coded phrases specific to different groups or generations. From a security perspective, it is particularly important to analyze suspicious terms and coded expressions in real time, convert them into understandable forms, and display warnings. However, current systems lack the means to efficiently perform such analysis and conversion, often resulting in delayed responses. A solution to this problem is needed.

[0126] 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.

[0127] In this invention, the server includes means for receiving text input from a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words unique to a specific group or generation from the words and phrases, means for analyzing the extracted words using an artificial intelligence model, means for generating a sentence converted into a form easy for the user to understand based on the analysis result, means for transmitting the generated sentence to a user terminal, and means for generating and displaying a warning message when a security risk is detected. This enables real-time analysis of terms used by different generations or groups and automatic generation of easy-to-understand warning messages based on the analysis.

[0128] The "means for receiving text input from a user" is a device or program that obtains text information input by a user and stores it for subsequent processing.

[0129] A "morphological analysis engine" is an analytical tool that divides input text into semantic units such as words and phrases.

[0130] The "means for dividing into words and phrases" is a device or program that divides input text into meaningful units, such as words and phrases, using a morphological analysis engine.

[0131] The "means for extracting words specific to a particular group or generation" is a device or program that identifies and extracts words specific to a particular group or generation from among the segmented words or phrases.

[0132] "Means for analyzing using an artificial intelligence model" refers to a device or program that uses artificial intelligence technology to perform analysis in order to understand the meaning of extracted words.

[0133] The "means for generating sentences converted into a form that is easy for the user to understand" is a device or program that converts words and phrases into a form that is easy for the user to understand based on the analysis results and generates new sentences.

[0134] The "means for transmitting the generated sentence to the user terminal" is a device or program that transfers the converted sentence to the user terminal and displays it.

[0135] The "means for generating and displaying a warning message when a security risk is detected" refers to a device or program that automatically generates a warning message and notifies the user when a security risk is detected as a result of the analysis.

[0136] As an embodiment of the present invention, we will specifically describe a system in which a security team analyzes suspicious text data in real time, converts it into an easy-to-understand format, and displays a warning. This system processes text data entered by a user using a morphological analysis engine and artificial intelligence technology, analyzing and converting words unique to specific groups or generations. Furthermore, if a security risk is detected based on the analysis results, a warning message is automatically generated and notified to the user.

[0137] System configuration

[0138] 1. Input reception:

[0139] The server receives text entered by users, such as chat logs, emails, social media posts, etc. For example, suppose a user enters, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0140] 2. Text preprocessing:

[0141] The server splits the received text into words and phrases using a morphological analysis engine (e.g., Mecab), and performs text normalization.

[0142] 3. Semantic and Intention Analysis:

[0143] The server extracts words specific to a particular group or generation from the segmented words and phrases. It then analyzes the extracted words using an artificial intelligence model (e.g., BERT or GPT). For example, it confirms that the word "oshikatsu" (supporting a specific character or artist) refers to the activity of supporting a specific character or artist.

[0144] 4. Transformation and Description Generation:

[0145] Based on the analysis results, the server converts the words into a form that is easy for the user to understand. For example, it generates an explanation such as, "'Oshikatsu' is the activity of supporting your favorite artist or character."

[0146] 5. Security Risk Analysis:

[0147] If the analysis reveals that certain words or phrases contain potential security risks, the server will detect this and generate a warning message.

[0148] 6. Sending and viewing results:

[0149] The server sends the generated explanatory text and warning message to the user's device, which then displays it to the user. For example, it might say, "Oshikatsu is the activity of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0150] Hardware and software used

[0151] Hardware:

[0152] Terminals (PCs, smartphones), servers

[0153] software:

[0154] Morphological analysis engine (Mecab)

[0155] Artificial intelligence models (BERT and GPT)

[0156] Databases (storing words specific to specific groups or generations)

[0157] Specific examples

[0158] For example, if a security operator sees a message in a chat log they are monitoring saying, "Let's go to that artist's concert tomorrow! 'Oshikatsu' is the best!", the system will generate an explanation in real time: "'Oshikatsu' is the activity of supporting your favorite artist or character. It's especially popular among young people." and display it, while also assessing the associated risks and displaying a warning message if necessary.

[0159] Prompt Sentence Examples

[0160] Extract suspicious words and phrases from the given text and explain their meaning: I'm going to see that artist's concert tomorrow! "Supporting my favorite artist" is the best!

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] A user inputs text into the device that contains words or phrases that are difficult to understand. For example, they might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." The device receives this input text and generates a request to send to the server. The input is the text entered by the user, and the output is the request to send to the server.

[0164] Step 2:

[0165] The server receives a text request sent from a device. It uses a morphological analysis engine (e.g., Mecab) to split this text into words and phrases. For example, it might split something like, "The other day, I heard the word 'oshikatsu' many times on TV, but I didn't understand what it meant." The input is the received text request, and the output is the split words and phrases.

[0166] Step 3:

[0167] The server extracts words specific to a particular group or generation from the segmented words and phrases. For example, to extract the word "oshikatsu," it refers to a specific database. The input is the segmented words and phrases, and the output is the extracted words.

[0168] Step 4:

[0169] The server analyzes the extracted words using an artificial intelligence model (e.g., BERT or GPT). It verifies that "oshikatsu" refers to the activity of supporting a specific character or artist. The input is the extracted words, and the output is the analysis results.

[0170] Step 5:

[0171] Based on the analysis results, the server generates a sentence that is converted into a form that is easy for the user to understand. For example, it converts it into a form such as "'Oshikatsu' is the activity of supporting a favorite artist or character." It may also generate an explanatory sentence that includes additional background information and context as needed. The input is the analysis results, and the output is the converted sentence.

[0172] Step 6:

[0173] If a security risk is detected as a result of the analysis, the server automatically generates a warning message. For example, it generates a message saying, "This phrase may contain a high security risk." The input is the analysis result, and the output is the warning message.

[0174] Step 7:

[0175] The server generates a request to send the generated explanatory text and warning message to the user's terminal. The terminal receives the explanatory text and warning message sent from the server and displays them to the user. The input is the generated explanatory text and warning message, and the output is the displayed result. For example, it could display "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people and is used as part of fan activities," and also display a warning message if necessary.

[0176] 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.

[0177] As an embodiment of the present invention, we will explain a specific configuration that combines an emotion engine with a system that analyzes and converts words and phrases that are difficult for users to understand. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology, and also recognizes the user's emotions and provides feedback in an appropriate form.

[0178] System program processing

[0179] Input Reception

[0180] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0181] The terminal receives input text from the user and generates a request to send this text to the server.

[0182] Text and sentiment preprocessing

[0183] The server receives a text request sent from the device. It uses a morphological analysis engine (e.g., Mecab) to split this text into words and phrases. For example, it could split the text into "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0184] The server simultaneously uses an emotion engine to recognize emotions from the text entered by the user, for example, the emotion engine recognizes "confused."

[0185] Semantic and Intention Analysis

[0186] The server extracts words specific to a particular group or generation from the segmented words and phrases. For example, it extracts the word "oshikatsu." It then analyzes the meaning of the extracted words using an artificial intelligence model (e.g., BERT or GPT). It verifies that "oshikatsu" refers to the activity of supporting a particular character or artist.

[0187] Transformation and Description Generation

[0188] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it generates a sentence such as, "'Oshikatsu' is the activity of supporting a favorite artist or character."

[0189] Here, the server takes into account the user's emotional information recognized by the emotion engine. For example, if the emotion "confusion" is recognized, it adds a sentence to ease the emotion or an encouraging message, such as "Don't worry, 'oshikatsu' is a very fun activity!"

[0190] Returning and displaying results

[0191] The server generates a request to send an additional message to the terminal according to the generated description and emotion.

[0192] The device receives the explanation and message request sent from the server and displays it to the user. For example, it displays something like, "'Oshikatsu' is the activity of supporting your favorite artist or character. It's a term that's especially popular among young people, and is used as part of fan activities. Don't worry, 'Oshikatsu' is a very fun activity!"

[0193] This added emotion engine allows users to receive explanations in a more familiar way and to more easily understand words and phrases that are difficult to understand. This invention can bridge the communication gap between different generations and groups, and also provide feedback that takes into account the user's emotions.

[0194] The processing flow will be explained below.

[0195] MODE FOR CARRYING OUT THE INVENTION

[0196] Step 1:

[0197] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0198] Step 2:

[0199] The terminal receives input text from the user and generates a request to send this text to the server.

[0200] Step 3:

[0201] The server receives the text request sent from the terminal.

[0202] Step 4:

[0203] The server uses a morphological analysis engine (e.g., Mecab) to split the received text into words and phrases, such as "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0204] Step 5:

[0205] The server simultaneously uses an emotion engine to recognize emotions from the text entered by the user, such as the emotion "confused." The emotion engine uses natural language processing to assess the emotional tone of the text.

[0206] Step 6:

[0207] The server extracts words that are specific to a particular group or generation from the segmented words and phrases. For example, the word "oshikatsu" (supporting someone) is extracted.

[0208] Step 7:

[0209] The server uses an artificial intelligence model (e.g., BERT or GPT) to analyze the meaning of the extracted words. For example, it confirms that "oshikatsu" refers to the activity of supporting a specific character or artist.

[0210] Step 8:

[0211] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it generates a sentence such as, "'Oshikatsu' is the activity of supporting a favorite artist or character."

[0212] Step 9:

[0213] The server takes into account the user's emotional information recognized by the emotion engine. For example, if the emotion "confusion" is recognized, it adds a message to ease the emotion or an encouraging message, such as "Don't worry, 'oshikatsu' is a very fun activity!"

[0214] Step 10:

[0215] The server generates a request to send an additional message to the terminal according to the generated description and emotion.

[0216] Step 11:

[0217] The terminal receives the explanatory text and the message request sent from the server.

[0218] Step 12:

[0219] The device then displays the received explanation to the user. For example, it might say, "'Oshikatsu' is the activity of supporting your favorite artist or character. It's a term that's especially popular among young people, and is used as part of fan activities. Don't worry, 'Oshikatsu' is a lot of fun!"

[0220] This concrete step allows users to understand difficult words and phrases in an easy-to-understand manner, while also receiving emotionally sensitive feedback.

[0221] Example 2

[0222] 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."

[0223] In today's world, the words and phrases used between generations and specific groups are becoming more diverse, making it difficult for users to understand their meanings. It is also important to consider the confusion and discomfort users may feel when searching for the meaning of a particular word or phrase. In such situations, a system that provides easy-to-understand explanations to users while also taking their feelings into consideration is required.

[0224] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0225] In this invention, the server includes means for receiving text input from a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words specific to a particular group or generation from the words and phrases, means for analyzing the extracted words using an artificial intelligence model, means for generating a sentence converted into a form that is easy for the user to understand based on the analysis result, means for recognizing the user's emotion, means for generating a message corresponding to the emotion based on the recognized emotion, and means for transmitting the generated sentence and the message based on the emotion to a user terminal. This makes it possible to clearly explain the meaning of words and phrases that are difficult for the user to understand, and further reduce the confusion and discomfort felt by the user.

[0226] "User" refers to someone who uses the system to find the meaning of words or phrases that are difficult to understand.

[0227] "Text" refers to a sentence or string of characters that a user sends to a system using an input device.

[0228] A "morphological analysis engine" refers to software that divides input text into words and phrases and analyzes their structure.

[0229] "Words and Phrases" refers to sequences of words that form small units of language or short sentences extracted from text by a morphological analysis engine.

[0230] "Group or generational idiom" refers to distinctive terms and expressions that are used specifically within a particular cultural background or generation.

[0231] An "artificial intelligence model" refers to an algorithm that uses machine learning and deep learning techniques to analyze and understand the meaning of words and phrases.

[0232] "Analysis results" refers to the information generated after an AI model analyzes a particular word or phrase.

[0233] "Sentences converted into a form that is easy for users to understand" refers to sentences in which technical terms and words specific to a particular group or generation have been replaced with expressions that are easy for the general public to understand, based on the analysis results.

[0234] "Emotion" refers to the psychological state a user feels when they input a particular piece of text.

[0235] An "emotion engine" refers to software that analyzes input text and automatically recognizes the user's psychological state from it.

[0236] "Emotion-responsive messages" refer to sentences generated to reassure, encourage, or otherwise respond to the user's emotions based on the user's recognized emotions.

[0237] "User terminal" refers to a computing device (e.g., smartphone, tablet, computer) used by a user that includes an interface for communicating with the system.

[0238] As an embodiment of the present invention, we will explain in detail a system that analyzes and converts words and phrases that are difficult for users to understand. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology, and also recognizes the user's emotions and provides feedback in an appropriate form.

[0239] Input Reception

[0240] The user inputs text into the device that includes words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." The device receives the input text from the user and generates a request to send this text to the server. Specifically, the device converts the input text into a data packet and sends it to the server as an HTTP POST request.

[0241] Text and sentiment preprocessing

[0242] The server receives a text request sent from the device. This text is stored in the server's input buffer. The server uses a morphological analysis engine (for example, the Japanese morphological analysis engine Mecab) to divide the text into words and phrases. For example, the server breaks down the text into "I heard the word 'oshikatsu' many times, but I didn't understand its meaning" into "oshikatsu" (words) many times, but I didn't understand its meaning. The server then uses an emotion engine to analyze emotions from the text entered by the user. For example, the emotion engine (for example, a natural language processing API) recognizes the emotion "confused."

[0243] Semantic and Intention Analysis

[0244] The server extracts words specific to a particular group or generation from the segmented words and phrases. Specifically, it references dictionaries and databases to extract the word "oshikatsu." The server then analyzes the meaning of the extracted words using an artificial intelligence model (e.g., BERT or GPT). The BERT model is used to understand the context of "oshikatsu" and confirm that it refers to the activity of supporting a specific character or artist.

[0245] Transformation and Description Generation

[0246] Based on the analysis results, the server generates a sentence that is easy for the user to understand. Specifically, it generates an explanatory sentence such as, "Oshikatsu is an activity to support your favorite artists or characters." Furthermore, the server takes into account the user's emotional information recognized by the emotion engine. For example, if the emotion "confusion" is recognized, the server adds an encouraging message to alleviate that emotion: "Don't worry, 'Oshikatsu' is a very fun activity!"

[0247] Returning and displaying results

[0248] The server generates a request to send the generated description and an additional message corresponding to the emotion to the device. Specifically, it converts the generated sentence and message into JSON data and sends it to the device as an HTTP response. The device receives the description and message sent from the server and displays it to the user. For example, it displays something like, "'Oshikatsu' is the activity of supporting your favorite artist or character. Don't worry, 'Oshikatsu' is a very fun activity!"

[0249] Examples of concrete examples and prompts

[0250] As a specific example, if a user types, "The word 'Egae' came up a lot at the party yesterday. What does it mean?", the server will generate the answer, "'Egae' means that a photo or video is beautifully taken and looks good. It is a term that is particularly commonly used on social media," and send it to the device.

[0251] An example of a prompt sentence is, "Please look up the meaning of a specific word or phrase. The text is 'What does XX (the word you want to look up) mean?'"

[0252] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0253] Step 1:

[0254] The user inputs text into the device that includes words and phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." Input: User's text data. Output: Text data input into the device.

[0255] Step 2:

[0256] The terminal receives input text from the user and generates a request to send to the server. Specifically, it converts the input text into a data packet and sends it to the server as an HTTP POST request. Input: User's text data. Output: HTTP POST request to the server.

[0257] Step 3:

[0258] The server receives a text request sent from the terminal. The text is saved in the server's input buffer. Input: HTTP request data. Output: Text data saved in the server's input buffer.

[0259] Step 4:

[0260] The server uses a morphological analysis engine (for example, a morphological analysis engine) to split the text into words and phrases. As a concrete example, the server splits the text "I heard the word 'oshikatsu' many times, but I didn't understand its meaning" into "oshikatsu" (the word) many times, but I didn't understand its meaning." Input: Text data saved in the server's input buffer. Output: A list of split words and phrases.

[0261] Step 5:

[0262] The server uses an emotion engine to analyze emotions from the text entered by the user. For example, the emotion engine recognizes the emotion "confused." Input: Text data stored in the server's input buffer. Output: Emotion data for "confused."

[0263] Step 6:

[0264] The server extracts words specific to a particular group or generation from the segmented words and phrases. Specifically, it extracts the word "oshikatsu" by referring to a dictionary or database. Input: A list of segmented words and phrases. Output: Extracted specific words.

[0265] Step 7:

[0266] The server uses an artificial intelligence model (e.g., a generative AI model) to analyze the meaning of the extracted words. As a specific example, it uses the BERT model to understand the context of "oshikatsu" and confirm that it refers to the activity of supporting a specific character or artist. Input: Specific extracted words. Output: Semantic data of the analysis results.

[0267] Step 8:

[0268] Based on the analysis results, the server generates a sentence that is converted into a form that is easy for the user to understand. As a specific example, it generates the sentence, "'Oshikatsu' is the activity of supporting a favorite artist or character." Input: Semantic data from the analysis results. Output: Sentence that has been converted into a form that is easy for the user to understand.

[0269] Step 9:

[0270] The server generates a message corresponding to the emotion, taking into account the user's emotional information recognized by the emotion engine. For example, to alleviate the emotion of "confusion," it adds a message such as "Don't worry, 'oshikatsu' is a very fun activity!". Input: Emotion data. Output: A sentence containing a message.

[0271] Step 10:

[0272] The server generates a request to send the generated description and a message based on the emotion to the device. Specifically, it converts the generated sentence and message into JSON data and sends it as an HTTP response to the device. Input: Sentence containing the message. Output: HTTP response to the device.

[0273] Step 11:

[0274] The device receives the explanation and message request sent from the server and displays them to the user. For example, it displays the following: "Oshikatsu is the activity of supporting your favorite artists or characters. Don't worry, oshikatsu is a very fun activity!" Input: HTTP response from the server. Output: Explanation and message displayed on the user's device.

[0275] (Application example 2)

[0276] 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."

[0277] In current food delivery services, user reviews and feedback often contain words and phrases that are difficult to understand. Furthermore, the feedback provided ignores the user's feelings, preventing improvements to the user experience. In particular, the inability to properly interpret user opinions and requests regarding the taste of food can delay improvements to the delivery service and the restaurant. Therefore, there is a need for a system that can properly analyze user feedback and provide easy-to-understand feedback that takes user feelings into consideration.

[0278] The identification process by the identification 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 input by a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words unique to a specific group or generation from the words and phrases, means for analyzing the extracted words using an artificial intelligence model, means for generating a sentence converted into a form easy for the user to understand based on the analysis result, means for adding feedback to the generated sentence that takes into account the user's emotions, and means for transmitting the generated sentence and feedback to the user terminal. This makes it possible to appropriately analyze reviews and feedback from users and provide feedback that is easy to understand and takes into account their emotions.

[0279] The "means for receiving text input from a user" is an interface for receiving text data such as reviews and feedback input by a user.

[0280] A "morphological analysis engine" is an analysis engine that divides natural languages ​​such as Japanese into words and phrases.

[0281] The "means for splitting into words and phrases" refers to a means for breaking down input text into individual words and phrases using a morphological analysis engine.

[0282] A "means for extracting words specific to a particular group or generation" is a means for searching for and extracting words or slang specific to a particular age group or community from text.

[0283] An "artificial intelligence model" is a machine learning model used to learn from large amounts of text data and analyze input text.

[0284] "Means for analyzing" refers to the means for analyzing extracted words and phrases using an artificial intelligence model to understand their meaning and context.

[0285] The "means for generating sentences converted into a form that is easy for the user to understand" is a means for reconstructing text into a form that is easy for the user to understand, based on the content analyzed by the artificial intelligence model.

[0286] The "means for adding feedback that takes into account the user's emotions" is a means for recognizing emotions from text entered by the user and adding feedback that matches those emotions.

[0287] The "means for transmitting to the user terminal" refers to a means for transmitting the generated text and feedback to the terminal used by the user.

[0288] The program of the system that realizes this invention performs the following process in stages: First, the specific steps when a user posts a review or feedback using a food delivery app will be explained.

[0289] System Overview

[0290] 1. Receiving user input

[0291] The server receives the text input by the user, for example, a review such as "The food was delicious, but the flavor was too strong, so it might not be suitable for children." This allows the text data input by the user to be incorporated into the system.

[0292] 2. Morphological analysis

[0293] The server uses Mecab as a morphological analysis engine to split the input text into words and phrases, such as "The food was delicious, but the flavor was too strong, so it might not be suitable for children."

[0294] 3. Extracting specific words

[0295] The server references the database to extract words that are specific to a particular group or generation, such as "delicious" or "not suitable" in reviews.

[0296] 4. Word Analysis

[0297] The server uses artificial intelligence models such as BERT and GPT to analyze the meaning and context of the extracted words, resulting in an interpretation such as "The food is delicious, but the flavor is too strong for children to eat."

[0298] 5. Generate feedback

[0299] The server generates feedback based on the analysis results in a format that is easy for the user to understand. Furthermore, it analyzes the user's emotions using the Google® Cloud Natural Language API, and if the emotion of "dissatisfaction" is recognized, this is reflected in the feedback. For example, the server may generate feedback such as, "Thank you for rating the taste of the dish. Your comment that the flavor is too strong and not suitable for children can be adjusted for your next order."

[0300] 6. Submitting Feedback

[0301] The server sends the generated feedback and analysis results to the user's device, which receives them and displays the review content in an easy-to-understand manner.

[0302] Hardware and software used

[0303] Morphological analysis engine: Mecab

[0304] Sentiment engine: Google Cloud Natural Language API

[0305] Artificial intelligence models: BERT, GPT

[0306] Specific examples

[0307] A user leaves the following review on a food delivery app:

[0308] "The food was delicious, but the flavor was too strong and probably not suitable for children. It's very different from my mother's cooking."

[0309] The server receives this and segments it using morphological analysis. It then extracts specific words and uses an AI model to obtain the analysis results. The emotion engine considers the emotion recognized as "unsatisfied" and generates appropriate feedback. The feedback the user will next see is as follows:

[0310] "Thank you for rating the taste of our food. We understand that the flavor is too strong and unsuitable for children. We will adjust it for your next order. We will also strive to recreate your mother's cooking style!"

[0311] Prompt Sentence Examples

[0312] Prompt sentence to input to the generative AI model:

[0313] "Please parse the following text, convert it to something understandable, and generate feedback taking into account sentiment:

[0314] Text: 'The food was delicious, but the flavor was too strong and perhaps not suitable for children. It's nothing like my mother's cooking.'

[0315] User sentiment: 'Unsatisfied'

[0316] Requirement: Convert into an understandable format and generate feedback for next time.

[0317] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0318] Step 1:

[0319] The server receives text input from the user. When the user enters a review or feedback through the food delivery app and clicks submit, this text data is sent to the server. The input is the text data posted by the user, and the output is the text data received as is.

[0320] Step 2:

[0321] The server uses a morphological analysis engine (Mecab) to divide the received text into words and phrases. Specifically, the server passes the text data to Mecab, which then performs a mechanical grammatical analysis to break it down into words and phrases. The input is the text data received in step 1, and the output is the text divided by morphological analysis. For example, the input "The food was delicious, but the flavor was too strong, so it might not be suitable for children" is changed to the output "The food was delicious, but the flavor was too strong, so it might not be suitable for children."

[0322] Step 3:

[0323] The server performs text normalization as preprocessing. This process involves removing unnecessary spaces and special characters from the text and performing pattern matching using regular expressions. The input is the text split in step 2, and the output is the normalized text. For example, "The food was delicious, but the flavor was too strong, so it might not be suitable for children" becomes "The food was delicious, but the flavor was too strong, so it might not be suitable for children."

[0324] Step 4:

[0325] The server references a database to extract words specific to a particular group or generation from the normalized text. For example, it may have a database listing words used by a particular age group or community, and searches through it to extract the relevant words. The input is the text normalized in step 3, and the output is the specific words extracted. For example, "delicious" or "not suitable."

[0326] Step 5:

[0327] The server analyzes the extracted words using an artificial intelligence model (BERT or GPT). Specifically, the extracted words and phrases are input into the AI ​​model, which analyzes their context and meaning. The input is the words extracted in step 4, and the output is the analysis result based on the context and meaning of those words. For example, the conclusion is "It's delicious, but the flavor is too strong for children to eat."

[0328] Step 6:

[0329] Based on the analysis results, the server generates a sentence that is converted into a form that is easy for the user to understand. In this step, an explanation is generated in a format that is easy for the user to understand based on the analysis results of the AI ​​model. The input is the analysis result obtained in step 5, and the output is a reconstructed explanation. For example, feedback such as "Thank you for rating the taste of the dish. Your opinion that the flavor is too strong and not suitable for children can be adjusted for your next order."

[0330] Step 7:

[0331] The server adds feedback to the generated description, taking into account the user's emotions. Using an emotion engine (Google Cloud Natural Language API), it recognizes emotions from the user's input text and generates an additional message based on that. The input is the description obtained in step 6 and the user's emotional data, and the output is the final feedback. For example, it could be something like, "We received feedback that the flavor was too strong, but we will adjust it for your next order. We will also try to recreate your mother's recipe!"

[0332] Step 8:

[0333] The server sends the generated sentence and feedback to the user's device, which receives it and displays it to the user in the app. The input is the final feedback sentence generated in step 7, and the output is the data sent to the user's device. This allows the user to see how their review is interpreted and fed back.

[0334] 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.

[0335] 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.

[0336] 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.

[0337] [Second embodiment]

[0338] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0339] 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.

[0340] 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).

[0341] 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.

[0342] 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.

[0343] 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).

[0344] 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.

[0345] 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.

[0346] 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.

[0347] 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.

[0348] 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.

[0349] 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."

[0350] As an embodiment of the present invention, we will specifically explain a system that analyzes and converts words and phrases that are difficult for users to understand. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology to convert words that are unique to a specific group or generation into an easier-to-understand form.

[0351] System program processing

[0352] Input Reception

[0353] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0354] The terminal receives input text from the user and generates a request to send this text to the server.

[0355] Text Preprocessing

[0356] The server receives a text request sent from the device. It uses a morphological analysis engine (e.g., Mecab) to split this text into words and phrases. For example, it could split the text into "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0357] Semantic and Intention Analysis

[0358] The server extracts words specific to a particular group or generation from the segmented words and phrases. For example, it extracts the word "oshikatsu." It then analyzes the meaning of the extracted words using an artificial intelligence model (e.g., BERT or GPT). It verifies that "oshikatsu" refers to the activity of supporting a particular character or artist.

[0359] Transformation and Description Generation

[0360] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it converts it into a form such as, "Oshikatsu is the activity of supporting a favorite artist or character." It also generates an explanatory text that includes additional background information and context as needed. For example, it adds an explanation such as, "It is a term that is particularly popular among young people and is used as part of fan activities."

[0361] Returning and displaying results

[0362] The server generates a request to transmit the generated description to the terminal.

[0363] The device receives the explanation request sent from the server and displays it to the user. For example, it displays something like, "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0364] In this way, users can understand words and phrases that are difficult to understand in an easy-to-understand manner.This invention can bridge the communication gap between different generations and groups.

[0365] The processing flow will be explained below.

[0366] Specific processing steps of the program

[0367] Step 1:

[0368] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0369] Step 2:

[0370] The terminal receives input text from the user and generates a request to send this text to the server.

[0371] Step 3:

[0372] The server receives the text request sent from the terminal.

[0373] Step 4:

[0374] The server uses a morphological analysis engine (e.g., Mecab) to split the received text into words and phrases, such as "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0375] Step 5:

[0376] The server extracts words that are specific to a particular group or generation from the segmented words and phrases. For example, it extracts the word "oshikatsu."

[0377] Step 6:

[0378] The server uses an artificial intelligence model (e.g., BERT or GPT) to analyze the meaning of the extracted words. For example, it confirms that "oshikatsu" refers to the activity of supporting a specific character or artist.

[0379] Step 7:

[0380] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it generates a sentence such as, "'Oshikatsu' is the activity of supporting a favorite artist or character."

[0381] Step 8:

[0382] The server generates a description with additional background information and context as needed, for example, "This term is popular among young people and is used as part of fan activities."

[0383] Step 9:

[0384] The server generates a request to transmit the generated description to the terminal.

[0385] Step 10:

[0386] The terminal receives the explanation request sent from the server.

[0387] Step 11:

[0388] The device then displays the received explanation to the user. For example, it might say, "Oshikatsu is the act of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0389] This concrete step allows users to understand difficult words and phrases in an easy-to-understand and explained way.

[0390] Example 1

[0391] 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."

[0392] Words and phrases used by different generations or specific groups can be difficult to understand, creating a communication gap. In such situations, a means is needed to easily understand the meaning of specific words and phrases, but traditional methods often do not adequately solve this problem. In particular, there is a need for technology that can convert words into a form that is easily understandable to users while understanding related background information and context.

[0393] 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.

[0394] In this invention, the server includes means for receiving text input from a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words specific to a specific group or generation, means for analyzing the extracted words using an artificial intelligence model, means for generating explanatory text in a form that is easy for the user to understand using a generative AI model using a prompt text, means for transmitting the generated explanatory text to a user terminal, and means for displaying the generated explanatory text on a user interface, thereby enabling users to intuitively understand the meanings of words and phrases of different generations or groups.

[0395] "User" refers to an individual or organization that uses the system.

[0396] "Terminal" refers to a device or equipment that allows a user to input information.

[0397] "Text" refers to a character string or sentence entered by a user.

[0398] A "morphological analysis engine" refers to a software tool that breaks text into morphemes (words and phrases).

[0399] A "prompt sentence" refers to an input sentence that gives instructions to a generative AI model for analysis or conversion.

[0400] A "generative AI model" refers to an algorithm or software that uses artificial intelligence techniques to analyze input data and generate an appropriate output.

[0401] "User interface" refers to the screen and operating means that allow a user to interact with a system.

[0402] "Means for splitting" refers to the function of splitting text into words and phrases using a morphological analysis engine.

[0403] "Means of extraction" refers to the function of finding words specific to a particular group or generation within text.

[0404] "Means of analysis" refers to the function of analyzing the meaning and intent of extracted words using an artificial intelligence model.

[0405] "Means for generating" refers to the function of creating an explanation that is easy for the user to understand based on the analysis results.

[0406] The "transmitting means" refers to a communication function for transmitting the generated explanatory text to the user terminal.

[0407] The "display means" refers to a function for displaying the generated explanatory text on the screen of the user terminal.

[0408] As an embodiment of the present invention, a system for analyzing and converting words and phrases that are difficult for users to understand will be specifically described. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology to convert words that are specific to a specific group or generation into an easier-to-understand form.

[0409] The main components of this system are the user terminal, server, morphological analysis engine, and generative AI model.

[0410] First, the user inputs text containing words or phrases that are difficult to understand into the device. For example, they might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." The device receives this input text, creates a request body in JSON format, and sends it to the server as an HTTP request. The specific hardware used by the device could be, for example, a smartphone or a PC.

[0411] The server receives a text request sent from the device. It uses a morphological analysis engine (e.g., Mecab) to break down the received text into words and phrases. For example, it might break down the text into something like, "The other day, I heard the word 'oshikatsu' many times on TV, but I didn't understand what it meant." The software used here is the morphological analysis engine Mecab.

[0412] Next, the server extracts words specific to a particular group or generation (e.g., "oshikatsu") from the segmented words and phrases. A generative AI model (e.g., BERT or GPT) is used to analyze the meaning and intent of the extracted words. The generative AI model receives instructions using prompts and performs the analysis. For example, the prompt might be, "Analyze the meaning of the word oshikatsu, convert it into a general term, and generate an explanatory text including background information."

[0413] The server generates an easy-to-understand explanation for the user based on the analysis results from the AI ​​model. For example, it converts the information into something like, "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0414] The generated explanation is sent from the server to the user's device as an HTTP response. The device receives this response and displays it in a text area or pop-up on the user interface (UI). The user can read and understand the explanation displayed on the screen. A specific example of what is displayed is, "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people, and is used as part of fan activities."

[0415] This allows users to intuitively understand the meaning of words and phrases from different generations and groups, thereby bridging communication gaps. This invention facilitates smooth communication between different generations and groups, and makes it easier to understand the meaning of words.

[0416] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0417] Step 1:

[0418] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, they might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." This input text becomes the input to the system. The device receives this text and temporarily stores it in its internal memory for subsequent processing.

[0419] Step 2:

[0420] The device generates a request to send the text received from the user to the server. This request is usually in JSON format and sent to the server using an HTTP POST request. The request body contains the text entered by the user.

[0421] Step 3:

[0422] The server receives an HTTP POST request sent from the device. It extracts text from the request body and uses a morphological analysis engine (e.g., Mecab) to split the text into words and phrases. The input to this step is the text entered by the user, and the output is a list of words and phrases split by morphological analysis. For example, the phrase might be split as follows: "The other day, I heard the word 'oshikatsu' many times on TV, but I didn't understand what it meant."

[0423] Step 4:

[0424] The server extracts words specific to a particular group or generation from the segmented words and phrases. This extraction can be done by referencing a database. For example, the word "oshikatsu" is extracted. The input of this step is a list of segmented words and phrases, and the output is a specific word (e.g., "oshikatsu").

[0425] Step 5:

[0426] The server uses a generative AI model (such as BERT or GPT) to analyze the meaning of the extracted words. A prompt is used to give instructions to the model and perform the analysis. For example, the prompt could be set as "Analyze the meaning of the word 'oshikatsu,' convert it into a general term, and generate an explanation including background information." The input of this step is the specific extracted words, and the output is the analysis results including the meaning of the words and background information.

[0427] Step 6:

[0428] The server generates an easy-to-understand explanation for the user based on the analysis results from the generative AI model. For example, it generates the explanation, "'Oshikatsu' refers to the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people and is used as part of fan activities." The input of this step is the analysis results, and the output is the generated explanation.

[0429] Step 7:

[0430] The server converts the generated description into a JSON-formatted response body and sends it to the terminal as an HTTP response. The input of this step is the generated description, and the output is the HTTP response.

[0431] Step 8:

[0432] The device receives the HTTP response sent from the server and extracts the description from the response body. The device displays this description in a text area or pop-up on the user interface (UI). For example, it might say, "Oshikatsu is the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people and is used as part of fan activities." The input of this step is the HTTP response, and the output is the description to be displayed.

[0433] Through these steps, users can intuitively understand the meaning of difficult-to-understand words and phrases contained in the input text.

[0434] (Application example 1)

[0435] 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."

[0436] In today's information society, diverse users increasingly use words and coded phrases specific to different groups or generations. From a security perspective, it is particularly important to analyze suspicious terms and coded expressions in real time, convert them into understandable forms, and display warnings. However, current systems lack the means to efficiently perform such analysis and conversion, often resulting in delayed responses. A solution to this problem is needed.

[0437] 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.

[0438] In this invention, the server includes means for receiving text input from a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words unique to a specific group or generation from the words and phrases, means for analyzing the extracted words using an artificial intelligence model, means for generating a sentence converted into a form easy for the user to understand based on the analysis result, means for transmitting the generated sentence to a user terminal, and means for generating and displaying a warning message when a security risk is detected. This enables real-time analysis of terms used by different generations or groups and automatic generation of easy-to-understand warning messages based on the analysis.

[0439] The "means for receiving text input from a user" is a device or program that obtains text information input by a user and stores it for subsequent processing.

[0440] A "morphological analysis engine" is an analytical tool that divides input text into semantic units such as words and phrases.

[0441] The "means for dividing into words and phrases" is a device or program that divides input text into meaningful units, such as words and phrases, using a morphological analysis engine.

[0442] The "means for extracting words specific to a particular group or generation" is a device or program that identifies and extracts words specific to a particular group or generation from among the segmented words or phrases.

[0443] "Means for analyzing using an artificial intelligence model" refers to a device or program that uses artificial intelligence technology to perform analysis in order to understand the meaning of extracted words.

[0444] The "means for generating sentences converted into a form that is easy for the user to understand" is a device or program that converts words and phrases into a form that is easy for the user to understand based on the analysis results and generates new sentences.

[0445] The "means for transmitting the generated sentence to the user terminal" is a device or program that transfers the converted sentence to the user terminal and displays it.

[0446] The "means for generating and displaying a warning message when a security risk is detected" refers to a device or program that automatically generates a warning message and notifies the user when a security risk is detected as a result of the analysis.

[0447] As an embodiment of the present invention, we will specifically describe a system in which a security team analyzes suspicious text data in real time, converts it into an easy-to-understand format, and displays a warning. This system processes text data entered by a user using a morphological analysis engine and artificial intelligence technology, analyzing and converting words unique to specific groups or generations. Furthermore, if a security risk is detected based on the analysis results, a warning message is automatically generated and notified to the user.

[0448] System configuration

[0449] 1. Input reception:

[0450] The server receives text entered by users, such as chat logs, emails, social media posts, etc. For example, suppose a user enters, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0451] 2. Text preprocessing:

[0452] The server splits the received text into words and phrases using a morphological analysis engine (e.g., Mecab), and performs text normalization.

[0453] 3. Semantic and Intention Analysis:

[0454] The server extracts words specific to a particular group or generation from the segmented words and phrases. It then analyzes the extracted words using an artificial intelligence model (e.g., BERT or GPT). For example, it confirms that the word "oshikatsu" (supporting a specific character or artist) refers to the activity of supporting a specific character or artist.

[0455] 4. Transformation and Description Generation:

[0456] Based on the analysis results, the server converts the words into a form that is easy for the user to understand. For example, it generates an explanation such as, "'Oshikatsu' is the activity of supporting your favorite artist or character."

[0457] 5. Security Risk Analysis:

[0458] If the analysis reveals that certain words or phrases contain potential security risks, the server will detect this and generate a warning message.

[0459] 6. Sending and viewing results:

[0460] The server sends the generated explanatory text and warning message to the user's device, which then displays it to the user. For example, it might say, "Oshikatsu is the activity of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0461] Hardware and software used

[0462] Hardware:

[0463] Terminals (PCs, smartphones), servers

[0464] software:

[0465] Morphological analysis engine (Mecab)

[0466] Artificial intelligence models (BERT and GPT)

[0467] Databases (storing words specific to specific groups or generations)

[0468] Specific examples

[0469] For example, if a security operator sees a message in a chat log they are monitoring saying, "Let's go to that artist's concert tomorrow! 'Oshikatsu' is the best!", the system will generate an explanation in real time: "'Oshikatsu' is the activity of supporting your favorite artist or character. It's especially popular among young people." and display it, while also assessing the associated risks and displaying a warning message if necessary.

[0470] Prompt Sentence Examples

[0471] Extract suspicious words and phrases from the given text and explain their meaning: I'm going to see that artist's concert tomorrow! "Supporting my favorite artist" is the best!

[0472] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0473] Step 1:

[0474] A user inputs text into the device that contains words or phrases that are difficult to understand. For example, they might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." The device receives this input text and generates a request to send to the server. The input is the text entered by the user, and the output is the request to send to the server.

[0475] Step 2:

[0476] The server receives a text request sent from a device. It uses a morphological analysis engine (e.g., Mecab) to split this text into words and phrases. For example, it might split something like, "The other day, I heard the word 'oshikatsu' many times on TV, but I didn't understand what it meant." The input is the received text request, and the output is the split words and phrases.

[0477] Step 3:

[0478] The server extracts words specific to a particular group or generation from the segmented words and phrases. For example, to extract the word "oshikatsu," it refers to a specific database. The input is the segmented words and phrases, and the output is the extracted words.

[0479] Step 4:

[0480] The server analyzes the extracted words using an artificial intelligence model (e.g., BERT or GPT). It verifies that "oshikatsu" refers to the activity of supporting a specific character or artist. The input is the extracted words, and the output is the analysis results.

[0481] Step 5:

[0482] Based on the analysis results, the server generates a sentence that is converted into a form that is easy for the user to understand. For example, it converts it into a form such as "'Oshikatsu' is the activity of supporting a favorite artist or character." It may also generate an explanatory sentence that includes additional background information and context as needed. The input is the analysis results, and the output is the converted sentence.

[0483] Step 6:

[0484] If a security risk is detected as a result of the analysis, the server automatically generates a warning message. For example, it generates a message saying, "This phrase may contain a high security risk." The input is the analysis result, and the output is the warning message.

[0485] Step 7:

[0486] The server generates a request to send the generated explanatory text and warning message to the user's terminal. The terminal receives the explanatory text and warning message sent from the server and displays them to the user. The input is the generated explanatory text and warning message, and the output is the displayed result. For example, it could display "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people and is used as part of fan activities," and also display a warning message if necessary.

[0487] 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.

[0488] As an embodiment of the present invention, we will explain a specific configuration that combines an emotion engine with a system that analyzes and converts words and phrases that are difficult for users to understand. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology, and also recognizes the user's emotions and provides feedback in an appropriate form.

[0489] System program processing

[0490] Input Reception

[0491] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0492] The terminal receives input text from the user and generates a request to send this text to the server.

[0493] Text and sentiment preprocessing

[0494] The server receives a text request sent from the device. It uses a morphological analysis engine (e.g., Mecab) to split this text into words and phrases. For example, it could split the text into "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0495] The server simultaneously uses an emotion engine to recognize emotions from the text entered by the user, for example, the emotion engine recognizes "confused."

[0496] Semantic and Intention Analysis

[0497] The server extracts words specific to a particular group or generation from the segmented words and phrases. For example, it extracts the word "oshikatsu." It then analyzes the meaning of the extracted words using an artificial intelligence model (e.g., BERT or GPT). It verifies that "oshikatsu" refers to the activity of supporting a particular character or artist.

[0498] Transformation and Description Generation

[0499] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it generates a sentence such as, "'Oshikatsu' is the activity of supporting a favorite artist or character."

[0500] Here, the server takes into account the user's emotional information recognized by the emotion engine. For example, if the emotion "confusion" is recognized, it adds a sentence to ease the emotion or an encouraging message, such as "Don't worry, 'oshikatsu' is a very fun activity!"

[0501] Returning and displaying results

[0502] The server generates a request to send an additional message to the terminal according to the generated description and emotion.

[0503] The device receives the explanation and message request sent from the server and displays it to the user. For example, it displays something like, "'Oshikatsu' is the activity of supporting your favorite artist or character. It's a term that's especially popular among young people, and is used as part of fan activities. Don't worry, 'Oshikatsu' is a very fun activity!"

[0504] This added emotion engine allows users to receive explanations in a more familiar way and to more easily understand words and phrases that are difficult to understand. This invention can bridge the communication gap between different generations and groups, and also provide feedback that takes into account the user's emotions.

[0505] The processing flow will be explained below.

[0506] MODE FOR CARRYING OUT THE INVENTION

[0507] Step 1:

[0508] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0509] Step 2:

[0510] The terminal receives input text from the user and generates a request to send this text to the server.

[0511] Step 3:

[0512] The server receives the text request sent from the terminal.

[0513] Step 4:

[0514] The server uses a morphological analysis engine (e.g., Mecab) to split the received text into words and phrases, such as "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0515] Step 5:

[0516] The server simultaneously uses an emotion engine to recognize emotions from the text entered by the user, such as the emotion "confused." The emotion engine uses natural language processing to assess the emotional tone of the text.

[0517] Step 6:

[0518] The server extracts words that are specific to a particular group or generation from the segmented words and phrases. For example, the word "oshikatsu" (supporting someone) is extracted.

[0519] Step 7:

[0520] The server uses an artificial intelligence model (e.g., BERT or GPT) to analyze the meaning of the extracted words. For example, it confirms that "oshikatsu" refers to the activity of supporting a specific character or artist.

[0521] Step 8:

[0522] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it generates a sentence such as, "'Oshikatsu' is the activity of supporting a favorite artist or character."

[0523] Step 9:

[0524] The server takes into account the user's emotional information recognized by the emotion engine. For example, if the emotion "confusion" is recognized, it adds a message to ease the emotion or an encouraging message, such as "Don't worry, 'oshikatsu' is a very fun activity!"

[0525] Step 10:

[0526] The server generates a request to send an additional message to the terminal according to the generated description and emotion.

[0527] Step 11:

[0528] The terminal receives the explanatory text and the message request sent from the server.

[0529] Step 12:

[0530] The device then displays the received explanation to the user. For example, it might say, "'Oshikatsu' is the activity of supporting your favorite artist or character. It's a term that's especially popular among young people, and is used as part of fan activities. Don't worry, 'Oshikatsu' is a lot of fun!"

[0531] This concrete step allows users to understand difficult words and phrases in an easy-to-understand manner, while also receiving emotionally sensitive feedback.

[0532] Example 2

[0533] 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."

[0534] In today's world, the words and phrases used between generations and specific groups are becoming more diverse, making it difficult for users to understand their meanings. It is also important to consider the confusion and discomfort users may feel when searching for the meaning of a particular word or phrase. In such situations, a system that provides easy-to-understand explanations to users while also taking their feelings into consideration is required.

[0535] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0536] In this invention, the server includes means for receiving text input from a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words specific to a particular group or generation from the words and phrases, means for analyzing the extracted words using an artificial intelligence model, means for generating a sentence converted into a form that is easy for the user to understand based on the analysis result, means for recognizing the user's emotion, means for generating a message corresponding to the emotion based on the recognized emotion, and means for transmitting the generated sentence and the message based on the emotion to a user terminal. This makes it possible to clearly explain the meaning of words and phrases that are difficult for the user to understand, and further reduce the confusion and discomfort felt by the user.

[0537] "User" refers to someone who uses the system to find the meaning of words or phrases that are difficult to understand.

[0538] "Text" refers to a sentence or string of characters that a user sends to a system using an input device.

[0539] A "morphological analysis engine" refers to software that divides input text into words and phrases and analyzes their structure.

[0540] "Words and Phrases" refers to sequences of words that form small units of language or short sentences extracted from text by a morphological analysis engine.

[0541] "Group or generational idiom" refers to distinctive terms and expressions that are used specifically within a particular cultural background or generation.

[0542] An "artificial intelligence model" refers to an algorithm that uses machine learning and deep learning techniques to analyze and understand the meaning of words and phrases.

[0543] "Analysis results" refers to the information generated after an AI model analyzes a particular word or phrase.

[0544] "Sentences converted into a form that is easy for users to understand" refers to sentences in which technical terms and words specific to a particular group or generation have been replaced with expressions that are easy for the general public to understand, based on the analysis results.

[0545] "Emotion" refers to the psychological state a user feels when they input a particular piece of text.

[0546] An "emotion engine" refers to software that analyzes input text and automatically recognizes the user's psychological state from it.

[0547] "Emotion-responsive messages" refer to sentences generated to reassure, encourage, or otherwise respond to the user's emotions based on the user's recognized emotions.

[0548] "User terminal" refers to a computing device (e.g., smartphone, tablet, computer) used by a user that includes an interface for communicating with the system.

[0549] As an embodiment of the present invention, we will explain in detail a system that analyzes and converts words and phrases that are difficult for users to understand. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology, and also recognizes the user's emotions and provides feedback in an appropriate form.

[0550] Input Reception

[0551] The user inputs text into the device that includes words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." The device receives the input text from the user and generates a request to send this text to the server. Specifically, the device converts the input text into a data packet and sends it to the server as an HTTP POST request.

[0552] Text and sentiment preprocessing

[0553] The server receives a text request sent from the device. This text is stored in the server's input buffer. The server uses a morphological analysis engine (for example, the Japanese morphological analysis engine Mecab) to divide the text into words and phrases. For example, the server breaks down the text into "I heard the word 'oshikatsu' many times, but I didn't understand its meaning" into "oshikatsu" (words) many times, but I didn't understand its meaning. The server then uses an emotion engine to analyze emotions from the text entered by the user. For example, the emotion engine (for example, a natural language processing API) recognizes the emotion "confused."

[0554] Semantic and Intention Analysis

[0555] The server extracts words specific to a particular group or generation from the segmented words and phrases. Specifically, it references dictionaries and databases to extract the word "oshikatsu." The server then analyzes the meaning of the extracted words using an artificial intelligence model (e.g., BERT or GPT). The BERT model is used to understand the context of "oshikatsu" and confirm that it refers to the activity of supporting a specific character or artist.

[0556] Transformation and Description Generation

[0557] Based on the analysis results, the server generates a sentence that is easy for the user to understand. Specifically, it generates an explanatory sentence such as, "Oshikatsu is an activity to support your favorite artists or characters." Furthermore, the server takes into account the user's emotional information recognized by the emotion engine. For example, if the emotion "confusion" is recognized, the server adds an encouraging message to alleviate that emotion: "Don't worry, 'Oshikatsu' is a very fun activity!"

[0558] Returning and displaying results

[0559] The server generates a request to send the generated description and an additional message corresponding to the emotion to the device. Specifically, it converts the generated sentence and message into JSON data and sends it to the device as an HTTP response. The device receives the description and message sent from the server and displays it to the user. For example, it displays something like, "'Oshikatsu' is the activity of supporting your favorite artist or character. Don't worry, 'Oshikatsu' is a very fun activity!"

[0560] Examples of concrete examples and prompts

[0561] As a specific example, if a user types, "The word 'Egae' came up a lot at the party yesterday. What does it mean?", the server will generate the answer, "'Egae' means that a photo or video is beautifully taken and looks good. It is a term that is particularly commonly used on social media," and send it to the device.

[0562] An example of a prompt sentence is, "Please look up the meaning of a specific word or phrase. The text is 'What does XX (the word you want to look up) mean?'"

[0563] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0564] Step 1:

[0565] The user inputs text into the device that includes words and phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." Input: User's text data. Output: Text data input into the device.

[0566] Step 2:

[0567] The terminal receives input text from the user and generates a request to send to the server. Specifically, it converts the input text into a data packet and sends it to the server as an HTTP POST request. Input: User's text data. Output: HTTP POST request to the server.

[0568] Step 3:

[0569] The server receives a text request sent from the terminal. The text is saved in the server's input buffer. Input: HTTP request data. Output: Text data saved in the server's input buffer.

[0570] Step 4:

[0571] The server uses a morphological analysis engine (for example, a morphological analysis engine) to split the text into words and phrases. As a concrete example, the server splits the text "I heard the word 'oshikatsu' many times, but I didn't understand its meaning" into "oshikatsu" (the word) many times, but I didn't understand its meaning." Input: Text data saved in the server's input buffer. Output: A list of split words and phrases.

[0572] Step 5:

[0573] The server uses an emotion engine to analyze emotions from the text entered by the user. For example, the emotion engine recognizes the emotion "confused." Input: Text data stored in the server's input buffer. Output: Emotion data for "confused."

[0574] Step 6:

[0575] The server extracts words specific to a particular group or generation from the segmented words and phrases. Specifically, it extracts the word "oshikatsu" by referring to a dictionary or database. Input: A list of segmented words and phrases. Output: Extracted specific words.

[0576] Step 7:

[0577] The server uses an artificial intelligence model (e.g., a generative AI model) to analyze the meaning of the extracted words. As a specific example, it uses the BERT model to understand the context of "oshikatsu" and confirm that it refers to the activity of supporting a specific character or artist. Input: Specific extracted words. Output: Semantic data of the analysis results.

[0578] Step 8:

[0579] Based on the analysis results, the server generates a sentence that is converted into a form that is easy for the user to understand. As a specific example, it generates the sentence, "'Oshikatsu' is the activity of supporting a favorite artist or character." Input: Semantic data from the analysis results. Output: Sentence that has been converted into a form that is easy for the user to understand.

[0580] Step 9:

[0581] The server generates a message corresponding to the emotion, taking into account the user's emotional information recognized by the emotion engine. For example, to alleviate the emotion of "confusion," it adds a message such as "Don't worry, 'oshikatsu' is a very fun activity!". Input: Emotion data. Output: A sentence containing a message.

[0582] Step 10:

[0583] The server generates a request to send the generated description and a message based on the emotion to the device. Specifically, it converts the generated sentence and message into JSON data and sends it as an HTTP response to the device. Input: Sentence containing the message. Output: HTTP response to the device.

[0584] Step 11:

[0585] The device receives the explanation and message request sent from the server and displays them to the user. For example, it displays the following: "Oshikatsu is the activity of supporting your favorite artists or characters. Don't worry, oshikatsu is a very fun activity!" Input: HTTP response from the server. Output: Explanation and message displayed on the user's device.

[0586] (Application example 2)

[0587] 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."

[0588] In current food delivery services, user reviews and feedback often contain words and phrases that are difficult to understand. Furthermore, the feedback provided ignores the user's feelings, preventing improvements to the user experience. In particular, the inability to properly interpret user opinions and requests regarding the taste of food can delay improvements to the delivery service and the restaurant. Therefore, there is a need for a system that can properly analyze user feedback and provide easy-to-understand feedback that takes user feelings into consideration.

[0589] The identification process by the identification 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 input by a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words unique to a specific group or generation from the words and phrases, means for analyzing the extracted words using an artificial intelligence model, means for generating a sentence converted into a form easy for the user to understand based on the analysis result, means for adding feedback to the generated sentence that takes into account the user's emotions, and means for transmitting the generated sentence and feedback to the user terminal. This makes it possible to appropriately analyze reviews and feedback from users and provide feedback that is easy to understand and takes into account their emotions.

[0590] The "means for receiving text input from a user" is an interface for receiving text data such as reviews and feedback input by a user.

[0591] A "morphological analysis engine" is an analysis engine that divides natural languages ​​such as Japanese into words and phrases.

[0592] The "means for splitting into words and phrases" refers to a means for breaking down input text into individual words and phrases using a morphological analysis engine.

[0593] A "means for extracting words specific to a particular group or generation" is a means for searching for and extracting words or slang specific to a particular age group or community from text.

[0594] An "artificial intelligence model" is a machine learning model used to learn from large amounts of text data and analyze input text.

[0595] "Means for analyzing" refers to the means for analyzing extracted words and phrases using an artificial intelligence model to understand their meaning and context.

[0596] The "means for generating sentences converted into a form that is easy for the user to understand" is a means for reconstructing text into a form that is easy for the user to understand, based on the content analyzed by the artificial intelligence model.

[0597] The "means for adding feedback that takes into account the user's emotions" is a means for recognizing emotions from text entered by the user and adding feedback that matches those emotions.

[0598] The "means for transmitting to the user terminal" refers to a means for transmitting the generated text and feedback to the terminal used by the user.

[0599] The program of the system that realizes this invention performs the following process in stages: First, the specific steps when a user posts a review or feedback using a food delivery app will be explained.

[0600] System Overview

[0601] 1. Receiving user input

[0602] The server receives the text input by the user, for example, a review such as "The food was delicious, but the flavor was too strong, so it might not be suitable for children." This allows the text data input by the user to be incorporated into the system.

[0603] 2. Morphological analysis

[0604] The server uses Mecab as a morphological analysis engine to split the input text into words and phrases, such as "The food was delicious, but the flavor was too strong, so it might not be suitable for children."

[0605] 3. Extracting specific words

[0606] The server references the database to extract words that are specific to a particular group or generation, such as "delicious" or "not suitable" in reviews.

[0607] 4. Word Analysis

[0608] The server uses artificial intelligence models such as BERT and GPT to analyze the meaning and context of the extracted words, resulting in an interpretation such as "The food is delicious, but the flavor is too strong for children to eat."

[0609] 5. Generate feedback

[0610] The server generates feedback based on the analysis results in a format that is easy for the user to understand. Furthermore, it analyzes the user's emotions using the Google Cloud Natural Language API, and if the emotion of "dissatisfaction" is recognized, this is reflected in the feedback. For example, the server may generate feedback such as, "Thank you for rating the taste of the dish. Your comment that the flavor is too strong and not suitable for children can be adjusted for your next order."

[0611] 6. Submitting Feedback

[0612] The server sends the generated feedback and analysis results to the user's device, which receives them and displays the review content in an easy-to-understand manner.

[0613] Hardware and software used

[0614] Morphological analysis engine: Mecab

[0615] Sentiment engine: Google Cloud Natural Language API

[0616] Artificial intelligence models: BERT, GPT

[0617] Specific examples

[0618] A user leaves the following review on a food delivery app:

[0619] "The food was delicious, but the flavor was too strong and probably not suitable for children. It's very different from my mother's cooking."

[0620] The server receives this and segments it using morphological analysis. It then extracts specific words and uses an AI model to obtain the analysis results. The emotion engine considers the emotion recognized as "unsatisfied" and generates appropriate feedback. The feedback the user will next see is as follows:

[0621] "Thank you for rating the taste of our food. We understand that the flavor is too strong and unsuitable for children. We will adjust it for your next order. We will also strive to recreate your mother's cooking style!"

[0622] Prompt Sentence Examples

[0623] Prompt sentence to input to the generative AI model:

[0624] "Please parse the following text, convert it to something understandable, and generate feedback taking into account sentiment:

[0625] Text: 'The food was delicious, but the flavor was too strong and perhaps not suitable for children. It's nothing like my mother's cooking.'

[0626] User sentiment: 'Unsatisfied'

[0627] Requirement: Convert into an understandable format and generate feedback for next time.

[0628] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0629] Step 1:

[0630] The server receives text input from the user. When the user enters a review or feedback through the food delivery app and clicks submit, this text data is sent to the server. The input is the text data posted by the user, and the output is the text data received as is.

[0631] Step 2:

[0632] The server uses a morphological analysis engine (Mecab) to divide the received text into words and phrases. Specifically, the server passes the text data to Mecab, which then performs a mechanical grammatical analysis to break it down into words and phrases. The input is the text data received in step 1, and the output is the text divided by morphological analysis. For example, the input "The food was delicious, but the flavor was too strong, so it might not be suitable for children" is changed to the output "The food was delicious, but the flavor was too strong, so it might not be suitable for children."

[0633] Step 3:

[0634] The server performs text normalization as preprocessing. This process involves removing unnecessary spaces and special characters from the text and performing pattern matching using regular expressions. The input is the text split in step 2, and the output is the normalized text. For example, "The food was delicious, but the flavor was too strong, so it might not be suitable for children" becomes "The food was delicious, but the flavor was too strong, so it might not be suitable for children."

[0635] Step 4:

[0636] The server references a database to extract words specific to a particular group or generation from the normalized text. For example, it may have a database listing words used by a particular age group or community, and searches through it to extract the relevant words. The input is the text normalized in step 3, and the output is the specific words extracted. For example, "delicious" or "not suitable."

[0637] Step 5:

[0638] The server analyzes the extracted words using an artificial intelligence model (BERT or GPT). Specifically, the extracted words and phrases are input into the AI ​​model, which analyzes their context and meaning. The input is the words extracted in step 4, and the output is the analysis result based on the context and meaning of those words. For example, the conclusion is "It's delicious, but the flavor is too strong for children to eat."

[0639] Step 6:

[0640] Based on the analysis results, the server generates a sentence that is converted into a form that is easy for the user to understand. In this step, an explanation is generated in a format that is easy for the user to understand based on the analysis results of the AI ​​model. The input is the analysis result obtained in step 5, and the output is a reconstructed explanation. For example, feedback such as "Thank you for rating the taste of the dish. Your opinion that the flavor is too strong and not suitable for children can be adjusted for your next order."

[0641] Step 7:

[0642] The server adds feedback to the generated description, taking into account the user's emotions. Using an emotion engine (Google Cloud Natural Language API), it recognizes emotions from the user's input text and generates an additional message based on that. The input is the description obtained in step 6 and the user's emotional data, and the output is the final feedback. For example, it could be something like, "We received feedback that the flavor was too strong, but we will adjust it for your next order. We will also try to recreate your mother's recipe!"

[0643] Step 8:

[0644] The server sends the generated sentence and feedback to the user's device, which receives it and displays it to the user in the app. The input is the final feedback sentence generated in step 7, and the output is the data sent to the user's device. This allows the user to see how their review is interpreted and fed back.

[0645] 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.

[0646] 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.

[0647] 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.

[0648] [Third embodiment]

[0649] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0650] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0651] 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).

[0652] 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.

[0653] 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.

[0654] 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).

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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."

[0661] As an embodiment of the present invention, we will specifically explain a system that analyzes and converts words and phrases that are difficult for users to understand. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology to convert words that are unique to a specific group or generation into an easier-to-understand form.

[0662] System program processing

[0663] Input Reception

[0664] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0665] The terminal receives input text from the user and generates a request to send this text to the server.

[0666] Text Preprocessing

[0667] The server receives a text request sent from the device. It uses a morphological analysis engine (e.g., Mecab) to split this text into words and phrases. For example, it could split the text into "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0668] Semantic and Intention Analysis

[0669] The server extracts words specific to a particular group or generation from the segmented words and phrases. For example, it extracts the word "oshikatsu." It then analyzes the meaning of the extracted words using an artificial intelligence model (e.g., BERT or GPT). It verifies that "oshikatsu" refers to the activity of supporting a particular character or artist.

[0670] Transformation and Description Generation

[0671] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it converts it into a form such as, "Oshikatsu is the activity of supporting a favorite artist or character." It also generates an explanatory text that includes additional background information and context as needed. For example, it adds an explanation such as, "It is a term that is particularly popular among young people and is used as part of fan activities."

[0672] Returning and displaying results

[0673] The server generates a request to transmit the generated description to the terminal.

[0674] The device receives the explanation request sent from the server and displays it to the user. For example, it displays something like, "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0675] In this way, users can understand words and phrases that are difficult to understand in an easy-to-understand manner.This invention can bridge the communication gap between different generations and groups.

[0676] The processing flow will be explained below.

[0677] Specific processing steps of the program

[0678] Step 1:

[0679] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0680] Step 2:

[0681] The terminal receives input text from the user and generates a request to send this text to the server.

[0682] Step 3:

[0683] The server receives the text request sent from the terminal.

[0684] Step 4:

[0685] The server uses a morphological analysis engine (e.g., Mecab) to split the received text into words and phrases, such as "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0686] Step 5:

[0687] The server extracts words that are specific to a particular group or generation from the segmented words and phrases. For example, it extracts the word "oshikatsu."

[0688] Step 6:

[0689] The server uses an artificial intelligence model (e.g., BERT or GPT) to analyze the meaning of the extracted words. For example, it confirms that "oshikatsu" refers to the activity of supporting a specific character or artist.

[0690] Step 7:

[0691] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it generates a sentence such as, "'Oshikatsu' is the activity of supporting a favorite artist or character."

[0692] Step 8:

[0693] The server generates a description with additional background information and context as needed, for example, "This term is popular among young people and is used as part of fan activities."

[0694] Step 9:

[0695] The server generates a request to transmit the generated description to the terminal.

[0696] Step 10:

[0697] The terminal receives the explanation request sent from the server.

[0698] Step 11:

[0699] The device then displays the received explanation to the user. For example, it might say, "Oshikatsu is the act of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0700] This concrete step allows users to understand difficult words and phrases in an easy-to-understand and explained way.

[0701] Example 1

[0702] 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."

[0703] Words and phrases used by different generations or specific groups can be difficult to understand, creating a communication gap. In such situations, a means is needed to easily understand the meaning of specific words and phrases, but traditional methods often do not adequately solve this problem. In particular, there is a need for technology that can convert words into a form that is easily understandable to users while understanding related background information and context.

[0704] 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.

[0705] In this invention, the server includes means for receiving text input from a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words specific to a specific group or generation, means for analyzing the extracted words using an artificial intelligence model, means for generating explanatory text in a form that is easy for the user to understand using a generative AI model using a prompt text, means for transmitting the generated explanatory text to a user terminal, and means for displaying the generated explanatory text on a user interface, thereby enabling users to intuitively understand the meanings of words and phrases of different generations or groups.

[0706] "User" refers to an individual or organization that uses the system.

[0707] "Terminal" refers to a device or equipment that allows a user to input information.

[0708] "Text" refers to a character string or sentence entered by a user.

[0709] A "morphological analysis engine" refers to a software tool that breaks text into morphemes (words and phrases).

[0710] A "prompt sentence" refers to an input sentence that gives instructions to a generative AI model for analysis or conversion.

[0711] A "generative AI model" refers to an algorithm or software that uses artificial intelligence techniques to analyze input data and generate an appropriate output.

[0712] "User interface" refers to the screen and operating means that allow a user to interact with a system.

[0713] "Means for splitting" refers to the function of splitting text into words and phrases using a morphological analysis engine.

[0714] "Means of extraction" refers to the function of finding words specific to a particular group or generation within text.

[0715] "Means of analysis" refers to the function of analyzing the meaning and intent of extracted words using an artificial intelligence model.

[0716] "Means for generating" refers to the function of creating an explanation that is easy for the user to understand based on the analysis results.

[0717] The "transmitting means" refers to a communication function for transmitting the generated explanatory text to the user terminal.

[0718] The "display means" refers to a function for displaying the generated explanatory text on the screen of the user terminal.

[0719] As an embodiment of the present invention, a system for analyzing and converting words and phrases that are difficult for users to understand will be specifically described. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology to convert words that are specific to a specific group or generation into an easier-to-understand form.

[0720] The main components of this system are the user terminal, server, morphological analysis engine, and generative AI model.

[0721] First, the user inputs text containing words or phrases that are difficult to understand into the device. For example, they might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." The device receives this input text, creates a request body in JSON format, and sends it to the server as an HTTP request. The specific hardware used by the device could be, for example, a smartphone or a PC.

[0722] The server receives a text request sent from the device. It uses a morphological analysis engine (e.g., Mecab) to break down the received text into words and phrases. For example, it might break down the text into something like, "The other day, I heard the word 'oshikatsu' many times on TV, but I didn't understand what it meant." The software used here is the morphological analysis engine Mecab.

[0723] Next, the server extracts words specific to a particular group or generation (e.g., "oshikatsu") from the segmented words and phrases. A generative AI model (e.g., BERT or GPT) is used to analyze the meaning and intent of the extracted words. The generative AI model receives instructions using prompts and performs the analysis. For example, the prompt might be, "Analyze the meaning of the word oshikatsu, convert it into a general term, and generate an explanatory text including background information."

[0724] The server generates an easy-to-understand explanation for the user based on the analysis results from the AI ​​model. For example, it converts the information into something like, "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0725] The generated explanation is sent from the server to the user's device as an HTTP response. The device receives this response and displays it in a text area or pop-up on the user interface (UI). The user can read and understand the explanation displayed on the screen. A specific example of what is displayed is, "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people, and is used as part of fan activities."

[0726] This allows users to intuitively understand the meaning of words and phrases from different generations and groups, thereby bridging communication gaps. This invention facilitates smooth communication between different generations and groups, and makes it easier to understand the meaning of words.

[0727] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0728] Step 1:

[0729] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, they might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." This input text becomes the input to the system. The device receives this text and temporarily stores it in its internal memory for subsequent processing.

[0730] Step 2:

[0731] The device generates a request to send the text received from the user to the server. This request is usually in JSON format and sent to the server using an HTTP POST request. The request body contains the text entered by the user.

[0732] Step 3:

[0733] The server receives an HTTP POST request sent from the device. It extracts text from the request body and uses a morphological analysis engine (e.g., Mecab) to split the text into words and phrases. The input to this step is the text entered by the user, and the output is a list of words and phrases split by morphological analysis. For example, the phrase might be split as follows: "The other day, I heard the word 'oshikatsu' many times on TV, but I didn't understand what it meant."

[0734] Step 4:

[0735] The server extracts words specific to a particular group or generation from the segmented words and phrases. This extraction can be done by referencing a database. For example, the word "oshikatsu" is extracted. The input of this step is a list of segmented words and phrases, and the output is a specific word (e.g., "oshikatsu").

[0736] Step 5:

[0737] The server uses a generative AI model (such as BERT or GPT) to analyze the meaning of the extracted words. A prompt is used to give instructions to the model and perform the analysis. For example, the prompt could be set as "Analyze the meaning of the word 'oshikatsu,' convert it into a general term, and generate an explanation including background information." The input of this step is the specific extracted words, and the output is the analysis results including the meaning of the words and background information.

[0738] Step 6:

[0739] The server generates an easy-to-understand explanation for the user based on the analysis results from the generative AI model. For example, it generates the explanation, "'Oshikatsu' refers to the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people and is used as part of fan activities." The input of this step is the analysis results, and the output is the generated explanation.

[0740] Step 7:

[0741] The server converts the generated description into a JSON-formatted response body and sends it to the terminal as an HTTP response. The input of this step is the generated description, and the output is the HTTP response.

[0742] Step 8:

[0743] The device receives the HTTP response sent from the server and extracts the description from the response body. The device displays this description in a text area or pop-up on the user interface (UI). For example, it might say, "Oshikatsu is the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people and is used as part of fan activities." The input of this step is the HTTP response, and the output is the description to be displayed.

[0744] Through these steps, users can intuitively understand the meaning of difficult-to-understand words and phrases contained in the input text.

[0745] (Application example 1)

[0746] 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."

[0747] In today's information society, diverse users increasingly use words and coded phrases specific to different groups or generations. From a security perspective, it is particularly important to analyze suspicious terms and coded expressions in real time, convert them into understandable forms, and display warnings. However, current systems lack the means to efficiently perform such analysis and conversion, often resulting in delayed responses. A solution to this problem is needed.

[0748] 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.

[0749] In this invention, the server includes means for receiving text input from a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words unique to a specific group or generation from the words and phrases, means for analyzing the extracted words using an artificial intelligence model, means for generating a sentence converted into a form easy for the user to understand based on the analysis result, means for transmitting the generated sentence to a user terminal, and means for generating and displaying a warning message when a security risk is detected. This enables real-time analysis of terms used by different generations or groups and automatic generation of easy-to-understand warning messages based on the analysis.

[0750] The "means for receiving text input from a user" is a device or program that obtains text information input by a user and stores it for subsequent processing.

[0751] A "morphological analysis engine" is an analytical tool that divides input text into semantic units such as words and phrases.

[0752] The "means for dividing into words and phrases" is a device or program that divides input text into meaningful units, such as words and phrases, using a morphological analysis engine.

[0753] The "means for extracting words specific to a particular group or generation" is a device or program that identifies and extracts words specific to a particular group or generation from among the segmented words or phrases.

[0754] "Means for analyzing using an artificial intelligence model" refers to a device or program that uses artificial intelligence technology to perform analysis in order to understand the meaning of extracted words.

[0755] The "means for generating sentences converted into a form that is easy for the user to understand" is a device or program that converts words and phrases into a form that is easy for the user to understand based on the analysis results and generates new sentences.

[0756] The "means for transmitting the generated sentence to the user terminal" is a device or program that transfers the converted sentence to the user terminal and displays it.

[0757] The "means for generating and displaying a warning message when a security risk is detected" refers to a device or program that automatically generates a warning message and notifies the user when a security risk is detected as a result of the analysis.

[0758] As an embodiment of the present invention, we will specifically describe a system in which a security team analyzes suspicious text data in real time, converts it into an easy-to-understand format, and displays a warning. This system processes text data entered by a user using a morphological analysis engine and artificial intelligence technology, analyzing and converting words unique to specific groups or generations. Furthermore, if a security risk is detected based on the analysis results, a warning message is automatically generated and notified to the user.

[0759] System configuration

[0760] 1. Input reception:

[0761] The server receives text entered by users, such as chat logs, emails, social media posts, etc. For example, suppose a user enters, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0762] 2. Text preprocessing:

[0763] The server splits the received text into words and phrases using a morphological analysis engine (e.g., Mecab), and performs text normalization.

[0764] 3. Semantic and Intention Analysis:

[0765] The server extracts words specific to a particular group or generation from the segmented words and phrases. It then analyzes the extracted words using an artificial intelligence model (e.g., BERT or GPT). For example, it confirms that the word "oshikatsu" (supporting a specific character or artist) refers to the activity of supporting a specific character or artist.

[0766] 4. Transformation and Description Generation:

[0767] Based on the analysis results, the server converts the words into a form that is easy for the user to understand. For example, it generates an explanation such as, "'Oshikatsu' is the activity of supporting your favorite artist or character."

[0768] 5. Security Risk Analysis:

[0769] If the analysis reveals that certain words or phrases contain potential security risks, the server will detect this and generate a warning message.

[0770] 6. Sending and viewing results:

[0771] The server sends the generated explanatory text and warning message to the user's device, which then displays it to the user. For example, it might say, "Oshikatsu is the activity of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0772] Hardware and software used

[0773] Hardware:

[0774] Terminals (PCs, smartphones), servers

[0775] software:

[0776] Morphological analysis engine (Mecab)

[0777] Artificial intelligence models (BERT and GPT)

[0778] Databases (storing words specific to specific groups or generations)

[0779] Specific examples

[0780] For example, if a security operator sees a message in a chat log they are monitoring saying, "Let's go to that artist's concert tomorrow! 'Oshikatsu' is the best!", the system will generate an explanation in real time: "'Oshikatsu' is the activity of supporting your favorite artist or character. It's especially popular among young people." and display it, while also assessing the associated risks and displaying a warning message if necessary.

[0781] Prompt Sentence Examples

[0782] Extract suspicious words and phrases from the given text and explain their meaning: I'm going to see that artist's concert tomorrow! "Supporting my favorite artist" is the best!

[0783] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0784] Step 1:

[0785] A user inputs text into the device that contains words or phrases that are difficult to understand. For example, they might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." The device receives this input text and generates a request to send to the server. The input is the text entered by the user, and the output is the request to send to the server.

[0786] Step 2:

[0787] The server receives a text request sent from a device. It uses a morphological analysis engine (e.g., Mecab) to split this text into words and phrases. For example, it might split something like, "The other day, I heard the word 'oshikatsu' many times on TV, but I didn't understand what it meant." The input is the received text request, and the output is the split words and phrases.

[0788] Step 3:

[0789] The server extracts words specific to a particular group or generation from the segmented words and phrases. For example, to extract the word "oshikatsu," it refers to a specific database. The input is the segmented words and phrases, and the output is the extracted words.

[0790] Step 4:

[0791] The server analyzes the extracted words using an artificial intelligence model (e.g., BERT or GPT). It verifies that "oshikatsu" refers to the activity of supporting a specific character or artist. The input is the extracted words, and the output is the analysis results.

[0792] Step 5:

[0793] Based on the analysis results, the server generates a sentence that is converted into a form that is easy for the user to understand. For example, it converts it into a form such as "'Oshikatsu' is the activity of supporting a favorite artist or character." It may also generate an explanatory sentence that includes additional background information and context as needed. The input is the analysis results, and the output is the converted sentence.

[0794] Step 6:

[0795] If a security risk is detected as a result of the analysis, the server automatically generates a warning message. For example, it generates a message saying, "This phrase may contain a high security risk." The input is the analysis result, and the output is the warning message.

[0796] Step 7:

[0797] The server generates a request to send the generated explanatory text and warning message to the user's terminal. The terminal receives the explanatory text and warning message sent from the server and displays them to the user. The input is the generated explanatory text and warning message, and the output is the displayed result. For example, it could display "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people and is used as part of fan activities," and also display a warning message if necessary.

[0798] 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.

[0799] As an embodiment of the present invention, we will explain a specific configuration that combines an emotion engine with a system that analyzes and converts words and phrases that are difficult for users to understand. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology, and also recognizes the user's emotions and provides feedback in an appropriate form.

[0800] System program processing

[0801] Input Reception

[0802] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0803] The terminal receives input text from the user and generates a request to send this text to the server.

[0804] Text and sentiment preprocessing

[0805] The server receives a text request sent from the device. It uses a morphological analysis engine (e.g., Mecab) to split this text into words and phrases. For example, it could split the text into "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0806] The server simultaneously uses an emotion engine to recognize emotions from the text entered by the user, for example, the emotion engine recognizes "confused."

[0807] Semantic and Intention Analysis

[0808] The server extracts words specific to a particular group or generation from the segmented words and phrases. For example, it extracts the word "oshikatsu." It then analyzes the meaning of the extracted words using an artificial intelligence model (e.g., BERT or GPT). It verifies that "oshikatsu" refers to the activity of supporting a particular character or artist.

[0809] Transformation and Description Generation

[0810] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it generates a sentence such as, "'Oshikatsu' is the activity of supporting a favorite artist or character."

[0811] Here, the server takes into account the user's emotional information recognized by the emotion engine. For example, if the emotion "confusion" is recognized, it adds a sentence to ease the emotion or an encouraging message, such as "Don't worry, 'oshikatsu' is a very fun activity!"

[0812] Returning and displaying results

[0813] The server generates a request to send an additional message to the terminal according to the generated description and emotion.

[0814] The device receives the explanation and message request sent from the server and displays it to the user. For example, it displays something like, "'Oshikatsu' is the activity of supporting your favorite artist or character. It's a term that's especially popular among young people, and is used as part of fan activities. Don't worry, 'Oshikatsu' is a very fun activity!"

[0815] This added emotion engine allows users to receive explanations in a more familiar way and to more easily understand words and phrases that are difficult to understand. This invention can bridge the communication gap between different generations and groups, and also provide feedback that takes into account the user's emotions.

[0816] The processing flow will be explained below.

[0817] MODE FOR CARRYING OUT THE INVENTION

[0818] Step 1:

[0819] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0820] Step 2:

[0821] The terminal receives input text from the user and generates a request to send this text to the server.

[0822] Step 3:

[0823] The server receives the text request sent from the terminal.

[0824] Step 4:

[0825] The server uses a morphological analysis engine (e.g., Mecab) to split the received text into words and phrases, such as "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0826] Step 5:

[0827] The server simultaneously uses an emotion engine to recognize emotions from the text entered by the user, such as the emotion "confused." The emotion engine uses natural language processing to assess the emotional tone of the text.

[0828] Step 6:

[0829] The server extracts words that are specific to a particular group or generation from the segmented words and phrases. For example, the word "oshikatsu" (supporting someone) is extracted.

[0830] Step 7:

[0831] The server uses an artificial intelligence model (e.g., BERT or GPT) to analyze the meaning of the extracted words. For example, it confirms that "oshikatsu" refers to the activity of supporting a specific character or artist.

[0832] Step 8:

[0833] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it generates a sentence such as, "'Oshikatsu' is the activity of supporting a favorite artist or character."

[0834] Step 9:

[0835] The server takes into account the user's emotional information recognized by the emotion engine. For example, if the emotion "confusion" is recognized, it adds a message to ease the emotion or an encouraging message, such as "Don't worry, 'oshikatsu' is a very fun activity!"

[0836] Step 10:

[0837] The server generates a request to send an additional message to the terminal according to the generated description and emotion.

[0838] Step 11:

[0839] The terminal receives the explanatory text and the message request sent from the server.

[0840] Step 12:

[0841] The device then displays the received explanation to the user. For example, it might say, "'Oshikatsu' is the activity of supporting your favorite artist or character. It's a term that's especially popular among young people, and is used as part of fan activities. Don't worry, 'Oshikatsu' is a lot of fun!"

[0842] This concrete step allows users to understand difficult words and phrases in an easy-to-understand manner, while also receiving emotionally sensitive feedback.

[0843] Example 2

[0844] 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."

[0845] In today's world, the words and phrases used between generations and specific groups are becoming more diverse, making it difficult for users to understand their meanings. It is also important to consider the confusion and discomfort users may feel when searching for the meaning of a particular word or phrase. In such situations, a system that provides easy-to-understand explanations to users while also taking their feelings into consideration is required.

[0846] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0847] In this invention, the server includes means for receiving text input from a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words specific to a particular group or generation from the words and phrases, means for analyzing the extracted words using an artificial intelligence model, means for generating a sentence converted into a form that is easy for the user to understand based on the analysis result, means for recognizing the user's emotion, means for generating a message corresponding to the emotion based on the recognized emotion, and means for transmitting the generated sentence and the message based on the emotion to a user terminal. This makes it possible to clearly explain the meaning of words and phrases that are difficult for the user to understand, and further reduce the confusion and discomfort felt by the user.

[0848] "User" refers to someone who uses the system to find the meaning of words or phrases that are difficult to understand.

[0849] "Text" refers to a sentence or string of characters that a user sends to a system using an input device.

[0850] A "morphological analysis engine" refers to software that divides input text into words and phrases and analyzes their structure.

[0851] "Words and Phrases" refers to sequences of words that form small units of language or short sentences extracted from text by a morphological analysis engine.

[0852] "Group or generational idiom" refers to distinctive terms and expressions that are used specifically within a particular cultural background or generation.

[0853] An "artificial intelligence model" refers to an algorithm that uses machine learning and deep learning techniques to analyze and understand the meaning of words and phrases.

[0854] "Analysis results" refers to the information generated after an AI model analyzes a particular word or phrase.

[0855] "Sentences converted into a form that is easy for users to understand" refers to sentences in which technical terms and words specific to a particular group or generation have been replaced with expressions that are easy for the general public to understand, based on the analysis results.

[0856] "Emotion" refers to the psychological state a user feels when they input a particular piece of text.

[0857] An "emotion engine" refers to software that analyzes input text and automatically recognizes the user's psychological state from it.

[0858] "Emotion-responsive messages" refer to sentences generated to reassure, encourage, or otherwise respond to the user's emotions based on the user's recognized emotions.

[0859] "User terminal" refers to a computing device (e.g., smartphone, tablet, computer) used by a user that includes an interface for communicating with the system.

[0860] As an embodiment of the present invention, we will explain in detail a system that analyzes and converts words and phrases that are difficult for users to understand. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology, and also recognizes the user's emotions and provides feedback in an appropriate form.

[0861] Input Reception

[0862] The user inputs text into the device that includes words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." The device receives the input text from the user and generates a request to send this text to the server. Specifically, the device converts the input text into a data packet and sends it to the server as an HTTP POST request.

[0863] Text and sentiment preprocessing

[0864] The server receives a text request sent from the device. This text is stored in the server's input buffer. The server uses a morphological analysis engine (for example, the Japanese morphological analysis engine Mecab) to divide the text into words and phrases. For example, the server breaks down the text into "I heard the word 'oshikatsu' many times, but I didn't understand its meaning" into "oshikatsu" (words) many times, but I didn't understand its meaning. The server then uses an emotion engine to analyze emotions from the text entered by the user. For example, the emotion engine (for example, a natural language processing API) recognizes the emotion "confused."

[0865] Semantic and Intention Analysis

[0866] The server extracts words specific to a particular group or generation from the segmented words and phrases. Specifically, it references dictionaries and databases to extract the word "oshikatsu." The server then analyzes the meaning of the extracted words using an artificial intelligence model (e.g., BERT or GPT). The BERT model is used to understand the context of "oshikatsu" and confirm that it refers to the activity of supporting a specific character or artist.

[0867] Transformation and Description Generation

[0868] Based on the analysis results, the server generates a sentence that is easy for the user to understand. Specifically, it generates an explanatory sentence such as, "Oshikatsu is an activity to support your favorite artists or characters." Furthermore, the server takes into account the user's emotional information recognized by the emotion engine. For example, if the emotion "confusion" is recognized, the server adds an encouraging message to alleviate that emotion: "Don't worry, 'Oshikatsu' is a very fun activity!"

[0869] Returning and displaying results

[0870] The server generates a request to send the generated description and an additional message corresponding to the emotion to the device. Specifically, it converts the generated sentence and message into JSON data and sends it to the device as an HTTP response. The device receives the description and message sent from the server and displays it to the user. For example, it displays something like, "'Oshikatsu' is the activity of supporting your favorite artist or character. Don't worry, 'Oshikatsu' is a very fun activity!"

[0871] Examples of concrete examples and prompts

[0872] As a specific example, if a user types, "The word 'Egae' came up a lot at the party yesterday. What does it mean?", the server will generate the answer, "'Egae' means that a photo or video is beautifully taken and looks good. It is a term that is particularly commonly used on social media," and send it to the device.

[0873] An example of a prompt sentence is, "Please look up the meaning of a specific word or phrase. The text is 'What does XX (the word you want to look up) mean?'"

[0874] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0875] Step 1:

[0876] The user inputs text into the device that includes words and phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." Input: User's text data. Output: Text data input into the device.

[0877] Step 2:

[0878] The terminal receives input text from the user and generates a request to send to the server. Specifically, it converts the input text into a data packet and sends it to the server as an HTTP POST request. Input: User's text data. Output: HTTP POST request to the server.

[0879] Step 3:

[0880] The server receives a text request sent from the terminal. The text is saved in the server's input buffer. Input: HTTP request data. Output: Text data saved in the server's input buffer.

[0881] Step 4:

[0882] The server uses a morphological analysis engine (for example, a morphological analysis engine) to split the text into words and phrases. As a concrete example, the server splits the text "I heard the word 'oshikatsu' many times, but I didn't understand its meaning" into "oshikatsu" (the word) many times, but I didn't understand its meaning." Input: Text data saved in the server's input buffer. Output: A list of split words and phrases.

[0883] Step 5:

[0884] The server uses an emotion engine to analyze emotions from the text entered by the user. For example, the emotion engine recognizes the emotion "confused." Input: Text data stored in the server's input buffer. Output: Emotion data for "confused."

[0885] Step 6:

[0886] The server extracts words specific to a particular group or generation from the segmented words and phrases. Specifically, it extracts the word "oshikatsu" by referring to a dictionary or database. Input: A list of segmented words and phrases. Output: Extracted specific words.

[0887] Step 7:

[0888] The server uses an artificial intelligence model (e.g., a generative AI model) to analyze the meaning of the extracted words. As a specific example, it uses the BERT model to understand the context of "oshikatsu" and confirm that it refers to the activity of supporting a specific character or artist. Input: Specific extracted words. Output: Semantic data of the analysis results.

[0889] Step 8:

[0890] Based on the analysis results, the server generates a sentence that is converted into a form that is easy for the user to understand. As a specific example, it generates the sentence, "'Oshikatsu' is the activity of supporting a favorite artist or character." Input: Semantic data from the analysis results. Output: Sentence that has been converted into a form that is easy for the user to understand.

[0891] Step 9:

[0892] The server generates a message corresponding to the emotion, taking into account the user's emotional information recognized by the emotion engine. For example, to alleviate the emotion of "confusion," it adds a message such as "Don't worry, 'oshikatsu' is a very fun activity!". Input: Emotion data. Output: A sentence containing a message.

[0893] Step 10:

[0894] The server generates a request to send the generated description and a message based on the emotion to the device. Specifically, it converts the generated sentence and message into JSON data and sends it as an HTTP response to the device. Input: Sentence containing the message. Output: HTTP response to the device.

[0895] Step 11:

[0896] The device receives the explanation and message request sent from the server and displays them to the user. For example, it displays the following: "Oshikatsu is the activity of supporting your favorite artists or characters. Don't worry, oshikatsu is a very fun activity!" Input: HTTP response from the server. Output: Explanation and message displayed on the user's device.

[0897] (Application example 2)

[0898] 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."

[0899] In current food delivery services, user reviews and feedback often contain words and phrases that are difficult to understand. Furthermore, the feedback provided ignores the user's feelings, preventing improvements to the user experience. In particular, the inability to properly interpret user opinions and requests regarding the taste of food can delay improvements to the delivery service and the restaurant. Therefore, there is a need for a system that can properly analyze user feedback and provide easy-to-understand feedback that takes user feelings into consideration.

[0900] The identification process by the identification 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 input by a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words unique to a specific group or generation from the words and phrases, means for analyzing the extracted words using an artificial intelligence model, means for generating a sentence converted into a form easy for the user to understand based on the analysis result, means for adding feedback to the generated sentence that takes into account the user's emotions, and means for transmitting the generated sentence and feedback to the user terminal. This makes it possible to appropriately analyze reviews and feedback from users and provide feedback that is easy to understand and takes into account their emotions.

[0901] The "means for receiving text input from a user" is an interface for receiving text data such as reviews and feedback input by a user.

[0902] A "morphological analysis engine" is an analysis engine that divides natural languages ​​such as Japanese into words and phrases.

[0903] The "means for splitting into words and phrases" refers to a means for breaking down input text into individual words and phrases using a morphological analysis engine.

[0904] A "means for extracting words specific to a particular group or generation" is a means for searching for and extracting words or slang specific to a particular age group or community from text.

[0905] An "artificial intelligence model" is a machine learning model used to learn from large amounts of text data and analyze input text.

[0906] "Means for analyzing" refers to the means for analyzing extracted words and phrases using an artificial intelligence model to understand their meaning and context.

[0907] The "means for generating sentences converted into a form that is easy for the user to understand" is a means for reconstructing text into a form that is easy for the user to understand, based on the content analyzed by the artificial intelligence model.

[0908] The "means for adding feedback that takes into account the user's emotions" is a means for recognizing emotions from text entered by the user and adding feedback that matches those emotions.

[0909] The "means for transmitting to the user terminal" refers to a means for transmitting the generated text and feedback to the terminal used by the user.

[0910] The program of the system that realizes this invention performs the following process in stages: First, the specific steps when a user posts a review or feedback using a food delivery app will be explained.

[0911] System Overview

[0912] 1. Receiving user input

[0913] The server receives the text input by the user, for example, a review such as "The food was delicious, but the flavor was too strong, so it might not be suitable for children." This allows the text data input by the user to be incorporated into the system.

[0914] 2. Morphological analysis

[0915] The server uses Mecab as a morphological analysis engine to split the input text into words and phrases, such as "The food was delicious, but the flavor was too strong, so it might not be suitable for children."

[0916] 3. Extracting specific words

[0917] The server references the database to extract words that are specific to a particular group or generation, such as "delicious" or "not suitable" in reviews.

[0918] 4. Word Analysis

[0919] The server uses artificial intelligence models such as BERT and GPT to analyze the meaning and context of the extracted words, resulting in an interpretation such as "The food is delicious, but the flavor is too strong for children to eat."

[0920] 5. Generate feedback

[0921] The server generates feedback based on the analysis results in a format that is easy for the user to understand. Furthermore, it analyzes the user's emotions using the Google Cloud Natural Language API, and if the emotion of "dissatisfaction" is recognized, this is reflected in the feedback. For example, the server may generate feedback such as, "Thank you for rating the taste of the dish. Your comment that the flavor is too strong and not suitable for children can be adjusted for your next order."

[0922] 6. Submitting Feedback

[0923] The server sends the generated feedback and analysis results to the user's device, which receives them and displays the review content in an easy-to-understand manner.

[0924] Hardware and software used

[0925] Morphological analysis engine: Mecab

[0926] Sentiment engine: Google Cloud Natural Language API

[0927] Artificial intelligence models: BERT, GPT

[0928] Specific examples

[0929] A user leaves the following review on a food delivery app:

[0930] "The food was delicious, but the flavor was too strong and probably not suitable for children. It's very different from my mother's cooking."

[0931] The server receives this and segments it using morphological analysis. It then extracts specific words and uses an AI model to obtain the analysis results. The emotion engine considers the emotion recognized as "unsatisfied" and generates appropriate feedback. The feedback the user will next see is as follows:

[0932] "Thank you for rating the taste of our food. We understand that the flavor is too strong and unsuitable for children. We will adjust it for your next order. We will also strive to recreate your mother's cooking style!"

[0933] Prompt Sentence Examples

[0934] Prompt sentence to input to the generative AI model:

[0935] "Please parse the following text, convert it to something understandable, and generate feedback taking into account sentiment:

[0936] Text: 'The food was delicious, but the flavor was too strong and perhaps not suitable for children. It's nothing like my mother's cooking.'

[0937] User sentiment: 'Unsatisfied'

[0938] Requirement: Convert into an understandable format and generate feedback for next time.

[0939] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0940] Step 1:

[0941] The server receives text input from the user. When the user enters a review or feedback through the food delivery app and clicks submit, this text data is sent to the server. The input is the text data posted by the user, and the output is the text data received as is.

[0942] Step 2:

[0943] The server uses a morphological analysis engine (Mecab) to divide the received text into words and phrases. Specifically, the server passes the text data to Mecab, which then performs a mechanical grammatical analysis to break it down into words and phrases. The input is the text data received in step 1, and the output is the text divided by morphological analysis. For example, the input "The food was delicious, but the flavor was too strong, so it might not be suitable for children" is changed to the output "The food was delicious, but the flavor was too strong, so it might not be suitable for children."

[0944] Step 3:

[0945] The server performs text normalization as preprocessing. This process involves removing unnecessary spaces and special characters from the text and performing pattern matching using regular expressions. The input is the text split in step 2, and the output is the normalized text. For example, "The food was delicious, but the flavor was too strong, so it might not be suitable for children" becomes "The food was delicious, but the flavor was too strong, so it might not be suitable for children."

[0946] Step 4:

[0947] The server references a database to extract words specific to a particular group or generation from the normalized text. For example, it may have a database listing words used by a particular age group or community, and searches through it to extract the relevant words. The input is the text normalized in step 3, and the output is the specific words extracted. For example, "delicious" or "not suitable."

[0948] Step 5:

[0949] The server analyzes the extracted words using an artificial intelligence model (BERT or GPT). Specifically, the extracted words and phrases are input into the AI ​​model, which analyzes their context and meaning. The input is the words extracted in step 4, and the output is the analysis result based on the context and meaning of those words. For example, the conclusion is "It's delicious, but the flavor is too strong for children to eat."

[0950] Step 6:

[0951] Based on the analysis results, the server generates a sentence that is converted into a form that is easy for the user to understand. In this step, an explanation is generated in a format that is easy for the user to understand based on the analysis results of the AI ​​model. The input is the analysis result obtained in step 5, and the output is a reconstructed explanation. For example, feedback such as "Thank you for rating the taste of the dish. Your opinion that the flavor is too strong and not suitable for children can be adjusted for your next order."

[0952] Step 7:

[0953] The server adds feedback to the generated description, taking into account the user's emotions. Using an emotion engine (Google Cloud Natural Language API), it recognizes emotions from the user's input text and generates an additional message based on that. The input is the description obtained in step 6 and the user's emotional data, and the output is the final feedback. For example, it could be something like, "We received feedback that the flavor was too strong, but we will adjust it for your next order. We will also try to recreate your mother's recipe!"

[0954] Step 8:

[0955] The server sends the generated sentence and feedback to the user's device, which receives it and displays it to the user in the app. The input is the final feedback sentence generated in step 7, and the output is the data sent to the user's device. This allows the user to see how their review is interpreted and fed back.

[0956] 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.

[0957] 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.

[0958] 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.

[0959] [Fourth embodiment]

[0960] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0961] 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.

[0962] 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).

[0963] 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.

[0964] 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.

[0965] 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).

[0966] 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.

[0967] 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.

[0968] 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.

[0969] 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.

[0970] 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.

[0971] 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.

[0972] 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."

[0973] As an embodiment of the present invention, we will specifically explain a system that analyzes and converts words and phrases that are difficult for users to understand. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology to convert words that are unique to a specific group or generation into an easier-to-understand form.

[0974] System program processing

[0975] Input Reception

[0976] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0977] The terminal receives input text from the user and generates a request to send this text to the server.

[0978] Text Preprocessing

[0979] The server receives a text request sent from the device. It uses a morphological analysis engine (e.g., Mecab) to split this text into words and phrases. For example, it could split the text into "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0980] Semantic and Intention Analysis

[0981] The server extracts words specific to a particular group or generation from the segmented words and phrases. For example, it extracts the word "oshikatsu." It then analyzes the meaning of the extracted words using an artificial intelligence model (e.g., BERT or GPT). It verifies that "oshikatsu" refers to the activity of supporting a particular character or artist.

[0982] Transformation and Description Generation

[0983] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it converts it into a form such as, "Oshikatsu is the activity of supporting a favorite artist or character." It also generates an explanatory text that includes additional background information and context as needed. For example, it adds an explanation such as, "It is a term that is particularly popular among young people and is used as part of fan activities."

[0984] Returning and displaying results

[0985] The server generates a request to transmit the generated description to the terminal.

[0986] The device receives the explanation request sent from the server and displays it to the user. For example, it displays something like, "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[0987] In this way, users can understand words and phrases that are difficult to understand in an easy-to-understand manner.This invention can bridge the communication gap between different generations and groups.

[0988] The processing flow will be explained below.

[0989] Specific processing steps of the program

[0990] Step 1:

[0991] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0992] Step 2:

[0993] The terminal receives input text from the user and generates a request to send this text to the server.

[0994] Step 3:

[0995] The server receives the text request sent from the terminal.

[0996] Step 4:

[0997] The server uses a morphological analysis engine (e.g., Mecab) to split the received text into words and phrases, such as "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[0998] Step 5:

[0999] The server extracts words that are specific to a particular group or generation from the segmented words and phrases. For example, it extracts the word "oshikatsu."

[1000] Step 6:

[1001] The server uses an artificial intelligence model (e.g., BERT or GPT) to analyze the meaning of the extracted words. For example, it confirms that "oshikatsu" refers to the activity of supporting a specific character or artist.

[1002] Step 7:

[1003] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it generates a sentence such as, "'Oshikatsu' is the activity of supporting a favorite artist or character."

[1004] Step 8:

[1005] The server generates a description with additional background information and context as needed, for example, "This term is popular among young people and is used as part of fan activities."

[1006] Step 9:

[1007] The server generates a request to transmit the generated description to the terminal.

[1008] Step 10:

[1009] The terminal receives the explanation request sent from the server.

[1010] Step 11:

[1011] The device then displays the received explanation to the user. For example, it might say, "Oshikatsu is the act of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[1012] This concrete step allows users to understand difficult words and phrases in an easy-to-understand and explained way.

[1013] Example 1

[1014] 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."

[1015] Words and phrases used by different generations or specific groups can be difficult to understand, creating a communication gap. In such situations, a means is needed to easily understand the meaning of specific words and phrases, but traditional methods often do not adequately solve this problem. In particular, there is a need for technology that can convert words into a form that is easily understandable to users while understanding related background information and context.

[1016] 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.

[1017] In this invention, the server includes means for receiving text input from a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words specific to a specific group or generation, means for analyzing the extracted words using an artificial intelligence model, means for generating explanatory text in a form that is easy for the user to understand using a generative AI model using a prompt text, means for transmitting the generated explanatory text to a user terminal, and means for displaying the generated explanatory text on a user interface, thereby enabling users to intuitively understand the meanings of words and phrases of different generations or groups.

[1018] "User" refers to an individual or organization that uses the system.

[1019] "Terminal" refers to a device or equipment that allows a user to input information.

[1020] "Text" refers to a character string or sentence entered by a user.

[1021] A "morphological analysis engine" refers to a software tool that breaks text into morphemes (words and phrases).

[1022] A "prompt sentence" refers to an input sentence that gives instructions to a generative AI model for analysis or conversion.

[1023] A "generative AI model" refers to an algorithm or software that uses artificial intelligence techniques to analyze input data and generate an appropriate output.

[1024] "User interface" refers to the screen and operating means that allow a user to interact with a system.

[1025] "Means for splitting" refers to the function of splitting text into words and phrases using a morphological analysis engine.

[1026] "Means of extraction" refers to the function of finding words specific to a particular group or generation within text.

[1027] "Means of analysis" refers to the function of analyzing the meaning and intent of extracted words using an artificial intelligence model.

[1028] "Means for generating" refers to the function of creating an explanation that is easy for the user to understand based on the analysis results.

[1029] The "transmitting means" refers to a communication function for transmitting the generated explanatory text to the user terminal.

[1030] The "display means" refers to a function for displaying the generated explanatory text on the screen of the user terminal.

[1031] As an embodiment of the present invention, a system for analyzing and converting words and phrases that are difficult for users to understand will be specifically described. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology to convert words that are specific to a specific group or generation into an easier-to-understand form.

[1032] The main components of this system are the user terminal, server, morphological analysis engine, and generative AI model.

[1033] First, the user inputs text containing words or phrases that are difficult to understand into the device. For example, they might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." The device receives this input text, creates a request body in JSON format, and sends it to the server as an HTTP request. The specific hardware used by the device could be, for example, a smartphone or a PC.

[1034] The server receives a text request sent from the device. It uses a morphological analysis engine (e.g., Mecab) to break down the received text into words and phrases. For example, it might break down the text into something like, "The other day, I heard the word 'oshikatsu' many times on TV, but I didn't understand what it meant." The software used here is the morphological analysis engine Mecab.

[1035] Next, the server extracts words specific to a particular group or generation (e.g., "oshikatsu") from the segmented words and phrases. A generative AI model (e.g., BERT or GPT) is used to analyze the meaning and intent of the extracted words. The generative AI model receives instructions using prompts and performs the analysis. For example, the prompt might be, "Analyze the meaning of the word oshikatsu, convert it into a general term, and generate an explanatory text including background information."

[1036] The server generates an easy-to-understand explanation for the user based on the analysis results from the AI ​​model. For example, it converts the information into something like, "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[1037] The generated explanation is sent from the server to the user's device as an HTTP response. The device receives this response and displays it in a text area or pop-up on the user interface (UI). The user can read and understand the explanation displayed on the screen. A specific example of what is displayed is, "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people, and is used as part of fan activities."

[1038] This allows users to intuitively understand the meaning of words and phrases from different generations and groups, thereby bridging communication gaps. This invention facilitates smooth communication between different generations and groups, and makes it easier to understand the meaning of words.

[1039] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1040] Step 1:

[1041] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, they might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." This input text becomes the input to the system. The device receives this text and temporarily stores it in its internal memory for subsequent processing.

[1042] Step 2:

[1043] The device generates a request to send the text received from the user to the server. This request is usually in JSON format and sent to the server using an HTTP POST request. The request body contains the text entered by the user.

[1044] Step 3:

[1045] The server receives an HTTP POST request sent from the device. It extracts text from the request body and uses a morphological analysis engine (e.g., Mecab) to split the text into words and phrases. The input to this step is the text entered by the user, and the output is a list of words and phrases split by morphological analysis. For example, the phrase might be split as follows: "The other day, I heard the word 'oshikatsu' many times on TV, but I didn't understand what it meant."

[1046] Step 4:

[1047] The server extracts words specific to a particular group or generation from the segmented words and phrases. This extraction can be done by referencing a database. For example, the word "oshikatsu" is extracted. The input of this step is a list of segmented words and phrases, and the output is a specific word (e.g., "oshikatsu").

[1048] Step 5:

[1049] The server uses a generative AI model (such as BERT or GPT) to analyze the meaning of the extracted words. A prompt is used to give instructions to the model and perform the analysis. For example, the prompt could be set as "Analyze the meaning of the word 'oshikatsu,' convert it into a general term, and generate an explanation including background information." The input of this step is the specific extracted words, and the output is the analysis results including the meaning of the words and background information.

[1050] Step 6:

[1051] The server generates an easy-to-understand explanation for the user based on the analysis results from the generative AI model. For example, it generates the explanation, "'Oshikatsu' refers to the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people and is used as part of fan activities." The input of this step is the analysis results, and the output is the generated explanation.

[1052] Step 7:

[1053] The server converts the generated description into a JSON-formatted response body and sends it to the terminal as an HTTP response. The input of this step is the generated description, and the output is the HTTP response.

[1054] Step 8:

[1055] The device receives the HTTP response sent from the server and extracts the description from the response body. The device displays this description in a text area or pop-up on the user interface (UI). For example, it might say, "Oshikatsu is the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people and is used as part of fan activities." The input of this step is the HTTP response, and the output is the description to be displayed.

[1056] Through these steps, users can intuitively understand the meaning of difficult-to-understand words and phrases contained in the input text.

[1057] (Application example 1)

[1058] 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."

[1059] In today's information society, diverse users increasingly use words and coded phrases specific to different groups or generations. From a security perspective, it is particularly important to analyze suspicious terms and coded expressions in real time, convert them into understandable forms, and display warnings. However, current systems lack the means to efficiently perform such analysis and conversion, often resulting in delayed responses. A solution to this problem is needed.

[1060] 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.

[1061] In this invention, the server includes means for receiving text input from a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words unique to a specific group or generation from the words and phrases, means for analyzing the extracted words using an artificial intelligence model, means for generating a sentence converted into a form easy for the user to understand based on the analysis result, means for transmitting the generated sentence to a user terminal, and means for generating and displaying a warning message when a security risk is detected. This enables real-time analysis of terms used by different generations or groups and automatic generation of easy-to-understand warning messages based on the analysis.

[1062] The "means for receiving text input from a user" is a device or program that obtains text information input by a user and stores it for subsequent processing.

[1063] A "morphological analysis engine" is an analytical tool that divides input text into semantic units such as words and phrases.

[1064] The "means for dividing into words and phrases" is a device or program that divides input text into meaningful units, such as words and phrases, using a morphological analysis engine.

[1065] The "means for extracting words specific to a particular group or generation" is a device or program that identifies and extracts words specific to a particular group or generation from among the segmented words or phrases.

[1066] "Means for analyzing using an artificial intelligence model" refers to a device or program that uses artificial intelligence technology to perform analysis in order to understand the meaning of extracted words.

[1067] The "means for generating sentences converted into a form that is easy for the user to understand" is a device or program that converts words and phrases into a form that is easy for the user to understand based on the analysis results and generates new sentences.

[1068] The "means for transmitting the generated sentence to the user terminal" is a device or program that transfers the converted sentence to the user terminal and displays it.

[1069] The "means for generating and displaying a warning message when a security risk is detected" refers to a device or program that automatically generates a warning message and notifies the user when a security risk is detected as a result of the analysis.

[1070] As an embodiment of the present invention, we will specifically describe a system in which a security team analyzes suspicious text data in real time, converts it into an easy-to-understand format, and displays a warning. This system processes text data entered by a user using a morphological analysis engine and artificial intelligence technology, analyzing and converting words unique to specific groups or generations. Furthermore, if a security risk is detected based on the analysis results, a warning message is automatically generated and notified to the user.

[1071] System configuration

[1072] 1. Input reception:

[1073] The server receives text entered by users, such as chat logs, emails, social media posts, etc. For example, suppose a user enters, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[1074] 2. Text preprocessing:

[1075] The server splits the received text into words and phrases using a morphological analysis engine (e.g., Mecab), and performs text normalization.

[1076] 3. Semantic and Intention Analysis:

[1077] The server extracts words specific to a particular group or generation from the segmented words and phrases. It then analyzes the extracted words using an artificial intelligence model (e.g., BERT or GPT). For example, it confirms that the word "oshikatsu" (supporting a specific character or artist) refers to the activity of supporting a specific character or artist.

[1078] 4. Transformation and Description Generation:

[1079] Based on the analysis results, the server converts the words into a form that is easy for the user to understand. For example, it generates an explanation such as, "'Oshikatsu' is the activity of supporting your favorite artist or character."

[1080] 5. Security Risk Analysis:

[1081] If the analysis reveals that certain words or phrases contain potential security risks, the server will detect this and generate a warning message.

[1082] 6. Sending and viewing results:

[1083] The server sends the generated explanatory text and warning message to the user's device, which then displays it to the user. For example, it might say, "Oshikatsu is the activity of supporting a favorite artist or character. It is a term that is especially popular among young people, and is used as part of fan activities."

[1084] Hardware and software used

[1085] Hardware:

[1086] Terminals (PCs, smartphones), servers

[1087] software:

[1088] Morphological analysis engine (Mecab)

[1089] Artificial intelligence models (BERT and GPT)

[1090] Databases (storing words specific to specific groups or generations)

[1091] Specific examples

[1092] For example, if a security operator sees a message in a chat log they are monitoring saying, "Let's go to that artist's concert tomorrow! 'Oshikatsu' is the best!", the system will generate an explanation in real time: "'Oshikatsu' is the activity of supporting your favorite artist or character. It's especially popular among young people." and display it, while also assessing the associated risks and displaying a warning message if necessary.

[1093] Prompt Sentence Examples

[1094] Extract suspicious words and phrases from the given text and explain their meaning: I'm going to see that artist's concert tomorrow! "Supporting my favorite artist" is the best!

[1095] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1096] Step 1:

[1097] A user inputs text into the device that contains words or phrases that are difficult to understand. For example, they might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." The device receives this input text and generates a request to send to the server. The input is the text entered by the user, and the output is the request to send to the server.

[1098] Step 2:

[1099] The server receives a text request sent from a device. It uses a morphological analysis engine (e.g., Mecab) to split this text into words and phrases. For example, it might split something like, "The other day, I heard the word 'oshikatsu' many times on TV, but I didn't understand what it meant." The input is the received text request, and the output is the split words and phrases.

[1100] Step 3:

[1101] The server extracts words specific to a particular group or generation from the segmented words and phrases. For example, to extract the word "oshikatsu," it refers to a specific database. The input is the segmented words and phrases, and the output is the extracted words.

[1102] Step 4:

[1103] The server analyzes the extracted words using an artificial intelligence model (e.g., BERT or GPT). It verifies that "oshikatsu" refers to the activity of supporting a specific character or artist. The input is the extracted words, and the output is the analysis results.

[1104] Step 5:

[1105] Based on the analysis results, the server generates a sentence that is converted into a form that is easy for the user to understand. For example, it converts it into a form such as "'Oshikatsu' is the activity of supporting a favorite artist or character." It may also generate an explanatory sentence that includes additional background information and context as needed. The input is the analysis results, and the output is the converted sentence.

[1106] Step 6:

[1107] If a security risk is detected as a result of the analysis, the server automatically generates a warning message. For example, it generates a message saying, "This phrase may contain a high security risk." The input is the analysis result, and the output is the warning message.

[1108] Step 7:

[1109] The server generates a request to send the generated explanatory text and warning message to the user's terminal. The terminal receives the explanatory text and warning message sent from the server and displays them to the user. The input is the generated explanatory text and warning message, and the output is the displayed result. For example, it could display "'Oshikatsu' is the activity of supporting a favorite artist or character. It is a term that is particularly popular among young people and is used as part of fan activities," and also display a warning message if necessary.

[1110] 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.

[1111] As an embodiment of the present invention, we will explain a specific configuration that combines an emotion engine with a system that analyzes and converts words and phrases that are difficult for users to understand. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology, and also recognizes the user's emotions and provides feedback in an appropriate form.

[1112] System program processing

[1113] Input Reception

[1114] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[1115] The terminal receives input text from the user and generates a request to send this text to the server.

[1116] Text and sentiment preprocessing

[1117] The server receives a text request sent from the device. It uses a morphological analysis engine (e.g., Mecab) to split this text into words and phrases. For example, it could split the text into "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[1118] The server simultaneously uses an emotion engine to recognize emotions from the text entered by the user, for example, the emotion engine recognizes "confused."

[1119] Semantic and Intention Analysis

[1120] The server extracts words specific to a particular group or generation from the segmented words and phrases. For example, it extracts the word "oshikatsu." It then analyzes the meaning of the extracted words using an artificial intelligence model (e.g., BERT or GPT). It verifies that "oshikatsu" refers to the activity of supporting a particular character or artist.

[1121] Transformation and Description Generation

[1122] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it generates a sentence such as, "'Oshikatsu' is the activity of supporting a favorite artist or character."

[1123] Here, the server takes into account the user's emotional information recognized by the emotion engine. For example, if the emotion "confusion" is recognized, it adds a sentence to ease the emotion or an encouraging message, such as "Don't worry, 'oshikatsu' is a very fun activity!"

[1124] Returning and displaying results

[1125] The server generates a request to send an additional message to the terminal according to the generated description and emotion.

[1126] The device receives the explanation and message request sent from the server and displays it to the user. For example, it displays something like, "'Oshikatsu' is the activity of supporting your favorite artist or character. It's a term that's especially popular among young people, and is used as part of fan activities. Don't worry, 'Oshikatsu' is a very fun activity!"

[1127] This added emotion engine allows users to receive explanations in a more familiar way and to more easily understand words and phrases that are difficult to understand. This invention can bridge the communication gap between different generations and groups, and also provide feedback that takes into account the user's emotions.

[1128] The processing flow will be explained below.

[1129] MODE FOR CARRYING OUT THE INVENTION

[1130] Step 1:

[1131] The user inputs text into the device that contains words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[1132] Step 2:

[1133] The terminal receives input text from the user and generates a request to send this text to the server.

[1134] Step 3:

[1135] The server receives the text request sent from the terminal.

[1136] Step 4:

[1137] The server uses a morphological analysis engine (e.g., Mecab) to split the received text into words and phrases, such as "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant."

[1138] Step 5:

[1139] The server simultaneously uses an emotion engine to recognize emotions from the text entered by the user, such as the emotion "confused." The emotion engine uses natural language processing to assess the emotional tone of the text.

[1140] Step 6:

[1141] The server extracts words that are specific to a particular group or generation from the segmented words and phrases. For example, the word "oshikatsu" (supporting someone) is extracted.

[1142] Step 7:

[1143] The server uses an artificial intelligence model (e.g., BERT or GPT) to analyze the meaning of the extracted words. For example, it confirms that "oshikatsu" refers to the activity of supporting a specific character or artist.

[1144] Step 8:

[1145] Based on the analysis results, the server generates a sentence that is easy for the user to understand. For example, it generates a sentence such as, "'Oshikatsu' is the activity of supporting a favorite artist or character."

[1146] Step 9:

[1147] The server takes into account the user's emotional information recognized by the emotion engine. For example, if the emotion "confusion" is recognized, it adds a message to ease the emotion or an encouraging message, such as "Don't worry, 'oshikatsu' is a very fun activity!"

[1148] Step 10:

[1149] The server generates a request to send an additional message to the terminal according to the generated description and emotion.

[1150] Step 11:

[1151] The terminal receives the explanatory text and the message request sent from the server.

[1152] Step 12:

[1153] The device then displays the received explanation to the user. For example, it might say, "'Oshikatsu' is the activity of supporting your favorite artist or character. It's a term that's especially popular among young people, and is used as part of fan activities. Don't worry, 'Oshikatsu' is a lot of fun!"

[1154] This concrete step allows users to understand difficult words and phrases in an easy-to-understand manner, while also receiving emotionally sensitive feedback.

[1155] Example 2

[1156] 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."

[1157] In today's world, the words and phrases used between generations and specific groups are becoming more diverse, making it difficult for users to understand their meanings. It is also important to consider the confusion and discomfort users may feel when searching for the meaning of a particular word or phrase. In such situations, a system that provides easy-to-understand explanations to users while also taking their feelings into consideration is required.

[1158] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1159] In this invention, the server includes means for receiving text input from a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words specific to a particular group or generation from the words and phrases, means for analyzing the extracted words using an artificial intelligence model, means for generating a sentence converted into a form that is easy for the user to understand based on the analysis result, means for recognizing the user's emotion, means for generating a message corresponding to the emotion based on the recognized emotion, and means for transmitting the generated sentence and the message based on the emotion to a user terminal. This makes it possible to clearly explain the meaning of words and phrases that are difficult for the user to understand, and further reduce the confusion and discomfort felt by the user.

[1160] "User" refers to someone who uses the system to find the meaning of words or phrases that are difficult to understand.

[1161] "Text" refers to a sentence or string of characters that a user sends to a system using an input device.

[1162] A "morphological analysis engine" refers to software that divides input text into words and phrases and analyzes their structure.

[1163] "Words and Phrases" refers to sequences of words that form small units of language or short sentences extracted from text by a morphological analysis engine.

[1164] "Group or generational idiom" refers to distinctive terms and expressions that are used specifically within a particular cultural background or generation.

[1165] An "artificial intelligence model" refers to an algorithm that uses machine learning and deep learning techniques to analyze and understand the meaning of words and phrases.

[1166] "Analysis results" refers to the information generated after an AI model analyzes a particular word or phrase.

[1167] "Sentences converted into a form that is easy for users to understand" refers to sentences in which technical terms and words specific to a particular group or generation have been replaced with expressions that are easy for the general public to understand, based on the analysis results.

[1168] "Emotion" refers to the psychological state a user feels when they input a particular piece of text.

[1169] An "emotion engine" refers to software that analyzes input text and automatically recognizes the user's psychological state from it.

[1170] "Emotion-responsive messages" refer to sentences generated to reassure, encourage, or otherwise respond to the user's emotions based on the user's recognized emotions.

[1171] "User terminal" refers to a computing device (e.g., smartphone, tablet, computer) used by a user that includes an interface for communicating with the system.

[1172] As an embodiment of the present invention, we will explain in detail a system that analyzes and converts words and phrases that are difficult for users to understand. This system processes text entered by a user using a morphological analysis engine and artificial intelligence technology, and also recognizes the user's emotions and provides feedback in an appropriate form.

[1173] Input Reception

[1174] The user inputs text into the device that includes words or phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." The device receives the input text from the user and generates a request to send this text to the server. Specifically, the device converts the input text into a data packet and sends it to the server as an HTTP POST request.

[1175] Text and sentiment preprocessing

[1176] The server receives a text request sent from the device. This text is stored in the server's input buffer. The server uses a morphological analysis engine (for example, the Japanese morphological analysis engine Mecab) to divide the text into words and phrases. For example, the server breaks down the text into "I heard the word 'oshikatsu' many times, but I didn't understand its meaning" into "oshikatsu" (words) many times, but I didn't understand its meaning. The server then uses an emotion engine to analyze emotions from the text entered by the user. For example, the emotion engine (for example, a natural language processing API) recognizes the emotion "confused."

[1177] Semantic and Intention Analysis

[1178] The server extracts words specific to a particular group or generation from the segmented words and phrases. Specifically, it references dictionaries and databases to extract the word "oshikatsu." The server then analyzes the meaning of the extracted words using an artificial intelligence model (e.g., BERT or GPT). The BERT model is used to understand the context of "oshikatsu" and confirm that it refers to the activity of supporting a specific character or artist.

[1179] Transformation and Description Generation

[1180] Based on the analysis results, the server generates a sentence that is easy for the user to understand. Specifically, it generates an explanatory sentence such as, "Oshikatsu is an activity to support your favorite artists or characters." Furthermore, the server takes into account the user's emotional information recognized by the emotion engine. For example, if the emotion "confusion" is recognized, the server adds an encouraging message to alleviate that emotion: "Don't worry, 'Oshikatsu' is a very fun activity!"

[1181] Returning and displaying results

[1182] The server generates a request to send the generated description and an additional message corresponding to the emotion to the device. Specifically, it converts the generated sentence and message into JSON data and sends it to the device as an HTTP response. The device receives the description and message sent from the server and displays it to the user. For example, it displays something like, "'Oshikatsu' is the activity of supporting your favorite artist or character. Don't worry, 'Oshikatsu' is a very fun activity!"

[1183] Examples of concrete examples and prompts

[1184] As a specific example, if a user types, "The word 'Egae' came up a lot at the party yesterday. What does it mean?", the server will generate the answer, "'Egae' means that a photo or video is beautifully taken and looks good. It is a term that is particularly commonly used on social media," and send it to the device.

[1185] An example of a prompt sentence is, "Please look up the meaning of a specific word or phrase. The text is 'What does XX (the word you want to look up) mean?'"

[1186] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1187] Step 1:

[1188] The user inputs text into the device that includes words and phrases that are difficult to understand. For example, the user might input, "I heard the word 'oshikatsu' many times on TV the other day, but I didn't understand what it meant." Input: User's text data. Output: Text data input into the device.

[1189] Step 2:

[1190] The terminal receives input text from the user and generates a request to send to the server. Specifically, it converts the input text into a data packet and sends it to the server as an HTTP POST request. Input: User's text data. Output: HTTP POST request to the server.

[1191] Step 3:

[1192] The server receives a text request sent from the terminal. The text is saved in the server's input buffer. Input: HTTP request data. Output: Text data saved in the server's input buffer.

[1193] Step 4:

[1194] The server uses a morphological analysis engine (for example, a morphological analysis engine) to split the text into words and phrases. As a concrete example, the server splits the text "I heard the word 'oshikatsu' many times, but I didn't understand its meaning" into "oshikatsu" (the word) many times, but I didn't understand its meaning." Input: Text data saved in the server's input buffer. Output: A list of split words and phrases.

[1195] Step 5:

[1196] The server uses an emotion engine to analyze emotions from the text entered by the user. For example, the emotion engine recognizes the emotion "confused." Input: Text data stored in the server's input buffer. Output: Emotion data for "confused."

[1197] Step 6:

[1198] The server extracts words specific to a particular group or generation from the segmented words and phrases. Specifically, it extracts the word "oshikatsu" by referring to a dictionary or database. Input: A list of segmented words and phrases. Output: Extracted specific words.

[1199] Step 7:

[1200] The server uses an artificial intelligence model (e.g., a generative AI model) to analyze the meaning of the extracted words. As a specific example, it uses the BERT model to understand the context of "oshikatsu" and confirm that it refers to the activity of supporting a specific character or artist. Input: Specific extracted words. Output: Semantic data of the analysis results.

[1201] Step 8:

[1202] Based on the analysis results, the server generates a sentence that is converted into a form that is easy for the user to understand. As a specific example, it generates the sentence, "'Oshikatsu' is the activity of supporting a favorite artist or character." Input: Semantic data from the analysis results. Output: Sentence that has been converted into a form that is easy for the user to understand.

[1203] Step 9:

[1204] The server generates a message corresponding to the emotion, taking into account the user's emotional information recognized by the emotion engine. For example, to alleviate the emotion of "confusion," it adds a message such as "Don't worry, 'oshikatsu' is a very fun activity!". Input: Emotion data. Output: A sentence containing a message.

[1205] Step 10:

[1206] The server generates a request to send the generated description and a message based on the emotion to the device. Specifically, it converts the generated sentence and message into JSON data and sends it as an HTTP response to the device. Input: Sentence containing the message. Output: HTTP response to the device.

[1207] Step 11:

[1208] The device receives the explanation and message request sent from the server and displays them to the user. For example, it displays the following: "Oshikatsu is the activity of supporting your favorite artists or characters. Don't worry, oshikatsu is a very fun activity!" Input: HTTP response from the server. Output: Explanation and message displayed on the user's device.

[1209] (Application example 2)

[1210] 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."

[1211] In current food delivery services, user reviews and feedback often contain words and phrases that are difficult to understand. Furthermore, the feedback provided ignores the user's feelings, preventing improvements to the user experience. In particular, the inability to properly interpret user opinions and requests regarding the taste of food can delay improvements to the delivery service and the restaurant. Therefore, there is a need for a system that can properly analyze user feedback and provide easy-to-understand feedback that takes user feelings into consideration.

[1212] The identification process by the identification 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 input by a user, means for dividing the text into words and phrases using a morphological analysis engine, means for extracting words unique to a specific group or generation from the words and phrases, means for analyzing the extracted words using an artificial intelligence model, means for generating a sentence converted into a form easy for the user to understand based on the analysis result, means for adding feedback to the generated sentence that takes into account the user's emotions, and means for transmitting the generated sentence and feedback to the user terminal. This makes it possible to appropriately analyze reviews and feedback from users and provide feedback that is easy to understand and takes into account their emotions.

[1213] The "means for receiving text input from a user" is an interface for receiving text data such as reviews and feedback input by a user.

[1214] A "morphological analysis engine" is an analysis engine that divides natural languages ​​such as Japanese into words and phrases.

[1215] The "means for splitting into words and phrases" refers to a means for breaking down input text into individual words and phrases using a morphological analysis engine.

[1216] A "means for extracting words specific to a particular group or generation" is a means for searching for and extracting words or slang specific to a particular age group or community from text.

[1217] An "artificial intelligence model" is a machine learning model used to learn from large amounts of text data and analyze input text.

[1218] "Means for analyzing" refers to the means for analyzing extracted words and phrases using an artificial intelligence model to understand their meaning and context.

[1219] The "means for generating sentences converted into a form that is easy for the user to understand" is a means for reconstructing text into a form that is easy for the user to understand, based on the content analyzed by the artificial intelligence model.

[1220] The "means for adding feedback that takes into account the user's emotions" is a means for recognizing emotions from text entered by the user and adding feedback that matches those emotions.

[1221] The "means for transmitting to the user terminal" refers to a means for transmitting the generated text and feedback to the terminal used by the user.

[1222] The program of the system that realizes this invention performs the following process in stages: First, the specific steps when a user posts a review or feedback using a food delivery app will be explained.

[1223] System Overview

[1224] 1. Receiving user input

[1225] The server receives the text input by the user, for example, a review such as "The food was delicious, but the flavor was too strong, so it might not be suitable for children." This allows the text data input by the user to be incorporated into the system.

[1226] 2. Morphological analysis

[1227] The server uses Mecab as a morphological analysis engine to split the input text into words and phrases, such as "The food was delicious, but the flavor was too strong, so it might not be suitable for children."

[1228] 3. Extracting specific words

[1229] The server references the database to extract words that are specific to a particular group or generation, such as "delicious" or "not suitable" in reviews.

[1230] 4. Word Analysis

[1231] The server uses artificial intelligence models such as BERT and GPT to analyze the meaning and context of the extracted words, resulting in an interpretation such as "The food is delicious, but the flavor is too strong for children to eat."

[1232] 5. Generate feedback

[1233] The server generates feedback based on the analysis results in a format that is easy for the user to understand. Furthermore, it analyzes the user's emotions using the Google Cloud Natural Language API, and if the emotion of "dissatisfaction" is recognized, this is reflected in the feedback. For example, the server may generate feedback such as, "Thank you for rating the taste of the dish. Your comment that the flavor is too strong and not suitable for children can be adjusted for your next order."

[1234] 6. Submitting Feedback

[1235] The server sends the generated feedback and analysis results to the user's device, which receives them and displays the review content in an easy-to-understand manner.

[1236] Hardware and software used

[1237] Morphological analysis engine: Mecab

[1238] Sentiment engine: Google Cloud Natural Language API

[1239] Artificial intelligence models: BERT, GPT

[1240] Specific examples

[1241] A user leaves the following review on a food delivery app:

[1242] "The food was delicious, but the flavor was too strong and probably not suitable for children. It's very different from my mother's cooking."

[1243] The server receives this and segments it using morphological analysis. It then extracts specific words and uses an AI model to obtain the analysis results. The emotion engine considers the emotion recognized as "unsatisfied" and generates appropriate feedback. The feedback the user will next see is as follows:

[1244] "Thank you for rating the taste of our food. We understand that the flavor is too strong and unsuitable for children. We will adjust it for your next order. We will also strive to recreate your mother's cooking style!"

[1245] Prompt Sentence Examples

[1246] Prompt sentence to input to the generative AI model:

[1247] "Please parse the following text, convert it to something understandable, and generate feedback taking into account sentiment:

[1248] Text: 'The food was delicious, but the flavor was too strong and perhaps not suitable for children. It's nothing like my mother's cooking.'

[1249] User sentiment: 'Unsatisfied'

[1250] Requirement: Convert into an understandable format and generate feedback for next time.

[1251] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1252] Step 1:

[1253] The server receives text input from the user. When the user enters a review or feedback through the food delivery app and clicks submit, this text data is sent to the server. The input is the text data posted by the user, and the output is the text data received as is.

[1254] Step 2:

[1255] The server uses a morphological analysis engine (Mecab) to divide the received text into words and phrases. Specifically, the server passes the text data to Mecab, which then performs a mechanical grammatical analysis to break it down into words and phrases. The input is the text data received in step 1, and the output is the text divided by morphological analysis. For example, the input "The food was delicious, but the flavor was too strong, so it might not be suitable for children" is changed to the output "The food was delicious, but the flavor was too strong, so it might not be suitable for children."

[1256] Step 3:

[1257] The server performs text normalization as preprocessing. This process involves removing unnecessary spaces and special characters from the text and performing pattern matching using regular expressions. The input is the text split in step 2, and the output is the normalized text. For example, "The food was delicious, but the flavor was too strong, so it might not be suitable for children" becomes "The food was delicious, but the flavor was too strong, so it might not be suitable for children."

[1258] Step 4:

[1259] The server references a database to extract words specific to a particular group or generation from the normalized text. For example, it may have a database listing words used by a particular age group or community, and searches through it to extract the relevant words. The input is the text normalized in step 3, and the output is the specific words extracted. For example, "delicious" or "not suitable."

[1260] Step 5:

[1261] The server analyzes the extracted words using an artificial intelligence model (BERT or GPT). Specifically, the extracted words and phrases are input into the AI ​​model, which analyzes their context and meaning. The input is the words extracted in step 4, and the output is the analysis result based on the context and meaning of those words. For example, the conclusion is "It's delicious, but the flavor is too strong for children to eat."

[1262] Step 6:

[1263] Based on the analysis results, the server generates a sentence that is converted into a form that is easy for the user to understand. In this step, an explanation is generated in a format that is easy for the user to understand based on the analysis results of the AI ​​model. The input is the analysis result obtained in step 5, and the output is a reconstructed explanation. For example, feedback such as "Thank you for rating the taste of the dish. Your opinion that the flavor is too strong and not suitable for children can be adjusted for your next order."

[1264] Step 7:

[1265] The server adds feedback to the generated description, taking into account the user's emotions. Using an emotion engine (Google Cloud Natural Language API), it recognizes emotions from the user's input text and generates an additional message based on that. The input is the description obtained in step 6 and the user's emotional data, and the output is the final feedback. For example, it could be something like, "We received feedback that the flavor was too strong, but we will adjust it for your next order. We will also try to recreate your mother's recipe!"

[1266] Step 8:

[1267] The server sends the generated sentence and feedback to the user's device, which receives it and displays it to the user in the app. The input is the final feedback sentence generated in step 7, and the output is the data sent to the user's device. This allows the user to see how their review is interpreted and fed back.

[1268] 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.

[1269] 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.

[1270] 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.

[1271] 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.

[1272] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1273] 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.

[1274] 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).

[1275] 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.

[1276] 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."

[1277] 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.

[1278] 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).

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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.

[1283] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1284] 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.

[1285] 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.

[1286] 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.

[1287] 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.

[1288] 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.

[1289] The following is further disclosed regarding the above embodiment.

[1290] (Claim 1)

[1291] means for receiving text input from a user;

[1292] means for segmenting the text into words and phrases using a morphological analysis engine;

[1293] means for extracting words and phrases characteristic of a particular group or generation from among said words and phrases;

[1294] means for analyzing the extracted words using an artificial intelligence model;

[1295] means for generating a sentence that is converted into a form that is easy for a user to understand based on the analysis result;

[1296] means for transmitting the generated sentence to a user terminal;

[1297] A system including:

[1298] (Claim 2)

[1299] 2. The system of claim 1, further comprising means for performing text normalization as preprocessing when the morphological analysis engine divides words and phrases.

[1300] (Claim 3)

[1301] 2. The system according to claim 1, further comprising means for identifying relevant words by referring to a database when extracting the words specific to a particular group or generation.

[1302] "Example 1"

[1303] (Claim 1)

[1304] means for receiving text input from a user;

[1305] means for segmenting the text into words and phrases using a morphological analysis engine;

[1306] means for extracting words and phrases characteristic of a particular group or generation from among said words and phrases;

[1307] means for analyzing the extracted words using an artificial intelligence model;

[1308] A means for generating explanatory text in a form that is easy for the user to understand using a generative AI model using the prompt text;

[1309] means for transmitting the generated explanation to a user terminal;

[1310] means for displaying the generated explanatory text on a user interface;

[1311] A system including:

[1312] (Claim 2)

[1313] 2. The system of claim 1, further comprising means for performing text normalization as preprocessing when the morphological analysis engine divides words and phrases.

[1314] (Claim 3)

[1315] 2. The system according to claim 1, further comprising means for identifying relevant words by referring to a database when extracting the words specific to a particular group or generation.

[1316] "Application Example 1"

[1317] (Claim 1)

[1318] means for receiving text input from a user;

[1319] means for segmenting the text into words and phrases using a morphological analysis engine;

[1320] means for extracting words and phrases characteristic of a particular group or generation from among said words and phrases;

[1321] means for analyzing the extracted words using an artificial intelligence model;

[1322] means for generating a sentence that is converted into a form that is easy for a user to understand based on the analysis result;

[1323] means for transmitting the generated sentence to a user terminal;

[1324] A means to generate and display warning messages when security risks are detected.

[1325] A system including:

[1326] (Claim 2)

[1327] 2. The system of claim 1, further comprising means for performing text normalization as preprocessing when the morphological analysis engine divides words and phrases.

[1328] (Claim 3)

[1329] 2. The system according to claim 1, further comprising means for identifying relevant words by referring to a database when extracting the words specific to a particular group or generation.

[1330] "Example 2: Combining Emotion Engines"

[1331] (Claim 1)

[1332] means for receiving text input from a user;

[1333] means for segmenting the text into words and phrases using a morphological analysis engine;

[1334] means for extracting words and phrases characteristic of a particular group or generation from among said words and phrases;

[1335] means for analyzing the extracted words using an artificial intelligence model;

[1336] means for generating a sentence that is converted into a form that is easy for a user to understand based on the analysis result;

[1337] means for recognizing a user's emotion;

[1338] means for generating a message corresponding to the emotion based on the recognized emotion;

[1339] means for transmitting a message based on the generated sentence and emotion to a user terminal;

[1340] A system including:

[1341] (Claim 2)

[1342] 2. The system of claim 1, further comprising means for performing text normalization as preprocessing when the morphological analysis engine divides words and phrases.

[1343] (Claim 3)

[1344] 2. The system according to claim 1, further comprising means for identifying relevant words by referring to a database when extracting the words specific to a particular group or generation.

[1345] "Application example 2 when combining emotion engines"

[1346] (Claim 1)

[1347] means for receiving text input from a user;

[1348] means for segmenting the text into words and phrases using a morphological analysis engine;

[1349] means for extracting words and phrases characteristic of a particular group or generation from among said words and phrases;

[1350] means for analyzing the extracted words using an artificial intelligence model;

[1351] means for generating a sentence that is converted into a form that is easy for a user to understand based on the analysis result;

[1352] means for adding feedback to the generated sentence taking into account the user's feelings;

[1353] means for transmitting the generated sentence and feedback to a user terminal;

[1354] A system including:

[1355] (Claim 2)

[1356] 2. The system of claim 1, further comprising means for performing text normalization as preprocessing when the morphological analysis engine divides words and phrases.

[1357] (Claim 3)

[1358] 2. The system according to claim 1, further comprising means for identifying relevant words by referring to a database when extracting the words specific to a particular group or generation. [Explanation of symbols]

[1359] 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 input from a user; means for segmenting the text into words and phrases using a morphological analysis engine; means for extracting words and phrases characteristic of a particular group or generation from among said words and phrases; means for analyzing the extracted words using an artificial intelligence model; means for generating a sentence that is converted into a form that is easy for a user to understand based on the analysis result; means for transmitting the generated sentence to a user terminal; A system including:

2. The system according to claim 1 , further comprising means for performing text normalization as a preprocessing step when the morphological analysis engine divides words and phrases.

3. The system according to claim 1, further comprising means for identifying the relevant words by referring to a database when extracting the words specific to the particular group or generation.

Images