System

Abstract

A system is provided.SOLUTION: A system comprising: acquisition means for acquiring voice or text data from a user; analysis means for analyzing the data acquired by the acquisition means; generation means for optimizing information using a user profile based on a result analyzed by the analysis means; and transmission means for transmitting the optimized information to a user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, there are many situations where people have difficulty conveying their thoughts to others or understanding what others are saying. In business and education in particular, differences in language ability and understanding among individuals can make communication difficult. This can lead to misunderstandings and miscommunication, hindering effective communication. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means: a system including an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the acquired data, a generation means for optimizing information using a user profile based on the analysis results, and a transmission means for transmitting the optimized information to a user terminal. Furthermore, the analysis means converts the voice data into text data using a voice recognition engine, and performs intent analysis, sentiment analysis, and extraction of important keywords using natural language processing technology. The generation means complements the context and provides additional explanations. Recording means is included for building and updating a user profile, thereby realizing the provision of personalized information according to the user's background and needs and promoting efficient communication.

[0006] "User" means any person or entity that uses the System and inputs voice or text data.

[0007] "User terminal" refers to the hardware device (e.g., smartphone, tablet, PC) that a user uses to interface with the system.

[0008] "Server" refers to a central processing unit that communicates with user terminals and analyzes, generates, and transmits data.

[0009] "Acquisition means" refers to a function or device for collecting voice or text data from a user.

[0010] "Analysis means" refers to a function or device for analyzing acquired data and extracting characteristics such as context, intent, and emotion.

[0011] The "generation means" refers to a function or device for reconstructing information in a format that is optimal for the listener based on the results obtained by the analysis means.

[0012] The term "transmitting means" refers to a function or device for transmitting the generated information to the user terminal.

[0013] "User Profile" refers to a data set that records and maintains an individual user's background knowledge, understanding, and interests and is used to optimize information generation methods.

[0014] "Speech recognition engine" refers to a combination of software or hardware for converting voice data into text data.

[0015] "Natural language processing technology" refers to technology that uses computers to analyze and process natural language.

[0016] "Intent analysis" refers to the process of extracting the purpose or intent behind user-entered data.

[0017] "Sentiment analysis" refers to the process of identifying and analyzing emotions and feelings from user input data.

[0018] "Keyword extraction" refers to the process of identifying and extracting significant keywords from input data.

[0019] "Context completion" refers to the process of supplementing insufficient information and making the overall context easier to understand. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[0042] System Configuration

[0043] The system consists of the following modules:

[0044] 1. Acquisition Module

[0045] The user terminal receives voice or text data from the user.

[0046] 2. Analysis Module

[0047] The server receives the data sent from the acquisition module, and if it is voice data, converts it into text data using a voice recognition engine.

[0048] In addition, natural language processing technology is used to analyze the intent and sentiment of the data and extract important keywords.

[0049] 3. Generator Module

[0050] The server then refers to the user profile based on the analysis results and reconstructs the information in a way that is easy for the listener to understand, for example, by adding contextual information and additional explanations.

[0051] 4. Transmission Module

[0052] The server transmits the generated information to the user terminal.

[0053] 5. Recording Module

[0054] The server records the user's usage history and updates the user profile.

[0055] Specific examples of implementation

[0056] Example 1: Simultaneous interpretation at a business meeting

[0057] Consider a scenario where User A is giving a presentation in English at a business meeting. The specific process flow is as follows:

[0058] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[0059] The terminal transmits the voice data to the server.

[0060] The server converts the voice data into text data using a voice recognition engine.

[0061] The server uses natural language processing techniques to analyze the intent and key keywords of the text.

[0062] Based on the user profile, the server reconstructs the information in a form that is optimal for the listener (for example, a Japanese-speaking employee) and generates, "Hello everyone. Today I'll be talking about our sales strategy."

[0063] The server sends the generated text to User B's terminal.

[0064] User B's terminal displays or plays back the transmitted text as audio.

[0065] Example 2: Context completion in education

[0066] Consider a situation where a teacher is discussing a math concept:

[0067] User C's (teacher's) device receives the voice message, "Integral calculation is the inverse operation of differential calculation."

[0068] The terminal transmits the voice data to the server.

[0069] The server converts the voice data into text data using a voice recognition engine.

[0070] The server uses natural language processing techniques to analyze the text and add any necessary complementary information.

[0071] The server generates a context-complete explanation: "Integration is a method for finding the area of ​​a function, and differentiation is the rate of change of that function."

[0072] The server transmits the generated text to the student terminal.

[0073] The student terminal displays the supplementary explanation, providing information in a format that is easy for students to understand.

[0074] In this way, this system achieves effective communication by analyzing and regenerating voice and text data from the user and providing information in a form that is easy for the listener to understand.

[0075] The processing flow will be explained below.

[0076] Step 1:

[0077] The user terminal acquires voice or text data from the user. For example, consider the case where voice data such as "Hello, everyone. Today we will discuss the sales strategy" is acquired.

[0078] Step 2:

[0079] The user device transmits the acquired data to the server, ideally in real time.

[0080] Step 3:

[0081] The server receives the voice data transmitted from the user terminal.

[0082] Step 4:

[0083] The server converts the received voice data into text data using a speech recognition engine, for example, "Hello, everyone. Today we will discuss the sales strategy."

[0084] Step 5:

[0085] The server analyzes the text data using natural language processing (NLP) technology. This analysis includes intent analysis, sentiment analysis, and extraction of important keywords. For example, the keyword "sales strategy" is extracted.

[0086] Step 6:

[0087] The server then uses the user profile based on the analysis results to optimize the information provided. For example, for a listener whose native language is Japanese, the message "Hello, everyone. Today we will discuss the sales strategy." is converted to "Hello, everyone. Today we will talk about our sales strategy."

[0088] Step 7:

[0089] The server completes the context and provides additional explanation as needed, for example, to elaborate on the concept of "sales strategy," it might add, "A sales strategy is a plan for a company to effectively deliver its products and services to customers."

[0090] Step 8:

[0091] The server reconverts the generated optimized information into voice data using a voice synthesis engine, or formats it as text data as is.

[0092] Step 9:

[0093] The server sends the generated information to the user's terminal. In the case of audio, it is sent as an audio file, and in the case of text, it is sent as text in UTF-8 format.

[0094] Step 10:

[0095] The user terminal plays the received data as voice or displays it as text. For example, if played as voice, it sounds like "Hello everyone. Today I'm going to talk about our sales strategy."

[0096] Step 11:

[0097] The server records the user's output history and updates the user profile, which further personalizes subsequent information generation.

[0098] In this way, the system efficiently analyzes and optimizes the user's voice and text, providing information in a format that is easy for the listener to understand.

[0099] Example 1

[0100] 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."

[0101] Language differences and the need to convey complex meanings are often barriers to modern communication. Voice data must be converted into text, analyzed using natural language processing, and then provided in an optimal format. However, existing technologies struggle to achieve this in real time, which can detract from the user experience. This problem needs to be addressed, particularly in business meetings and educational settings, where rapid and accurate information transmission is crucial.

[0102] 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.

[0103] In this invention, the server includes an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the data acquired by the acquisition means, a generation means for optimizing information using a user profile based on the analysis result by the analysis means, a transmission means for transmitting the optimized information to a user terminal, and a recording means for recording the analyzed data and the optimized information and updating the user profile, thereby enabling the user to receive accurate and optimized information in real time.

[0104] The "acquisition means" is a means for acquiring voice or text data from a user.

[0105] The "analysis means" is a means for analyzing the data acquired by the acquisition means.

[0106] The "generation means" is a means for optimizing information by utilizing a user profile based on the results of analysis by the analysis means.

[0107] The "transmitting means" is a means for transmitting optimized information to a user terminal.

[0108] The "recording means" is a means for recording analyzed data and optimized information and updating a user profile.

[0109] A "voice recognition engine" is an engine for converting voice data into text data.

[0110] "Natural language processing technology" is a technology that analyzes the intent and sentiment of data and extracts important keywords.

[0111] A "generative AI model" is an AI model that adds context and additional explanation to information.

[0112] "Real-time communication technology" refers to communication technology for sending and receiving information in real time.

[0113] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[0114] System Configuration

[0115] The system consists of the following modules:

[0116] 1. Acquisition method

[0117] The user terminal receives voice or text data from the user and includes a microphone and a text input device.

[0118] The acquired audio data is saved in formats such as WAV or MP3 and temporarily stored in memory.

[0119] 2. Analysis method

[0120] The server receives the data sent from the acquisition means and converts the voice data into text data using a voice recognition engine (for example, Google Cloud Speech-to-Text).

[0121] In addition, natural language processing technologies such as Hugging Face's Transformers and SpaCy are used to analyze the intent and sentiment of the data and extract important keywords.

[0122] 3. Generation means

[0123] The server then uses the analysis results, references the user profile, and reconstructs the information in a way that is easy for the listener to understand. In particular, it uses a generative AI model to provide context and additional explanations for the information.

[0124] For example, if the input is "Hello, the weather is nice today," it will be reconstructed into "Hello, it's a sunny day. I have an important meeting today."

[0125] 4. Transmission Method

[0126] The server transmits the regenerated information to the user terminal, using real-time communication techniques (e.g., WebSocket or Push notification).

[0127] 5. Recording Method

[0128] The server records the analyzed data and generated information in a database and updates the user profile, enabling it to provide more optimal information the next time the user uses the service.

[0129] Specific examples of implementation

[0130] Example 1: Simultaneous interpretation at a business meeting

[0131] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[0132] The terminal transmits the voice data to the server.

[0133] The server converts the voice data into text data using a voice recognition engine.

[0134] The server uses natural language processing techniques to analyze the intent and key keywords of the text.

[0135] The server regenerates "Hello everyone, today we'll talk about our sales strategy" based on the user profile.

[0136] The server sends the generated text to User B's terminal.

[0137] User B's terminal displays the text and provides it to the user.

[0138] Example 2: Context completion in education

[0139] User C's (teacher's) device receives the voice message, "Integral calculation is the inverse operation of differential calculation."

[0140] The terminal transmits the voice data to the server.

[0141] The server converts the voice data into text data using a voice recognition engine.

[0142] The server uses natural language processing techniques to analyze the text and add any necessary complementary information.

[0143] The server generates a context-complete explanation: "Integration is a method for finding the area of ​​a function, and differentiation is the rate of change of that function."

[0144] The server transmits the generated text to the student terminal.

[0145] The student terminals display supplementary explanations, providing information in a format that is easy for students to understand.

[0146] Examples of prompt statements

[0147] "The system converts the voice data entered by the user into text data and generates explanatory text based on the text, adding supplementary information."

[0148] "A communication optimization system that translates English presentations used in business meetings into Japanese in real time and sends the translation to the devices of all parties involved."

[0149] In this way, this system analyzes and regenerates the user's voice and text data, providing information in a format that is easy for the listener to understand, thereby achieving effective communication.

[0150] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0151] Step 1:

[0152] The user terminal receives voice or text data from the user. For example, the user may say, "Hello, the weather is nice today." The input voice data is temporarily stored in memory and saved in an appropriate format (e.g., WAV or MP3). This is the input voice data.

[0153] Step 2:

[0154] The user device compresses the acquired audio data and sends it to the specified server endpoint. For example, the audio data is sent to the server via a POST request via a REST API. The input is the acquired audio data, and the output is the data to be sent to the server. Specifically, authentication information is added to the HTTP request header, and the audio data is included in the body in binary format.

[0155] Step 3:

[0156] The server temporarily stores the received voice data and passes the data to a voice recognition engine (for example, a general voice recognition engine). The input is the voice data sent to the server, and the output is the text data obtained by voice recognition. Specifically, the server generates the text data "Hello, the weather is nice today."

[0157] Step 4:

[0158] The server passes the text data obtained from the speech recognition to a natural language processing engine (such as a general natural language processing engine). This is where intent analysis, sentiment analysis, and extraction of important keywords are performed. The input is text data generated by speech recognition, and the output is the analysis results. Specifically, the greeting "Hello" is analyzed as the intent, and "The weather is nice" is analyzed as a positive sentiment. The keywords "weather" and "good" are also extracted.

[0159] Step 5:

[0160] The server regenerates information based on the analysis results, referencing the user profile. In particular, it uses a generative AI model to add context and additional explanations. The input is the analysis results and user profile data, and the output is the regenerated information. For example, it could be reconstructed as "Hello, it's a sunny day. I have an important meeting today."

[0161] Step 6:

[0162] The server sends the regenerated text data to the specific user device. It uses real-time communication technology (for example, WebSocket or Push notification). The input is the regenerated information, and the output is the data to be sent to the user device. The server sends an HTTP response containing the new text data to the specific user device.

[0163] Step 7:

[0164] The server records the analyzed data and generated information in a database and updates the user profile. The input is the analyzed and regenerated data, and the output is the updated user profile. Specifically, the server records the usage history and saves data to provide more optimized information to the user the next time they use the service.

[0165] (Application example 1)

[0166] 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."

[0167] In food delivery, communication between users and delivery personnel is often insufficient, resulting in misunderstandings of instructions and delivery errors. While quick and accurate responses to customer inquiries are required, current systems have difficulty meeting these demands. Furthermore, there is a lack of efficient ways to optimize information from voice and text to make it easier for users to understand.

[0168] 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.

[0169] In this invention, the server includes an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the data acquired by the acquisition means, a voice recognition means for converting the voice data into text data using a voice recognition engine, a natural language processing means for analyzing the intention and emotion of the text data and extracting important keywords using natural language processing technology, a complement generation means for referencing the order history and generating complement information for the user based on the analysis results, and a transmission means for transmitting optimized information to the user terminal. This enables efficient communication by optimizing information in a form that is easy for the user to understand in response to delivery instructions or inquiries.

[0170] The "acquisition means" is a means for acquiring voice or text data from a user.

[0171] The "analysis means" is a means for analyzing the data acquired by the acquisition means.

[0172] The "voice recognition means" is a means that uses a voice recognition engine to convert voice data into text data.

[0173] The "natural language processing means" is a means for using natural language processing technology to perform intent analysis, sentiment analysis, and extraction of important keywords from text data.

[0174] The "generation means" is a means for optimizing information using a user profile based on the analysis results and reconstructing the information in a form that is easy for the user to understand.

[0175] The "complementary information generating means" refers to a means for referencing the order history and generating complementary information for the user based on the analysis results.

[0176] The "transmitting means" is a means for transmitting optimized information to a user terminal.

[0177] "User terminal" means a device used by a user, and is a general computing device that has the function of inputting and receiving voice and text data.

[0178] The present invention is a communication optimization system that analyzes voice or text data from users and converts it into a format that is easy for other users to understand. This system is specialized for food delivery services and is designed to efficiently process instructions and inquiries from users.

[0179] System configuration

[0180] The system consists of the following modules:

[0181] 1. Acquisition method

[0182] The server acquires voice or text data from a user device, such as a smartphone or tablet, using the voice input or text input function.

[0183] 2. Analysis method

[0184] The server converts the acquired voice data into text data using speech recognition technology, and then uses natural language processing technology to analyze the intent and sentiment of the text data and extract important keywords. Specifically, it uses the "Google Cloud Speech-to-Text API" and "Google Cloud Natural Language API."

[0185] 3. Generation means

[0186] Based on the analysis results, the server references the user profile and generates optimized information, supplementing it with context-appropriate information by taking into account order history and past instructions.

[0187] 4. Transmission Method

[0188] The server sends optimized information to the user terminal, enabling efficient communication.

[0189] Specific examples

[0190] Example 1: Optimizing delivery instructions

[0191] scenario:

[0192] The user may say, "Please leave the food at the entrance."

[0193] Process flow:

[0194] 1. The user's smartphone acquires the voice data and sends it to the server.

[0195] 2. The server converts the speech into text using the Google Cloud Speech-to-Text API.

[0196] 3. The server analyzes the intent of the text and important keywords using the Google Cloud Natural Language API.

[0197] 4. The server compares the order history and generates an optimized instruction: "Place the food to the right of the entrance."

[0198] 5. The server sends optimized instructions to the delivery person's smartphone, and the delivery person receives the information in an easy-to-understand format.

[0199] Example 2: Customer inquiry optimization

[0200] scenario:

[0201] A customer might ask by voice, "Does the salad I ordered come with dressing?"

[0202] Process flow:

[0203] 1. The customer's smartphone captures the voice data and sends it to the server.

[0204] 2. The server converts the speech into text using the Google Cloud Speech-to-Text API.

[0205] 3. The server analyzes the intent of the text and important keywords using the Google Cloud Natural Language API.

[0206] 4. The server references the order history, checks whether or not dressing is included, and generates the response "The salad you ordered comes with dressing."

[0207] 5. The server sends the optimized answer to the customer's smartphone, where the customer receives the information in an easily understandable format.

[0208] Prompt Sentence Examples

[0209] "Start typing. Enter instructions or questions. For example, 'Please leave my food at the door,' or 'Does the salad I ordered come with dressing?'"

[0210] Through these steps, the system can optimize communication in food delivery operations and reduce misunderstandings and errors.

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

[0212] Step 1:

[0213] The user inputs instructions or inquiries into a device (smartphone or tablet) by voice or text.

[0214] Input: User's voice data

[0215] Output: Acquire audio data

[0216] Specific action: The user gives the voice command, "Please leave the food at the entrance."

[0217] Step 2:

[0218] The terminal transmits the acquired voice data to the server.

[0219] Input: Audio data acquired by the device

[0220] Output: Sending audio data to the server

[0221] Specific operation: Audio data is sent from the device to the server in real time.

[0222] Step 3:

[0223] The server converts the voice data into text data using a speech recognition method (e.g., Google Cloud Speech-to-Text API).

[0224] Input: Audio data

[0225] Output: Text data

[0226] Specific action: The server converts the speech into text, "Please leave the food at the entrance."

[0227] Step 4:

[0228] The server uses natural language processing means (e.g., Google Cloud Natural Language API) to analyze the intent and sentiment of the text data and extract important keywords.

[0229] Input: Text data

[0230] Output: Intention analysis results, emotion analysis results, important keywords

[0231] Specific operation: The server analyzes the intent of "Please leave it at the entrance" and extracts the important keywords "entrance" and "place."

[0232] Step 5:

[0233] The server generates optimized information using a complementary generation means based on the analysis results and the user profile.

[0234] Input: Analysis results, user profile

[0235] Output: Optimized instructions

[0236] Specific behavior: The server references the order history and completes the instruction with "Please place the food to the right of the entrance."

[0237] Step 6:

[0238] The server sends the optimized information to the delivery person's terminal.

[0239] Input: Optimized instructions

[0240] Output: Send instructions to delivery person's terminal

[0241] Specific operation: The server sends the instruction "Please place the food on the right side of the entrance" to the delivery person's smartphone.

[0242] Step 7:

[0243] The delivery person's device displays or plays back optimized instructions.

[0244] Input: Optimized instructions

[0245] Output: Display or audio for delivery personnel to understand

[0246] Specific actions: The delivery person's device will display instructions on the screen or say aloud, "Please leave the food to the right of the entrance."

[0247] Through each of the above steps, a system is built that efficiently processes instructions and inquiries from users and optimizes communication in food delivery.

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

[0249] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand, and further combines it with an emotion engine that recognizes the user's emotions. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[0250] System Configuration

[0251] The system consists of the following modules:

[0252] 1. Acquisition Module

[0253] The user terminal receives voice or text data from the user.

[0254] 2. Emotion Engine

[0255] The server uses an emotion engine to extract the user's emotion from the captured voice or text data, and the emotion data is provided to the analysis means.

[0256] 3. Analysis Module

[0257] The server receives the data sent from the acquisition module and the emotion data provided by the emotion engine, and in the case of voice data, converts it into text data using a voice recognition engine.

[0258] In addition, natural language processing technology is used to analyze the intent and sentiment of the data and extract important keywords.

[0259] 4. Generator Module

[0260] The server references the user profile based on the analysis results and emotional data, and reconstructs the information in a way that is easy for the listener to understand, for example, by adding contextual information and additional explanations.

[0261] 5. Transmission Module

[0262] The server transmits the generated information to the user terminal.

[0263] 6. Recording Module

[0264] The server records the user's usage history and emotion data and updates the user profile.

[0265] Specific examples of implementation

[0266] Example 1: Simultaneous interpretation at a business meeting

[0267] Consider a scenario where User A is giving a presentation in English at a business meeting. The specific process flow is as follows:

[0268] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[0269] The terminal transmits the voice data to the server.

[0270] The server converts the voice data into text data using a voice recognition engine.

[0271] The server uses natural language processing technology to analyze the intent and key keywords of the text, and uses an emotion engine to analyze the tone of the speech. For example, if User A is speaking enthusiastically, the emotion engine will detect "high enthusiasm."

[0272] Based on the user profile, the server translates "Hello, everyone. Today we will discuss the sales strategy." into "Hello, everyone. Today we will discuss our sales strategy." and reproduces it to the listener in a tone that reflects "high enthusiasm."

[0273] The server sends the generated text to User B's terminal.

[0274] User B's device displays the text or plays it back as audio. For example, if it is played back as audio, it will sound like "Hello everyone. Today I'll be talking about our sales strategy," but it will be adjusted to reflect User A's enthusiasm.

[0275] Example 2: Contextual Complement and Emotional Feedback in Educational Settings

[0276] Consider a situation where a teacher is discussing a math concept:

[0277] User C's (teacher's) device receives the voice message, "Integral calculation is the inverse operation of differential calculation."

[0278] The terminal transmits the voice data to the server.

[0279] The server converts the voice data into text data using a voice recognition engine.

[0280] The server uses natural language processing technology to analyze the text and an emotion engine to analyze the accumulated student comprehension and emotion data, for example, to detect whether a student is confused.

[0281] The server then uses the analysis results and emotion data to complete the context and provide additional explanations. The server completes the context by saying, "Integral calculation is a method for finding the area of ​​a function, and differential calculation is the rate of change of that function."

[0282] The server transmits the generated optimization information to the student terminal.

[0283] The student device displays the supplementary explanation, providing the information in a way that is easy for the student to understand, and also records feedback on whether the student has demonstrated understanding.

[0284] In this way, the system efficiently analyzes and optimizes voice and text, including the user's emotions, and provides information in a form that is easy for the listener to understand.

[0285] The processing flow will be explained below.

[0286] Example 1: Simultaneous interpretation at a business meeting

[0287] Step 1:

[0288] The terminal of user A receives the voice data from user A, "Hello, everyone. Today we will discuss the sales strategy."

[0289] Step 2:

[0290] User A's terminal transmits the acquired voice data to the server.

[0291] Step 3:

[0292] The server receives the audio data.

[0293] Step 4:

[0294] The server uses a speech recognition engine to convert the voice data into text data: "Hello, everyone. Today we will discuss the sales strategy."

[0295] Step 5:

[0296] The server uses an emotion engine to extract User A's emotion from the voice data. For example, it detects "high enthusiasm" from the tone and tempo of User A's speech.

[0297] Step 6:

[0298] The server uses natural language processing technology to analyze the text data and extract intent, sentiment, and key keywords. For example, it extracts "sales strategy" as a key keyword and also analyzes the results of the sentiment engine.

[0299] Step 7:

[0300] The server then refers to the user profile based on the analysis results and emotional data, optimizing the information. For example, it converts "Hello, everyone. Today we will discuss the sales strategy" into "Hello, everyone. Today we will discuss our sales strategy," adjusting the information to reflect the speaker's "high enthusiasm."

[0301] Step 8:

[0302] The server reconverts the optimized information into voice data using a voice synthesis engine or formats it as text data.

[0303] Step 9:

[0304] The server transmits the generated information to User B's terminal.

[0305] Step 10:

[0306] User B's device plays the received information as voice or displays it as text. For example, if it is played as voice, it will sound like "Hello everyone. Today I'll talk about our sales strategy," which reflects User A's "high enthusiasm."

[0307] Step 11:

[0308] The server records the data obtained during the analysis and generation process in the user profile and uses it for the next processing.

[0309] Example 2: Contextual Complement and Emotional Feedback in Educational Settings

[0310] Step 1:

[0311] User C's (teacher's) device receives the voice data from User C saying, "Integral calculation is the inverse operation of differential calculation."

[0312] Step 2:

[0313] User C's terminal transmits the acquired voice data to the server.

[0314] Step 3:

[0315] The server receives the audio data.

[0316] Step 4:

[0317] The server uses a speech recognition engine to convert the speech data into text data "Integral calculation is the inverse operation of differential calculation."

[0318] Step 5:

[0319] The server uses an emotion engine to extract User C's emotion from the voice data. For example, it detects a "calm tone" from User C's speaking style.

[0320] Step 6:

[0321] The server uses natural language processing technology to analyze the text data and extract intent, sentiment, and important keywords. For example, it extracts the keywords "integral calculation" and "differential calculation," and also analyzes sentiment data.

[0322] Step 7:

[0323] The server then refers to the user profile based on the analysis results and sentiment data, optimizes the information, and provides necessary contextual completion and additional explanations. For example, it adds additional information such as, "Integral calculation is a method for calculating the area of ​​a function, and differential calculation is the rate of change of that function."

[0324] Step 8:

[0325] The server reconverts the optimized information into voice data using a voice synthesis engine or formats it as text data.

[0326] Step 9:

[0327] The server transmits the generated information to the student terminal.

[0328] Step 10:

[0329] The student device will then play the received information as audio or display it as text. For example, a supplementary explanation may be displayed as text, such as, "Integration is a method for finding the area of ​​a function, and differentiation is the rate of change of that function."

[0330] Step 11:

[0331] The server records the data obtained during the analysis and generation process in a user profile for future use. It also records changes in the student's understanding and emotional feedback.

[0332] In this way, the system efficiently analyzes voice and text, including the user's emotions, and provides information in a format that is easy for the listener to understand.

[0333] Example 2

[0334] 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."

[0335] In modern communication systems, it is difficult to understand a user's intentions and emotions and provide optimal information based on them. In particular, when analyzing voice and text data, it is necessary to accurately grasp the user's emotions and intentions and reconstruct information in a form that is easy for the listener to understand. As a result, conventional systems have issues such as an insufficient user experience and reduced information transmission efficiency.

[0336] 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.

[0337] In this invention, the server includes an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the data acquired by the acquisition means, an emotion analysis means for extracting emotion data analyzed by the analysis means, a generation means for optimizing information using a user profile based on the analysis results by the analysis means, a transmission means for transmitting the optimized information to a user terminal, and a reconstructing means for reconstructing the optimized information based on the user profile. This makes it possible to accurately understand the user's intentions and emotions and generate and provide optimal information.

[0338] The "acquisition means" is a means for acquiring voice or text data from a user.

[0339] The "analysis means" is a means for analyzing the data acquired by the acquisition means.

[0340] The "emotion analysis means" is a means for extracting emotion data analyzed by the analysis means.

[0341] The "generating means" is a means for optimizing information by utilizing a user profile based on the results of the analysis by the analyzing means.

[0342] The "transmitting means" is a means for transmitting optimized information to a user terminal.

[0343] The "reconstruction means" is a means for reconstructing optimized information based on a user profile.

[0344] A "voice recognition engine" is a program or system for converting voice data into text data.

[0345] "Natural language processing technology" is a technology for analyzing the intent and emotions of text data and extracting important keywords.

[0346] A "user profile" is a database that includes each user's past usage history and setting information.

[0347] MODE FOR CARRYING OUT THE INVENTION

[0348] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand, and further combines it with an emotion engine that recognizes the user's emotions. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[0349] System Configuration

[0350] The system consists of the following modules:

[0351] 1. Acquisition method

[0352] The user terminal captures voice or text data from the user, for example, when the user says "What are your plans for tomorrow?" using a microphone subsystem or a text input field.

[0353] 2. Analysis method

[0354] The server receives the voice data sent from the user's device and converts it into text using a voice recognition engine called "SpeechToTextEngine." Examples of such engines include Google Speech-to-Text API and IBM Watson.

[0355] Furthermore, natural language processing techniques are used to analyze the intent and sentiment of the text and extract important keywords, using the natural language processing libraries "spaCy" and "NLTK."

[0356] 3. Emotion analysis method

[0357] The server passes the text data to the emotion analysis engine "EmotionAnalyzer" to extract emotional data. This engine analyzes the user's emotions (e.g., joy, sadness, surprise, etc.) from the text.

[0358] 4. Generation means

[0359] Based on the analysis results and emotion data, the server references the user profile "UserProfileDB" and reconstructs the information in a format that is easy for the listener to understand, for example by adding supplementary explanations and detailed information according to the context.

[0360] 5. Transmission Method

[0361] The server sends the generated information to the user's terminal. For example, it also provides a service that sends text information as an HTTP response and synthesizes it as voice data.

[0362] 6. Reconstruction means

[0363] The server reconstructs optimized information based on the user profile, allowing it to present information in a form that is most relevant to each individual user.

[0364] Specific examples of implementation

[0365] Example 1: Simultaneous interpretation at a business meeting

[0366] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[0367] The terminal transmits the voice data to the server.

[0368] The server converts the voice data into text data using the voice recognition engine "SpeechToTextEngine."

[0369] The server uses natural language processing technology and the emotion engine "EmotionAnalyzer" to analyze the intent and important keywords of the text and detects that User A's emotion is "high enthusiasm."

[0370] The server translates the English text based on the user profile into "Hello everyone, today I'll be talking about our sales strategy," and reproduces it in a tone that reflects high enthusiasm.

[0371] The server sends the generated Japanese text to User B's terminal.

[0372] User B's terminal displays or plays back the transmitted text as audio.

[0373] Example prompts for generative AI models:

[0374] Please translate the following English speech data into Japanese and reproduce it in a way that reflects the user's emotion of "high enthusiasm."

[0375] Audio data: "Hello, everyone. Today we will discuss the sales strategy."

[0376] Example 2: Contextual Complement and Emotional Feedback in Educational Settings

[0377] In a situation where the teacher is talking about a mathematical concept, the device of user C (teacher) receives the audio message, "Integral calculus is the inverse operation of differential calculus."

[0378] The terminal transmits the voice data to the server.

[0379] The server converts the voice data into text data using the voice recognition engine "SpeechToTextEngine."

[0380] The server uses natural language processing technology and the emotion engine "EmotionAnalyzer" to analyze text data and detect students' level of understanding and emotions.

[0381] Based on the analysis results and emotion data, the server completes the context and provides additional explanation: "Integral calculation is a method for finding the area of ​​a function, and differential calculation is the rate of change of that function."

[0382] The server transmits the generated supplementary explanation to the student terminal.

[0383] The student's device displays the supplemented explanation and also records the comprehension feedback.

[0384] Example prompts for generative AI models:

[0385] Please convert the audio data below into easy-to-understand text, and provide context and additional explanations if the student gets confused during the speech.

[0386] Audio: "Integral calculus is the inverse operation of differential calculus."

[0387] In this way, the system efficiently analyzes and optimizes voice and text, including the user's emotions, and provides information in a form that is easy for the listener to understand.

[0388] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0389] Step 1:

[0390] The user enters a message by voice or text, for example saying "What's the weather like tomorrow?"

[0391] Input: User's voice or text data.

[0392] Output: Captured audio or text data.

[0393] Step 2:

[0394] The device captures the user's voice using its internal microphone subsystem or a text input field. For example, a microphone sensor receives voice input. The captured data is kept raw.

[0395] Input: User's voice data.

[0396] Output: Audio data stored on the device.

[0397] Step 3:

[0398] The device transmits the acquired audio data to the server using an HTTP POST request. For example, the device uploads the audio data to the server in MIME format.

[0399] Input: Audio data stored on the device.

[0400] Output: The audio data sent to the server.

[0401] Step 4:

[0402] The server receives the transmitted audio data and stores it in temporary storage, making it ready to be analyzed.

[0403] Input: Audio data sent from the device.

[0404] Output: Audio data stored on the server.

[0405] Step 5:

[0406] The server converts the voice data into text data using a speech recognition engine called "SpeechToTextEngine," such as the Google Speech-to-Text API.

[0407] Input: Audio data stored on the server.

[0408] Output: The converted text data.

[0409] Step 6:

[0410] The server uses natural language processing technology (such as spaCy or NLTK) to analyze the intent and sentiment of the text data and extract important keywords. For example, from the text "What's the weather like tomorrow?", the important keyword "weather" and the sentiment "curiosity" are extracted.

[0411] Input: The converted text data.

[0412] Output: Analyzed intent data, sentiment data, and important keywords.

[0413] Step 7:

[0414] The server uses the emotion analysis engine "EmotionAnalyzer" to extract emotional data from the text data. For example, it determines that the user's emotion is "curiosity."

[0415] Input: The converted text data.

[0416] Output: Extracted emotion data.

[0417] Step 8:

[0418] The server then references the user profile (UserProfileDB) based on the analysis results and emotion data to generate the optimal answer. For example, it could reconstruct the answer as "Tomorrow's weather will be sunny" based on the profile and past data.

[0419] Input: Analyzed intent data, sentiment data, important keywords, user profile.

[0420] Output: The generated optimized information.

[0421] Step 9:

[0422] The server sends the generated information to the user terminal. For example, it may send text information as an HTTP response and provide a service to synthesize it as voice data.

[0423] Input: Optimized information.

[0424] Output: Information sent to the user's terminal.

[0425] Step 10:

[0426] The terminal receives the information sent from the server and displays it to the user, or plays it as audio using an audio playback device. For example, the terminal displays "Tomorrow's weather will be sunny" and plays it as audio.

[0427] Input: Information sent by the server.

[0428] Output: The information that is displayed to the user or played as sound.

[0429] Step 11:

[0430] The server records the user's usage history and emotional data in the "UserHistoryDB" along with the processing results data, which will be used in future processing.

[0431] Input: Optimization information, emotional data, usage history.

[0432] Output: Updated user profile, recorded historical data.

[0433] In this way, the system efficiently analyzes the user's voice and text and provides optimal information based on their emotions.

[0434] (Application example 2)

[0435] 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."

[0436] Conventional communication systems provide information without fully understanding the user's emotions and intentions, which means that users are unable to obtain the most appropriate information. Furthermore, particularly in virtual stores, the system is unable to provide appropriate product suggestions or responses based on the user's emotions, resulting in a poor purchasing experience.

[0437] 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 an acquisition means for acquiring voice or text data from the user, an analysis means for analyzing emotions and intentions, a generation means for generating optimized information, and a transmission means. This makes it possible to provide optimal responses and product suggestions according to the user's emotions.

[0438] The "acquisition means" is a function for acquiring voice or text data from the user.

[0439] The "analysis means" is a function that analyzes the data acquired by the acquisition means.

[0440] The "generation means" is a function that recognizes the user's emotions based on the results of the analysis by the analysis means and optimizes information by utilizing a user profile.

[0441] The "transmitting means" is a function that transmits optimized information to a user terminal.

[0442] A "voice recognition engine" is a system for converting voice data into text data.

[0443] "Natural language processing technology" is a technology that analyzes the intent and emotions of text data and extracts important keywords.

[0444] "Emotion recognition" is a function that extracts and analyzes emotions from a user's voice or text.

[0445] A "user profile" is a data set that includes information such as a user's behavior, preferences, and emotional history.

[0446] An embodiment of the present invention is a system that acquires voice or text data from a user, analyzes it, recognizes the user's emotions, uses a user profile to generate optimal information, and transmits it back to the user's terminal.

[0447] System Configuration

[0448] The system consists of the following modules:

[0449] 1. Acquisition method

[0450] The user terminal receives voice or text data from the user, and the terminal may be a smartphone, tablet, or PC.

[0451] 2. Analysis method

[0452] The server analyzes the acquired data. This analysis includes a speech recognition engine, natural language processing technology, and emotion recognition models. The speech recognition engine utilizes the "SpeechRecognition" library, while the natural language processing technology and emotion recognition utilize the "Transformers" library.

[0453] 3. Generation means

[0454] The server recognizes the user's emotions based on the analysis results and generates optimal responses by referencing the user profile. The generated information includes product suggestions and additional explanations based on the user's emotions and intentions.

[0455] 4. Transmission Method

[0456] The server transmits the generated information to the user terminal using Internet communication, Bluetooth, or other communication means.

[0457] Specific examples

[0458] Example 1: Virtual store application

[0459] scenario:

[0460] Consider a user searching for a "red dress" in a virtual store.

[0461] User dictation: The user dictates, "I'm looking for a red dress."

[0462] Acquisition means: The user terminal acquires the voice data and sends it to the server.

[0463] Analysis method: The server converts the voice data into text data and performs emotion recognition and intent analysis. For example, if the user is feeling stressed, the emotion label "NEGATIVE" is added.

[0464] Generation method: The server generates a response based on the emotion recognition results and the user profile: "Can I help you? What style of red dress are you looking for?"

[0465] Transmission means: The server transmits the generated response to the user terminal, and the user receives this response.

[0466] Example prompt sentence:

[0467] "What are the emotions a user feels when searching for a red dress?"

[0468] "Analyze user intent when searching for a red dress."

[0469] In this way, the system can provide optimal responses and product suggestions based on the user's emotions, improving the user experience in the virtual store and increasing their willingness to purchase.

[0470] Hardware and Software

[0471] Hardware: User devices (smartphones, tablets, PCs), servers

[0472] Software: SpeechRecognition library (speech recognition engine), Transformers library (natural language processing technology and emotion recognition model)

[0473] As described above, a specific embodiment for carrying out the present invention has been described. This system makes it possible to provide information according to the user's emotions and intentions, thereby improving the purchasing experience, particularly in virtual stores.

[0474] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0475] Step 1:

[0476] The user terminal receives a voice input or a text input from the user. In the case of voice input, the voice data is recorded, and in the case of text input, the text data is directly received.

[0477] Input: User voice or text data

[0478] Output: Captured audio or text data

[0479] Step 2:

[0480] The user terminal transmits the acquired voice data or text data to the server.

[0481] Input: Captured audio or text data

[0482] Output: Audio or text data sent to the server

[0483] Step 3:

[0484] The server converts the voice data into text data using a speech recognition engine (SpeechRecognition library). If the data is text, this step is skipped.

[0485] Input: Transmitted audio data

[0486] Output: Converted text data

[0487] Step 4:

[0488] The server analyzes the emotions in the text data using an emotion recognition model (Transformers library) and recognizes the user's emotions.

[0489] Input: Converted text data

[0490] Output: Emotion label and emotion score

[0491] Step 5:

[0492] The server analyzes the intent of the text data using natural language processing technology (Transformers library) and extracts the intent of the data and important keywords.

[0493] Input: Converted text data

[0494] Output: Intent labels and important keywords

[0495] Step 6:

[0496] The server then references the user profile based on the emotion recognition and intent analysis results and generates the optimal response content, including product suggestions and additional explanations that take the user's emotions and intent into account.

[0497] Input: emotion label, emotion score, intent label, important keywords, user profile

[0498] Output: Optimized response content

[0499] Step 7:

[0500] The server transmits the generated response content to the user terminal.

[0501] Input: Optimized response content

[0502] Output: Response sent to the user's terminal

[0503] Step 8:

[0504] The user terminal presents the received response to the user. If it is to be played as audio, the text data is converted into audio data and output.

[0505] Input: Received response

[0506] Output: The response presented to the user

[0507] 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.

[0508] 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.

[0509] 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.

[0510] [Second embodiment]

[0511] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0512] 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.

[0513] 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).

[0514] 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.

[0515] 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.

[0516] 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).

[0517] 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.

[0518] 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.

[0519] 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.

[0520] 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.

[0521] 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.

[0522] 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."

[0523] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[0524] System Configuration

[0525] The system consists of the following modules:

[0526] 1. Acquisition Module

[0527] The user terminal receives voice or text data from the user.

[0528] 2. Analysis Module

[0529] The server receives the data sent from the acquisition module, and if it is voice data, converts it into text data using a voice recognition engine.

[0530] In addition, natural language processing technology is used to analyze the intent and sentiment of the data and extract important keywords.

[0531] 3. Generator Module

[0532] The server then refers to the user profile based on the analysis results and reconstructs the information in a way that is easy for the listener to understand, for example, by adding contextual information and additional explanations.

[0533] 4. Transmission Module

[0534] The server transmits the generated information to the user terminal.

[0535] 5. Recording Module

[0536] The server records the user's usage history and updates the user profile.

[0537] Specific examples of implementation

[0538] Example 1: Simultaneous interpretation at a business meeting

[0539] Consider a scenario where User A is giving a presentation in English at a business meeting. The specific process flow is as follows:

[0540] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[0541] The terminal transmits the voice data to the server.

[0542] The server converts the voice data into text data using a voice recognition engine.

[0543] The server uses natural language processing techniques to analyze the intent and key keywords of the text.

[0544] Based on the user profile, the server reconstructs the information in a form that is optimal for the listener (for example, a Japanese-speaking employee) and generates, "Hello everyone. Today I'll be talking about our sales strategy."

[0545] The server sends the generated text to User B's terminal.

[0546] User B's terminal displays or plays back the transmitted text as audio.

[0547] Example 2: Context completion in education

[0548] Consider a situation where a teacher is discussing a math concept:

[0549] User C's (teacher's) device receives the voice message, "Integral calculation is the inverse operation of differential calculation."

[0550] The terminal transmits the voice data to the server.

[0551] The server converts the voice data into text data using a voice recognition engine.

[0552] The server uses natural language processing techniques to analyze the text and add any necessary complementary information.

[0553] The server generates a context-complete explanation: "Integration is a method for finding the area of ​​a function, and differentiation is the rate of change of that function."

[0554] The server transmits the generated text to the student terminal.

[0555] The student terminal displays the supplementary explanation, providing information in a format that is easy for students to understand.

[0556] In this way, this system achieves effective communication by analyzing and regenerating voice and text data from the user and providing information in a form that is easy for the listener to understand.

[0557] The processing flow will be explained below.

[0558] Step 1:

[0559] The user terminal acquires voice or text data from the user. For example, consider the case where voice data such as "Hello, everyone. Today we will discuss the sales strategy" is acquired.

[0560] Step 2:

[0561] The user device transmits the acquired data to the server, ideally in real time.

[0562] Step 3:

[0563] The server receives the voice data transmitted from the user terminal.

[0564] Step 4:

[0565] The server converts the received voice data into text data using a speech recognition engine, for example, "Hello, everyone. Today we will discuss the sales strategy."

[0566] Step 5:

[0567] The server analyzes the text data using natural language processing (NLP) technology. This analysis includes intent analysis, sentiment analysis, and extraction of important keywords. For example, the keyword "sales strategy" is extracted.

[0568] Step 6:

[0569] The server then uses the user profile based on the analysis results to optimize the information provided. For example, for a listener whose native language is Japanese, the message "Hello, everyone. Today we will discuss the sales strategy." is converted to "Hello, everyone. Today we will talk about our sales strategy."

[0570] Step 7:

[0571] The server completes the context and provides additional explanation as needed, for example, to elaborate on the concept of "sales strategy," it might add, "A sales strategy is a plan for a company to effectively deliver its products and services to customers."

[0572] Step 8:

[0573] The server reconverts the generated optimized information into voice data using a voice synthesis engine, or formats it as text data as is.

[0574] Step 9:

[0575] The server sends the generated information to the user's terminal. In the case of audio, it is sent as an audio file, and in the case of text, it is sent as text in UTF-8 format.

[0576] Step 10:

[0577] The user terminal plays the received data as voice or displays it as text. For example, if played as voice, it sounds like "Hello everyone. Today I'm going to talk about our sales strategy."

[0578] Step 11:

[0579] The server records the user's output history and updates the user profile, which further personalizes subsequent information generation.

[0580] In this way, the system efficiently analyzes and optimizes the user's voice and text, providing information in a format that is easy for the listener to understand.

[0581] Example 1

[0582] 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."

[0583] Language differences and the need to convey complex meanings are often barriers to modern communication. Voice data must be converted into text, analyzed using natural language processing, and then provided in an optimal format. However, existing technologies struggle to achieve this in real time, which can detract from the user experience. This problem needs to be addressed, particularly in business meetings and educational settings, where rapid and accurate information transmission is crucial.

[0584] 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.

[0585] In this invention, the server includes an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the data acquired by the acquisition means, a generation means for optimizing information using a user profile based on the analysis result by the analysis means, a transmission means for transmitting the optimized information to a user terminal, and a recording means for recording the analyzed data and the optimized information and updating the user profile, thereby enabling the user to receive accurate and optimized information in real time.

[0586] The "acquisition means" is a means for acquiring voice or text data from a user.

[0587] The "analysis means" is a means for analyzing the data acquired by the acquisition means.

[0588] The "generation means" is a means for optimizing information by utilizing a user profile based on the results of analysis by the analysis means.

[0589] The "transmitting means" is a means for transmitting optimized information to a user terminal.

[0590] The "recording means" is a means for recording analyzed data and optimized information and updating a user profile.

[0591] A "voice recognition engine" is an engine for converting voice data into text data.

[0592] "Natural language processing technology" is a technology that analyzes the intent and sentiment of data and extracts important keywords.

[0593] A "generative AI model" is an AI model that adds context and additional explanation to information.

[0594] "Real-time communication technology" refers to communication technology for sending and receiving information in real time.

[0595] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[0596] System Configuration

[0597] The system consists of the following modules:

[0598] 1. Acquisition method

[0599] The user terminal receives voice or text data from the user and includes a microphone and a text input device.

[0600] The acquired audio data is saved in formats such as WAV or MP3 and temporarily stored in memory.

[0601] 2. Analysis method

[0602] The server receives the data sent from the acquisition means and converts the voice data into text data using a voice recognition engine (for example, Google Cloud Speech-to-Text).

[0603] In addition, natural language processing technologies such as Hugging Face's Transformers and SpaCy are used to analyze the intent and sentiment of the data and extract important keywords.

[0604] 3. Generation means

[0605] The server then uses the analysis results, references the user profile, and reconstructs the information in a way that is easy for the listener to understand. In particular, it uses a generative AI model to provide context and additional explanations for the information.

[0606] For example, if the input is "Hello, the weather is nice today," it will be reconstructed into "Hello, it's a sunny day. I have an important meeting today."

[0607] 4. Transmission Method

[0608] The server transmits the regenerated information to the user terminal, using real-time communication techniques (e.g., WebSocket or Push notification).

[0609] 5. Recording Method

[0610] The server records the analyzed data and generated information in a database and updates the user profile, enabling it to provide more optimal information the next time the user uses the service.

[0611] Specific examples of implementation

[0612] Example 1: Simultaneous interpretation at a business meeting

[0613] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[0614] The terminal transmits the voice data to the server.

[0615] The server converts the voice data into text data using a voice recognition engine.

[0616] The server uses natural language processing techniques to analyze the intent and key keywords of the text.

[0617] The server regenerates "Hello everyone, today we'll talk about our sales strategy" based on the user profile.

[0618] The server sends the generated text to User B's terminal.

[0619] User B's terminal displays the text and provides it to the user.

[0620] Example 2: Context completion in education

[0621] User C's (teacher's) device receives the voice message, "Integral calculation is the inverse operation of differential calculation."

[0622] The terminal transmits the voice data to the server.

[0623] The server converts the voice data into text data using a voice recognition engine.

[0624] The server uses natural language processing techniques to analyze the text and add any necessary complementary information.

[0625] The server generates a context-complete explanation: "Integration is a method for finding the area of ​​a function, and differentiation is the rate of change of that function."

[0626] The server transmits the generated text to the student terminal.

[0627] The student terminals display supplementary explanations, providing information in a format that is easy for students to understand.

[0628] Examples of prompt statements

[0629] "The system converts the voice data entered by the user into text data and generates explanatory text based on the text, adding supplementary information."

[0630] "A communication optimization system that translates English presentations used in business meetings into Japanese in real time and sends the translation to the devices of all parties involved."

[0631] In this way, this system analyzes and regenerates the user's voice and text data, providing information in a format that is easy for the listener to understand, thereby achieving effective communication.

[0632] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0633] Step 1:

[0634] The user terminal receives voice or text data from the user. For example, the user may say, "Hello, the weather is nice today." The input voice data is temporarily stored in memory and saved in an appropriate format (e.g., WAV or MP3). This is the input voice data.

[0635] Step 2:

[0636] The user device compresses the acquired audio data and sends it to the specified server endpoint. For example, the audio data is sent to the server via a POST request via a REST API. The input is the acquired audio data, and the output is the data to be sent to the server. Specifically, authentication information is added to the HTTP request header, and the audio data is included in the body in binary format.

[0637] Step 3:

[0638] The server temporarily stores the received voice data and passes the data to a voice recognition engine (for example, a general voice recognition engine). The input is the voice data sent to the server, and the output is the text data obtained by voice recognition. Specifically, the server generates the text data "Hello, the weather is nice today."

[0639] Step 4:

[0640] The server passes the text data obtained from the speech recognition to a natural language processing engine (such as a general natural language processing engine). This is where intent analysis, sentiment analysis, and extraction of important keywords are performed. The input is text data generated by speech recognition, and the output is the analysis results. Specifically, the greeting "Hello" is analyzed as the intent, and "The weather is nice" is analyzed as a positive sentiment. The keywords "weather" and "good" are also extracted.

[0641] Step 5:

[0642] The server regenerates information based on the analysis results, referencing the user profile. In particular, it uses a generative AI model to add context and additional explanations. The input is the analysis results and user profile data, and the output is the regenerated information. For example, it could be reconstructed as "Hello, it's a sunny day. I have an important meeting today."

[0643] Step 6:

[0644] The server sends the regenerated text data to the specific user device. It uses real-time communication technology (for example, WebSocket or Push notification). The input is the regenerated information, and the output is the data to be sent to the user device. The server sends an HTTP response containing the new text data to the specific user device.

[0645] Step 7:

[0646] The server records the analyzed data and generated information in a database and updates the user profile. The input is the analyzed and regenerated data, and the output is the updated user profile. Specifically, the server records the usage history and saves data to provide more optimized information to the user the next time they use the service.

[0647] (Application example 1)

[0648] 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."

[0649] In food delivery, communication between users and delivery personnel is often insufficient, resulting in misunderstandings of instructions and delivery errors. While quick and accurate responses to customer inquiries are required, current systems have difficulty meeting these demands. Furthermore, there is a lack of efficient ways to optimize information from voice and text to make it easier for users to understand.

[0650] 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.

[0651] In this invention, the server includes an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the data acquired by the acquisition means, a voice recognition means for converting the voice data into text data using a voice recognition engine, a natural language processing means for analyzing the intention and emotion of the text data and extracting important keywords using natural language processing technology, a complement generation means for referencing the order history and generating complement information for the user based on the analysis results, and a transmission means for transmitting optimized information to the user terminal. This enables efficient communication by optimizing information in a form that is easy for the user to understand in response to delivery instructions or inquiries.

[0652] The "acquisition means" is a means for acquiring voice or text data from a user.

[0653] The "analysis means" is a means for analyzing the data acquired by the acquisition means.

[0654] The "voice recognition means" is a means that uses a voice recognition engine to convert voice data into text data.

[0655] The "natural language processing means" is a means for using natural language processing technology to perform intent analysis, sentiment analysis, and extraction of important keywords from text data.

[0656] The "generation means" is a means for optimizing information using a user profile based on the analysis results and reconstructing the information in a form that is easy for the user to understand.

[0657] The "complementary information generating means" refers to a means for referencing the order history and generating complementary information for the user based on the analysis results.

[0658] The "transmitting means" is a means for transmitting optimized information to a user terminal.

[0659] "User terminal" means a device used by a user, and is a general computing device that has the function of inputting and receiving voice and text data.

[0660] The present invention is a communication optimization system that analyzes voice or text data from users and converts it into a format that is easy for other users to understand. This system is specialized for food delivery services and is designed to efficiently process instructions and inquiries from users.

[0661] System configuration

[0662] The system consists of the following modules:

[0663] 1. Acquisition method

[0664] The server acquires voice or text data from a user device, such as a smartphone or tablet, using the voice input or text input function.

[0665] 2. Analysis method

[0666] The server converts the acquired voice data into text data using speech recognition technology, and then uses natural language processing technology to analyze the intent and sentiment of the text data and extract important keywords. Specifically, it uses the "Google Cloud Speech-to-Text API" and "Google Cloud Natural Language API."

[0667] 3. Generation means

[0668] Based on the analysis results, the server references the user profile and generates optimized information, supplementing it with context-appropriate information by taking into account order history and past instructions.

[0669] 4. Transmission Method

[0670] The server sends optimized information to the user terminal, enabling efficient communication.

[0671] Specific examples

[0672] Example 1: Optimizing delivery instructions

[0673] scenario:

[0674] The user may say, "Please leave the food at the entrance."

[0675] Process flow:

[0676] 1. The user's smartphone acquires the voice data and sends it to the server.

[0677] 2. The server converts the speech into text using the Google Cloud Speech-to-Text API.

[0678] 3. The server analyzes the intent of the text and important keywords using the Google Cloud Natural Language API.

[0679] 4. The server compares the order history and generates an optimized instruction: "Place the food to the right of the entrance."

[0680] 5. The server sends optimized instructions to the delivery person's smartphone, and the delivery person receives the information in an easy-to-understand format.

[0681] Example 2: Customer inquiry optimization

[0682] scenario:

[0683] A customer might ask by voice, "Does the salad I ordered come with dressing?"

[0684] Process flow:

[0685] 1. The customer's smartphone captures the voice data and sends it to the server.

[0686] 2. The server converts the speech into text using the Google Cloud Speech-to-Text API.

[0687] 3. The server analyzes the intent of the text and important keywords using the Google Cloud Natural Language API.

[0688] 4. The server references the order history, checks whether or not dressing is included, and generates the response "The salad you ordered comes with dressing."

[0689] 5. The server sends the optimized answer to the customer's smartphone, where the customer receives the information in an easily understandable format.

[0690] Prompt Sentence Examples

[0691] "Start typing. Enter instructions or questions. For example, 'Please leave my food at the door,' or 'Does the salad I ordered come with dressing?'"

[0692] Through these steps, the system can optimize communication in food delivery operations and reduce misunderstandings and errors.

[0693] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0694] Step 1:

[0695] The user inputs instructions or inquiries into a device (smartphone or tablet) by voice or text.

[0696] Input: User's voice data

[0697] Output: Acquire audio data

[0698] Specific action: The user gives the voice command, "Please leave the food at the entrance."

[0699] Step 2:

[0700] The terminal transmits the acquired voice data to the server.

[0701] Input: Audio data acquired by the device

[0702] Output: Sending audio data to the server

[0703] Specific operation: Audio data is sent from the device to the server in real time.

[0704] Step 3:

[0705] The server converts the voice data into text data using a speech recognition method (e.g., Google Cloud Speech-to-Text API).

[0706] Input: Audio data

[0707] Output: Text data

[0708] Specific action: The server converts the speech into text, "Please leave the food at the entrance."

[0709] Step 4:

[0710] The server uses natural language processing means (e.g., Google Cloud Natural Language API) to analyze the intent and sentiment of the text data and extract important keywords.

[0711] Input: Text data

[0712] Output: Intention analysis results, emotion analysis results, important keywords

[0713] Specific operation: The server analyzes the intent of "Please leave it at the entrance" and extracts the important keywords "entrance" and "place."

[0714] Step 5:

[0715] The server generates optimized information using a complementary generation means based on the analysis results and the user profile.

[0716] Input: Analysis results, user profile

[0717] Output: Optimized instructions

[0718] Specific behavior: The server references the order history and completes the instruction with "Please place the food to the right of the entrance."

[0719] Step 6:

[0720] The server sends the optimized information to the delivery person's terminal.

[0721] Input: Optimized instructions

[0722] Output: Send instructions to delivery person's terminal

[0723] Specific operation: The server sends the instruction "Please place the food on the right side of the entrance" to the delivery person's smartphone.

[0724] Step 7:

[0725] The delivery person's device displays or plays back optimized instructions.

[0726] Input: Optimized instructions

[0727] Output: Display or audio for delivery personnel to understand

[0728] Specific actions: The delivery person's device will display instructions on the screen or say aloud, "Please leave the food to the right of the entrance."

[0729] Through each of the above steps, a system is built that efficiently processes instructions and inquiries from users and optimizes communication in food delivery.

[0730] 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.

[0731] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand, and further combines it with an emotion engine that recognizes the user's emotions. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[0732] System Configuration

[0733] The system consists of the following modules:

[0734] 1. Acquisition Module

[0735] The user terminal receives voice or text data from the user.

[0736] 2. Emotion Engine

[0737] The server uses an emotion engine to extract the user's emotion from the captured voice or text data, and the emotion data is provided to the analysis means.

[0738] 3. Analysis Module

[0739] The server receives the data sent from the acquisition module and the emotion data provided by the emotion engine, and in the case of voice data, converts it into text data using a voice recognition engine.

[0740] In addition, natural language processing technology is used to analyze the intent and sentiment of the data and extract important keywords.

[0741] 4. Generator Module

[0742] The server references the user profile based on the analysis results and emotional data, and reconstructs the information in a way that is easy for the listener to understand, for example, by adding contextual information and additional explanations.

[0743] 5. Transmission Module

[0744] The server transmits the generated information to the user terminal.

[0745] 6. Recording Module

[0746] The server records the user's usage history and emotion data and updates the user profile.

[0747] Specific examples of implementation

[0748] Example 1: Simultaneous interpretation at a business meeting

[0749] Consider a scenario where User A is giving a presentation in English at a business meeting. The specific process flow is as follows:

[0750] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[0751] The terminal transmits the voice data to the server.

[0752] The server converts the voice data into text data using a voice recognition engine.

[0753] The server uses natural language processing technology to analyze the intent and key keywords of the text, and uses an emotion engine to analyze the tone of the speech. For example, if User A is speaking enthusiastically, the emotion engine will detect "high enthusiasm."

[0754] Based on the user profile, the server translates "Hello, everyone. Today we will discuss the sales strategy." into "Hello, everyone. Today we will discuss our sales strategy." and reproduces it to the listener in a tone that reflects "high enthusiasm."

[0755] The server sends the generated text to User B's terminal.

[0756] User B's device displays the text or plays it back as audio. For example, if it is played back as audio, it will sound like "Hello everyone. Today I'll be talking about our sales strategy," but it will be adjusted to reflect User A's enthusiasm.

[0757] Example 2: Contextual Complement and Emotional Feedback in Educational Settings

[0758] Consider a situation where a teacher is discussing a math concept:

[0759] User C's (teacher's) device receives the voice message, "Integral calculation is the inverse operation of differential calculation."

[0760] The terminal transmits the voice data to the server.

[0761] The server converts the voice data into text data using a voice recognition engine.

[0762] The server uses natural language processing technology to analyze the text and an emotion engine to analyze the accumulated student comprehension and emotion data, for example, to detect whether a student is confused.

[0763] The server then uses the analysis results and emotion data to complete the context and provide additional explanations. The server completes the context by saying, "Integral calculation is a method for finding the area of ​​a function, and differential calculation is the rate of change of that function."

[0764] The server transmits the generated optimization information to the student terminal.

[0765] The student device displays the supplementary explanation, providing the information in a way that is easy for the student to understand, and also records feedback on whether the student has demonstrated understanding.

[0766] In this way, the system efficiently analyzes and optimizes voice and text, including the user's emotions, and provides information in a form that is easy for the listener to understand.

[0767] The processing flow will be explained below.

[0768] Example 1: Simultaneous interpretation at a business meeting

[0769] Step 1:

[0770] The terminal of user A receives the voice data from user A, "Hello, everyone. Today we will discuss the sales strategy."

[0771] Step 2:

[0772] User A's terminal transmits the acquired voice data to the server.

[0773] Step 3:

[0774] The server receives the audio data.

[0775] Step 4:

[0776] The server uses a speech recognition engine to convert the voice data into text data: "Hello, everyone. Today we will discuss the sales strategy."

[0777] Step 5:

[0778] The server uses an emotion engine to extract User A's emotion from the voice data. For example, it detects "high enthusiasm" from the tone and tempo of User A's speech.

[0779] Step 6:

[0780] The server uses natural language processing technology to analyze the text data and extract intent, sentiment, and key keywords. For example, it extracts "sales strategy" as a key keyword and also analyzes the results of the sentiment engine.

[0781] Step 7:

[0782] The server then refers to the user profile based on the analysis results and emotional data, optimizing the information. For example, it converts "Hello, everyone. Today we will discuss the sales strategy" into "Hello, everyone. Today we will discuss our sales strategy," adjusting the information to reflect the speaker's "high enthusiasm."

[0783] Step 8:

[0784] The server reconverts the optimized information into voice data using a voice synthesis engine or formats it as text data.

[0785] Step 9:

[0786] The server transmits the generated information to User B's terminal.

[0787] Step 10:

[0788] User B's device plays the received information as voice or displays it as text. For example, if it is played as voice, it will sound like "Hello everyone. Today I'll talk about our sales strategy," which reflects User A's "high enthusiasm."

[0789] Step 11:

[0790] The server records the data obtained during the analysis and generation process in the user profile and uses it for the next processing.

[0791] Example 2: Contextual Complement and Emotional Feedback in Educational Settings

[0792] Step 1:

[0793] User C's (teacher's) device receives the voice data from User C saying, "Integral calculation is the inverse operation of differential calculation."

[0794] Step 2:

[0795] User C's terminal transmits the acquired voice data to the server.

[0796] Step 3:

[0797] The server receives the audio data.

[0798] Step 4:

[0799] The server uses a speech recognition engine to convert the speech data into text data "Integral calculation is the inverse operation of differential calculation."

[0800] Step 5:

[0801] The server uses an emotion engine to extract User C's emotion from the voice data. For example, it detects a "calm tone" from User C's speaking style.

[0802] Step 6:

[0803] The server uses natural language processing technology to analyze the text data and extract intent, sentiment, and important keywords. For example, it extracts the keywords "integral calculation" and "differential calculation," and also analyzes sentiment data.

[0804] Step 7:

[0805] The server then refers to the user profile based on the analysis results and sentiment data, optimizes the information, and provides necessary contextual completion and additional explanations. For example, it adds additional information such as, "Integral calculation is a method for calculating the area of ​​a function, and differential calculation is the rate of change of that function."

[0806] Step 8:

[0807] The server reconverts the optimized information into voice data using a voice synthesis engine or formats it as text data.

[0808] Step 9:

[0809] The server transmits the generated information to the student terminal.

[0810] Step 10:

[0811] The student device will then play the received information as audio or display it as text. For example, a supplementary explanation may be displayed as text, such as, "Integration is a method for finding the area of ​​a function, and differentiation is the rate of change of that function."

[0812] Step 11:

[0813] The server records the data obtained during the analysis and generation process in a user profile for future use. It also records changes in the student's understanding and emotional feedback.

[0814] In this way, the system efficiently analyzes voice and text, including the user's emotions, and provides information in a format that is easy for the listener to understand.

[0815] Example 2

[0816] 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."

[0817] In modern communication systems, it is difficult to understand a user's intentions and emotions and provide optimal information based on them. In particular, when analyzing voice and text data, it is necessary to accurately grasp the user's emotions and intentions and reconstruct information in a form that is easy for the listener to understand. As a result, conventional systems have issues such as an insufficient user experience and reduced information transmission efficiency.

[0818] 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.

[0819] In this invention, the server includes an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the data acquired by the acquisition means, an emotion analysis means for extracting emotion data analyzed by the analysis means, a generation means for optimizing information using a user profile based on the analysis results by the analysis means, a transmission means for transmitting the optimized information to a user terminal, and a reconstructing means for reconstructing the optimized information based on the user profile. This makes it possible to accurately understand the user's intentions and emotions and generate and provide optimal information.

[0820] The "acquisition means" is a means for acquiring voice or text data from a user.

[0821] The "analysis means" is a means for analyzing the data acquired by the acquisition means.

[0822] The "emotion analysis means" is a means for extracting emotion data analyzed by the analysis means.

[0823] The "generating means" is a means for optimizing information by utilizing a user profile based on the results of the analysis by the analyzing means.

[0824] The "transmitting means" is a means for transmitting optimized information to a user terminal.

[0825] The "reconstruction means" is a means for reconstructing optimized information based on a user profile.

[0826] A "voice recognition engine" is a program or system for converting voice data into text data.

[0827] "Natural language processing technology" is a technology for analyzing the intent and emotions of text data and extracting important keywords.

[0828] A "user profile" is a database that includes each user's past usage history and setting information.

[0829] MODE FOR CARRYING OUT THE INVENTION

[0830] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand, and further combines it with an emotion engine that recognizes the user's emotions. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[0831] System Configuration

[0832] The system consists of the following modules:

[0833] 1. Acquisition method

[0834] The user terminal captures voice or text data from the user, for example, when the user says "What are your plans for tomorrow?" using a microphone subsystem or a text input field.

[0835] 2. Analysis method

[0836] The server receives the voice data sent from the user's device and converts it into text using a voice recognition engine called "SpeechToTextEngine." Examples of such engines include Google Speech-to-Text API and IBM Watson.

[0837] Furthermore, natural language processing techniques are used to analyze the intent and sentiment of the text and extract important keywords, using the natural language processing libraries "spaCy" and "NLTK."

[0838] 3. Emotion analysis method

[0839] The server passes the text data to the emotion analysis engine "EmotionAnalyzer" to extract emotional data. This engine analyzes the user's emotions (e.g., joy, sadness, surprise, etc.) from the text.

[0840] 4. Generation means

[0841] Based on the analysis results and emotion data, the server references the user profile "UserProfileDB" and reconstructs the information in a format that is easy for the listener to understand, for example by adding supplementary explanations and detailed information according to the context.

[0842] 5. Transmission Method

[0843] The server sends the generated information to the user's terminal. For example, it also provides a service that sends text information as an HTTP response and synthesizes it as voice data.

[0844] 6. Reconstruction means

[0845] The server reconstructs optimized information based on the user profile, allowing it to present information in a form that is most relevant to each individual user.

[0846] Specific examples of implementation

[0847] Example 1: Simultaneous interpretation at a business meeting

[0848] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[0849] The terminal transmits the voice data to the server.

[0850] The server converts the voice data into text data using the voice recognition engine "SpeechToTextEngine."

[0851] The server uses natural language processing technology and the emotion engine "EmotionAnalyzer" to analyze the intent and important keywords of the text and detects that User A's emotion is "high enthusiasm."

[0852] The server translates the English text based on the user profile into "Hello everyone, today I'll be talking about our sales strategy," and reproduces it in a tone that reflects high enthusiasm.

[0853] The server sends the generated Japanese text to User B's terminal.

[0854] User B's terminal displays or plays back the transmitted text as audio.

[0855] Example prompts for generative AI models:

[0856] Please translate the following English speech data into Japanese and reproduce it in a way that reflects the user's emotion of "high enthusiasm."

[0857] Audio data: "Hello, everyone. Today we will discuss the sales strategy."

[0858] Example 2: Contextual Complement and Emotional Feedback in Educational Settings

[0859] In a situation where the teacher is talking about a mathematical concept, the device of user C (teacher) receives the audio message, "Integral calculus is the inverse operation of differential calculus."

[0860] The terminal transmits the voice data to the server.

[0861] The server converts the voice data into text data using the voice recognition engine "SpeechToTextEngine."

[0862] The server uses natural language processing technology and the emotion engine "EmotionAnalyzer" to analyze text data and detect students' level of understanding and emotions.

[0863] Based on the analysis results and emotion data, the server completes the context and provides additional explanation: "Integral calculation is a method for finding the area of ​​a function, and differential calculation is the rate of change of that function."

[0864] The server transmits the generated supplementary explanation to the student terminal.

[0865] The student's device displays the supplemented explanation and also records the comprehension feedback.

[0866] Example prompts for generative AI models:

[0867] Please convert the audio data below into easy-to-understand text, and provide context and additional explanations if the student gets confused during the speech.

[0868] Audio: "Integral calculus is the inverse operation of differential calculus."

[0869] In this way, the system efficiently analyzes and optimizes voice and text, including the user's emotions, and provides information in a form that is easy for the listener to understand.

[0870] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0871] Step 1:

[0872] The user enters a message by voice or text, for example saying "What's the weather like tomorrow?"

[0873] Input: User's voice or text data.

[0874] Output: Captured audio or text data.

[0875] Step 2:

[0876] The device captures the user's voice using its internal microphone subsystem or a text input field. For example, a microphone sensor receives voice input. The captured data is kept raw.

[0877] Input: User's voice data.

[0878] Output: Audio data stored on the device.

[0879] Step 3:

[0880] The device transmits the acquired audio data to the server using an HTTP POST request. For example, the device uploads the audio data to the server in MIME format.

[0881] Input: Audio data stored on the device.

[0882] Output: The audio data sent to the server.

[0883] Step 4:

[0884] The server receives the transmitted audio data and stores it in temporary storage, making it ready to be analyzed.

[0885] Input: Audio data sent from the device.

[0886] Output: Audio data stored on the server.

[0887] Step 5:

[0888] The server converts the voice data into text data using a speech recognition engine called "SpeechToTextEngine," such as the Google Speech-to-Text API.

[0889] Input: Audio data stored on the server.

[0890] Output: The converted text data.

[0891] Step 6:

[0892] The server uses natural language processing technology (such as spaCy or NLTK) to analyze the intent and sentiment of the text data and extract important keywords. For example, from the text "What's the weather like tomorrow?", the important keyword "weather" and the sentiment "curiosity" are extracted.

[0893] Input: The converted text data.

[0894] Output: Analyzed intent data, sentiment data, and important keywords.

[0895] Step 7:

[0896] The server uses the emotion analysis engine "EmotionAnalyzer" to extract emotional data from the text data. For example, it determines that the user's emotion is "curiosity."

[0897] Input: The converted text data.

[0898] Output: Extracted emotion data.

[0899] Step 8:

[0900] The server then references the user profile (UserProfileDB) based on the analysis results and emotion data to generate the optimal answer. For example, it could reconstruct the answer as "Tomorrow's weather will be sunny" based on the profile and past data.

[0901] Input: Analyzed intent data, sentiment data, important keywords, user profile.

[0902] Output: The generated optimized information.

[0903] Step 9:

[0904] The server sends the generated information to the user terminal. For example, it may send text information as an HTTP response and provide a service to synthesize it as voice data.

[0905] Input: Optimized information.

[0906] Output: Information sent to the user's terminal.

[0907] Step 10:

[0908] The terminal receives the information sent from the server and displays it to the user, or plays it as audio using an audio playback device. For example, the terminal displays "Tomorrow's weather will be sunny" and plays it as audio.

[0909] Input: Information sent by the server.

[0910] Output: The information that is displayed to the user or played as sound.

[0911] Step 11:

[0912] The server records the user's usage history and emotional data in the "UserHistoryDB" along with the processing results data, which will be used in future processing.

[0913] Input: Optimization information, emotional data, usage history.

[0914] Output: Updated user profile, recorded historical data.

[0915] In this way, the system efficiently analyzes the user's voice and text and provides optimal information based on their emotions.

[0916] (Application example 2)

[0917] 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."

[0918] Conventional communication systems provide information without fully understanding the user's emotions and intentions, which means that users are unable to obtain the most appropriate information. Furthermore, particularly in virtual stores, the system is unable to provide appropriate product suggestions or responses based on the user's emotions, resulting in a poor purchasing experience.

[0919] 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 an acquisition means for acquiring voice or text data from the user, an analysis means for analyzing emotions and intentions, a generation means for generating optimized information, and a transmission means. This makes it possible to provide optimal responses and product suggestions according to the user's emotions.

[0920] The "acquisition means" is a function for acquiring voice or text data from the user.

[0921] The "analysis means" is a function that analyzes the data acquired by the acquisition means.

[0922] The "generation means" is a function that recognizes the user's emotions based on the results of the analysis by the analysis means and optimizes information by utilizing a user profile.

[0923] The "transmitting means" is a function that transmits optimized information to a user terminal.

[0924] A "voice recognition engine" is a system for converting voice data into text data.

[0925] "Natural language processing technology" is a technology that analyzes the intent and emotions of text data and extracts important keywords.

[0926] "Emotion recognition" is a function that extracts and analyzes emotions from a user's voice or text.

[0927] A "user profile" is a data set that includes information such as a user's behavior, preferences, and emotional history.

[0928] An embodiment of the present invention is a system that acquires voice or text data from a user, analyzes it, recognizes the user's emotions, uses a user profile to generate optimal information, and transmits it back to the user's terminal.

[0929] System Configuration

[0930] The system consists of the following modules:

[0931] 1. Acquisition method

[0932] The user terminal receives voice or text data from the user, and the terminal may be a smartphone, tablet, or PC.

[0933] 2. Analysis method

[0934] The server analyzes the acquired data. This analysis includes a speech recognition engine, natural language processing technology, and emotion recognition models. The speech recognition engine utilizes the "SpeechRecognition" library, while the natural language processing technology and emotion recognition utilize the "Transformers" library.

[0935] 3. Generation means

[0936] The server recognizes the user's emotions based on the analysis results and generates optimal responses by referencing the user profile. The generated information includes product suggestions and additional explanations based on the user's emotions and intentions.

[0937] 4. Transmission Method

[0938] The server transmits the generated information to the user terminal using Internet communication, Bluetooth, or other communication means.

[0939] Specific examples

[0940] Example 1: Virtual store application

[0941] scenario:

[0942] Consider a user searching for a "red dress" in a virtual store.

[0943] User dictation: The user dictates, "I'm looking for a red dress."

[0944] Acquisition means: The user terminal acquires the voice data and sends it to the server.

[0945] Analysis method: The server converts the voice data into text data and performs emotion recognition and intent analysis. For example, if the user is feeling stressed, the emotion label "NEGATIVE" is added.

[0946] Generation method: The server generates a response based on the emotion recognition results and the user profile: "Can I help you? What style of red dress are you looking for?"

[0947] Transmission means: The server transmits the generated response to the user terminal, and the user receives this response.

[0948] Example prompt sentence:

[0949] "What are the emotions a user feels when searching for a red dress?"

[0950] "Analyze user intent when searching for a red dress."

[0951] In this way, the system can provide optimal responses and product suggestions based on the user's emotions, improving the user experience in the virtual store and increasing their willingness to purchase.

[0952] Hardware and Software

[0953] Hardware: User devices (smartphones, tablets, PCs), servers

[0954] Software: SpeechRecognition library (speech recognition engine), Transformers library (natural language processing technology and emotion recognition model)

[0955] As described above, a specific embodiment for carrying out the present invention has been described. This system makes it possible to provide information according to the user's emotions and intentions, thereby improving the purchasing experience, particularly in virtual stores.

[0956] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0957] Step 1:

[0958] The user terminal receives a voice input or a text input from the user. In the case of voice input, the voice data is recorded, and in the case of text input, the text data is directly received.

[0959] Input: User voice or text data

[0960] Output: Captured audio or text data

[0961] Step 2:

[0962] The user terminal transmits the acquired voice data or text data to the server.

[0963] Input: Captured audio or text data

[0964] Output: Audio or text data sent to the server

[0965] Step 3:

[0966] The server converts the voice data into text data using a speech recognition engine (SpeechRecognition library). If the data is text, this step is skipped.

[0967] Input: Transmitted audio data

[0968] Output: Converted text data

[0969] Step 4:

[0970] The server analyzes the emotions in the text data using an emotion recognition model (Transformers library) and recognizes the user's emotions.

[0971] Input: Converted text data

[0972] Output: Emotion label and emotion score

[0973] Step 5:

[0974] The server analyzes the intent of the text data using natural language processing technology (Transformers library) and extracts the intent of the data and important keywords.

[0975] Input: Converted text data

[0976] Output: Intent labels and important keywords

[0977] Step 6:

[0978] The server then references the user profile based on the emotion recognition and intent analysis results and generates the optimal response content, including product suggestions and additional explanations that take the user's emotions and intent into account.

[0979] Input: emotion label, emotion score, intent label, important keywords, user profile

[0980] Output: Optimized response content

[0981] Step 7:

[0982] The server transmits the generated response content to the user terminal.

[0983] Input: Optimized response content

[0984] Output: Response sent to the user's terminal

[0985] Step 8:

[0986] The user terminal presents the received response to the user. If it is to be played as audio, the text data is converted into audio data and output.

[0987] Input: Received response

[0988] Output: The response presented to the user

[0989] 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.

[0990] 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.

[0991] 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.

[0992] [Third embodiment]

[0993] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0994] 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.

[0995] 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).

[0996] 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.

[0997] 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.

[0998] 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).

[0999] 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.

[1000] 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.

[1001] 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.

[1002] 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.

[1003] 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.

[1004] 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."

[1005] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[1006] System Configuration

[1007] The system consists of the following modules:

[1008] 1. Acquisition Module

[1009] The user terminal receives voice or text data from the user.

[1010] 2. Analysis Module

[1011] The server receives the data sent from the acquisition module, and if it is voice data, converts it into text data using a voice recognition engine.

[1012] In addition, natural language processing technology is used to analyze the intent and sentiment of the data and extract important keywords.

[1013] 3. Generator Module

[1014] The server then refers to the user profile based on the analysis results and reconstructs the information in a way that is easy for the listener to understand, for example, by adding contextual information and additional explanations.

[1015] 4. Transmission Module

[1016] The server transmits the generated information to the user terminal.

[1017] 5. Recording Module

[1018] The server records the user's usage history and updates the user profile.

[1019] Specific examples of implementation

[1020] Example 1: Simultaneous interpretation at a business meeting

[1021] Consider a scenario where User A is giving a presentation in English at a business meeting. The specific process flow is as follows:

[1022] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[1023] The terminal transmits the voice data to the server.

[1024] The server converts the voice data into text data using a voice recognition engine.

[1025] The server uses natural language processing techniques to analyze the intent and key keywords of the text.

[1026] Based on the user profile, the server reconstructs the information in a form that is optimal for the listener (for example, a Japanese-speaking employee) and generates, "Hello everyone. Today I'll be talking about our sales strategy."

[1027] The server sends the generated text to User B's terminal.

[1028] User B's terminal displays or plays back the transmitted text as audio.

[1029] Example 2: Context completion in education

[1030] Consider a situation where a teacher is discussing a math concept:

[1031] User C's (teacher's) device receives the voice message, "Integral calculation is the inverse operation of differential calculation."

[1032] The terminal transmits the voice data to the server.

[1033] The server converts the voice data into text data using a voice recognition engine.

[1034] The server uses natural language processing techniques to analyze the text and add any necessary complementary information.

[1035] The server generates a context-complete explanation: "Integration is a method for finding the area of ​​a function, and differentiation is the rate of change of that function."

[1036] The server transmits the generated text to the student terminal.

[1037] The student terminal displays the supplementary explanation, providing information in a format that is easy for students to understand.

[1038] In this way, this system achieves effective communication by analyzing and regenerating voice and text data from the user and providing information in a form that is easy for the listener to understand.

[1039] The processing flow will be explained below.

[1040] Step 1:

[1041] The user terminal acquires voice or text data from the user. For example, consider the case where voice data such as "Hello, everyone. Today we will discuss the sales strategy" is acquired.

[1042] Step 2:

[1043] The user device transmits the acquired data to the server, ideally in real time.

[1044] Step 3:

[1045] The server receives the voice data transmitted from the user terminal.

[1046] Step 4:

[1047] The server converts the received voice data into text data using a speech recognition engine, for example, "Hello, everyone. Today we will discuss the sales strategy."

[1048] Step 5:

[1049] The server analyzes the text data using natural language processing (NLP) technology. This analysis includes intent analysis, sentiment analysis, and extraction of important keywords. For example, the keyword "sales strategy" is extracted.

[1050] Step 6:

[1051] The server then uses the user profile based on the analysis results to optimize the information provided. For example, for a listener whose native language is Japanese, the message "Hello, everyone. Today we will discuss the sales strategy." is converted to "Hello, everyone. Today we will talk about our sales strategy."

[1052] Step 7:

[1053] The server completes the context and provides additional explanation as needed, for example, to elaborate on the concept of "sales strategy," it might add, "A sales strategy is a plan for a company to effectively deliver its products and services to customers."

[1054] Step 8:

[1055] The server reconverts the generated optimized information into voice data using a voice synthesis engine, or formats it as text data as is.

[1056] Step 9:

[1057] The server sends the generated information to the user's terminal. In the case of audio, it is sent as an audio file, and in the case of text, it is sent as text in UTF-8 format.

[1058] Step 10:

[1059] The user terminal plays the received data as voice or displays it as text. For example, if played as voice, it sounds like "Hello everyone. Today I'm going to talk about our sales strategy."

[1060] Step 11:

[1061] The server records the user's output history and updates the user profile, which further personalizes subsequent information generation.

[1062] In this way, the system efficiently analyzes and optimizes the user's voice and text, providing information in a format that is easy for the listener to understand.

[1063] Example 1

[1064] 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."

[1065] Language differences and the need to convey complex meanings are often barriers to modern communication. Voice data must be converted into text, analyzed using natural language processing, and then provided in an optimal format. However, existing technologies struggle to achieve this in real time, which can detract from the user experience. This problem needs to be addressed, particularly in business meetings and educational settings, where rapid and accurate information transmission is crucial.

[1066] 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.

[1067] In this invention, the server includes an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the data acquired by the acquisition means, a generation means for optimizing information using a user profile based on the analysis result by the analysis means, a transmission means for transmitting the optimized information to a user terminal, and a recording means for recording the analyzed data and the optimized information and updating the user profile, thereby enabling the user to receive accurate and optimized information in real time.

[1068] The "acquisition means" is a means for acquiring voice or text data from a user.

[1069] The "analysis means" is a means for analyzing the data acquired by the acquisition means.

[1070] The "generation means" is a means for optimizing information by utilizing a user profile based on the results of analysis by the analysis means.

[1071] The "transmitting means" is a means for transmitting optimized information to a user terminal.

[1072] The "recording means" is a means for recording analyzed data and optimized information and updating a user profile.

[1073] A "voice recognition engine" is an engine for converting voice data into text data.

[1074] "Natural language processing technology" is a technology that analyzes the intent and sentiment of data and extracts important keywords.

[1075] A "generative AI model" is an AI model that adds context and additional explanation to information.

[1076] "Real-time communication technology" refers to communication technology for sending and receiving information in real time.

[1077] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[1078] System Configuration

[1079] The system consists of the following modules:

[1080] 1. Acquisition method

[1081] The user terminal receives voice or text data from the user and includes a microphone and a text input device.

[1082] The acquired audio data is saved in formats such as WAV or MP3 and temporarily stored in memory.

[1083] 2. Analysis method

[1084] The server receives the data sent from the acquisition means and converts the voice data into text data using a voice recognition engine (for example, Google Cloud Speech-to-Text).

[1085] In addition, natural language processing technologies such as Hugging Face's Transformers and SpaCy are used to analyze the intent and sentiment of the data and extract important keywords.

[1086] 3. Generation means

[1087] The server then uses the analysis results, references the user profile, and reconstructs the information in a way that is easy for the listener to understand. In particular, it uses a generative AI model to provide context and additional explanations for the information.

[1088] For example, if the input is "Hello, the weather is nice today," it will be reconstructed into "Hello, it's a sunny day. I have an important meeting today."

[1089] 4. Transmission Method

[1090] The server transmits the regenerated information to the user terminal, using real-time communication techniques (e.g., WebSocket or Push notification).

[1091] 5. Recording Method

[1092] The server records the analyzed data and generated information in a database and updates the user profile, enabling it to provide more optimal information the next time the user uses the service.

[1093] Specific examples of implementation

[1094] Example 1: Simultaneous interpretation at a business meeting

[1095] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[1096] The terminal transmits the voice data to the server.

[1097] The server converts the voice data into text data using a voice recognition engine.

[1098] The server uses natural language processing techniques to analyze the intent and key keywords of the text.

[1099] The server regenerates "Hello everyone, today we'll talk about our sales strategy" based on the user profile.

[1100] The server sends the generated text to User B's terminal.

[1101] User B's terminal displays the text and provides it to the user.

[1102] Example 2: Context completion in education

[1103] User C's (teacher's) device receives the voice message, "Integral calculation is the inverse operation of differential calculation."

[1104] The terminal transmits the voice data to the server.

[1105] The server converts the voice data into text data using a voice recognition engine.

[1106] The server uses natural language processing techniques to analyze the text and add any necessary complementary information.

[1107] The server generates a context-complete explanation: "Integration is a method for finding the area of ​​a function, and differentiation is the rate of change of that function."

[1108] The server transmits the generated text to the student terminal.

[1109] The student terminals display supplementary explanations, providing information in a format that is easy for students to understand.

[1110] Examples of prompt statements

[1111] "The system converts the voice data entered by the user into text data and generates explanatory text based on the text, adding supplementary information."

[1112] "A communication optimization system that translates English presentations used in business meetings into Japanese in real time and sends the translation to the devices of all parties involved."

[1113] In this way, this system analyzes and regenerates the user's voice and text data, providing information in a format that is easy for the listener to understand, thereby achieving effective communication.

[1114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1115] Step 1:

[1116] The user terminal receives voice or text data from the user. For example, the user may say, "Hello, the weather is nice today." The input voice data is temporarily stored in memory and saved in an appropriate format (e.g., WAV or MP3). This is the input voice data.

[1117] Step 2:

[1118] The user device compresses the acquired audio data and sends it to the specified server endpoint. For example, the audio data is sent to the server via a POST request via a REST API. The input is the acquired audio data, and the output is the data to be sent to the server. Specifically, authentication information is added to the HTTP request header, and the audio data is included in the body in binary format.

[1119] Step 3:

[1120] The server temporarily stores the received voice data and passes the data to a voice recognition engine (for example, a general voice recognition engine). The input is the voice data sent to the server, and the output is the text data obtained by voice recognition. Specifically, the server generates the text data "Hello, the weather is nice today."

[1121] Step 4:

[1122] The server passes the text data obtained from the speech recognition to a natural language processing engine (such as a general natural language processing engine). This is where intent analysis, sentiment analysis, and extraction of important keywords are performed. The input is text data generated by speech recognition, and the output is the analysis results. Specifically, the greeting "Hello" is analyzed as the intent, and "The weather is nice" is analyzed as a positive sentiment. The keywords "weather" and "good" are also extracted.

[1123] Step 5:

[1124] The server regenerates information based on the analysis results, referencing the user profile. In particular, it uses a generative AI model to add context and additional explanations. The input is the analysis results and user profile data, and the output is the regenerated information. For example, it could be reconstructed as "Hello, it's a sunny day. I have an important meeting today."

[1125] Step 6:

[1126] The server sends the regenerated text data to the specific user device. It uses real-time communication technology (for example, WebSocket or Push notification). The input is the regenerated information, and the output is the data to be sent to the user device. The server sends an HTTP response containing the new text data to the specific user device.

[1127] Step 7:

[1128] The server records the analyzed data and generated information in a database and updates the user profile. The input is the analyzed and regenerated data, and the output is the updated user profile. Specifically, the server records the usage history and saves data to provide more optimized information to the user the next time they use the service.

[1129] (Application example 1)

[1130] 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."

[1131] In food delivery, communication between users and delivery personnel is often insufficient, resulting in misunderstandings of instructions and delivery errors. While quick and accurate responses to customer inquiries are required, current systems have difficulty meeting these demands. Furthermore, there is a lack of efficient ways to optimize information from voice and text to make it easier for users to understand.

[1132] 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.

[1133] In this invention, the server includes an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the data acquired by the acquisition means, a voice recognition means for converting the voice data into text data using a voice recognition engine, a natural language processing means for analyzing the intention and emotion of the text data and extracting important keywords using natural language processing technology, a complement generation means for referencing the order history and generating complement information for the user based on the analysis results, and a transmission means for transmitting optimized information to the user terminal. This enables efficient communication by optimizing information in a form that is easy for the user to understand in response to delivery instructions or inquiries.

[1134] The "acquisition means" is a means for acquiring voice or text data from a user.

[1135] The "analysis means" is a means for analyzing the data acquired by the acquisition means.

[1136] The "voice recognition means" is a means that uses a voice recognition engine to convert voice data into text data.

[1137] The "natural language processing means" is a means for using natural language processing technology to perform intent analysis, sentiment analysis, and extraction of important keywords from text data.

[1138] The "generation means" is a means for optimizing information using a user profile based on the analysis results and reconstructing the information in a form that is easy for the user to understand.

[1139] The "complementary information generating means" refers to a means for referencing the order history and generating complementary information for the user based on the analysis results.

[1140] The "transmitting means" is a means for transmitting optimized information to a user terminal.

[1141] "User terminal" means a device used by a user, and is a general computing device that has the function of inputting and receiving voice and text data.

[1142] The present invention is a communication optimization system that analyzes voice or text data from users and converts it into a format that is easy for other users to understand. This system is specialized for food delivery services and is designed to efficiently process instructions and inquiries from users.

[1143] System configuration

[1144] The system consists of the following modules:

[1145] 1. Acquisition method

[1146] The server acquires voice or text data from a user device, such as a smartphone or tablet, using the voice input or text input function.

[1147] 2. Analysis method

[1148] The server converts the acquired voice data into text data using speech recognition technology, and then uses natural language processing technology to analyze the intent and sentiment of the text data and extract important keywords. Specifically, it uses the "Google Cloud Speech-to-Text API" and "Google Cloud Natural Language API."

[1149] 3. Generation means

[1150] Based on the analysis results, the server references the user profile and generates optimized information, supplementing it with context-appropriate information by taking into account order history and past instructions.

[1151] 4. Transmission Method

[1152] The server sends optimized information to the user terminal, enabling efficient communication.

[1153] Specific examples

[1154] Example 1: Optimizing delivery instructions

[1155] scenario:

[1156] The user may say, "Please leave the food at the entrance."

[1157] Process flow:

[1158] 1. The user's smartphone acquires the voice data and sends it to the server.

[1159] 2. The server converts the speech into text using the Google Cloud Speech-to-Text API.

[1160] 3. The server analyzes the intent of the text and important keywords using the Google Cloud Natural Language API.

[1161] 4. The server compares the order history and generates an optimized instruction: "Place the food to the right of the entrance."

[1162] 5. The server sends optimized instructions to the delivery person's smartphone, and the delivery person receives the information in an easy-to-understand format.

[1163] Example 2: Customer inquiry optimization

[1164] scenario:

[1165] A customer might ask by voice, "Does the salad I ordered come with dressing?"

[1166] Process flow:

[1167] 1. The customer's smartphone captures the voice data and sends it to the server.

[1168] 2. The server converts the speech into text using the Google Cloud Speech-to-Text API.

[1169] 3. The server analyzes the intent of the text and important keywords using the Google Cloud Natural Language API.

[1170] 4. The server references the order history, checks whether or not dressing is included, and generates the response "The salad you ordered comes with dressing."

[1171] 5. The server sends the optimized answer to the customer's smartphone, where the customer receives the information in an easily understandable format.

[1172] Prompt Sentence Examples

[1173] "Start typing. Enter instructions or questions. For example, 'Please leave my food at the door,' or 'Does the salad I ordered come with dressing?'"

[1174] Through these steps, the system can optimize communication in food delivery operations and reduce misunderstandings and errors.

[1175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1176] Step 1:

[1177] The user inputs instructions or inquiries into a device (smartphone or tablet) by voice or text.

[1178] Input: User's voice data

[1179] Output: Acquire audio data

[1180] Specific action: The user gives the voice command, "Please leave the food at the entrance."

[1181] Step 2:

[1182] The terminal transmits the acquired voice data to the server.

[1183] Input: Audio data acquired by the device

[1184] Output: Sending audio data to the server

[1185] Specific operation: Audio data is sent from the device to the server in real time.

[1186] Step 3:

[1187] The server converts the voice data into text data using a speech recognition method (e.g., Google Cloud Speech-to-Text API).

[1188] Input: Audio data

[1189] Output: Text data

[1190] Specific action: The server converts the speech into text, "Please leave the food at the entrance."

[1191] Step 4:

[1192] The server uses natural language processing means (e.g., Google Cloud Natural Language API) to analyze the intent and sentiment of the text data and extract important keywords.

[1193] Input: Text data

[1194] Output: Intention analysis results, emotion analysis results, important keywords

[1195] Specific operation: The server analyzes the intent of "Please leave it at the entrance" and extracts the important keywords "entrance" and "place."

[1196] Step 5:

[1197] The server generates optimized information using a complementary generation means based on the analysis results and the user profile.

[1198] Input: Analysis results, user profile

[1199] Output: Optimized instructions

[1200] Specific behavior: The server references the order history and completes the instruction with "Please place the food to the right of the entrance."

[1201] Step 6:

[1202] The server sends the optimized information to the delivery person's terminal.

[1203] Input: Optimized instructions

[1204] Output: Send instructions to delivery person's terminal

[1205] Specific operation: The server sends the instruction "Please place the food on the right side of the entrance" to the delivery person's smartphone.

[1206] Step 7:

[1207] The delivery person's device displays or plays back optimized instructions.

[1208] Input: Optimized instructions

[1209] Output: Display or audio for delivery personnel to understand

[1210] Specific actions: The delivery person's device will display instructions on the screen or say aloud, "Please leave the food to the right of the entrance."

[1211] Through each of the above steps, a system is built that efficiently processes instructions and inquiries from users and optimizes communication in food delivery.

[1212] 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.

[1213] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand, and further combines it with an emotion engine that recognizes the user's emotions. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[1214] System Configuration

[1215] The system consists of the following modules:

[1216] 1. Acquisition Module

[1217] The user terminal receives voice or text data from the user.

[1218] 2. Emotion Engine

[1219] The server uses an emotion engine to extract the user's emotion from the captured voice or text data, and the emotion data is provided to the analysis means.

[1220] 3. Analysis Module

[1221] The server receives the data sent from the acquisition module and the emotion data provided by the emotion engine, and in the case of voice data, converts it into text data using a voice recognition engine.

[1222] In addition, natural language processing technology is used to analyze the intent and sentiment of the data and extract important keywords.

[1223] 4. Generator Module

[1224] The server references the user profile based on the analysis results and emotional data, and reconstructs the information in a way that is easy for the listener to understand, for example, by adding contextual information and additional explanations.

[1225] 5. Transmission Module

[1226] The server transmits the generated information to the user terminal.

[1227] 6. Recording Module

[1228] The server records the user's usage history and emotion data and updates the user profile.

[1229] Specific examples of implementation

[1230] Example 1: Simultaneous interpretation at a business meeting

[1231] Consider a scenario where User A is giving a presentation in English at a business meeting. The specific process flow is as follows:

[1232] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[1233] The terminal transmits the voice data to the server.

[1234] The server converts the voice data into text data using a voice recognition engine.

[1235] The server uses natural language processing technology to analyze the intent and key keywords of the text, and uses an emotion engine to analyze the tone of the speech. For example, if User A is speaking enthusiastically, the emotion engine will detect "high enthusiasm."

[1236] Based on the user profile, the server translates "Hello, everyone. Today we will discuss the sales strategy." into "Hello, everyone. Today we will discuss our sales strategy." and reproduces it to the listener in a tone that reflects "high enthusiasm."

[1237] The server sends the generated text to User B's terminal.

[1238] User B's device displays the text or plays it back as audio. For example, if it is played back as audio, it will sound like "Hello everyone. Today I'll be talking about our sales strategy," but it will be adjusted to reflect User A's enthusiasm.

[1239] Example 2: Contextual Complement and Emotional Feedback in Educational Settings

[1240] Consider a situation where a teacher is discussing a math concept:

[1241] User C's (teacher's) device receives the voice message, "Integral calculation is the inverse operation of differential calculation."

[1242] The terminal transmits the voice data to the server.

[1243] The server converts the voice data into text data using a voice recognition engine.

[1244] The server uses natural language processing technology to analyze the text and an emotion engine to analyze the accumulated student comprehension and emotion data, for example, to detect whether a student is confused.

[1245] The server then uses the analysis results and emotion data to complete the context and provide additional explanations. The server completes the context by saying, "Integral calculation is a method for finding the area of ​​a function, and differential calculation is the rate of change of that function."

[1246] The server transmits the generated optimization information to the student terminal.

[1247] The student device displays the supplementary explanation, providing the information in a way that is easy for the student to understand, and also records feedback on whether the student has demonstrated understanding.

[1248] In this way, the system efficiently analyzes and optimizes voice and text, including the user's emotions, and provides information in a form that is easy for the listener to understand.

[1249] The processing flow will be explained below.

[1250] Example 1: Simultaneous interpretation at a business meeting

[1251] Step 1:

[1252] The terminal of user A receives the voice data from user A, "Hello, everyone. Today we will discuss the sales strategy."

[1253] Step 2:

[1254] User A's terminal transmits the acquired voice data to the server.

[1255] Step 3:

[1256] The server receives the audio data.

[1257] Step 4:

[1258] The server uses a speech recognition engine to convert the voice data into text data: "Hello, everyone. Today we will discuss the sales strategy."

[1259] Step 5:

[1260] The server uses an emotion engine to extract User A's emotion from the voice data. For example, it detects "high enthusiasm" from the tone and tempo of User A's speech.

[1261] Step 6:

[1262] The server uses natural language processing technology to analyze the text data and extract intent, sentiment, and key keywords. For example, it extracts "sales strategy" as a key keyword and also analyzes the results of the sentiment engine.

[1263] Step 7:

[1264] The server then refers to the user profile based on the analysis results and emotional data, optimizing the information. For example, it converts "Hello, everyone. Today we will discuss the sales strategy" into "Hello, everyone. Today we will discuss our sales strategy," adjusting the information to reflect the speaker's "high enthusiasm."

[1265] Step 8:

[1266] The server reconverts the optimized information into voice data using a voice synthesis engine or formats it as text data.

[1267] Step 9:

[1268] The server transmits the generated information to User B's terminal.

[1269] Step 10:

[1270] User B's device plays the received information as voice or displays it as text. For example, if it is played as voice, it will sound like "Hello everyone. Today I'll talk about our sales strategy," which reflects User A's "high enthusiasm."

[1271] Step 11:

[1272] The server records the data obtained during the analysis and generation process in the user profile and uses it for the next processing.

[1273] Example 2: Contextual Complement and Emotional Feedback in Educational Settings

[1274] Step 1:

[1275] User C's (teacher's) device receives the voice data from User C saying, "Integral calculation is the inverse operation of differential calculation."

[1276] Step 2:

[1277] User C's terminal transmits the acquired voice data to the server.

[1278] Step 3:

[1279] The server receives the audio data.

[1280] Step 4:

[1281] The server uses a speech recognition engine to convert the speech data into text data "Integral calculation is the inverse operation of differential calculation."

[1282] Step 5:

[1283] The server uses an emotion engine to extract User C's emotion from the voice data. For example, it detects a "calm tone" from User C's speaking style.

[1284] Step 6:

[1285] The server uses natural language processing technology to analyze the text data and extract intent, sentiment, and important keywords. For example, it extracts the keywords "integral calculation" and "differential calculation," and also analyzes sentiment data.

[1286] Step 7:

[1287] The server then refers to the user profile based on the analysis results and sentiment data, optimizes the information, and provides necessary contextual completion and additional explanations. For example, it adds additional information such as, "Integral calculation is a method for calculating the area of ​​a function, and differential calculation is the rate of change of that function."

[1288] Step 8:

[1289] The server reconverts the optimized information into voice data using a voice synthesis engine or formats it as text data.

[1290] Step 9:

[1291] The server transmits the generated information to the student terminal.

[1292] Step 10:

[1293] The student device will then play the received information as audio or display it as text. For example, a supplementary explanation may be displayed as text, such as, "Integration is a method for finding the area of ​​a function, and differentiation is the rate of change of that function."

[1294] Step 11:

[1295] The server records the data obtained during the analysis and generation process in a user profile for future use. It also records changes in the student's understanding and emotional feedback.

[1296] In this way, the system efficiently analyzes voice and text, including the user's emotions, and provides information in a format that is easy for the listener to understand.

[1297] Example 2

[1298] 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."

[1299] In modern communication systems, it is difficult to understand a user's intentions and emotions and provide optimal information based on them. In particular, when analyzing voice and text data, it is necessary to accurately grasp the user's emotions and intentions and reconstruct information in a form that is easy for the listener to understand. As a result, conventional systems have issues such as an insufficient user experience and reduced information transmission efficiency.

[1300] 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.

[1301] In this invention, the server includes an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the data acquired by the acquisition means, an emotion analysis means for extracting emotion data analyzed by the analysis means, a generation means for optimizing information using a user profile based on the analysis results by the analysis means, a transmission means for transmitting the optimized information to a user terminal, and a reconstructing means for reconstructing the optimized information based on the user profile. This makes it possible to accurately understand the user's intentions and emotions and generate and provide optimal information.

[1302] The "acquisition means" is a means for acquiring voice or text data from a user.

[1303] The "analysis means" is a means for analyzing the data acquired by the acquisition means.

[1304] The "emotion analysis means" is a means for extracting emotion data analyzed by the analysis means.

[1305] The "generating means" is a means for optimizing information by utilizing a user profile based on the results of the analysis by the analyzing means.

[1306] The "transmitting means" is a means for transmitting optimized information to a user terminal.

[1307] The "reconstruction means" is a means for reconstructing optimized information based on a user profile.

[1308] A "voice recognition engine" is a program or system for converting voice data into text data.

[1309] "Natural language processing technology" is a technology for analyzing the intent and emotions of text data and extracting important keywords.

[1310] A "user profile" is a database that includes each user's past usage history and setting information.

[1311] MODE FOR CARRYING OUT THE INVENTION

[1312] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand, and further combines it with an emotion engine that recognizes the user's emotions. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[1313] System Configuration

[1314] The system consists of the following modules:

[1315] 1. Acquisition method

[1316] The user terminal captures voice or text data from the user, for example, when the user says "What are your plans for tomorrow?" using a microphone subsystem or a text input field.

[1317] 2. Analysis method

[1318] The server receives the voice data sent from the user's device and converts it into text using a voice recognition engine called "SpeechToTextEngine." Examples of such engines include Google Speech-to-Text API and IBM Watson.

[1319] Furthermore, natural language processing techniques are used to analyze the intent and sentiment of the text and extract important keywords, using the natural language processing libraries "spaCy" and "NLTK."

[1320] 3. Emotion analysis method

[1321] The server passes the text data to the emotion analysis engine "EmotionAnalyzer" to extract emotional data. This engine analyzes the user's emotions (e.g., joy, sadness, surprise, etc.) from the text.

[1322] 4. Generation means

[1323] Based on the analysis results and emotion data, the server references the user profile "UserProfileDB" and reconstructs the information in a format that is easy for the listener to understand, for example by adding supplementary explanations and detailed information according to the context.

[1324] 5. Transmission Method

[1325] The server sends the generated information to the user's terminal. For example, it also provides a service that sends text information as an HTTP response and synthesizes it as voice data.

[1326] 6. Reconstruction means

[1327] The server reconstructs optimized information based on the user profile, allowing it to present information in a form that is most relevant to each individual user.

[1328] Specific examples of implementation

[1329] Example 1: Simultaneous interpretation at a business meeting

[1330] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[1331] The terminal transmits the voice data to the server.

[1332] The server converts the voice data into text data using the voice recognition engine "SpeechToTextEngine."

[1333] The server uses natural language processing technology and the emotion engine "EmotionAnalyzer" to analyze the intent and important keywords of the text and detects that User A's emotion is "high enthusiasm."

[1334] The server translates the English text based on the user profile into "Hello everyone, today I'll be talking about our sales strategy," and reproduces it in a tone that reflects high enthusiasm.

[1335] The server sends the generated Japanese text to User B's terminal.

[1336] User B's terminal displays or plays back the transmitted text as audio.

[1337] Example prompts for generative AI models:

[1338] Please translate the following English speech data into Japanese and reproduce it in a way that reflects the user's emotion of "high enthusiasm."

[1339] Audio data: "Hello, everyone. Today we will discuss the sales strategy."

[1340] Example 2: Contextual Complement and Emotional Feedback in Educational Settings

[1341] In a situation where the teacher is talking about a mathematical concept, the device of user C (teacher) receives the audio message, "Integral calculus is the inverse operation of differential calculus."

[1342] The terminal transmits the voice data to the server.

[1343] The server converts the voice data into text data using the voice recognition engine "SpeechToTextEngine."

[1344] The server uses natural language processing technology and the emotion engine "EmotionAnalyzer" to analyze text data and detect students' level of understanding and emotions.

[1345] Based on the analysis results and emotion data, the server completes the context and provides additional explanation: "Integral calculation is a method for finding the area of ​​a function, and differential calculation is the rate of change of that function."

[1346] The server transmits the generated supplementary explanation to the student terminal.

[1347] The student's device displays the supplemented explanation and also records the comprehension feedback.

[1348] Example prompts for generative AI models:

[1349] Please convert the audio data below into easy-to-understand text, and provide context and additional explanations if the student gets confused during the speech.

[1350] Audio: "Integral calculus is the inverse operation of differential calculus."

[1351] In this way, the system efficiently analyzes and optimizes voice and text, including the user's emotions, and provides information in a form that is easy for the listener to understand.

[1352] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1353] Step 1:

[1354] The user enters a message by voice or text, for example saying "What's the weather like tomorrow?"

[1355] Input: User's voice or text data.

[1356] Output: Captured audio or text data.

[1357] Step 2:

[1358] The device captures the user's voice using its internal microphone subsystem or a text input field. For example, a microphone sensor receives voice input. The captured data is kept raw.

[1359] Input: User's voice data.

[1360] Output: Audio data stored on the device.

[1361] Step 3:

[1362] The device transmits the acquired audio data to the server using an HTTP POST request. For example, the device uploads the audio data to the server in MIME format.

[1363] Input: Audio data stored on the device.

[1364] Output: The audio data sent to the server.

[1365] Step 4:

[1366] The server receives the transmitted audio data and stores it in temporary storage, making it ready to be analyzed.

[1367] Input: Audio data sent from the device.

[1368] Output: Audio data stored on the server.

[1369] Step 5:

[1370] The server converts the voice data into text data using a speech recognition engine called "SpeechToTextEngine," such as the Google Speech-to-Text API.

[1371] Input: Audio data stored on the server.

[1372] Output: The converted text data.

[1373] Step 6:

[1374] The server uses natural language processing technology (such as spaCy or NLTK) to analyze the intent and sentiment of the text data and extract important keywords. For example, from the text "What's the weather like tomorrow?", the important keyword "weather" and the sentiment "curiosity" are extracted.

[1375] Input: The converted text data.

[1376] Output: Analyzed intent data, sentiment data, and important keywords.

[1377] Step 7:

[1378] The server uses the emotion analysis engine "EmotionAnalyzer" to extract emotional data from the text data. For example, it determines that the user's emotion is "curiosity."

[1379] Input: The converted text data.

[1380] Output: Extracted emotion data.

[1381] Step 8:

[1382] The server then references the user profile (UserProfileDB) based on the analysis results and emotion data to generate the optimal answer. For example, it could reconstruct the answer as "Tomorrow's weather will be sunny" based on the profile and past data.

[1383] Input: Analyzed intent data, sentiment data, important keywords, user profile.

[1384] Output: The generated optimized information.

[1385] Step 9:

[1386] The server sends the generated information to the user terminal. For example, it may send text information as an HTTP response and provide a service to synthesize it as voice data.

[1387] Input: Optimized information.

[1388] Output: Information sent to the user's terminal.

[1389] Step 10:

[1390] The terminal receives the information sent from the server and displays it to the user, or plays it as audio using an audio playback device. For example, the terminal displays "Tomorrow's weather will be sunny" and plays it as audio.

[1391] Input: Information sent by the server.

[1392] Output: The information that is displayed to the user or played as sound.

[1393] Step 11:

[1394] The server records the user's usage history and emotional data in the "UserHistoryDB" along with the processing results data, which will be used in future processing.

[1395] Input: Optimization information, emotional data, usage history.

[1396] Output: Updated user profile, recorded historical data.

[1397] In this way, the system efficiently analyzes the user's voice and text and provides optimal information based on their emotions.

[1398] (Application example 2)

[1399] 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."

[1400] Conventional communication systems provide information without fully understanding the user's emotions and intentions, which means that users are unable to obtain the most appropriate information. Furthermore, particularly in virtual stores, the system is unable to provide appropriate product suggestions or responses based on the user's emotions, resulting in a poor purchasing experience.

[1401] 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 an acquisition means for acquiring voice or text data from the user, an analysis means for analyzing emotions and intentions, a generation means for generating optimized information, and a transmission means. This makes it possible to provide optimal responses and product suggestions according to the user's emotions.

[1402] The "acquisition means" is a function for acquiring voice or text data from the user.

[1403] The "analysis means" is a function that analyzes the data acquired by the acquisition means.

[1404] The "generation means" is a function that recognizes the user's emotions based on the results of the analysis by the analysis means and optimizes information by utilizing a user profile.

[1405] The "transmitting means" is a function that transmits optimized information to a user terminal.

[1406] A "voice recognition engine" is a system for converting voice data into text data.

[1407] "Natural language processing technology" is a technology that analyzes the intent and emotions of text data and extracts important keywords.

[1408] "Emotion recognition" is a function that extracts and analyzes emotions from a user's voice or text.

[1409] A "user profile" is a data set that includes information such as a user's behavior, preferences, and emotional history.

[1410] An embodiment of the present invention is a system that acquires voice or text data from a user, analyzes it, recognizes the user's emotions, uses a user profile to generate optimal information, and transmits it back to the user's terminal.

[1411] System Configuration

[1412] The system consists of the following modules:

[1413] 1. Acquisition method

[1414] The user terminal receives voice or text data from the user, and the terminal may be a smartphone, tablet, or PC.

[1415] 2. Analysis method

[1416] The server analyzes the acquired data. This analysis includes a speech recognition engine, natural language processing technology, and emotion recognition models. The speech recognition engine utilizes the "SpeechRecognition" library, while the natural language processing technology and emotion recognition utilize the "Transformers" library.

[1417] 3. Generation means

[1418] The server recognizes the user's emotions based on the analysis results and generates optimal responses by referencing the user profile. The generated information includes product suggestions and additional explanations based on the user's emotions and intentions.

[1419] 4. Transmission Method

[1420] The server transmits the generated information to the user terminal using Internet communication, Bluetooth, or other communication means.

[1421] Specific examples

[1422] Example 1: Virtual store application

[1423] scenario:

[1424] Consider a user searching for a "red dress" in a virtual store.

[1425] User dictation: The user dictates, "I'm looking for a red dress."

[1426] Acquisition means: The user terminal acquires the voice data and sends it to the server.

[1427] Analysis method: The server converts the voice data into text data and performs emotion recognition and intent analysis. For example, if the user is feeling stressed, the emotion label "NEGATIVE" is added.

[1428] Generation method: The server generates a response based on the emotion recognition results and the user profile: "Can I help you? What style of red dress are you looking for?"

[1429] Transmission means: The server transmits the generated response to the user terminal, and the user receives this response.

[1430] Example prompt sentence:

[1431] "What are the emotions a user feels when searching for a red dress?"

[1432] "Analyze user intent when searching for a red dress."

[1433] In this way, the system can provide optimal responses and product suggestions based on the user's emotions, improving the user experience in the virtual store and increasing their willingness to purchase.

[1434] Hardware and Software

[1435] Hardware: User devices (smartphones, tablets, PCs), servers

[1436] Software: SpeechRecognition library (speech recognition engine), Transformers library (natural language processing technology and emotion recognition model)

[1437] As described above, a specific embodiment for carrying out the present invention has been described. This system makes it possible to provide information according to the user's emotions and intentions, thereby improving the purchasing experience, particularly in virtual stores.

[1438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1439] Step 1:

[1440] The user terminal receives a voice input or a text input from the user. In the case of voice input, the voice data is recorded, and in the case of text input, the text data is directly received.

[1441] Input: User voice or text data

[1442] Output: Captured audio or text data

[1443] Step 2:

[1444] The user terminal transmits the acquired voice data or text data to the server.

[1445] Input: Captured audio or text data

[1446] Output: Audio or text data sent to the server

[1447] Step 3:

[1448] The server converts the voice data into text data using a speech recognition engine (SpeechRecognition library). If the data is text, this step is skipped.

[1449] Input: Transmitted audio data

[1450] Output: Converted text data

[1451] Step 4:

[1452] The server analyzes the emotions in the text data using an emotion recognition model (Transformers library) and recognizes the user's emotions.

[1453] Input: Converted text data

[1454] Output: Emotion label and emotion score

[1455] Step 5:

[1456] The server analyzes the intent of the text data using natural language processing technology (Transformers library) and extracts the intent of the data and important keywords.

[1457] Input: Converted text data

[1458] Output: Intent labels and important keywords

[1459] Step 6:

[1460] The server then references the user profile based on the emotion recognition and intent analysis results and generates the optimal response content, including product suggestions and additional explanations that take the user's emotions and intent into account.

[1461] Input: emotion label, emotion score, intent label, important keywords, user profile

[1462] Output: Optimized response content

[1463] Step 7:

[1464] The server transmits the generated response content to the user terminal.

[1465] Input: Optimized response content

[1466] Output: Response sent to the user's terminal

[1467] Step 8:

[1468] The user terminal presents the received response to the user. If it is to be played as audio, the text data is converted into audio data and output.

[1469] Input: Received response

[1470] Output: The response presented to the user

[1471] 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.

[1472] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1473] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1474] [Fourth embodiment]

[1475] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1476] 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.

[1477] 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).

[1478] 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.

[1479] 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.

[1480] 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).

[1481] 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.

[1482] 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.

[1483] 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.

[1484] 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.

[1485] 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.

[1486] 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.

[1487] 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."

[1488] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[1489] System Configuration

[1490] The system consists of the following modules:

[1491] 1. Acquisition Module

[1492] The user terminal receives voice or text data from the user.

[1493] 2. Analysis Module

[1494] The server receives the data sent from the acquisition module, and if it is voice data, converts it into text data using a voice recognition engine.

[1495] In addition, natural language processing technology is used to analyze the intent and sentiment of the data and extract important keywords.

[1496] 3. Generator Module

[1497] The server then refers to the user profile based on the analysis results and reconstructs the information in a way that is easy for the listener to understand, for example, by adding contextual information and additional explanations.

[1498] 4. Transmission Module

[1499] The server transmits the generated information to the user terminal.

[1500] 5. Recording Module

[1501] The server records the user's usage history and updates the user profile.

[1502] Specific examples of implementation

[1503] Example 1: Simultaneous interpretation at a business meeting

[1504] Consider a scenario where User A is giving a presentation in English at a business meeting. The specific process flow is as follows:

[1505] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[1506] The terminal transmits the voice data to the server.

[1507] The server converts the voice data into text data using a voice recognition engine.

[1508] The server uses natural language processing techniques to analyze the intent and key keywords of the text.

[1509] Based on the user profile, the server reconstructs the information in a form that is optimal for the listener (for example, a Japanese-speaking employee) and generates, "Hello everyone. Today I'll be talking about our sales strategy."

[1510] The server sends the generated text to User B's terminal.

[1511] User B's terminal displays or plays back the transmitted text as audio.

[1512] Example 2: Context completion in education

[1513] Consider a situation where a teacher is discussing a math concept:

[1514] User C's (teacher's) device receives the voice message, "Integral calculation is the inverse operation of differential calculation."

[1515] The terminal transmits the voice data to the server.

[1516] The server converts the voice data into text data using a voice recognition engine.

[1517] The server uses natural language processing techniques to analyze the text and add any necessary complementary information.

[1518] The server generates a context-complete explanation: "Integration is a method for finding the area of ​​a function, and differentiation is the rate of change of that function."

[1519] The server transmits the generated text to the student terminal.

[1520] The student terminal displays the supplementary explanation, providing information in a format that is easy for students to understand.

[1521] In this way, this system achieves effective communication by analyzing and regenerating voice and text data from the user and providing information in a form that is easy for the listener to understand.

[1522] The processing flow will be explained below.

[1523] Step 1:

[1524] The user terminal acquires voice or text data from the user. For example, consider the case where voice data such as "Hello, everyone. Today we will discuss the sales strategy" is acquired.

[1525] Step 2:

[1526] The user device transmits the acquired data to the server, ideally in real time.

[1527] Step 3:

[1528] The server receives the voice data transmitted from the user terminal.

[1529] Step 4:

[1530] The server converts the received voice data into text data using a speech recognition engine, for example, "Hello, everyone. Today we will discuss the sales strategy."

[1531] Step 5:

[1532] The server analyzes the text data using natural language processing (NLP) technology. This analysis includes intent analysis, sentiment analysis, and extraction of important keywords. For example, the keyword "sales strategy" is extracted.

[1533] Step 6:

[1534] The server then uses the user profile based on the analysis results to optimize the information provided. For example, for a listener whose native language is Japanese, the message "Hello, everyone. Today we will discuss the sales strategy." is converted to "Hello, everyone. Today we will talk about our sales strategy."

[1535] Step 7:

[1536] The server completes the context and provides additional explanation as needed, for example, to elaborate on the concept of "sales strategy," it might add, "A sales strategy is a plan for a company to effectively deliver its products and services to customers."

[1537] Step 8:

[1538] The server reconverts the generated optimized information into voice data using a voice synthesis engine, or formats it as text data as is.

[1539] Step 9:

[1540] The server sends the generated information to the user's terminal. In the case of audio, it is sent as an audio file, and in the case of text, it is sent as text in UTF-8 format.

[1541] Step 10:

[1542] The user terminal plays the received data as voice or displays it as text. For example, if played as voice, it sounds like "Hello everyone. Today I'm going to talk about our sales strategy."

[1543] Step 11:

[1544] The server records the user's output history and updates the user profile, which further personalizes subsequent information generation.

[1545] In this way, the system efficiently analyzes and optimizes the user's voice and text, providing information in a format that is easy for the listener to understand.

[1546] Example 1

[1547] 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."

[1548] Language differences and the need to convey complex meanings are often barriers to modern communication. Voice data must be converted into text, analyzed using natural language processing, and then provided in an optimal format. However, existing technologies struggle to achieve this in real time, which can detract from the user experience. This problem needs to be addressed, particularly in business meetings and educational settings, where rapid and accurate information transmission is crucial.

[1549] 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.

[1550] In this invention, the server includes an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the data acquired by the acquisition means, a generation means for optimizing information using a user profile based on the analysis result by the analysis means, a transmission means for transmitting the optimized information to a user terminal, and a recording means for recording the analyzed data and the optimized information and updating the user profile, thereby enabling the user to receive accurate and optimized information in real time.

[1551] The "acquisition means" is a means for acquiring voice or text data from a user.

[1552] The "analysis means" is a means for analyzing the data acquired by the acquisition means.

[1553] The "generation means" is a means for optimizing information by utilizing a user profile based on the results of analysis by the analysis means.

[1554] The "transmitting means" is a means for transmitting optimized information to a user terminal.

[1555] The "recording means" is a means for recording analyzed data and optimized information and updating a user profile.

[1556] A "voice recognition engine" is an engine for converting voice data into text data.

[1557] "Natural language processing technology" is a technology that analyzes the intent and sentiment of data and extracts important keywords.

[1558] A "generative AI model" is an AI model that adds context and additional explanation to information.

[1559] "Real-time communication technology" refers to communication technology for sending and receiving information in real time.

[1560] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[1561] System Configuration

[1562] The system consists of the following modules:

[1563] 1. Acquisition method

[1564] The user terminal receives voice or text data from the user and includes a microphone and a text input device.

[1565] The acquired audio data is saved in formats such as WAV or MP3 and temporarily stored in memory.

[1566] 2. Analysis method

[1567] The server receives the data sent from the acquisition means and converts the voice data into text data using a voice recognition engine (for example, Google Cloud Speech-to-Text).

[1568] In addition, natural language processing technologies such as Hugging Face's Transformers and SpaCy are used to analyze the intent and sentiment of the data and extract important keywords.

[1569] 3. Generation means

[1570] The server then uses the analysis results, references the user profile, and reconstructs the information in a way that is easy for the listener to understand. In particular, it uses a generative AI model to provide context and additional explanations for the information.

[1571] For example, if the input is "Hello, the weather is nice today," it will be reconstructed into "Hello, it's a sunny day. I have an important meeting today."

[1572] 4. Transmission Method

[1573] The server transmits the regenerated information to the user terminal, using real-time communication techniques (e.g., WebSocket or Push notification).

[1574] 5. Recording Method

[1575] The server records the analyzed data and generated information in a database and updates the user profile, enabling it to provide more optimal information the next time the user uses the service.

[1576] Specific examples of implementation

[1577] Example 1: Simultaneous interpretation at a business meeting

[1578] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[1579] The terminal transmits the voice data to the server.

[1580] The server converts the voice data into text data using a voice recognition engine.

[1581] The server uses natural language processing techniques to analyze the intent and key keywords of the text.

[1582] The server regenerates "Hello everyone, today we'll talk about our sales strategy" based on the user profile.

[1583] The server sends the generated text to User B's terminal.

[1584] User B's terminal displays the text and provides it to the user.

[1585] Example 2: Context completion in education

[1586] User C's (teacher's) device receives the voice message, "Integral calculation is the inverse operation of differential calculation."

[1587] The terminal transmits the voice data to the server.

[1588] The server converts the voice data into text data using a voice recognition engine.

[1589] The server uses natural language processing techniques to analyze the text and add any necessary complementary information.

[1590] The server generates a context-complete explanation: "Integration is a method for finding the area of ​​a function, and differentiation is the rate of change of that function."

[1591] The server transmits the generated text to the student terminal.

[1592] The student terminals display supplementary explanations, providing information in a format that is easy for students to understand.

[1593] Examples of prompt statements

[1594] "The system converts the voice data entered by the user into text data and generates explanatory text based on the text, adding supplementary information."

[1595] "A communication optimization system that translates English presentations used in business meetings into Japanese in real time and sends the translation to the devices of all parties involved."

[1596] In this way, this system analyzes and regenerates the user's voice and text data, providing information in a format that is easy for the listener to understand, thereby achieving effective communication.

[1597] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1598] Step 1:

[1599] The user terminal receives voice or text data from the user. For example, the user may say, "Hello, the weather is nice today." The input voice data is temporarily stored in memory and saved in an appropriate format (e.g., WAV or MP3). This is the input voice data.

[1600] Step 2:

[1601] The user device compresses the acquired audio data and sends it to the specified server endpoint. For example, the audio data is sent to the server via a POST request via a REST API. The input is the acquired audio data, and the output is the data to be sent to the server. Specifically, authentication information is added to the HTTP request header, and the audio data is included in the body in binary format.

[1602] Step 3:

[1603] The server temporarily stores the received voice data and passes the data to a voice recognition engine (for example, a general voice recognition engine). The input is the voice data sent to the server, and the output is the text data obtained by voice recognition. Specifically, the server generates the text data "Hello, the weather is nice today."

[1604] Step 4:

[1605] The server passes the text data obtained from the speech recognition to a natural language processing engine (such as a general natural language processing engine). This is where intent analysis, sentiment analysis, and extraction of important keywords are performed. The input is text data generated by speech recognition, and the output is the analysis results. Specifically, the greeting "Hello" is analyzed as the intent, and "The weather is nice" is analyzed as a positive sentiment. The keywords "weather" and "good" are also extracted.

[1606] Step 5:

[1607] The server regenerates information based on the analysis results, referencing the user profile. In particular, it uses a generative AI model to add context and additional explanations. The input is the analysis results and user profile data, and the output is the regenerated information. For example, it could be reconstructed as "Hello, it's a sunny day. I have an important meeting today."

[1608] Step 6:

[1609] The server sends the regenerated text data to the specific user device. It uses real-time communication technology (for example, WebSocket or Push notification). The input is the regenerated information, and the output is the data to be sent to the user device. The server sends an HTTP response containing the new text data to the specific user device.

[1610] Step 7:

[1611] The server records the analyzed data and generated information in a database and updates the user profile. The input is the analyzed and regenerated data, and the output is the updated user profile. Specifically, the server records the usage history and saves data to provide more optimized information to the user the next time they use the service.

[1612] (Application example 1)

[1613] 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."

[1614] In food delivery, communication between users and delivery personnel is often insufficient, resulting in misunderstandings of instructions and delivery errors. While quick and accurate responses to customer inquiries are required, current systems have difficulty meeting these demands. Furthermore, there is a lack of efficient ways to optimize information from voice and text to make it easier for users to understand.

[1615] 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.

[1616] In this invention, the server includes an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the data acquired by the acquisition means, a voice recognition means for converting the voice data into text data using a voice recognition engine, a natural language processing means for analyzing the intention and emotion of the text data and extracting important keywords using natural language processing technology, a complement generation means for referencing the order history and generating complement information for the user based on the analysis results, and a transmission means for transmitting optimized information to the user terminal. This enables efficient communication by optimizing information in a form that is easy for the user to understand in response to delivery instructions or inquiries.

[1617] The "acquisition means" is a means for acquiring voice or text data from a user.

[1618] The "analysis means" is a means for analyzing the data acquired by the acquisition means.

[1619] The "voice recognition means" is a means that uses a voice recognition engine to convert voice data into text data.

[1620] The "natural language processing means" is a means for using natural language processing technology to perform intent analysis, sentiment analysis, and extraction of important keywords from text data.

[1621] The "generation means" is a means for optimizing information using a user profile based on the analysis results and reconstructing the information in a form that is easy for the user to understand.

[1622] The "complementary information generating means" refers to a means for referencing the order history and generating complementary information for the user based on the analysis results.

[1623] The "transmitting means" is a means for transmitting optimized information to a user terminal.

[1624] "User terminal" means a device used by a user, and is a general computing device that has the function of inputting and receiving voice and text data.

[1625] The present invention is a communication optimization system that analyzes voice or text data from users and converts it into a format that is easy for other users to understand. This system is specialized for food delivery services and is designed to efficiently process instructions and inquiries from users.

[1626] System configuration

[1627] The system consists of the following modules:

[1628] 1. Acquisition method

[1629] The server acquires voice or text data from a user device, such as a smartphone or tablet, using the voice input or text input function.

[1630] 2. Analysis method

[1631] The server converts the acquired voice data into text data using speech recognition technology, and then uses natural language processing technology to analyze the intent and sentiment of the text data and extract important keywords. Specifically, it uses the "Google Cloud Speech-to-Text API" and "Google Cloud Natural Language API."

[1632] 3. Generation means

[1633] Based on the analysis results, the server references the user profile and generates optimized information, supplementing it with context-appropriate information by taking into account order history and past instructions.

[1634] 4. Transmission Method

[1635] The server sends optimized information to the user terminal, enabling efficient communication.

[1636] Specific examples

[1637] Example 1: Optimizing delivery instructions

[1638] scenario:

[1639] The user may say, "Please leave the food at the entrance."

[1640] Process flow:

[1641] 1. The user's smartphone acquires the voice data and sends it to the server.

[1642] 2. The server converts the speech into text using the Google Cloud Speech-to-Text API.

[1643] 3. The server analyzes the intent of the text and important keywords using the Google Cloud Natural Language API.

[1644] 4. The server compares the order history and generates an optimized instruction: "Place the food to the right of the entrance."

[1645] 5. The server sends optimized instructions to the delivery person's smartphone, and the delivery person receives the information in an easy-to-understand format.

[1646] Example 2: Customer inquiry optimization

[1647] scenario:

[1648] A customer might ask by voice, "Does the salad I ordered come with dressing?"

[1649] Process flow:

[1650] 1. The customer's smartphone captures the voice data and sends it to the server.

[1651] 2. The server converts the speech into text using the Google Cloud Speech-to-Text API.

[1652] 3. The server analyzes the intent of the text and important keywords using the Google Cloud Natural Language API.

[1653] 4. The server references the order history, checks whether or not dressing is included, and generates the response "The salad you ordered comes with dressing."

[1654] 5. The server sends the optimized answer to the customer's smartphone, where the customer receives the information in an easily understandable format.

[1655] Prompt Sentence Examples

[1656] "Start typing. Enter instructions or questions. For example, 'Please leave my food at the door,' or 'Does the salad I ordered come with dressing?'"

[1657] Through these steps, the system can optimize communication in food delivery operations and reduce misunderstandings and errors.

[1658] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1659] Step 1:

[1660] The user inputs instructions or inquiries into a device (smartphone or tablet) by voice or text.

[1661] Input: User's voice data

[1662] Output: Acquire audio data

[1663] Specific action: The user gives the voice command, "Please leave the food at the entrance."

[1664] Step 2:

[1665] The terminal transmits the acquired voice data to the server.

[1666] Input: Audio data acquired by the device

[1667] Output: Sending audio data to the server

[1668] Specific operation: Audio data is sent from the device to the server in real time.

[1669] Step 3:

[1670] The server converts the voice data into text data using a speech recognition method (e.g., Google Cloud Speech-to-Text API).

[1671] Input: Audio data

[1672] Output: Text data

[1673] Specific action: The server converts the speech into text, "Please leave the food at the entrance."

[1674] Step 4:

[1675] The server uses natural language processing means (e.g., Google Cloud Natural Language API) to analyze the intent and sentiment of the text data and extract important keywords.

[1676] Input: Text data

[1677] Output: Intention analysis results, emotion analysis results, important keywords

[1678] Specific operation: The server analyzes the intent of "Please leave it at the entrance" and extracts the important keywords "entrance" and "place."

[1679] Step 5:

[1680] The server generates optimized information using a complementary generation means based on the analysis results and the user profile.

[1681] Input: Analysis results, user profile

[1682] Output: Optimized instructions

[1683] Specific behavior: The server references the order history and completes the instruction with "Please place the food to the right of the entrance."

[1684] Step 6:

[1685] The server sends the optimized information to the delivery person's terminal.

[1686] Input: Optimized instructions

[1687] Output: Send instructions to delivery person's terminal

[1688] Specific operation: The server sends the instruction "Please place the food on the right side of the entrance" to the delivery person's smartphone.

[1689] Step 7:

[1690] The delivery person's device displays or plays back optimized instructions.

[1691] Input: Optimized instructions

[1692] Output: Display or audio for delivery personnel to understand

[1693] Specific actions: The delivery person's device will display instructions on the screen or say aloud, "Please leave the food to the right of the entrance."

[1694] Through each of the above steps, a system is built that efficiently processes instructions and inquiries from users and optimizes communication in food delivery.

[1695] 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.

[1696] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand, and further combines it with an emotion engine that recognizes the user's emotions. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[1697] System Configuration

[1698] The system consists of the following modules:

[1699] 1. Acquisition Module

[1700] The user terminal receives voice or text data from the user.

[1701] 2. Emotion Engine

[1702] The server uses an emotion engine to extract the user's emotion from the captured voice or text data, and the emotion data is provided to the analysis means.

[1703] 3. Analysis Module

[1704] The server receives the data sent from the acquisition module and the emotion data provided by the emotion engine, and in the case of voice data, converts it into text data using a voice recognition engine.

[1705] In addition, natural language processing technology is used to analyze the intent and sentiment of the data and extract important keywords.

[1706] 4. Generator Module

[1707] The server references the user profile based on the analysis results and emotional data, and reconstructs the information in a way that is easy for the listener to understand, for example, by adding contextual information and additional explanations.

[1708] 5. Transmission Module

[1709] The server transmits the generated information to the user terminal.

[1710] 6. Recording Module

[1711] The server records the user's usage history and emotion data and updates the user profile.

[1712] Specific examples of implementation

[1713] Example 1: Simultaneous interpretation at a business meeting

[1714] Consider a scenario where User A is giving a presentation in English at a business meeting. The specific process flow is as follows:

[1715] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[1716] The terminal transmits the voice data to the server.

[1717] The server converts the voice data into text data using a voice recognition engine.

[1718] The server uses natural language processing technology to analyze the intent and key keywords of the text, and uses an emotion engine to analyze the tone of the speech. For example, if User A is speaking enthusiastically, the emotion engine will detect "high enthusiasm."

[1719] Based on the user profile, the server translates "Hello, everyone. Today we will discuss the sales strategy." into "Hello, everyone. Today we will discuss our sales strategy." and reproduces it to the listener in a tone that reflects "high enthusiasm."

[1720] The server sends the generated text to User B's terminal.

[1721] User B's device displays the text or plays it back as audio. For example, if it is played back as audio, it will sound like "Hello everyone. Today I'll be talking about our sales strategy," but it will be adjusted to reflect User A's enthusiasm.

[1722] Example 2: Contextual Complement and Emotional Feedback in Educational Settings

[1723] Consider a situation where a teacher is discussing a math concept:

[1724] User C's (teacher's) device receives the voice message, "Integral calculation is the inverse operation of differential calculation."

[1725] The terminal transmits the voice data to the server.

[1726] The server converts the voice data into text data using a voice recognition engine.

[1727] The server uses natural language processing technology to analyze the text and an emotion engine to analyze the accumulated student comprehension and emotion data, for example, to detect whether a student is confused.

[1728] The server then uses the analysis results and emotion data to complete the context and provide additional explanations. The server completes the context by saying, "Integral calculation is a method for finding the area of ​​a function, and differential calculation is the rate of change of that function."

[1729] The server transmits the generated optimization information to the student terminal.

[1730] The student device displays the supplementary explanation, providing the information in a way that is easy for the student to understand, and also records feedback on whether the student has demonstrated understanding.

[1731] In this way, the system efficiently analyzes and optimizes voice and text, including the user's emotions, and provides information in a form that is easy for the listener to understand.

[1732] The processing flow will be explained below.

[1733] Example 1: Simultaneous interpretation at a business meeting

[1734] Step 1:

[1735] The terminal of user A receives the voice data from user A, "Hello, everyone. Today we will discuss the sales strategy."

[1736] Step 2:

[1737] User A's terminal transmits the acquired voice data to the server.

[1738] Step 3:

[1739] The server receives the audio data.

[1740] Step 4:

[1741] The server uses a speech recognition engine to convert the voice data into text data: "Hello, everyone. Today we will discuss the sales strategy."

[1742] Step 5:

[1743] The server uses an emotion engine to extract User A's emotion from the voice data. For example, it detects "high enthusiasm" from the tone and tempo of User A's speech.

[1744] Step 6:

[1745] The server uses natural language processing technology to analyze the text data and extract intent, sentiment, and key keywords. For example, it extracts "sales strategy" as a key keyword and also analyzes the results of the sentiment engine.

[1746] Step 7:

[1747] The server then refers to the user profile based on the analysis results and emotional data, optimizing the information. For example, it converts "Hello, everyone. Today we will discuss the sales strategy" into "Hello, everyone. Today we will discuss our sales strategy," adjusting the information to reflect the speaker's "high enthusiasm."

[1748] Step 8:

[1749] The server reconverts the optimized information into voice data using a voice synthesis engine or formats it as text data.

[1750] Step 9:

[1751] The server transmits the generated information to User B's terminal.

[1752] Step 10:

[1753] User B's device plays the received information as voice or displays it as text. For example, if it is played as voice, it will sound like "Hello everyone. Today I'll talk about our sales strategy," which reflects User A's "high enthusiasm."

[1754] Step 11:

[1755] The server records the data obtained during the analysis and generation process in the user profile and uses it for the next processing.

[1756] Example 2: Contextual Complement and Emotional Feedback in Educational Settings

[1757] Step 1:

[1758] User C's (teacher's) device receives the voice data from User C saying, "Integral calculation is the inverse operation of differential calculation."

[1759] Step 2:

[1760] User C's terminal transmits the acquired voice data to the server.

[1761] Step 3:

[1762] The server receives the audio data.

[1763] Step 4:

[1764] The server uses a speech recognition engine to convert the speech data into text data "Integral calculation is the inverse operation of differential calculation."

[1765] Step 5:

[1766] The server uses an emotion engine to extract User C's emotion from the voice data. For example, it detects a "calm tone" from User C's speaking style.

[1767] Step 6:

[1768] The server uses natural language processing technology to analyze the text data and extract intent, sentiment, and important keywords. For example, it extracts the keywords "integral calculation" and "differential calculation," and also analyzes sentiment data.

[1769] Step 7:

[1770] The server then refers to the user profile based on the analysis results and sentiment data, optimizes the information, and provides necessary contextual completion and additional explanations. For example, it adds additional information such as, "Integral calculation is a method for calculating the area of ​​a function, and differential calculation is the rate of change of that function."

[1771] Step 8:

[1772] The server reconverts the optimized information into voice data using a voice synthesis engine or formats it as text data.

[1773] Step 9:

[1774] The server transmits the generated information to the student terminal.

[1775] Step 10:

[1776] The student device will then play the received information as audio or display it as text. For example, a supplementary explanation may be displayed as text, such as, "Integration is a method for finding the area of ​​a function, and differentiation is the rate of change of that function."

[1777] Step 11:

[1778] The server records the data obtained during the analysis and generation process in a user profile for future use. It also records changes in the student's understanding and emotional feedback.

[1779] In this way, the system efficiently analyzes voice and text, including the user's emotions, and provides information in a format that is easy for the listener to understand.

[1780] Example 2

[1781] 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."

[1782] In modern communication systems, it is difficult to understand a user's intentions and emotions and provide optimal information based on them. In particular, when analyzing voice and text data, it is necessary to accurately grasp the user's emotions and intentions and reconstruct information in a form that is easy for the listener to understand. As a result, conventional systems have issues such as an insufficient user experience and reduced information transmission efficiency.

[1783] 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.

[1784] In this invention, the server includes an acquisition means for acquiring voice or text data from a user, an analysis means for analyzing the data acquired by the acquisition means, an emotion analysis means for extracting emotion data analyzed by the analysis means, a generation means for optimizing information using a user profile based on the analysis results by the analysis means, a transmission means for transmitting the optimized information to a user terminal, and a reconstructing means for reconstructing the optimized information based on the user profile. This makes it possible to accurately understand the user's intentions and emotions and generate and provide optimal information.

[1785] The "acquisition means" is a means for acquiring voice or text data from a user.

[1786] The "analysis means" is a means for analyzing the data acquired by the acquisition means.

[1787] The "emotion analysis means" is a means for extracting emotion data analyzed by the analysis means.

[1788] The "generating means" is a means for optimizing information by utilizing a user profile based on the results of the analysis by the analyzing means.

[1789] The "transmitting means" is a means for transmitting optimized information to a user terminal.

[1790] The "reconstruction means" is a means for reconstructing optimized information based on a user profile.

[1791] A "voice recognition engine" is a program or system for converting voice data into text data.

[1792] "Natural language processing technology" is a technology for analyzing the intent and emotions of text data and extracting important keywords.

[1793] A "user profile" is a database that includes each user's past usage history and setting information.

[1794] MODE FOR CARRYING OUT THE INVENTION

[1795] This invention is a communication optimization system that analyzes voice or text data from a user and converts it into a form that is easy for other users to understand, and further combines it with an emotion engine that recognizes the user's emotions. This system analyzes and generates optimized information on a server, acquiring data from the user's device, and then transmits the optimized information back to the user's device.

[1796] System Configuration

[1797] The system consists of the following modules:

[1798] 1. Acquisition method

[1799] The user terminal captures voice or text data from the user, for example, when the user says "What are your plans for tomorrow?" using a microphone subsystem or a text input field.

[1800] 2. Analysis method

[1801] The server receives the voice data sent from the user's device and converts it into text using a voice recognition engine called "SpeechToTextEngine." Examples of such engines include Google Speech-to-Text API and IBM Watson.

[1802] Furthermore, natural language processing techniques are used to analyze the intent and sentiment of the text and extract important keywords, using the natural language processing libraries "spaCy" and "NLTK."

[1803] 3. Emotion analysis method

[1804] The server passes the text data to the emotion analysis engine "EmotionAnalyzer" to extract emotional data. This engine analyzes the user's emotions (e.g., joy, sadness, surprise, etc.) from the text.

[1805] 4. Generation means

[1806] Based on the analysis results and emotion data, the server references the user profile "UserProfileDB" and reconstructs the information in a format that is easy for the listener to understand, for example by adding supplementary explanations and detailed information according to the context.

[1807] 5. Transmission Method

[1808] The server sends the generated information to the user's terminal. For example, it also provides a service that sends text information as an HTTP response and synthesizes it as voice data.

[1809] 6. Reconstruction means

[1810] The server reconstructs optimized information based on the user profile, allowing it to present information in a form that is most relevant to each individual user.

[1811] Specific examples of implementation

[1812] Example 1: Simultaneous interpretation at a business meeting

[1813] User A's terminal receives the voice message "Hello, everyone. Today we will discuss the sales strategy."

[1814] The terminal transmits the voice data to the server.

[1815] The server converts the voice data into text data using the voice recognition engine "SpeechToTextEngine."

[1816] The server uses natural language processing technology and the emotion engine "EmotionAnalyzer" to analyze the intent and important keywords of the text and detects that User A's emotion is "high enthusiasm."

[1817] The server translates the English text based on the user profile into "Hello everyone, today I'll be talking about our sales strategy," and reproduces it in a tone that reflects high enthusiasm.

[1818] The server sends the generated Japanese text to User B's terminal.

[1819] User B's terminal displays or plays back the transmitted text as audio.

[1820] Example prompts for generative AI models:

[1821] Please translate the following English speech data into Japanese and reproduce it in a way that reflects the user's emotion of "high enthusiasm."

[1822] Audio data: "Hello, everyone. Today we will discuss the sales strategy."

[1823] Example 2: Contextual Complement and Emotional Feedback in Educational Settings

[1824] In a situation where the teacher is talking about a mathematical concept, the device of user C (teacher) receives the audio message, "Integral calculus is the inverse operation of differential calculus."

[1825] The terminal transmits the voice data to the server.

[1826] The server converts the voice data into text data using the voice recognition engine "SpeechToTextEngine."

[1827] The server uses natural language processing technology and the emotion engine "EmotionAnalyzer" to analyze text data and detect students' level of understanding and emotions.

[1828] Based on the analysis results and emotion data, the server completes the context and provides additional explanation: "Integral calculation is a method for finding the area of ​​a function, and differential calculation is the rate of change of that function."

[1829] The server transmits the generated supplementary explanation to the student terminal.

[1830] The student's device displays the supplemented explanation and also records the comprehension feedback.

[1831] Example prompts for generative AI models:

[1832] Please convert the audio data below into easy-to-understand text, and provide context and additional explanations if the student gets confused during the speech.

[1833] Audio: "Integral calculus is the inverse operation of differential calculus."

[1834] In this way, the system efficiently analyzes and optimizes voice and text, including the user's emotions, and provides information in a form that is easy for the listener to understand.

[1835] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1836] Step 1:

[1837] The user enters a message by voice or text, for example saying "What's the weather like tomorrow?"

[1838] Input: User's voice or text data.

[1839] Output: Captured audio or text data.

[1840] Step 2:

[1841] The device captures the user's voice using its internal microphone subsystem or a text input field. For example, a microphone sensor receives voice input. The captured data is kept raw.

[1842] Input: User's voice data.

[1843] Output: Audio data stored on the device.

[1844] Step 3:

[1845] The device transmits the acquired audio data to the server using an HTTP POST request. For example, the device uploads the audio data to the server in MIME format.

[1846] Input: Audio data stored on the device.

[1847] Output: The audio data sent to the server.

[1848] Step 4:

[1849] The server receives the transmitted audio data and stores it in temporary storage, making it ready to be analyzed.

[1850] Input: Audio data sent from the device.

[1851] Output: Audio data stored on the server.

[1852] Step 5:

[1853] The server converts the voice data into text data using a speech recognition engine called "SpeechToTextEngine," such as the Google Speech-to-Text API.

[1854] Input: Audio data stored on the server.

[1855] Output: The converted text data.

[1856] Step 6:

[1857] The server uses natural language processing technology (such as spaCy or NLTK) to analyze the intent and sentiment of the text data and extract important keywords. For example, from the text "What's the weather like tomorrow?", the important keyword "weather" and the sentiment "curiosity" are extracted.

[1858] Input: The converted text data.

[1859] Output: Analyzed intent data, sentiment data, and important keywords.

[1860] Step 7:

[1861] The server uses the emotion analysis engine "EmotionAnalyzer" to extract emotional data from the text data. For example, it determines that the user's emotion is "curiosity."

[1862] Input: The converted text data.

[1863] Output: Extracted emotion data.

[1864] Step 8:

[1865] The server then references the user profile (UserProfileDB) based on the analysis results and emotion data to generate the optimal answer. For example, it could reconstruct the answer as "Tomorrow's weather will be sunny" based on the profile and past data.

[1866] Input: Analyzed intent data, sentiment data, important keywords, user profile.

[1867] Output: The generated optimized information.

[1868] Step 9:

[1869] The server sends the generated information to the user terminal. For example, it may send text information as an HTTP response and provide a service to synthesize it as voice data.

[1870] Input: Optimized information.

[1871] Output: Information sent to the user's terminal.

[1872] Step 10:

[1873] The terminal receives the information sent from the server and displays it to the user, or plays it as audio using an audio playback device. For example, the terminal displays "Tomorrow's weather will be sunny" and plays it as audio.

[1874] Input: Information sent by the server.

[1875] Output: The information that is displayed to the user or played as sound.

[1876] Step 11:

[1877] The server records the user's usage history and emotional data in the "UserHistoryDB" along with the processing results data, which will be used in future processing.

[1878] Input: Optimization information, emotional data, usage history.

[1879] Output: Updated user profile, recorded historical data.

[1880] In this way, the system efficiently analyzes the user's voice and text and provides optimal information based on their emotions.

[1881] (Application example 2)

[1882] 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."

[1883] Conventional communication systems provide information without fully understanding the user's emotions and intentions, which means that users are unable to obtain the most appropriate information. Furthermore, particularly in virtual stores, the system is unable to provide appropriate product suggestions or responses based on the user's emotions, resulting in a poor purchasing experience.

[1884] 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 an acquisition means for acquiring voice or text data from the user, an analysis means for analyzing emotions and intentions, a generation means for generating optimized information, and a transmission means. This makes it possible to provide optimal responses and product suggestions according to the user's emotions.

[1885] The "acquisition means" is a function for acquiring voice or text data from the user.

[1886] The "analysis means" is a function that analyzes the data acquired by the acquisition means.

[1887] The "generation means" is a function that recognizes the user's emotions based on the results of the analysis by the analysis means and optimizes information by utilizing a user profile.

[1888] The "transmitting means" is a function that transmits optimized information to a user terminal.

[1889] A "voice recognition engine" is a system for converting voice data into text data.

[1890] "Natural language processing technology" is a technology that analyzes the intent and emotions of text data and extracts important keywords.

[1891] "Emotion recognition" is a function that extracts and analyzes emotions from a user's voice or text.

[1892] A "user profile" is a data set that includes information such as a user's behavior, preferences, and emotional history.

[1893] An embodiment of the present invention is a system that acquires voice or text data from a user, analyzes it, recognizes the user's emotions, uses a user profile to generate optimal information, and transmits it back to the user's terminal.

[1894] System Configuration

[1895] The system consists of the following modules:

[1896] 1. Acquisition method

[1897] The user terminal receives voice or text data from the user, and the terminal may be a smartphone, tablet, or PC.

[1898] 2. Analysis method

[1899] The server analyzes the acquired data. This analysis includes a speech recognition engine, natural language processing technology, and emotion recognition models. The speech recognition engine utilizes the "SpeechRecognition" library, while the natural language processing technology and emotion recognition utilize the "Transformers" library.

[1900] 3. Generation means

[1901] The server recognizes the user's emotions based on the analysis results and generates optimal responses by referencing the user profile. The generated information includes product suggestions and additional explanations based on the user's emotions and intentions.

[1902] 4. Transmission Method

[1903] The server transmits the generated information to the user terminal using Internet communication, Bluetooth, or other communication means.

[1904] Specific examples

[1905] Example 1: Virtual store application

[1906] scenario:

[1907] Consider a user searching for a "red dress" in a virtual store.

[1908] User dictation: The user dictates, "I'm looking for a red dress."

[1909] Acquisition means: The user terminal acquires the voice data and sends it to the server.

[1910] Analysis method: The server converts the voice data into text data and performs emotion recognition and intent analysis. For example, if the user is feeling stressed, the emotion label "NEGATIVE" is added.

[1911] Generation method: The server generates a response based on the emotion recognition results and the user profile: "Can I help you? What style of red dress are you looking for?"

[1912] Transmission means: The server transmits the generated response to the user terminal, and the user receives this response.

[1913] Example prompt sentence:

[1914] "What are the emotions a user feels when searching for a red dress?"

[1915] "Analyze user intent when searching for a red dress."

[1916] In this way, the system can provide optimal responses and product suggestions based on the user's emotions, improving the user experience in the virtual store and increasing their willingness to purchase.

[1917] Hardware and Software

[1918] Hardware: User devices (smartphones, tablets, PCs), servers

[1919] Software: SpeechRecognition library (speech recognition engine), Transformers library (natural language processing technology and emotion recognition model)

[1920] As described above, a specific embodiment for carrying out the present invention has been described. This system makes it possible to provide information according to the user's emotions and intentions, thereby improving the purchasing experience, particularly in virtual stores.

[1921] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1922] Step 1:

[1923] The user terminal receives a voice input or a text input from the user. In the case of voice input, the voice data is recorded, and in the case of text input, the text data is directly received.

[1924] Input: User voice or text data

[1925] Output: Captured audio or text data

[1926] Step 2:

[1927] The user terminal transmits the acquired voice data or text data to the server.

[1928] Input: Captured audio or text data

[1929] Output: Audio or text data sent to the server

[1930] Step 3:

[1931] The server converts the voice data into text data using a speech recognition engine (SpeechRecognition library). If the data is text, this step is skipped.

[1932] Input: Transmitted audio data

[1933] Output: Converted text data

[1934] Step 4:

[1935] The server analyzes the emotions in the text data using an emotion recognition model (Transformers library) and recognizes the user's emotions.

[1936] Input: Converted text data

[1937] Output: Emotion label and emotion score

[1938] Step 5:

[1939] The server analyzes the intent of the text data using natural language processing technology (Transformers library) and extracts the intent of the data and important keywords.

[1940] Input: Converted text data

[1941] Output: Intent labels and important keywords

[1942] Step 6:

[1943] The server then references the user profile based on the emotion recognition and intent analysis results and generates the optimal response content, including product suggestions and additional explanations that take the user's emotions and intent into account.

[1944] Input: emotion label, emotion score, intent label, important keywords, user profile

[1945] Output: Optimized response content

[1946] Step 7:

[1947] The server transmits the generated response content to the user terminal.

[1948] Input: Optimized response content

[1949] Output: Response sent to the user's terminal

[1950] Step 8:

[1951] The user terminal presents the received response to the user. If it is to be played as audio, the text data is converted into audio data and output.

[1952] Input: Received response

[1953] Output: The response presented to the user

[1954] 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.

[1955] 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.

[1956] 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.

[1957] 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.

[1958] 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.

[1959] 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.

[1960] 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).

[1961] 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.

[1962] 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."

[1963] 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.

[1964] 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).

[1965] 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.

[1966] 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.

[1967] 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.

[1968] 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.

[1969] 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.

[1970] 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.

[1971] 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.

[1972] 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.

[1973] 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.

[1974] 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.

[1975] The following is further disclosed regarding the above embodiment.

[1976] (Claim 1)

[1977] an acquisition means for acquiring voice or text data from a user;

[1978] analysis means for analyzing the data acquired by the acquisition means;

[1979] a generating means for optimizing information by utilizing a user profile based on the results of the analysis by the analyzing means;

[1980] a transmitting means for transmitting the optimized information to a user terminal;

[1981] A system including:

[1982] (Claim 2)

[1983] 2. The system according to claim 1, wherein the analyzing means converts the voice data into text data using a voice recognition engine.

[1984] (Claim 3)

[1985] 2. The system according to claim 1, wherein the analysis means uses natural language processing technology to perform intent analysis, sentiment analysis, and extraction of important keywords from the data.

[1986] (Claim 4)

[1987] 10. The system of claim 1, wherein the generating means complements the context and provides additional explanation.

[1988] (Claim 5)

[1989] 10. The system of claim 1, further comprising a recording means for building and updating a user profile.

[1990] "Example 1"

[1991] (Claim 1)

[1992] an acquisition means for acquiring voice or text data from a user;

[1993] analysis means for analyzing the data acquired by the acquisition means;

[1994] a generating means for optimizing information by utilizing a user profile based on the results of the analysis by the analyzing means;

[1995] a transmitting means for transmitting the optimized information to a user terminal;

[1996] a recording means for recording the analyzed data and optimized information and updating a user profile;

[1997] A system including:

[1998] (Claim 2)

[1999] 2. The system according to claim 1, wherein the analyzing means converts the voice data into text data using a voice recognition engine.

[2000] (Claim 3)

[2001] 2. The system according to claim 1, wherein the analysis means uses natural language processing technology to perform intent analysis, sentiment analysis, and extraction of important keywords from the data.

[2002] (Claim 4)

[2003] The system of claim 1, wherein the generating means uses a generative AI model to provide contextual complement and additional explanation to the information.

[2004] (Claim 5)

[2005] 2. The system of claim 1, wherein the transmitting means transmits the optimized information to the user terminal using real-time communication technology.

[2006] "Application Example 1"

[2007] (Claim 1)

[2008] an acquisition means for acquiring voice or text data from a user;

[2009] analysis means for analyzing the data acquired by the acquisition means;

[2010] a generating means for optimizing information by utilizing a user profile based on the results of the analysis by the analyzing means;

[2011] a transmitting means for transmitting the optimized information to a user terminal;

[2012] a speech recognition means for converting speech data into text data using a speech recognition engine;

[2013] natural language processing means for analyzing intent and sentiment of text data and extracting important keywords using natural language processing technology;

[2014] a complementary information generating means for generating complementary information for a user based on an analysis result by referring to an order history;

[2015] A system including:

[2016] (Claim 2)

[2017] 2. The system according to claim 1, wherein the analyzing means converts the voice data into text data using a voice recognition engine.

[2018] (Claim 3)

[2019] 2. The system according to claim 1, wherein the analysis means uses natural language processing technology to perform intent analysis, sentiment analysis, and extraction of important keywords from the data.

[2020] (Claim 4)

[2021] The system according to claim 1, characterized in that the analysis means analyzes voice and text data related to food delivery from users and generates optimized delivery instructions and responses to inquiries.

[2022] "Example 2: Combining Emotion Engines"

[2023] (Claim 1)

[2024] an acquisition means for acquiring voice or text data from a user;

[2025] analysis means for analyzing the data acquired by the acquisition means;

[2026] emotion analysis means for extracting emotion data analyzed by the analysis means;

[2027] a generating means for optimizing information by utilizing a user profile based on the results of the analysis by the analyzing means;

[2028] a transmitting means for transmitting the optimized information to a user terminal;

[2029] means for reconstructing the optimized information based on a user profile;

[2030] A system including:

[2031] (Claim 2)

[2032] 2. The system according to claim 1, wherein the analyzing means converts the voice data into text data using a voice recognition engine.

[2033] (Claim 3)

[2034] 2. The system according to claim 1, wherein the analysis means uses natural language processing technology to perform intent analysis, sentiment analysis, and extraction of important keywords from the data.

[2035] "Application example 2 when combining emotion engines"

[2036] (Claim 1)

[2037] an acquisition means for acquiring voice or text data from a user;

[2038] analysis means for analyzing the data acquired by the acquisition means;

[2039] a generating means for recognizing a user's emotion based on the result of the analysis by the analyzing means and optimizing information by utilizing a user profile;

[2040] a transmitting means for transmitting the optimized information to a user terminal;

[2041] A system including:

[2042] (Claim 2)

[2043] 2. The system according to claim 1, wherein the analyzing means converts the voice data into text data using a voice recognition engine.

[2044] (Claim 3)

[2045] The system according to claim 1, characterized in that the analysis means uses natural language processing technology to perform intent analysis, sentiment analysis, and extraction of important keywords in the data, and the generation means generates response content. [Explanation of symbols]

[2046] 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. an acquisition means for acquiring voice or text data from a user; analysis means for analyzing the data acquired by the acquisition means; a generating means for optimizing information by utilizing a user profile based on the results of the analysis by the analyzing means; a transmitting means for transmitting the optimized information to a user terminal; A system including:

2. 2. The system according to claim 1, wherein the analyzing means converts the voice data into text data using a voice recognition engine.

3. 2. The system according to claim 1, wherein the analysis means uses natural language processing technology to perform intent analysis, sentiment analysis, and extraction of important keywords from the data.

4. 10. The system of claim 1, wherein the generating means completes the context and provides additional explanation.

5. 2. The system of claim 1, further comprising: recording means for building and updating a user profile.

Images