System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving voice data 24 hours 365 days; means for converting the received voice data into text data; means for storing the converted text data together with a time stamp; means for analyzing the stored text data and extracting an important keyword or task; means for searching for text data related to a question of a user and generating an answer; means for providing the generated answer to the user by voice; and means for notifying the user of necessary remind information.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] When it comes to conversations and information sharing within the home, people often have difficulty accurately remembering and instantly recalling small details and past events. It takes time and effort to organize information, especially shopping lists, schedules, and the causes of arguments. Conventional smart speakers are unable to effectively share detailed information or provide reminders, and therefore do not adequately support communication within the home. [Means for solving the problem]

[0005] This invention is a system that records conversations within a household in real time and uses this information to organize and provide necessary information using a generation AI. Specifically, it includes a means for receiving voice data 24 hours a day, 365 days a year, a means for converting the received voice data into text data, a means for saving the converted text data with a timestamp, a means for analyzing the saved text data and extracting important keywords and tasks, a means for searching text data related to a user's question and generating an answer, a means for providing the generated answer to the user by voice, and a means for notifying the user of necessary reminders. This facilitates information sharing within the household and enables quick resolution of minor questions and forgotten information in daily life.

[0006] "Audio data" refers to data that is generated by digitizing an audio signal and expressing it as digital information.

[0007] The "receiving means" is a device or function that acquires audio data and takes it into the system.

[0008] "Means for converting into text data" refers to a device or function that analyzes voice data and converts it into text information.

[0009] A "timestamp" is digital information that indicates the specific date and time that data was generated or acquired.

[0010] An "analyzing means" is a device or function that analyzes text data and extracts important information and patterns.

[0011] "Keywords" are key words or phrases that indicate specific information in text data.

[0012] A "task" is a specific task or plan that a user needs to perform.

[0013] A "searching means" is a device or function that locates relevant information within a stored database.

[0014] An "answer generating means" is a device or function that generates an appropriate response to a user's question based on the search results.

[0015] The "means for providing" is a device or function that presents the generated answers and information to the user.

[0016] "Reminder information" is information that notifies or calls attention to encourage the user to take a specific action.

[0017] The "notification means" is a device or function that transmits reminder information to the user. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The system of the present invention records conversations within the home in real time, organizes necessary information, provides answers, and provides reminder functions. The system effectively supports information sharing within the home through the following functions: receiving and analyzing voice data, storing and searching text data, providing real-time answers to user questions, and sending reminder notifications.

[0040] Receiving and converting audio data

[0041] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. The received voice data is sent to a server in real time and converted into text data using voice recognition technology. For example, a user's statement, "What's for dinner tonight?" is received as voice data and converted into text data.

[0042] Analyzing and storing text data

[0043] The server analyzes the converted text data and extracts important keywords and tasks. Natural language processing technology is used for this analysis. The extracted keywords and tasks are organized by category and saved in a database with a timestamp. For example, a statement such as "I need to buy eggs and milk" is classified as a shopping list and saved in the database.

[0044] Real-time answers to user questions

[0045] When a user asks, "What did we have for dinner last night?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text and searches a database for related past conversation data. For example, if someone says something about dinner last night, the device generates an answer based on that information, such as "We had curry rice for dinner last night," and provides it to the user via the device.

[0046] Reminder function

[0047] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. For example, if a user says, "Don't forget to take out the trash tomorrow morning," the server prepares to notify the user of that information the next morning. At the specified time, the device will notify the user by voice, "Don't forget to take out the trash."

[0048] Specific examples

[0049] As a concrete example, consider the following usage scenario:

[0050] 1. A user says, "I need to buy eggs and milk tomorrow morning."

[0051] 2. The device receives this audio and sends it to the server.

[0052] 3. The server converts the speech into text, analyzes it, and stores it in a database.

[0053] 4. The next morning, the server retrieves the reminder information from the database and sends a voice notification to the terminal saying, "Don't forget to buy eggs and milk."

[0054] In this way, the system of the present invention provides innovative support for information management within the home by using real-time reception and text conversion of voice data, data analysis and storage, real-time answers to user questions, and reminder notification functions.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] A user says, "I need to buy eggs and milk tomorrow morning."

[0058] Step 2:

[0059] The device receives the user's speech through the microphone, captures it as audio data, and temporarily stores it in a buffer.

[0060] Step 3:

[0061] The terminal packetizes the voice data stored in the buffer and transmits it to the server in real time.

[0062] Step 4:

[0063] The server converts the received voice data into text data using a voice recognition API.

[0064] Step 5:

[0065] The server analyzes the converted text data and extracts important keywords and tasks, such as buying "eggs" and "milk."

[0066] Step 6:

[0067] The server organizes the extracted keywords and tasks into categories and stores them in a database along with timestamps.

[0068] Step 7:

[0069] The next morning, the server periodically checks the stored database for reminder information.

[0070] Step 8:

[0071] The server extracts the relevant reminder information and identifies the task that needs to be reminded at the moment. In this case, "buy eggs and milk" is extracted as an important task.

[0072] Step 9:

[0073] The server generates a message based on the extracted reminder information and sends it to the terminal.

[0074] Step 10:

[0075] The terminal receives the sent reminder information and issues a voice message to the user saying "Don't forget to buy eggs and milk" at the specified time.

[0076] Step 11:

[0077] The user receives a reminder message and performs the specified task.

[0078] In this way, the system of the present invention supports information management in daily life by recording user comments in real time, analyzing and saving necessary information, and sending reminders at appropriate times.

[0079] Example 1

[0080] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0081] In modern homes, a large amount of information is exchanged on a daily basis, and there is a need to efficiently manage this information and provide necessary information in a timely manner. However, conventional systems have had difficulty recording, organizing, and searching household conversation information in real time, and providing immediate answers to user questions. In particular, problems arise with missing information within the home, such as sudden reminder notifications and confirmation of important tasks. This invention aims to solve these problems.

[0082] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0083] In this invention, the server includes means for converting voice data into text data in real time using voice recognition technology, means for analyzing the text data and extracting important keywords and tasks using natural language processing technology, means for storing and searching the text data organized by category in a database, and means for notifying users of reminder information by voice at specified times. This allows for efficient information management within the home, enabling quick answers to users' questions and timely reminder notifications.

[0084] "Audio data" refers to digital data such as human speech and environmental sounds collected via a voice input device such as a microphone.

[0085] "Text data" is character string data that is expressed as text by analyzing voice data using voice recognition technology.

[0086] A "timestamp" is information indicating the date and time when data was generated, and is a time marker that is saved together with the text data.

[0087] "Natural language processing technology" is a computer technology that analyzes text data to understand meaning and extract keywords.

[0088] A "database" is a digital recording system that allows for the systematic accumulation, management, and retrieval of text data and related information.

[0089] "Reminder information" is information for notifying the user at a specific time about a task or event that the user has set in advance.

[0090] "Answer generation" is a process of searching for information related to a user's question and creating an appropriate response based on that information.

[0091] "Real-time" refers to a situation in which processing or response occurs immediately without delay.

[0092] The system of the present invention is designed to record conversations within the home in real time, organize necessary information, provide answers, and provide reminder functions. Specific embodiments will be described below.

[0093] The system of the present invention is composed of a terminal installed in the home and a server installed on the cloud or in the home.

[0094] Receiving and converting audio data

[0095] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. The device's built-in microphone captures the user's speech and environmental sounds. For example, if a user says, "I have to take out the trash tomorrow," the voice data is recorded on the device via the microphone.

[0096] The received voice data is sent in real time to the server, which then uses voice recognition technology (e.g., Google Cloud Speech-to-Text API) to convert the voice data into text data.

[0097] Analyzing and storing text data

[0098] The server analyzes the converted text data and uses natural language processing technology (e.g., SpaCy) to extract important keywords and tasks. The analyzed text data is organized by category and stored in a database (e.g., MySQL) with a timestamp.

[0099] For example, if a user says, "I need to buy eggs and milk," this will be classified as a shopping list category and stored in the database.

[0100] Real-time answers to user questions

[0101] When a user asks, "What did we have for dinner last night?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text and searches a database for relevant past conversation data. For example, if someone says something about dinner last night, the device generates an answer based on that information, such as "We had curry rice for dinner last night," and provides it to the user via the device.

[0102] Reminder function

[0103] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. For example, if a user says, "Don't forget to take out the trash tomorrow morning," the server prepares to notify the user of that information the next morning. At the specified time, the device will notify the user by voice, "Don't forget to take out the trash."

[0104] Specific examples

[0105] As a concrete example, consider the following usage scenario:

[0106] 1. A user says, "I need to buy eggs and milk tomorrow morning."

[0107] 2. The device receives this audio and sends it to the server.

[0108] 3. The server converts the speech into text, analyzes it, and stores it in a database.

[0109] 4. The next morning, the server retrieves the reminder information from the database and sends a voice notification to the terminal saying, "Don't forget to buy eggs and milk."

[0110] In this way, the system of the present invention effectively supports information management within the home through real-time reception and text conversion of voice data, data analysis and storage, real-time answers to user questions, and reminder notification functions.

[0111] Prompt Sentence Examples

[0112] You can see how the system works by inputting prompts like the following into the generative AI model:

[0113] "Tell me what you had for dinner last night."

[0114] "Do you have any reminders set for tomorrow?"

[0115] "What items have you added to your shopping list this week?"

[0116] This makes it easy to check that the system is working as expected.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1: Receiving audio data

[0119] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. It captures what the user says (input) and converts that voice data into a digital format in real time (output). For example, a microphone might capture someone saying, "I have to take out the trash tomorrow."

[0120] Specific behavior:

[0121] A microphone captures the user's voice.

[0122] The captured audio data is converted into a digital format within the device.

[0123] Step 2: Sending audio data

[0124] The device sends the received voice data to the server. The digital voice data (input) is transferred to the server via the Internet (output).

[0125] Specific behavior:

[0126] The terminal breaks down the voice data into packets and sends them to a server over the Internet.

[0127] The server receives the transmitted packets and reconstructs the audio data.

[0128] Step 3: Convert the audio data

[0129] The server converts the received voice data into text data using voice recognition technology. The voice data (input) is analyzed and converted into character string data (output).

[0130] Specific behavior:

[0131] The server performs voice analysis using voice recognition technology (e.g., Google Cloud Speech-to-Text API).

[0132] The analyzed voice data is output as text data.

[0133] Step 4: Analyzing the text data

[0134] The server analyzes the converted text data and extracts important keywords and tasks. The text data (input) is analyzed using natural language processing technology (e.g., SpaCy), and the extracted keywords and tasks (output) are stored in a database.

[0135] Specific behavior:

[0136] The server uses natural language processing technology to perform semantic analysis of the text data.

[0137] Important keywords (e.g., taking out the trash) are extracted.

[0138] The extracted keywords are organized into categories (e.g., housework reminders) and stored in a database.

[0139] Step 5: Generate answers to user questions

[0140] When a user asks, "What did I have for dinner last night?", the device receives the question as voice data (input) and sends it to the server, which converts the voice data into text, searches past conversation data, and generates a relevant answer (output).

[0141] Specific behavior:

[0142] The terminal transmits the voice data to the server.

[0143] The server converts the speech into text and searches the database.

[0144] Based on the search results, the answer "I had curry rice for dinner last night" is generated and sent to the device.

[0145] The terminal generates a response and provides it to the user as a voice.

[0146] Step 6: Execute the reminder function

[0147] The server periodically checks the saved keywords and tasks, extracts information that requires reminders, and generates notifications at specific times based on the information (input) and sends them to the device (output).

[0148] Specific behavior:

[0149] The server runs a scheduled job to check the stored data.

[0150] Reminder information is extracted and notification content is generated.

[0151] At the specified time, the server transmits the notification data to the terminal.

[0152] The device will notify you with a voice message saying, "Don't forget to take out the trash."

[0153] (Application example 1)

[0154] 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."

[0155] Communication between store clerks and customers in brick-and-mortar stores must be accurate and efficient. However, in reality, it is difficult for store clerks to accurately remember past conversations or to provide appropriate responses quickly. Furthermore, they tend to forget specific work tasks, which reduces work efficiency. To solve these problems, a system is needed that can record and analyze conversations between store clerks and customers in real time.

[0156] 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.

[0157] In this invention, the server includes means for receiving voice data 24 hours a day, 365 days a year, means for converting the received voice data into text data, means for saving the converted text data together with a timestamp, means for analyzing the saved text data and extracting important keywords and tasks, means for searching for text data related to a user's question and generating an answer, means for providing the generated answer to the user by voice, means for notifying the user of necessary reminder information, means for recording and analyzing conversations between a store clerk and a customer in real time, means for generating an appropriate answer based on past conversation data and providing it to the store clerk, and means for sending reminder notifications for specific tasks. This allows the store clerk to provide an appropriate answer based on past conversation data and receive reminders for specific work tasks.

[0158] "Audio data" refers to data that represents an audio signal in digital or analog form.

[0159] "Text data" refers to digital data expressed as character string information.

[0160] A "timestamp" is date and time information recorded for specific data.

[0161] A "server" is a computer system that processes and stores data over a network.

[0162] "Important keywords" are words or phrases that deserve special attention within the text data being analyzed.

[0163] A "task" is a task or action to achieve a specific purpose.

[0164] "User" means a person or individual who uses the System.

[0165] "Reminder information" refers to information that notifies or alerts the user to specific tasks or matters.

[0166] A "means" is a method or apparatus for achieving a particular function.

[0167] A "store associate" is an employee who provides services to customers in a physical store.

[0168] A "customer" is a person who visits a physical store and uses a product or service.

[0169] "Conversation data" refers to the content of a conversation that is recorded as voice data and analyzed.

[0170] "Real-time recording" means that there is little time delay and the audio data is recorded at the exact moment the conversation occurs.

[0171] "Means of analysis" refers to techniques and methods for analyzing the content of data and extracting meaning.

[0172] A "means for generating an answer" is a method or device for automatically generating an appropriate response from the analyzed data.

[0173] A "reminder notification" is a notification that notifies the user not to forget specific information or tasks.

[0174] The system for implementing the present invention includes a voice receiving terminal installed in a physical store, a server that performs text conversion and data analysis, a database, and a device that performs notifications.

[0175] 1. Receiving and converting audio data

[0176] The terminal is installed in the store and receives conversations between store staff and customers 24 hours a day, 365 days a year. This records all interactions within the store. The received voice data is sent to a server in real time and converted into text data using a speech recognition engine (e.g., TensorFlow or PyTorch).

[0177] 2. Analyzing and saving text data

[0178] The converted text data is then analyzed by the server. Natural language processing technology is used in this analysis to extract important keywords and tasks. The extracted keywords and tasks are then stored in a database with a timestamp using Elasticsearch. For example, if someone says, "Update sale information at 3 p.m.", it is organized and saved in the appropriate category.

[0179] 3. Real-time answers to user questions

[0180] When a store clerk asks through smart glasses or a smartphone, "What was the special sale information yesterday?", the server converts this voice data into text and uses Elasticsearch to search for related past conversation data. If a conversation about special sales information has been recorded in the past, the server generates an answer such as "Yesterday's special sale item was drinking water," and displays this information on the smart glasses or smartphone.

[0181] 4. Reminder function

[0182] The server periodically checks the saved keywords and tasks and extracts information that requires a reminder. For example, if the information is "We need to organize the shelves in preparation for tomorrow's opening," it will send a notification to the store clerk's smartphone at the specified time saying, "Please organize the shelves."

[0183] Specific examples

[0184] For example, consider the following usage scenario:

[0185] 1. A store clerk says, "We need to update the sale information at 3:00 PM."

[0186] 2. The device receives this audio and sends it to the server.

[0187] 3. The server converts the speech into text, analyzes it, and stores it in a database.

[0188] 4. At 3:00 p.m., the server retrieves the reminder information from the database and sends a voice notification to the terminal saying, "Please update your sale information."

[0189] Prompt Sentence Examples

[0190] Example: "What products were on sale yesterday?"

[0191] Sample answer: "There was a sale on drinking water yesterday."

[0192] The system of the present invention enables accurate and efficient communication between store staff and customers in physical stores, thereby improving business efficiency.

[0193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0194] Step 1: Receiving audio data

[0195] The terminal is installed in the store and receives conversations between store staff and customers 24 hours a day, 365 days a year. The input is voice data, which the terminal receives in real time. The output is the voice data itself.

[0196] Step 2: Send and convert audio data

[0197] The device sends the received voice data to the server in real time. The server uses a speech recognition engine (e.g., TensorFlow or PyTorch) to convert the voice data into text data. The input is voice data, and the output is text data.

[0198] Step 3: Analyze and save the text data

[0199] The server analyzes the converted text data using natural language processing technology, extracts important keywords and tasks, and stores them in a database with a timestamp using Elasticsearch. The input is text data, and the data that is analyzed and classified is output. A timestamp is added to the stored data.

[0200] Step 4: Generate answers to user questions

[0201] A store clerk asks a question through smart glasses or a smartphone. The question is received as voice data and sent to a server. The server converts the voice to text and uses Elasticsearch to search relevant past conversation data. The input is the voice data (question) and the output is the search results. The server generates an appropriate answer and displays it on the smart glasses or smartphone.

[0202] Step 5: Execute the reminder function

[0203] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. At the specified time, a reminder notification is sent to the terminal or the store clerk's smartphone. The input is the task information saved in the database, and the output is the reminder notification. The notification is displayed on the smart glasses or smartphone.

[0204] Step 6: Providing responses and notifications

[0205] The server generates answers and provides them to the smart glasses or smartphone as text or voice, as well as reminder notifications. The input is the generated answers or reminder information, and the output is a notification message for the user.

[0206] As described above, the system of the present invention executes each step in a step-by-step manner, from receiving voice data to converting it into text, analyzing it, saving it, and then sending reminders and providing appropriate responses. This allows for accurate recording and analysis of communications between store staff and customers in physical stores, enabling efficient responses.

[0207] 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.

[0208] This invention is a system that records conversations within the home in real time and recognizes the user's emotions, thereby enabling more effective information organization, answer provision, and reminder functions.In addition to receiving and converting voice data, saving and analyzing text data, providing answers to user questions, and sending reminder notifications, the invention incorporates an emotion recognition engine, making it possible to respond based on the user's emotions.

[0209] Receiving and converting audio data

[0210] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. The received voice data is sent to a server in real time and converted into text data using voice recognition technology. For example, a user's statement such as "I need to buy eggs and milk tomorrow morning" is received as voice data and converted into text data.

[0211] Analyzing and storing text data

[0212] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing technology. The extracted keywords and tasks are organized by category and saved in a database with a timestamp. For example, "eggs" and "milk" are added to the "shopping" category.

[0213] emotion recognition

[0214] The server is equipped with an emotion engine that recognizes the user's emotions from the voice data. For example, it can infer the user's stress level from a statement such as "I have a meeting tomorrow, so I'm feeling stressed." This information is saved along with the text data and used to adjust future task priorities and response content.

[0215] Real-time answers to user questions

[0216] When a user asks, "What did you have for dinner last night?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text and searches a database for related past conversation data. For example, if the comment about last night's dinner was "curry rice," the device generates the answer "We had curry rice for dinner last night" and provides it to the user via the device. It is also possible to adjust the tone and content of the answer based on emotion recognition information.

[0217] Reminder function

[0218] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. For example, if a task is set to "buy eggs and milk tomorrow morning," the server prepares to notify the user of that information the following morning. At the specified time, the device will notify the user with a voice message saying, "Don't forget to buy eggs and milk." If the user is under stress, the server will also adjust the tone of the notification to be softer.

[0219] Specific examples

[0220] As a concrete example, consider the following usage scenario:

[0221] 1. A user says, "I need to buy eggs and milk tomorrow morning."

[0222] 2. The device receives this audio and sends it to the server.

[0223] 3. The server converts the voice data into text, analyzes it, and stores it in a database.

[0224] 4. The server uses the emotion engine to recognize the user's emotion as "a little tired."

[0225] 5. The next morning, the server retrieves the reminder information from the database and generates a notification message in a soft tone, taking into account your emotional state, saying, "Don't forget to buy eggs and milk."

[0226] 6. The device will notify the user by voice, "Don't forget to buy eggs and milk."

[0227] In this way, the system of the present invention provides information management and support functions that take into account the user's emotions, thereby realizing higher quality communication and information management within the home.

[0228] The processing flow will be explained below.

[0229] Step 1:

[0230] A user says, "I need to buy eggs and milk tomorrow morning."

[0231] Step 2:

[0232] The device receives the user's speech through a microphone and captures it as voice data.

[0233] Step 3:

[0234] The device transmits the audio data to the server in real time.

[0235] Step 4:

[0236] The server converts the voice data into text data using a voice recognition API.

[0237] Step 5:

[0238] The server analyzes the text data and extracts the important keywords "egg" and "milk."

[0239] Step 6:

[0240] The server uses an emotion engine to analyze the user's emotions from the voice data and recognizes that the user is "feeling a little stressed."

[0241] Step 7:

[0242] The server organizes the extracted keywords and emotion data by category and stores them in a database along with a timestamp.

[0243] Step 8:

[0244] The next morning, the server periodically checks the stored database and extracts the information that needs to be reminded: "Buy eggs and milk."

[0245] Step 9:

[0246] The server takes emotion data into consideration when generating a notification message, where the tone is softened based on the emotion data.

[0247] Step 10:

[0248] The server sends the generated remind message to the terminal.

[0249] Step 11:

[0250] The device will then play a soft voice reminder message to the user saying, "Don't forget to buy eggs and milk."

[0251] Step 12:

[0252] The user receives a reminder message and performs the specified task.

[0253] Example 2

[0254] 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."

[0255] There is a demand for systems to effectively record and organize conversations within the home and provide necessary information in a timely manner. They are also expected to improve the user experience by understanding the user's emotions and responding accordingly. However, current systems lack sufficient functionality to meet these requirements, resulting in suboptimal information management and communication within the home. In particular, they lack the ability to recognize the user's emotions and provide information or reminders based on them.

[0256] 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.

[0257] In this invention, the server includes a means for converting voice data into text data, a means for analyzing text using natural language processing technology, and a means for recognizing emotions and saving them as data. By converting and analyzing voice data into text data and recognizing and saving emotions, the server can organize and provide information according to user needs. Furthermore, the content and tone of responses and reminders can be adjusted based on the user's emotions, enabling higher-quality information management and a better user experience.

[0258] "Audio data" is a recording of sounds, including the user's speech, captured within the home.

[0259] "Text data" is information obtained by converting voice data into a character string format.

[0260] A "timestamp" is information about the exact date and time when data was created or modified.

[0261] "Keywords" are important words or phrases extracted during text data analysis.

[0262] "Tasks" are user action plans or things to do that are derived from keywords.

[0263] "Emotion recognition" is a technology that determines a user's emotional state from voice data and text data.

[0264] "Natural language processing technology" is a set of computer technologies for analyzing, understanding, and generating human language.

[0265] A "database" is a system that systematically stores and manages text data and related information.

[0266] A "remind" is a notification that prompts the user to reconfirm a specific piece of information or task.

[0267] "Answer generation" is the process of providing appropriate information in response to a user's question.

[0268] This invention is a system that records conversations within the home in real time and recognizes the user's emotions to effectively organize information, provide answers, and provide reminder functions.In addition to receiving and converting voice data, saving and analyzing text data, providing answers to user questions, and sending reminder notifications, the system incorporates an emotion recognition engine, making it possible to respond based on the user's emotions.

[0269] Receiving and converting audio data

[0270] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. A voice recognition device (e.g., a smart speaker with a microphone) is used to receive the voice data. The received voice data is sent to a server in real time and converted into text data using voice recognition software (e.g., a voice recognition API). For example, if a user says, "I need to buy eggs and milk tomorrow morning," this voice data is sent from the device to the server in real time and converted into text data.

[0271] Analyzing and storing text data

[0272] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing technology (e.g., a natural language processing library). The extracted keywords and tasks are organized by category and stored in a database with a timestamp. For example, the words "eggs" and "milk" uttered by the user are added to the "shopping" category.

[0273] emotion recognition

[0274] The server is equipped with an emotion recognition engine that can recognize the user's emotions from the voice data. For example, if a user says, "I'm stressed because I have a meeting tomorrow," the server analyzes this information and recognizes that the user is feeling stressed. This emotional information is saved along with the text data and used to adjust future task priorities and responses.

[0275] Real-time answers to user questions

[0276] When a user asks, "What did you have for dinner last night?", the device receives the voice and sends it to the server. The server converts the voice data into text and searches a database for related past conversation data. For example, if the user has recorded, "I had curry rice for dinner last night," the server generates a response, "I had curry rice for dinner last night," and notifies the user via the device. If necessary, the tone and content of the response can be adjusted based on emotion recognition information.

[0277] Reminder function

[0278] The server periodically checks the saved keywords and tasks and extracts tasks that require reminders. For example, if a user sets a task to "buy eggs and milk tomorrow morning," the server prepares to remind the user of this information the next morning. At the specified time, the server generates a reminder message saying, "Don't forget to buy eggs and milk," and notifies the user of this message by voice via the device. The tone of the message can also be adjusted taking into account the user's emotional state.

[0279] for example:

[0280] A user says, "I need to buy eggs and milk tomorrow morning."

[0281] The terminal receives this audio and sends it to the server.

[0282] The server converts the voice data into text, analyzes it, and stores it in a database.

[0283] The server uses an emotion recognition engine to recognize the user's emotion as "a little tired."

[0284] The next morning, the server retrieves the reminder information from the database and generates a notification message in a soft tone, taking into account the user's emotional state, saying, "Don't forget to buy eggs and milk."

[0285] The device will notify the user by voice, "Don't forget to buy eggs and milk."

[0286] This system provides information management and support functions that take the user's emotions into consideration, realizing high-quality communication and information management within the home.

[0287] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0288] Step 1:

[0289] The device receives voice 24 hours a day, 365 days a year. User speech is captured through a microphone as voice data input. This voice data is converted into digital format and sent to the server in real time. For example, if a user says, "I need to buy eggs and milk tomorrow morning," the voice data is captured and sent to the server.

[0290] Step 2:

[0291] The server converts the received voice data into text data. It receives the voice data as input, analyzes it using voice recognition software (e.g., a voice recognition API), and generates text data in the form of a string. The output is the text data, "I need to buy eggs and milk tomorrow morning."

[0292] Step 3:

[0293] The server analyzes the converted text data. It receives the text data as input and uses natural language processing technology (e.g., a natural language processing library) to extract important keywords and tasks. Specifically, it extracts nouns and verbs and identifies important words. The keywords "egg," "milk," and "buy" are extracted as output.

[0294] Step 4:

[0295] The server performs emotion recognition using the extracted keywords. It receives voice and text data as input and analyzes the user's emotions using an emotion recognition engine (e.g., emotion analysis API). Specifically, it analyzes the tone and context of the speech to determine emotional states such as stress and fatigue. The output identifies the emotional information "I'm a little tired."

[0296] Step 5:

[0297] The server stores the analyzed text data and emotional information in a database. It receives text data and emotional information as input and records them in the database along with a timestamp. Specifically, it organizes the data by category and adds "eggs" and "milk" to the "shopping" category.

[0298] Step 6:

[0299] When a user asks, "What was for dinner last night?", the device receives the question as voice data and sends it to the server. It receives voice data as input and forwards it to the server.

[0300] Step 7:

[0301] The server converts the received voice data back into text data and searches the database for related past conversation data. It obtains the newly converted text data as input. Specifically, it searches past records related to "dinner" and generates an answer such as "Last night's dinner was curry rice." It then generates the answer text as output.

[0302] Step 8:

[0303] The device plays back the answer sent from the server as voice. It receives the answer in text format as input and converts it into voice data using voice synthesis technology (e.g., voice synthesis API). Specifically, it notifies the user by voice, "I had curry rice for dinner last night."

[0304] Step 9:

[0305] The server periodically checks the set tasks and information that requires reminders, and prepares reminders in a timely manner. It references previously saved task information as input and checks the timing of the reminder. Specifically, if a task such as "Buy eggs and milk tomorrow morning" is set, it prepares that information.

[0306] Step 10:

[0307] When the specified time arrives, the server generates a reminder message and notifies the user via the device. It receives reminder task information as input and generates a message that takes emotional information into account. Specifically, it generates a gentle voice message saying, "Don't forget to buy eggs and milk," and the device notifies the user.

[0308] Through the above process, this system provides information management and support functions that take the user's emotions into consideration, improving the quality of communication and information management within the home.

[0309] (Application example 2)

[0310] 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."

[0311] Conventional home conversation recording systems convert users' voices into text data and provide information management and reminder functions, but they only provide simple information without considering the user's emotional state. This has led to problems such as missing important information and failing to convey the nuances desired by the user. Furthermore, in certain application areas such as virtual stores, the systems lack the functionality to contribute to improving the user experience, and have not been able to sufficiently improve user satisfaction.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving voice data 24 hours a day, 365 days a year, means for converting the received voice data into text data, means for saving the converted text data together with a timestamp, means for analyzing the saved text data and extracting important keywords and tasks, means for searching for text data related to a user's question and generating an answer, means for providing the generated answer to the user by voice, means for notifying the user of necessary reminder information, means for analyzing the user's emotions using emotion recognition technology, means for adjusting the tone of the answer based on the analyzed emotion, and means for providing detailed product information in a virtual store. This enables the provision of higher quality information and reminders that take the user's emotions into consideration.

[0313] "Means for receiving voice data 24 hours a day, 365 days a year" refers to equipment and software that constantly receives the user's voice and transmits it to the system.

[0314] "Means for converting received voice data into text data" refers to software or algorithms that convert voice received from a user into text information in real time.

[0315] "Means for saving the converted text data together with a timestamp" refers to equipment or software for adding time information to the converted text data and saving it in a database.

[0316] "Means of analyzing stored text data and extracting important keywords and tasks" refers to software that uses natural language processing technology to analyze and extract necessary information from stored text data.

[0317] "Means for searching text data related to a user's question and generating an answer" refers to software for searching a database for information related to a user's question and generating an appropriate answer.

[0318] The "means for providing the generated answer to the user by voice" refers to a speaker or voice output software for transmitting the generated answer to the user as voice.

[0319] "Means for notifying the user of necessary reminder information" refers to an alert or message issuing device for notifying the user of tasks or information set by the user.

[0320] "Means of analyzing user emotions using emotion recognition technology" refers to software or algorithms for inferring user emotions from voice data or text data.

[0321] "Means for adjusting the tone of a response based on the analyzed emotions" refers to technology or software for appropriately changing the wording or tone of a response depending on the user's emotions.

[0322] "Means for providing detailed product information within a virtual store" refers to a system or software for providing information about products that users want in a virtual store in text or audio format.

[0323] System Overview

[0324] This system receives voice data in real time, converts it into text data, analyzes it, saves it, recognizes the user's emotions, and provides information and reminders accordingly. It is primarily intended for use in the home, but can also be applied to virtual stores. The main components of the system include a voice data receiving device, a text conversion device, a natural language processing analysis engine, an emotion recognition engine, a database, and a reminder notification device.

[0325] Receiving and converting audio data

[0326] The device is installed in a home or virtual store and receives voice data 24 hours a day, 365 days a year. For example, this could be a smartphone or smart glasses. The received voice data is sent to a server in real time. The server uses a speech recognition API (e.g., Google Cloud Speech-to-Text API) to convert the voice data into text data.

[0327] Analyzing and storing text data

[0328] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing techniques, such as natural language processing libraries (e.g., SpaCy or NLTK). The extracted keywords and tasks are organized by category and stored in a database (e.g., MongoDB) with a timestamp.

[0329] emotion recognition

[0330] The server is equipped with an emotion recognition engine (e.g., IBM Watson Tone Analyzer) that analyzes the user's emotions from voice and text data. For example, a statement such as "This product is great" can be used to recognize the user's positive emotions. This emotional information is stored along with the text data and used for later information provision and reminders.

[0331] Real-time answers and reminders

[0332] For example, if a user asks, "What is this shirt made of?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text using a voice recognition API and searches a database for related text data. For example, it retrieves the material information of the relevant shirt from a product database, generates a response such as "This shirt is made of 100% cotton," and provides it to the user via the device. It is also possible to adjust the tone and content of the response based on emotion recognition information.

[0333] For reminder functions, the server periodically checks saved keywords and tasks and extracts information that requires a reminder. For example, if a user sets a meeting for tomorrow at 12 o'clock, the device will notify them at the specified time, saying, "It's almost time for the meeting." If the user is under stress, the notification tone will be softened.

[0334] Specific examples

[0335] When a user says, "I'd like to know more about this red dress," the device receives the voice and sends it to the server. The server converts the voice data into text, and an emotion recognition engine determines that the user is excited. It then searches a product database and generates detailed information about the corresponding dress. The generated information is provided as a spoken answer, such as, "The price of this red dress is XXX yen, and the material is YYY."

[0336] Example prompts for generative AI models

[0337] User: "I want to know more about this red dress."

[0338] Assistant: "What information are you looking for? Price, ingredients, reviews, etc."

[0339] In this way, this system has information management and support functions that take the user's emotions into consideration, providing a higher quality experience at home or in a virtual store.

[0340] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0341] Step 1:

[0342] When a user speaks at home or in a virtual store, the voice data is received by a device (such as a smartphone or smart glasses). The voice data contains the content of the user's speech and is sent to the server as "voice data."

[0343] Input: User's voice data

[0344] Output: Audio data sent to the server

[0345] Specific operation: When a user says, "I want to know more about this red dress," the smartphone or smart glasses receive it and send it to the server as voice data.

[0346] Step 2:

[0347] The server passes the received voice data to a speech recognition API and converts it into text data. This process uses speech recognition technologies such as the Google Cloud Speech-to-Text API. The converted text data contains the user's speech as text information.

[0348] Input: Received audio data

[0349] Output: Text data

[0350] Specific operation: The server calls the speech recognition API and converts the speech "I want to know more about this red dress" into text data "I want to know more about this red dress."

[0351] Step 3:

[0352] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing libraries (SpaCy and NLTK). The analyzed information is organized by cargo and stored in a database.

[0353] Input: Text data

[0354] Output: Parsed keywords and tasks

[0355] Specific operation: The server extracts important keywords such as "red dress" and "want to know" and stores them in the product information category.

[0356] Step 4:

[0357] The server uses an emotion recognition engine (IBM Watson Tone Analyzer) to analyze the user's emotions from the text data. The analyzed emotion information is saved in the form of, for example, "excitement."

[0358] Input: Text data

[0359] Output: Emotional information

[0360] Specific operation: The server recognizes the emotional state of "excitement" and assigns it to text data and saves it.

[0361] Step 5:

[0362] The server searches a database for text data related to the user's question and generates an answer, for example, by searching a product database to obtain detailed information about the relevant product.

[0363] Input: Text data as a user question

[0364] Output: The generated answer

[0365] Specific operation: The server searches for information related to "red dress" and generates an answer such as "The price of the red dress is XXX yen and the material is YYY."

[0366] Step 6:

[0367] The server adjusts the tone of the response based on the analyzed emotion information: if the emotion is "excited," the server sets the tone of the response to be more energetic.

[0368] Input: Generated answers, sentiment information

[0369] Output: Tone-adjusted answer

[0370] Specific behavior: The server sets the tone with an energetic "The price is XXX yen and the ingredients are YYY!"

[0371] Step 7:

[0372] The terminal provides the generated answer to the user by voice, and the answer is communicated to the user through the audio output device.

[0373] Input: Generated Answer

[0374] Output: Provides answers to the user via voice

[0375] Specific operation: Through a smartphone or smart glasses, a voice message is provided to the user saying, "This red dress costs XXX yen and is made of YYY material!"

[0376] Step 8:

[0377] The server periodically checks the reminder information set by the user and notifies the user of necessary information using a reminder notification device.

[0378] Input: Saved keywords or tasks

[0379] Output: Reminder notification

[0380] Specific operation: The server checks the reminder information that "there is a meeting at 12 o'clock tomorrow" and notifies the smartphone that "it's almost time for the meeting."

[0381] Prompt Sentence Examples

[0382] User: "I want to know more about this red dress."

[0383] Assistant: "What information are you looking for? Price, ingredients, reviews, etc."

[0384] Through the above processing steps, the system provides high-quality information and reminder functions that take the user's emotions into consideration.

[0385] 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.

[0386] 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.

[0387] 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.

[0388] [Second embodiment]

[0389] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0390] 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.

[0391] 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).

[0392] 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.

[0393] 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.

[0394] 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).

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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."

[0401] The system of the present invention records conversations within the home in real time, organizes necessary information, provides answers, and provides reminder functions. The system effectively supports information sharing within the home through the following functions: receiving and analyzing voice data, storing and searching text data, providing real-time answers to user questions, and sending reminder notifications.

[0402] Receiving and converting audio data

[0403] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. The received voice data is sent to a server in real time and converted into text data using voice recognition technology. For example, a user's statement, "What's for dinner tonight?" is received as voice data and converted into text data.

[0404] Analyzing and storing text data

[0405] The server analyzes the converted text data and extracts important keywords and tasks. Natural language processing technology is used for this analysis. The extracted keywords and tasks are organized by category and saved in a database with a timestamp. For example, a statement such as "I need to buy eggs and milk" is classified as a shopping list and saved in the database.

[0406] Real-time answers to user questions

[0407] When a user asks, "What did we have for dinner last night?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text and searches a database for related past conversation data. For example, if someone says something about dinner last night, the device generates an answer based on that information, such as "We had curry rice for dinner last night," and provides it to the user via the device.

[0408] Reminder function

[0409] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. For example, if a user says, "Don't forget to take out the trash tomorrow morning," the server prepares to notify the user of that information the next morning. At the specified time, the device will notify the user by voice, "Don't forget to take out the trash."

[0410] Specific examples

[0411] As a concrete example, consider the following usage scenario:

[0412] 1. A user says, "I need to buy eggs and milk tomorrow morning."

[0413] 2. The device receives this audio and sends it to the server.

[0414] 3. The server converts the speech into text, analyzes it, and stores it in a database.

[0415] 4. The next morning, the server retrieves the reminder information from the database and sends a voice notification to the terminal saying, "Don't forget to buy eggs and milk."

[0416] In this way, the system of the present invention provides innovative support for information management within the home by using real-time reception and text conversion of voice data, data analysis and storage, real-time answers to user questions, and reminder notification functions.

[0417] The processing flow will be explained below.

[0418] Step 1:

[0419] A user says, "I need to buy eggs and milk tomorrow morning."

[0420] Step 2:

[0421] The device receives the user's speech through the microphone, captures it as audio data, and temporarily stores it in a buffer.

[0422] Step 3:

[0423] The terminal packetizes the voice data stored in the buffer and transmits it to the server in real time.

[0424] Step 4:

[0425] The server converts the received voice data into text data using a voice recognition API.

[0426] Step 5:

[0427] The server analyzes the converted text data and extracts important keywords and tasks, such as buying "eggs" and "milk."

[0428] Step 6:

[0429] The server organizes the extracted keywords and tasks into categories and stores them in a database along with timestamps.

[0430] Step 7:

[0431] The next morning, the server periodically checks the stored database for reminder information.

[0432] Step 8:

[0433] The server extracts the relevant reminder information and identifies the task that needs to be reminded at the moment. In this case, "buy eggs and milk" is extracted as an important task.

[0434] Step 9:

[0435] The server generates a message based on the extracted reminder information and sends it to the terminal.

[0436] Step 10:

[0437] The terminal receives the sent reminder information and issues a voice message to the user saying "Don't forget to buy eggs and milk" at the specified time.

[0438] Step 11:

[0439] The user receives a reminder message and performs the specified task.

[0440] In this way, the system of the present invention supports information management in daily life by recording user comments in real time, analyzing and saving necessary information, and sending reminders at appropriate times.

[0441] Example 1

[0442] 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."

[0443] In modern homes, a large amount of information is exchanged on a daily basis, and there is a need to efficiently manage this information and provide necessary information in a timely manner. However, conventional systems have had difficulty recording, organizing, and searching household conversation information in real time, and providing immediate answers to user questions. In particular, problems arise with missing information within the home, such as sudden reminder notifications and confirmation of important tasks. This invention aims to solve these problems.

[0444] 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.

[0445] In this invention, the server includes means for converting voice data into text data in real time using voice recognition technology, means for analyzing the text data and extracting important keywords and tasks using natural language processing technology, means for storing and searching the text data organized by category in a database, and means for notifying users of reminder information by voice at specified times. This allows for efficient information management within the home, enabling quick answers to users' questions and timely reminder notifications.

[0446] "Audio data" refers to digital data such as human speech and environmental sounds collected via a voice input device such as a microphone.

[0447] "Text data" is character string data that is expressed as text by analyzing voice data using voice recognition technology.

[0448] A "timestamp" is information indicating the date and time when data was generated, and is a time marker that is saved together with the text data.

[0449] "Natural language processing technology" is a computer technology that analyzes text data to understand meaning and extract keywords.

[0450] A "database" is a digital recording system that allows for the systematic accumulation, management, and retrieval of text data and related information.

[0451] "Reminder information" is information for notifying the user at a specific time about a task or event that the user has set in advance.

[0452] "Answer generation" is a process of searching for information related to a user's question and creating an appropriate response based on that information.

[0453] "Real-time" refers to a situation in which processing or response occurs immediately without delay.

[0454] The system of the present invention is designed to record conversations within the home in real time, organize necessary information, provide answers, and provide reminder functions. Specific embodiments will be described below.

[0455] The system of the present invention is composed of a terminal installed in the home and a server installed on the cloud or in the home.

[0456] Receiving and converting audio data

[0457] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. The device's built-in microphone captures the user's speech and environmental sounds. For example, if a user says, "I have to take out the trash tomorrow," the voice data is recorded on the device via the microphone.

[0458] The received voice data is sent in real time to the server, which then uses voice recognition technology (e.g., Google Cloud Speech-to-Text API) to convert the voice data into text data.

[0459] Analyzing and storing text data

[0460] The server analyzes the converted text data and uses natural language processing technology (e.g., SpaCy) to extract important keywords and tasks. The analyzed text data is organized by category and stored in a database (e.g., MySQL) with a timestamp.

[0461] For example, if a user says, "I need to buy eggs and milk," this will be classified as a shopping list category and stored in the database.

[0462] Real-time answers to user questions

[0463] When a user asks, "What did we have for dinner last night?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text and searches a database for relevant past conversation data. For example, if someone says something about dinner last night, the device generates an answer based on that information, such as "We had curry rice for dinner last night," and provides it to the user via the device.

[0464] Reminder function

[0465] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. For example, if a user says, "Don't forget to take out the trash tomorrow morning," the server prepares to notify the user of that information the next morning. At the specified time, the device will notify the user by voice, "Don't forget to take out the trash."

[0466] Specific examples

[0467] As a concrete example, consider the following usage scenario:

[0468] 1. A user says, "I need to buy eggs and milk tomorrow morning."

[0469] 2. The device receives this audio and sends it to the server.

[0470] 3. The server converts the speech into text, analyzes it, and stores it in a database.

[0471] 4. The next morning, the server retrieves the reminder information from the database and sends a voice notification to the terminal saying, "Don't forget to buy eggs and milk."

[0472] In this way, the system of the present invention effectively supports information management within the home through real-time reception and text conversion of voice data, data analysis and storage, real-time answers to user questions, and reminder notification functions.

[0473] Prompt Sentence Examples

[0474] You can see how the system works by inputting prompts like the following into the generative AI model:

[0475] "Tell me what you had for dinner last night."

[0476] "Do you have any reminders set for tomorrow?"

[0477] "What items have you added to your shopping list this week?"

[0478] This makes it easy to check that the system is working as expected.

[0479] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0480] Step 1: Receiving audio data

[0481] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. It captures what the user says (input) and converts that voice data into a digital format in real time (output). For example, a microphone might capture someone saying, "I have to take out the trash tomorrow."

[0482] Specific behavior:

[0483] A microphone captures the user's voice.

[0484] The captured audio data is converted into a digital format within the device.

[0485] Step 2: Sending audio data

[0486] The device sends the received voice data to the server. The digital voice data (input) is transferred to the server via the Internet (output).

[0487] Specific behavior:

[0488] The terminal breaks down the voice data into packets and sends them to a server over the Internet.

[0489] The server receives the transmitted packets and reconstructs the audio data.

[0490] Step 3: Convert the audio data

[0491] The server converts the received voice data into text data using voice recognition technology. The voice data (input) is analyzed and converted into character string data (output).

[0492] Specific behavior:

[0493] The server performs voice analysis using voice recognition technology (e.g., Google Cloud Speech-to-Text API).

[0494] The analyzed voice data is output as text data.

[0495] Step 4: Analyzing the text data

[0496] The server analyzes the converted text data and extracts important keywords and tasks. The text data (input) is analyzed using natural language processing technology (e.g., SpaCy), and the extracted keywords and tasks (output) are stored in a database.

[0497] Specific behavior:

[0498] The server uses natural language processing technology to perform semantic analysis of the text data.

[0499] Important keywords (e.g., taking out the trash) are extracted.

[0500] The extracted keywords are organized into categories (e.g., housework reminders) and stored in a database.

[0501] Step 5: Generate answers to user questions

[0502] When a user asks, "What did I have for dinner last night?", the device receives the question as voice data (input) and sends it to the server, which converts the voice data into text, searches past conversation data, and generates a relevant answer (output).

[0503] Specific behavior:

[0504] The terminal transmits the voice data to the server.

[0505] The server converts the speech into text and searches the database.

[0506] Based on the search results, the answer "I had curry rice for dinner last night" is generated and sent to the device.

[0507] The terminal generates a response and provides it to the user as a voice.

[0508] Step 6: Execute the reminder function

[0509] The server periodically checks the saved keywords and tasks, extracts information that requires reminders, and generates notifications at specific times based on the information (input) and sends them to the device (output).

[0510] Specific behavior:

[0511] The server runs a scheduled job to check the stored data.

[0512] Reminder information is extracted and notification content is generated.

[0513] At the specified time, the server transmits the notification data to the terminal.

[0514] The device will notify you with a voice message saying, "Don't forget to take out the trash."

[0515] (Application example 1)

[0516] 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."

[0517] Communication between store clerks and customers in brick-and-mortar stores must be accurate and efficient. However, in reality, it is difficult for store clerks to accurately remember past conversations or to provide appropriate responses quickly. Furthermore, they tend to forget specific work tasks, which reduces work efficiency. To solve these problems, a system is needed that can record and analyze conversations between store clerks and customers in real time.

[0518] 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.

[0519] In this invention, the server includes means for receiving voice data 24 hours a day, 365 days a year, means for converting the received voice data into text data, means for saving the converted text data together with a timestamp, means for analyzing the saved text data and extracting important keywords and tasks, means for searching for text data related to a user's question and generating an answer, means for providing the generated answer to the user by voice, means for notifying the user of necessary reminder information, means for recording and analyzing conversations between a store clerk and a customer in real time, means for generating an appropriate answer based on past conversation data and providing it to the store clerk, and means for sending reminder notifications for specific tasks. This allows the store clerk to provide an appropriate answer based on past conversation data and receive reminders for specific work tasks.

[0520] "Audio data" refers to data that represents an audio signal in digital or analog form.

[0521] "Text data" refers to digital data expressed as character string information.

[0522] A "timestamp" is date and time information recorded for specific data.

[0523] A "server" is a computer system that processes and stores data over a network.

[0524] "Important keywords" are words or phrases that deserve special attention within the text data being analyzed.

[0525] A "task" is a task or action to achieve a specific purpose.

[0526] "User" means a person or individual who uses the System.

[0527] "Reminder information" refers to information that notifies or alerts the user to specific tasks or matters.

[0528] A "means" is a method or apparatus for achieving a particular function.

[0529] A "store associate" is an employee who provides services to customers in a physical store.

[0530] A "customer" is a person who visits a physical store and uses a product or service.

[0531] "Conversation data" refers to the content of a conversation that is recorded as voice data and analyzed.

[0532] "Real-time recording" means that there is little time delay and the audio data is recorded at the exact moment the conversation occurs.

[0533] "Means of analysis" refers to techniques and methods for analyzing the content of data and extracting meaning.

[0534] A "means for generating an answer" is a method or device for automatically generating an appropriate response from the analyzed data.

[0535] A "reminder notification" is a notification that notifies the user not to forget specific information or tasks.

[0536] The system for implementing the present invention includes a voice receiving terminal installed in a physical store, a server that performs text conversion and data analysis, a database, and a device that performs notifications.

[0537] 1. Receiving and converting audio data

[0538] The terminal is installed in the store and receives conversations between store staff and customers 24 hours a day, 365 days a year. This records all interactions within the store. The received voice data is sent to a server in real time and converted into text data using a speech recognition engine (e.g., TensorFlow or PyTorch).

[0539] 2. Analyzing and saving text data

[0540] The converted text data is then analyzed by the server. Natural language processing technology is used in this analysis to extract important keywords and tasks. The extracted keywords and tasks are then stored in a database with a timestamp using Elasticsearch. For example, if someone says, "Update sale information at 3 p.m.", it is organized and saved in the appropriate category.

[0541] 3. Real-time answers to user questions

[0542] When a store clerk asks through smart glasses or a smartphone, "What was the special sale information yesterday?", the server converts this voice data into text and uses Elasticsearch to search for related past conversation data. If a conversation about special sales information has been recorded in the past, the server generates an answer such as "Yesterday's special sale item was drinking water," and displays this information on the smart glasses or smartphone.

[0543] 4. Reminder function

[0544] The server periodically checks the saved keywords and tasks and extracts information that requires a reminder. For example, if the information is "We need to organize the shelves in preparation for tomorrow's opening," it will send a notification to the store clerk's smartphone at the specified time saying, "Please organize the shelves."

[0545] Specific examples

[0546] For example, consider the following usage scenario:

[0547] 1. A store clerk says, "We need to update the sale information at 3:00 PM."

[0548] 2. The device receives this audio and sends it to the server.

[0549] 3. The server converts the speech into text, analyzes it, and stores it in a database.

[0550] 4. At 3:00 p.m., the server retrieves the reminder information from the database and sends a voice notification to the terminal saying, "Please update your sale information."

[0551] Prompt Sentence Examples

[0552] Example: "What products were on sale yesterday?"

[0553] Sample answer: "There was a sale on drinking water yesterday."

[0554] The system of the present invention enables accurate and efficient communication between store staff and customers in physical stores, thereby improving business efficiency.

[0555] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0556] Step 1: Receiving audio data

[0557] The terminal is installed in the store and receives conversations between store staff and customers 24 hours a day, 365 days a year. The input is voice data, which the terminal receives in real time. The output is the voice data itself.

[0558] Step 2: Send and convert audio data

[0559] The device sends the received voice data to the server in real time. The server uses a speech recognition engine (e.g., TensorFlow or PyTorch) to convert the voice data into text data. The input is voice data, and the output is text data.

[0560] Step 3: Analyze and save the text data

[0561] The server analyzes the converted text data using natural language processing technology, extracts important keywords and tasks, and stores them in a database with a timestamp using Elasticsearch. The input is text data, and the data that is analyzed and classified is output. A timestamp is added to the stored data.

[0562] Step 4: Generate answers to user questions

[0563] A store clerk asks a question through smart glasses or a smartphone. The question is received as voice data and sent to a server. The server converts the voice to text and uses Elasticsearch to search relevant past conversation data. The input is the voice data (question) and the output is the search results. The server generates an appropriate answer and displays it on the smart glasses or smartphone.

[0564] Step 5: Execute the reminder function

[0565] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. At the specified time, a reminder notification is sent to the terminal or the store clerk's smartphone. The input is the task information saved in the database, and the output is the reminder notification. The notification is displayed on the smart glasses or smartphone.

[0566] Step 6: Providing responses and notifications

[0567] The server generates answers and provides them to the smart glasses or smartphone as text or voice, as well as reminder notifications. The input is the generated answers or reminder information, and the output is a notification message for the user.

[0568] As described above, the system of the present invention executes each step in a step-by-step manner, from receiving voice data to converting it into text, analyzing it, saving it, and then sending reminders and providing appropriate responses. This allows for accurate recording and analysis of communications between store staff and customers in physical stores, enabling efficient responses.

[0569] 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.

[0570] This invention is a system that records conversations within the home in real time and recognizes the user's emotions, thereby enabling more effective information organization, answer provision, and reminder functions.In addition to receiving and converting voice data, saving and analyzing text data, providing answers to user questions, and sending reminder notifications, the invention incorporates an emotion recognition engine, making it possible to respond based on the user's emotions.

[0571] Receiving and converting audio data

[0572] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. The received voice data is sent to a server in real time and converted into text data using voice recognition technology. For example, a user's statement such as "I need to buy eggs and milk tomorrow morning" is received as voice data and converted into text data.

[0573] Analyzing and storing text data

[0574] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing technology. The extracted keywords and tasks are organized by category and saved in a database with a timestamp. For example, "eggs" and "milk" are added to the "shopping" category.

[0575] emotion recognition

[0576] The server is equipped with an emotion engine that recognizes the user's emotions from the voice data. For example, it can infer the user's stress level from a statement such as "I have a meeting tomorrow, so I'm feeling stressed." This information is saved along with the text data and used to adjust future task priorities and response content.

[0577] Real-time answers to user questions

[0578] When a user asks, "What did you have for dinner last night?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text and searches a database for related past conversation data. For example, if the comment about last night's dinner was "curry rice," the device generates the answer "We had curry rice for dinner last night" and provides it to the user via the device. It is also possible to adjust the tone and content of the answer based on emotion recognition information.

[0579] Reminder function

[0580] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. For example, if a task is set to "buy eggs and milk tomorrow morning," the server prepares to notify the user of that information the following morning. At the specified time, the device will notify the user with a voice message saying, "Don't forget to buy eggs and milk." If the user is under stress, the server will also adjust the tone of the notification to be softer.

[0581] Specific examples

[0582] As a concrete example, consider the following usage scenario:

[0583] 1. A user says, "I need to buy eggs and milk tomorrow morning."

[0584] 2. The device receives this audio and sends it to the server.

[0585] 3. The server converts the voice data into text, analyzes it, and stores it in a database.

[0586] 4. The server uses the emotion engine to recognize the user's emotion as "a little tired."

[0587] 5. The next morning, the server retrieves the reminder information from the database and generates a notification message in a soft tone, taking into account your emotional state, saying, "Don't forget to buy eggs and milk."

[0588] 6. The device will notify the user by voice, "Don't forget to buy eggs and milk."

[0589] In this way, the system of the present invention provides information management and support functions that take into account the user's emotions, thereby realizing higher quality communication and information management within the home.

[0590] The processing flow will be explained below.

[0591] Step 1:

[0592] A user says, "I need to buy eggs and milk tomorrow morning."

[0593] Step 2:

[0594] The device receives the user's speech through a microphone and captures it as voice data.

[0595] Step 3:

[0596] The device transmits the audio data to the server in real time.

[0597] Step 4:

[0598] The server converts the voice data into text data using a voice recognition API.

[0599] Step 5:

[0600] The server analyzes the text data and extracts the important keywords "egg" and "milk."

[0601] Step 6:

[0602] The server uses an emotion engine to analyze the user's emotions from the voice data and recognizes that the user is "feeling a little stressed."

[0603] Step 7:

[0604] The server organizes the extracted keywords and emotion data by category and stores them in a database along with a timestamp.

[0605] Step 8:

[0606] The next morning, the server periodically checks the stored database and extracts the information that needs to be reminded: "Buy eggs and milk."

[0607] Step 9:

[0608] The server takes emotion data into consideration when generating a notification message, where the tone is softened based on the emotion data.

[0609] Step 10:

[0610] The server sends the generated remind message to the terminal.

[0611] Step 11:

[0612] The device will then play a soft voice reminder message to the user saying, "Don't forget to buy eggs and milk."

[0613] Step 12:

[0614] The user receives a reminder message and performs the specified task.

[0615] Example 2

[0616] 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."

[0617] There is a demand for systems to effectively record and organize conversations within the home and provide necessary information in a timely manner. They are also expected to improve the user experience by understanding the user's emotions and responding accordingly. However, current systems lack sufficient functionality to meet these requirements, resulting in suboptimal information management and communication within the home. In particular, they lack the ability to recognize the user's emotions and provide information or reminders based on them.

[0618] 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.

[0619] In this invention, the server includes a means for converting voice data into text data, a means for analyzing text using natural language processing technology, and a means for recognizing emotions and saving them as data. By converting and analyzing voice data into text data and recognizing and saving emotions, the server can organize and provide information according to user needs. Furthermore, the content and tone of responses and reminders can be adjusted based on the user's emotions, enabling higher-quality information management and a better user experience.

[0620] "Audio data" is a recording of sounds, including the user's speech, captured within the home.

[0621] "Text data" is information obtained by converting voice data into a character string format.

[0622] A "timestamp" is information about the exact date and time when data was created or modified.

[0623] "Keywords" are important words or phrases extracted during text data analysis.

[0624] "Tasks" are user action plans or things to do that are derived from keywords.

[0625] "Emotion recognition" is a technology that determines a user's emotional state from voice data and text data.

[0626] "Natural language processing technology" is a set of computer technologies for analyzing, understanding, and generating human language.

[0627] A "database" is a system that systematically stores and manages text data and related information.

[0628] A "remind" is a notification that prompts the user to reconfirm a specific piece of information or task.

[0629] "Answer generation" is the process of providing appropriate information in response to a user's question.

[0630] This invention is a system that records conversations within the home in real time and recognizes the user's emotions to effectively organize information, provide answers, and provide reminder functions.In addition to receiving and converting voice data, saving and analyzing text data, providing answers to user questions, and sending reminder notifications, the system incorporates an emotion recognition engine, making it possible to respond based on the user's emotions.

[0631] Receiving and converting audio data

[0632] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. A voice recognition device (e.g., a smart speaker with a microphone) is used to receive the voice data. The received voice data is sent to a server in real time and converted into text data using voice recognition software (e.g., a voice recognition API). For example, if a user says, "I need to buy eggs and milk tomorrow morning," this voice data is sent from the device to the server in real time and converted into text data.

[0633] Analyzing and storing text data

[0634] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing technology (e.g., a natural language processing library). The extracted keywords and tasks are organized by category and stored in a database with a timestamp. For example, the words "eggs" and "milk" uttered by the user are added to the "shopping" category.

[0635] emotion recognition

[0636] The server is equipped with an emotion recognition engine that can recognize the user's emotions from the voice data. For example, if a user says, "I'm stressed because I have a meeting tomorrow," the server analyzes this information and recognizes that the user is feeling stressed. This emotional information is saved along with the text data and used to adjust future task priorities and responses.

[0637] Real-time answers to user questions

[0638] When a user asks, "What did you have for dinner last night?", the device receives the voice and sends it to the server. The server converts the voice data into text and searches a database for related past conversation data. For example, if the user has recorded, "I had curry rice for dinner last night," the server generates a response, "I had curry rice for dinner last night," and notifies the user via the device. If necessary, the tone and content of the response can be adjusted based on emotion recognition information.

[0639] Reminder function

[0640] The server periodically checks the saved keywords and tasks and extracts tasks that require reminders. For example, if a user sets a task to "buy eggs and milk tomorrow morning," the server prepares to remind the user of this information the next morning. At the specified time, the server generates a reminder message saying, "Don't forget to buy eggs and milk," and notifies the user of this message by voice via the device. The tone of the message can also be adjusted taking into account the user's emotional state.

[0641] for example:

[0642] A user says, "I need to buy eggs and milk tomorrow morning."

[0643] The terminal receives this audio and sends it to the server.

[0644] The server converts the voice data into text, analyzes it, and stores it in a database.

[0645] The server uses an emotion recognition engine to recognize the user's emotion as "a little tired."

[0646] The next morning, the server retrieves the reminder information from the database and generates a notification message in a soft tone, taking into account the user's emotional state, saying, "Don't forget to buy eggs and milk."

[0647] The device will notify the user by voice, "Don't forget to buy eggs and milk."

[0648] This system provides information management and support functions that take the user's emotions into consideration, realizing high-quality communication and information management within the home.

[0649] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0650] Step 1:

[0651] The device receives voice 24 hours a day, 365 days a year. User speech is captured through a microphone as voice data input. This voice data is converted into digital format and sent to the server in real time. For example, if a user says, "I need to buy eggs and milk tomorrow morning," the voice data is captured and sent to the server.

[0652] Step 2:

[0653] The server converts the received voice data into text data. It receives the voice data as input, analyzes it using voice recognition software (e.g., a voice recognition API), and generates text data in the form of a string. The output is the text data, "I need to buy eggs and milk tomorrow morning."

[0654] Step 3:

[0655] The server analyzes the converted text data. It receives the text data as input and uses natural language processing technology (e.g., a natural language processing library) to extract important keywords and tasks. Specifically, it extracts nouns and verbs and identifies important words. The keywords "egg," "milk," and "buy" are extracted as output.

[0656] Step 4:

[0657] The server performs emotion recognition using the extracted keywords. It receives voice and text data as input and analyzes the user's emotions using an emotion recognition engine (e.g., emotion analysis API). Specifically, it analyzes the tone and context of the speech to determine emotional states such as stress and fatigue. The output identifies the emotional information "I'm a little tired."

[0658] Step 5:

[0659] The server stores the analyzed text data and emotional information in a database. It receives text data and emotional information as input and records them in the database along with a timestamp. Specifically, it organizes the data by category and adds "eggs" and "milk" to the "shopping" category.

[0660] Step 6:

[0661] When a user asks, "What was for dinner last night?", the device receives the question as voice data and sends it to the server. It receives voice data as input and forwards it to the server.

[0662] Step 7:

[0663] The server converts the received voice data back into text data and searches the database for related past conversation data. It obtains the newly converted text data as input. Specifically, it searches past records related to "dinner" and generates an answer such as "Last night's dinner was curry rice." It then generates the answer text as output.

[0664] Step 8:

[0665] The device plays back the answer sent from the server as voice. It receives the answer in text format as input and converts it into voice data using voice synthesis technology (e.g., voice synthesis API). Specifically, it notifies the user by voice, "I had curry rice for dinner last night."

[0666] Step 9:

[0667] The server periodically checks the set tasks and information that requires reminders, and prepares reminders in a timely manner. It references previously saved task information as input and checks the timing of the reminder. Specifically, if a task such as "Buy eggs and milk tomorrow morning" is set, it prepares that information.

[0668] Step 10:

[0669] When the specified time arrives, the server generates a reminder message and notifies the user via the device. It receives reminder task information as input and generates a message that takes emotional information into account. Specifically, it generates a gentle voice message saying, "Don't forget to buy eggs and milk," and the device notifies the user.

[0670] Through the above process, this system provides information management and support functions that take the user's emotions into consideration, improving the quality of communication and information management within the home.

[0671] (Application example 2)

[0672] 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."

[0673] Conventional home conversation recording systems convert users' voices into text data and provide information management and reminder functions, but they only provide simple information without considering the user's emotional state. This has led to problems such as missing important information and failing to convey the nuances desired by the user. Furthermore, in certain application areas such as virtual stores, the systems lack the functionality to contribute to improving the user experience, and have not been able to sufficiently improve user satisfaction.

[0674] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving voice data 24 hours a day, 365 days a year, means for converting the received voice data into text data, means for saving the converted text data together with a timestamp, means for analyzing the saved text data and extracting important keywords and tasks, means for searching for text data related to a user's question and generating an answer, means for providing the generated answer to the user by voice, means for notifying the user of necessary reminder information, means for analyzing the user's emotions using emotion recognition technology, means for adjusting the tone of the answer based on the analyzed emotion, and means for providing detailed product information in a virtual store. This enables the provision of higher quality information and reminders that take the user's emotions into consideration.

[0675] "Means for receiving voice data 24 hours a day, 365 days a year" refers to equipment and software that constantly receives the user's voice and transmits it to the system.

[0676] "Means for converting received voice data into text data" refers to software or algorithms that convert voice received from a user into text information in real time.

[0677] "Means for saving the converted text data together with a timestamp" refers to equipment or software for adding time information to the converted text data and saving it in a database.

[0678] "Means of analyzing stored text data and extracting important keywords and tasks" refers to software that uses natural language processing technology to analyze and extract necessary information from stored text data.

[0679] "Means for searching text data related to a user's question and generating an answer" refers to software for searching a database for information related to a user's question and generating an appropriate answer.

[0680] The "means for providing the generated answer to the user by voice" refers to a speaker or voice output software for transmitting the generated answer to the user as voice.

[0681] "Means for notifying the user of necessary reminder information" refers to an alert or message issuing device for notifying the user of tasks or information set by the user.

[0682] "Means of analyzing user emotions using emotion recognition technology" refers to software or algorithms for inferring user emotions from voice data or text data.

[0683] "Means for adjusting the tone of a response based on the analyzed emotions" refers to technology or software for appropriately changing the wording or tone of a response depending on the user's emotions.

[0684] "Means for providing detailed product information within a virtual store" refers to a system or software for providing information about products that users want in a virtual store in text or audio format.

[0685] System Overview

[0686] This system receives voice data in real time, converts it into text data, analyzes it, saves it, recognizes the user's emotions, and provides information and reminders accordingly. It is primarily intended for use in the home, but can also be applied to virtual stores. The main components of the system include a voice data receiving device, a text conversion device, a natural language processing analysis engine, an emotion recognition engine, a database, and a reminder notification device.

[0687] Receiving and converting audio data

[0688] The device is installed in a home or virtual store and receives voice data 24 hours a day, 365 days a year. For example, this could be a smartphone or smart glasses. The received voice data is sent to a server in real time. The server uses a speech recognition API (e.g., Google Cloud Speech-to-Text API) to convert the voice data into text data.

[0689] Analyzing and storing text data

[0690] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing techniques, such as natural language processing libraries (e.g., SpaCy or NLTK). The extracted keywords and tasks are organized by category and stored in a database (e.g., MongoDB) with a timestamp.

[0691] emotion recognition

[0692] The server is equipped with an emotion recognition engine (e.g., IBM Watson Tone Analyzer) that analyzes the user's emotions from voice and text data. For example, a statement such as "This product is great" can be used to recognize the user's positive emotions. This emotional information is stored along with the text data and used for later information provision and reminders.

[0693] Real-time answers and reminders

[0694] For example, if a user asks, "What is this shirt made of?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text using a voice recognition API and searches a database for related text data. For example, it retrieves the material information of the relevant shirt from a product database, generates a response such as "This shirt is made of 100% cotton," and provides it to the user via the device. It is also possible to adjust the tone and content of the response based on emotion recognition information.

[0695] For reminder functions, the server periodically checks saved keywords and tasks and extracts information that requires a reminder. For example, if a user sets a meeting for tomorrow at 12 o'clock, the device will notify them at the specified time, saying, "It's almost time for the meeting." If the user is under stress, the notification tone will be softened.

[0696] Specific examples

[0697] When a user says, "I'd like to know more about this red dress," the device receives the voice and sends it to the server. The server converts the voice data into text, and an emotion recognition engine determines that the user is excited. It then searches a product database and generates detailed information about the corresponding dress. The generated information is provided as a spoken answer, such as, "The price of this red dress is XXX yen, and the material is YYY."

[0698] Example prompts for generative AI models

[0699] User: "I want to know more about this red dress."

[0700] Assistant: "What information are you looking for? Price, ingredients, reviews, etc."

[0701] In this way, this system has information management and support functions that take the user's emotions into consideration, providing a higher quality experience at home or in a virtual store.

[0702] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0703] Step 1:

[0704] When a user speaks at home or in a virtual store, the voice data is received by a device (such as a smartphone or smart glasses). The voice data contains the content of the user's speech and is sent to the server as "voice data."

[0705] Input: User's voice data

[0706] Output: Audio data sent to the server

[0707] Specific operation: When a user says, "I want to know more about this red dress," the smartphone or smart glasses receive it and send it to the server as voice data.

[0708] Step 2:

[0709] The server passes the received voice data to a speech recognition API and converts it into text data. This process uses speech recognition technologies such as the Google Cloud Speech-to-Text API. The converted text data contains the user's speech as text information.

[0710] Input: Received audio data

[0711] Output: Text data

[0712] Specific operation: The server calls the speech recognition API and converts the speech "I want to know more about this red dress" into text data "I want to know more about this red dress."

[0713] Step 3:

[0714] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing libraries (SpaCy and NLTK). The analyzed information is organized by cargo and stored in a database.

[0715] Input: Text data

[0716] Output: Parsed keywords and tasks

[0717] Specific operation: The server extracts important keywords such as "red dress" and "want to know" and stores them in the product information category.

[0718] Step 4:

[0719] The server uses an emotion recognition engine (IBM Watson Tone Analyzer) to analyze the user's emotions from the text data. The analyzed emotion information is saved in the form of, for example, "excitement."

[0720] Input: Text data

[0721] Output: Emotional information

[0722] Specific operation: The server recognizes the emotional state of "excitement" and assigns it to text data and saves it.

[0723] Step 5:

[0724] The server searches a database for text data related to the user's question and generates an answer, for example, by searching a product database to obtain detailed information about the relevant product.

[0725] Input: Text data as a user question

[0726] Output: The generated answer

[0727] Specific operation: The server searches for information related to "red dress" and generates an answer such as "The price of the red dress is XXX yen and the material is YYY."

[0728] Step 6:

[0729] The server adjusts the tone of the response based on the analyzed emotion information: if the emotion is "excited," the server sets the tone of the response to be more energetic.

[0730] Input: Generated answers, sentiment information

[0731] Output: Tone-adjusted answer

[0732] Specific behavior: The server sets the tone with an energetic "The price is XXX yen and the ingredients are YYY!"

[0733] Step 7:

[0734] The terminal provides the generated answer to the user by voice, and the answer is communicated to the user through the audio output device.

[0735] Input: Generated Answer

[0736] Output: Provides answers to the user via voice

[0737] Specific operation: Through a smartphone or smart glasses, a voice message is provided to the user saying, "This red dress costs XXX yen and is made of YYY material!"

[0738] Step 8:

[0739] The server periodically checks the reminder information set by the user and notifies the user of necessary information using a reminder notification device.

[0740] Input: Saved keywords or tasks

[0741] Output: Reminder notification

[0742] Specific operation: The server checks the reminder information that "there is a meeting at 12 o'clock tomorrow" and notifies the smartphone that "it's almost time for the meeting."

[0743] Prompt Sentence Examples

[0744] User: "I want to know more about this red dress."

[0745] Assistant: "What information are you looking for? Price, ingredients, reviews, etc."

[0746] Through the above processing steps, the system provides high-quality information and reminder functions that take the user's emotions into consideration.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] [Third embodiment]

[0751] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0752] 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.

[0753] 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).

[0754] 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.

[0755] 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.

[0756] 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).

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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."

[0763] The system of the present invention records conversations within the home in real time, organizes necessary information, provides answers, and provides reminder functions. The system effectively supports information sharing within the home through the following functions: receiving and analyzing voice data, storing and searching text data, providing real-time answers to user questions, and sending reminder notifications.

[0764] Receiving and converting audio data

[0765] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. The received voice data is sent to a server in real time and converted into text data using voice recognition technology. For example, a user's statement, "What's for dinner tonight?" is received as voice data and converted into text data.

[0766] Analyzing and storing text data

[0767] The server analyzes the converted text data and extracts important keywords and tasks. Natural language processing technology is used for this analysis. The extracted keywords and tasks are organized by category and saved in a database with a timestamp. For example, a statement such as "I need to buy eggs and milk" is classified as a shopping list and saved in the database.

[0768] Real-time answers to user questions

[0769] When a user asks, "What did we have for dinner last night?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text and searches a database for related past conversation data. For example, if someone says something about dinner last night, the device generates an answer based on that information, such as "We had curry rice for dinner last night," and provides it to the user via the device.

[0770] Reminder function

[0771] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. For example, if a user says, "Don't forget to take out the trash tomorrow morning," the server prepares to notify the user of that information the next morning. At the specified time, the device will notify the user by voice, "Don't forget to take out the trash."

[0772] Specific examples

[0773] As a concrete example, consider the following usage scenario:

[0774] 1. A user says, "I need to buy eggs and milk tomorrow morning."

[0775] 2. The device receives this audio and sends it to the server.

[0776] 3. The server converts the speech into text, analyzes it, and stores it in a database.

[0777] 4. The next morning, the server retrieves the reminder information from the database and sends a voice notification to the terminal saying, "Don't forget to buy eggs and milk."

[0778] In this way, the system of the present invention provides innovative support for information management within the home by using real-time reception and text conversion of voice data, data analysis and storage, real-time answers to user questions, and reminder notification functions.

[0779] The processing flow will be explained below.

[0780] Step 1:

[0781] A user says, "I need to buy eggs and milk tomorrow morning."

[0782] Step 2:

[0783] The device receives the user's speech through the microphone, captures it as audio data, and temporarily stores it in a buffer.

[0784] Step 3:

[0785] The terminal packetizes the voice data stored in the buffer and transmits it to the server in real time.

[0786] Step 4:

[0787] The server converts the received voice data into text data using a voice recognition API.

[0788] Step 5:

[0789] The server analyzes the converted text data and extracts important keywords and tasks, such as buying "eggs" and "milk."

[0790] Step 6:

[0791] The server organizes the extracted keywords and tasks into categories and stores them in a database along with timestamps.

[0792] Step 7:

[0793] The next morning, the server periodically checks the stored database for reminder information.

[0794] Step 8:

[0795] The server extracts the relevant reminder information and identifies the task that needs to be reminded at the moment. In this case, "buy eggs and milk" is extracted as an important task.

[0796] Step 9:

[0797] The server generates a message based on the extracted reminder information and sends it to the terminal.

[0798] Step 10:

[0799] The terminal receives the sent reminder information and issues a voice message to the user saying "Don't forget to buy eggs and milk" at the specified time.

[0800] Step 11:

[0801] The user receives a reminder message and performs the specified task.

[0802] In this way, the system of the present invention supports information management in daily life by recording user comments in real time, analyzing and saving necessary information, and sending reminders at appropriate times.

[0803] Example 1

[0804] 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."

[0805] In modern homes, a large amount of information is exchanged on a daily basis, and there is a need to efficiently manage this information and provide necessary information in a timely manner. However, conventional systems have had difficulty recording, organizing, and searching household conversation information in real time, and providing immediate answers to user questions. In particular, problems arise with missing information within the home, such as sudden reminder notifications and confirmation of important tasks. This invention aims to solve these problems.

[0806] 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.

[0807] In this invention, the server includes means for converting voice data into text data in real time using voice recognition technology, means for analyzing the text data and extracting important keywords and tasks using natural language processing technology, means for storing and searching the text data organized by category in a database, and means for notifying users of reminder information by voice at specified times. This allows for efficient information management within the home, enabling quick answers to users' questions and timely reminder notifications.

[0808] "Audio data" refers to digital data such as human speech and environmental sounds collected via a voice input device such as a microphone.

[0809] "Text data" is character string data that is expressed as text by analyzing voice data using voice recognition technology.

[0810] A "timestamp" is information indicating the date and time when data was generated, and is a time marker that is saved together with the text data.

[0811] "Natural language processing technology" is a computer technology that analyzes text data to understand meaning and extract keywords.

[0812] A "database" is a digital recording system that allows for the systematic accumulation, management, and retrieval of text data and related information.

[0813] "Reminder information" is information for notifying the user at a specific time about a task or event that the user has set in advance.

[0814] "Answer generation" is a process of searching for information related to a user's question and creating an appropriate response based on that information.

[0815] "Real-time" refers to a situation in which processing or response occurs immediately without delay.

[0816] The system of the present invention is designed to record conversations within the home in real time, organize necessary information, provide answers, and provide reminder functions. Specific embodiments will be described below.

[0817] The system of the present invention is composed of a terminal installed in the home and a server installed on the cloud or in the home.

[0818] Receiving and converting audio data

[0819] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. The device's built-in microphone captures the user's speech and environmental sounds. For example, if a user says, "I have to take out the trash tomorrow," the voice data is recorded on the device via the microphone.

[0820] The received voice data is sent in real time to the server, which then uses voice recognition technology (e.g., Google Cloud Speech-to-Text API) to convert the voice data into text data.

[0821] Analyzing and storing text data

[0822] The server analyzes the converted text data and uses natural language processing technology (e.g., SpaCy) to extract important keywords and tasks. The analyzed text data is organized by category and stored in a database (e.g., MySQL) with a timestamp.

[0823] For example, if a user says, "I need to buy eggs and milk," this will be classified as a shopping list category and stored in the database.

[0824] Real-time answers to user questions

[0825] When a user asks, "What did we have for dinner last night?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text and searches a database for relevant past conversation data. For example, if someone says something about dinner last night, the device generates an answer based on that information, such as "We had curry rice for dinner last night," and provides it to the user via the device.

[0826] Reminder function

[0827] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. For example, if a user says, "Don't forget to take out the trash tomorrow morning," the server prepares to notify the user of that information the next morning. At the specified time, the device will notify the user by voice, "Don't forget to take out the trash."

[0828] Specific examples

[0829] As a concrete example, consider the following usage scenario:

[0830] 1. A user says, "I need to buy eggs and milk tomorrow morning."

[0831] 2. The device receives this audio and sends it to the server.

[0832] 3. The server converts the speech into text, analyzes it, and stores it in a database.

[0833] 4. The next morning, the server retrieves the reminder information from the database and sends a voice notification to the terminal saying, "Don't forget to buy eggs and milk."

[0834] In this way, the system of the present invention effectively supports information management within the home through real-time reception and text conversion of voice data, data analysis and storage, real-time answers to user questions, and reminder notification functions.

[0835] Prompt Sentence Examples

[0836] You can see how the system works by inputting prompts like the following into the generative AI model:

[0837] "Tell me what you had for dinner last night."

[0838] "Do you have any reminders set for tomorrow?"

[0839] "What items have you added to your shopping list this week?"

[0840] This makes it easy to check that the system is working as expected.

[0841] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0842] Step 1: Receiving audio data

[0843] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. It captures what the user says (input) and converts that voice data into a digital format in real time (output). For example, a microphone might capture someone saying, "I have to take out the trash tomorrow."

[0844] Specific behavior:

[0845] A microphone captures the user's voice.

[0846] The captured audio data is converted into a digital format within the device.

[0847] Step 2: Sending audio data

[0848] The device sends the received voice data to the server. The digital voice data (input) is transferred to the server via the Internet (output).

[0849] Specific behavior:

[0850] The terminal breaks down the voice data into packets and sends them to a server over the Internet.

[0851] The server receives the transmitted packets and reconstructs the audio data.

[0852] Step 3: Convert the audio data

[0853] The server converts the received voice data into text data using voice recognition technology. The voice data (input) is analyzed and converted into character string data (output).

[0854] Specific behavior:

[0855] The server performs voice analysis using voice recognition technology (e.g., Google Cloud Speech-to-Text API).

[0856] The analyzed voice data is output as text data.

[0857] Step 4: Analyzing the text data

[0858] The server analyzes the converted text data and extracts important keywords and tasks. The text data (input) is analyzed using natural language processing technology (e.g., SpaCy), and the extracted keywords and tasks (output) are stored in a database.

[0859] Specific behavior:

[0860] The server uses natural language processing technology to perform semantic analysis of the text data.

[0861] Important keywords (e.g., taking out the trash) are extracted.

[0862] The extracted keywords are organized into categories (e.g., housework reminders) and stored in a database.

[0863] Step 5: Generate answers to user questions

[0864] When a user asks, "What did I have for dinner last night?", the device receives the question as voice data (input) and sends it to the server, which converts the voice data into text, searches past conversation data, and generates a relevant answer (output).

[0865] Specific behavior:

[0866] The terminal transmits the voice data to the server.

[0867] The server converts the speech into text and searches the database.

[0868] Based on the search results, the answer "I had curry rice for dinner last night" is generated and sent to the device.

[0869] The terminal generates a response and provides it to the user as a voice.

[0870] Step 6: Execute the reminder function

[0871] The server periodically checks the saved keywords and tasks, extracts information that requires reminders, and generates notifications at specific times based on the information (input) and sends them to the device (output).

[0872] Specific behavior:

[0873] The server runs a scheduled job to check the stored data.

[0874] Reminder information is extracted and notification content is generated.

[0875] At the specified time, the server transmits the notification data to the terminal.

[0876] The device will notify you with a voice message saying, "Don't forget to take out the trash."

[0877] (Application example 1)

[0878] 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."

[0879] Communication between store clerks and customers in brick-and-mortar stores must be accurate and efficient. However, in reality, it is difficult for store clerks to accurately remember past conversations or to provide appropriate responses quickly. Furthermore, they tend to forget specific work tasks, which reduces work efficiency. To solve these problems, a system is needed that can record and analyze conversations between store clerks and customers in real time.

[0880] 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.

[0881] In this invention, the server includes means for receiving voice data 24 hours a day, 365 days a year, means for converting the received voice data into text data, means for saving the converted text data together with a timestamp, means for analyzing the saved text data and extracting important keywords and tasks, means for searching for text data related to a user's question and generating an answer, means for providing the generated answer to the user by voice, means for notifying the user of necessary reminder information, means for recording and analyzing conversations between a store clerk and a customer in real time, means for generating an appropriate answer based on past conversation data and providing it to the store clerk, and means for sending reminder notifications for specific tasks. This allows the store clerk to provide an appropriate answer based on past conversation data and receive reminders for specific work tasks.

[0882] "Audio data" refers to data that represents an audio signal in digital or analog form.

[0883] "Text data" refers to digital data expressed as character string information.

[0884] A "timestamp" is date and time information recorded for specific data.

[0885] A "server" is a computer system that processes and stores data over a network.

[0886] "Important keywords" are words or phrases that deserve special attention within the text data being analyzed.

[0887] A "task" is a task or action to achieve a specific purpose.

[0888] "User" means a person or individual who uses the System.

[0889] "Reminder information" refers to information that notifies or alerts the user to specific tasks or matters.

[0890] A "means" is a method or apparatus for achieving a particular function.

[0891] A "store associate" is an employee who provides services to customers in a physical store.

[0892] A "customer" is a person who visits a physical store and uses a product or service.

[0893] "Conversation data" refers to the content of a conversation that is recorded as voice data and analyzed.

[0894] "Real-time recording" means that there is little time delay and the audio data is recorded at the exact moment the conversation occurs.

[0895] "Means of analysis" refers to techniques and methods for analyzing the content of data and extracting meaning.

[0896] A "means for generating an answer" is a method or device for automatically generating an appropriate response from the analyzed data.

[0897] A "reminder notification" is a notification that notifies the user not to forget specific information or tasks.

[0898] The system for implementing the present invention includes a voice receiving terminal installed in a physical store, a server that performs text conversion and data analysis, a database, and a device that performs notifications.

[0899] 1. Receiving and converting audio data

[0900] The terminal is installed in the store and receives conversations between store staff and customers 24 hours a day, 365 days a year. This records all interactions within the store. The received voice data is sent to a server in real time and converted into text data using a speech recognition engine (e.g., TensorFlow or PyTorch).

[0901] 2. Analyzing and saving text data

[0902] The converted text data is then analyzed by the server. Natural language processing technology is used in this analysis to extract important keywords and tasks. The extracted keywords and tasks are then stored in a database with a timestamp using Elasticsearch. For example, if someone says, "Update sale information at 3 p.m.", it is organized and saved in the appropriate category.

[0903] 3. Real-time answers to user questions

[0904] When a store clerk asks through smart glasses or a smartphone, "What was the special sale information yesterday?", the server converts this voice data into text and uses Elasticsearch to search for related past conversation data. If a conversation about special sales information has been recorded in the past, the server generates an answer such as "Yesterday's special sale item was drinking water," and displays this information on the smart glasses or smartphone.

[0905] 4. Reminder function

[0906] The server periodically checks the saved keywords and tasks and extracts information that requires a reminder. For example, if the information is "We need to organize the shelves in preparation for tomorrow's opening," it will send a notification to the store clerk's smartphone at the specified time saying, "Please organize the shelves."

[0907] Specific examples

[0908] For example, consider the following usage scenario:

[0909] 1. A store clerk says, "We need to update the sale information at 3:00 PM."

[0910] 2. The device receives this audio and sends it to the server.

[0911] 3. The server converts the speech into text, analyzes it, and stores it in a database.

[0912] 4. At 3:00 p.m., the server retrieves the reminder information from the database and sends a voice notification to the terminal saying, "Please update your sale information."

[0913] Prompt Sentence Examples

[0914] Example: "What products were on sale yesterday?"

[0915] Sample answer: "There was a sale on drinking water yesterday."

[0916] The system of the present invention enables accurate and efficient communication between store staff and customers in physical stores, thereby improving business efficiency.

[0917] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0918] Step 1: Receiving audio data

[0919] The terminal is installed in the store and receives conversations between store staff and customers 24 hours a day, 365 days a year. The input is voice data, which the terminal receives in real time. The output is the voice data itself.

[0920] Step 2: Send and convert audio data

[0921] The device sends the received voice data to the server in real time. The server uses a speech recognition engine (e.g., TensorFlow or PyTorch) to convert the voice data into text data. The input is voice data, and the output is text data.

[0922] Step 3: Analyze and save the text data

[0923] The server analyzes the converted text data using natural language processing technology, extracts important keywords and tasks, and stores them in a database with a timestamp using Elasticsearch. The input is text data, and the data that is analyzed and classified is output. A timestamp is added to the stored data.

[0924] Step 4: Generate answers to user questions

[0925] A store clerk asks a question through smart glasses or a smartphone. The question is received as voice data and sent to a server. The server converts the voice to text and uses Elasticsearch to search relevant past conversation data. The input is the voice data (question) and the output is the search results. The server generates an appropriate answer and displays it on the smart glasses or smartphone.

[0926] Step 5: Execute the reminder function

[0927] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. At the specified time, a reminder notification is sent to the terminal or the store clerk's smartphone. The input is the task information saved in the database, and the output is the reminder notification. The notification is displayed on the smart glasses or smartphone.

[0928] Step 6: Providing responses and notifications

[0929] The server generates answers and provides them to the smart glasses or smartphone as text or voice, as well as reminder notifications. The input is the generated answers or reminder information, and the output is a notification message for the user.

[0930] As described above, the system of the present invention executes each step in a step-by-step manner, from receiving voice data to converting it into text, analyzing it, saving it, and then sending reminders and providing appropriate responses. This allows for accurate recording and analysis of communications between store staff and customers in physical stores, enabling efficient responses.

[0931] 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.

[0932] This invention is a system that records conversations within the home in real time and recognizes the user's emotions, thereby enabling more effective information organization, answer provision, and reminder functions.In addition to receiving and converting voice data, saving and analyzing text data, providing answers to user questions, and sending reminder notifications, the invention incorporates an emotion recognition engine, making it possible to respond based on the user's emotions.

[0933] Receiving and converting audio data

[0934] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. The received voice data is sent to a server in real time and converted into text data using voice recognition technology. For example, a user's statement such as "I need to buy eggs and milk tomorrow morning" is received as voice data and converted into text data.

[0935] Analyzing and storing text data

[0936] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing technology. The extracted keywords and tasks are organized by category and saved in a database with a timestamp. For example, "eggs" and "milk" are added to the "shopping" category.

[0937] emotion recognition

[0938] The server is equipped with an emotion engine that recognizes the user's emotions from the voice data. For example, it can infer the user's stress level from a statement such as "I have a meeting tomorrow, so I'm feeling stressed." This information is saved along with the text data and used to adjust future task priorities and response content.

[0939] Real-time answers to user questions

[0940] When a user asks, "What did you have for dinner last night?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text and searches a database for related past conversation data. For example, if the comment about last night's dinner was "curry rice," the device generates the answer "We had curry rice for dinner last night" and provides it to the user via the device. It is also possible to adjust the tone and content of the answer based on emotion recognition information.

[0941] Reminder function

[0942] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. For example, if a task is set to "buy eggs and milk tomorrow morning," the server prepares to notify the user of that information the following morning. At the specified time, the device will notify the user with a voice message saying, "Don't forget to buy eggs and milk." If the user is under stress, the server will also adjust the tone of the notification to be softer.

[0943] Specific examples

[0944] As a concrete example, consider the following usage scenario:

[0945] 1. A user says, "I need to buy eggs and milk tomorrow morning."

[0946] 2. The device receives this audio and sends it to the server.

[0947] 3. The server converts the voice data into text, analyzes it, and stores it in a database.

[0948] 4. The server uses the emotion engine to recognize the user's emotion as "a little tired."

[0949] 5. The next morning, the server retrieves the reminder information from the database and generates a notification message in a soft tone, taking into account your emotional state, saying, "Don't forget to buy eggs and milk."

[0950] 6. The device will notify the user by voice, "Don't forget to buy eggs and milk."

[0951] In this way, the system of the present invention provides information management and support functions that take into account the user's emotions, thereby realizing higher quality communication and information management within the home.

[0952] The processing flow will be explained below.

[0953] Step 1:

[0954] A user says, "I need to buy eggs and milk tomorrow morning."

[0955] Step 2:

[0956] The device receives the user's speech through a microphone and captures it as voice data.

[0957] Step 3:

[0958] The device transmits the audio data to the server in real time.

[0959] Step 4:

[0960] The server converts the voice data into text data using a voice recognition API.

[0961] Step 5:

[0962] The server analyzes the text data and extracts the important keywords "egg" and "milk."

[0963] Step 6:

[0964] The server uses an emotion engine to analyze the user's emotions from the voice data and recognizes that the user is "feeling a little stressed."

[0965] Step 7:

[0966] The server organizes the extracted keywords and emotion data by category and stores them in a database along with a timestamp.

[0967] Step 8:

[0968] The next morning, the server periodically checks the stored database and extracts the information that needs to be reminded: "Buy eggs and milk."

[0969] Step 9:

[0970] The server takes emotion data into consideration when generating a notification message, where the tone is softened based on the emotion data.

[0971] Step 10:

[0972] The server sends the generated remind message to the terminal.

[0973] Step 11:

[0974] The device will then play a soft voice reminder message to the user saying, "Don't forget to buy eggs and milk."

[0975] Step 12:

[0976] The user receives a reminder message and performs the specified task.

[0977] Example 2

[0978] 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."

[0979] There is a demand for systems to effectively record and organize conversations within the home and provide necessary information in a timely manner. They are also expected to improve the user experience by understanding the user's emotions and responding accordingly. However, current systems lack sufficient functionality to meet these requirements, resulting in suboptimal information management and communication within the home. In particular, they lack the ability to recognize the user's emotions and provide information or reminders based on them.

[0980] 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.

[0981] In this invention, the server includes a means for converting voice data into text data, a means for analyzing text using natural language processing technology, and a means for recognizing emotions and saving them as data. By converting and analyzing voice data into text data and recognizing and saving emotions, the server can organize and provide information according to user needs. Furthermore, the content and tone of responses and reminders can be adjusted based on the user's emotions, enabling higher-quality information management and a better user experience.

[0982] "Audio data" is a recording of sounds, including the user's speech, captured within the home.

[0983] "Text data" is information obtained by converting voice data into a character string format.

[0984] A "timestamp" is information about the exact date and time when data was created or modified.

[0985] "Keywords" are important words or phrases extracted during text data analysis.

[0986] "Tasks" are user action plans or things to do that are derived from keywords.

[0987] "Emotion recognition" is a technology that determines a user's emotional state from voice data and text data.

[0988] "Natural language processing technology" is a set of computer technologies for analyzing, understanding, and generating human language.

[0989] A "database" is a system that systematically stores and manages text data and related information.

[0990] A "remind" is a notification that prompts the user to reconfirm a specific piece of information or task.

[0991] "Answer generation" is the process of providing appropriate information in response to a user's question.

[0992] This invention is a system that records conversations within the home in real time and recognizes the user's emotions to effectively organize information, provide answers, and provide reminder functions.In addition to receiving and converting voice data, saving and analyzing text data, providing answers to user questions, and sending reminder notifications, the system incorporates an emotion recognition engine, making it possible to respond based on the user's emotions.

[0993] Receiving and converting audio data

[0994] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. A voice recognition device (e.g., a smart speaker with a microphone) is used to receive the voice data. The received voice data is sent to a server in real time and converted into text data using voice recognition software (e.g., a voice recognition API). For example, if a user says, "I need to buy eggs and milk tomorrow morning," this voice data is sent from the device to the server in real time and converted into text data.

[0995] Analyzing and storing text data

[0996] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing technology (e.g., a natural language processing library). The extracted keywords and tasks are organized by category and stored in a database with a timestamp. For example, the words "eggs" and "milk" uttered by the user are added to the "shopping" category.

[0997] emotion recognition

[0998] The server is equipped with an emotion recognition engine that can recognize the user's emotions from the voice data. For example, if a user says, "I'm stressed because I have a meeting tomorrow," the server analyzes this information and recognizes that the user is feeling stressed. This emotional information is saved along with the text data and used to adjust future task priorities and responses.

[0999] Real-time answers to user questions

[1000] When a user asks, "What did you have for dinner last night?", the device receives the voice and sends it to the server. The server converts the voice data into text and searches a database for related past conversation data. For example, if the user has recorded, "I had curry rice for dinner last night," the server generates a response, "I had curry rice for dinner last night," and notifies the user via the device. If necessary, the tone and content of the response can be adjusted based on emotion recognition information.

[1001] Reminder function

[1002] The server periodically checks the saved keywords and tasks and extracts tasks that require reminders. For example, if a user sets a task to "buy eggs and milk tomorrow morning," the server prepares to remind the user of this information the next morning. At the specified time, the server generates a reminder message saying, "Don't forget to buy eggs and milk," and notifies the user of this message by voice via the device. The tone of the message can also be adjusted taking into account the user's emotional state.

[1003] for example:

[1004] A user says, "I need to buy eggs and milk tomorrow morning."

[1005] The terminal receives this audio and sends it to the server.

[1006] The server converts the voice data into text, analyzes it, and stores it in a database.

[1007] The server uses an emotion recognition engine to recognize the user's emotion as "a little tired."

[1008] The next morning, the server retrieves the reminder information from the database and generates a notification message in a soft tone, taking into account the user's emotional state, saying, "Don't forget to buy eggs and milk."

[1009] The device will notify the user by voice, "Don't forget to buy eggs and milk."

[1010] This system provides information management and support functions that take the user's emotions into consideration, realizing high-quality communication and information management within the home.

[1011] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1012] Step 1:

[1013] The device receives voice 24 hours a day, 365 days a year. User speech is captured through a microphone as voice data input. This voice data is converted into digital format and sent to the server in real time. For example, if a user says, "I need to buy eggs and milk tomorrow morning," the voice data is captured and sent to the server.

[1014] Step 2:

[1015] The server converts the received voice data into text data. It receives the voice data as input, analyzes it using voice recognition software (e.g., a voice recognition API), and generates text data in the form of a string. The output is the text data, "I need to buy eggs and milk tomorrow morning."

[1016] Step 3:

[1017] The server analyzes the converted text data. It receives the text data as input and uses natural language processing technology (e.g., a natural language processing library) to extract important keywords and tasks. Specifically, it extracts nouns and verbs and identifies important words. The keywords "egg," "milk," and "buy" are extracted as output.

[1018] Step 4:

[1019] The server performs emotion recognition using the extracted keywords. It receives voice and text data as input and analyzes the user's emotions using an emotion recognition engine (e.g., emotion analysis API). Specifically, it analyzes the tone and context of the speech to determine emotional states such as stress and fatigue. The output identifies the emotional information "I'm a little tired."

[1020] Step 5:

[1021] The server stores the analyzed text data and emotional information in a database. It receives text data and emotional information as input and records them in the database along with a timestamp. Specifically, it organizes the data by category and adds "eggs" and "milk" to the "shopping" category.

[1022] Step 6:

[1023] When a user asks, "What was for dinner last night?", the device receives the question as voice data and sends it to the server. It receives voice data as input and forwards it to the server.

[1024] Step 7:

[1025] The server converts the received voice data back into text data and searches the database for related past conversation data. It obtains the newly converted text data as input. Specifically, it searches past records related to "dinner" and generates an answer such as "Last night's dinner was curry rice." It then generates the answer text as output.

[1026] Step 8:

[1027] The device plays back the answer sent from the server as voice. It receives the answer in text format as input and converts it into voice data using voice synthesis technology (e.g., voice synthesis API). Specifically, it notifies the user by voice, "I had curry rice for dinner last night."

[1028] Step 9:

[1029] The server periodically checks the set tasks and information that requires reminders, and prepares reminders in a timely manner. It references previously saved task information as input and checks the timing of the reminder. Specifically, if a task such as "Buy eggs and milk tomorrow morning" is set, it prepares that information.

[1030] Step 10:

[1031] When the specified time arrives, the server generates a reminder message and notifies the user via the device. It receives reminder task information as input and generates a message that takes emotional information into account. Specifically, it generates a gentle voice message saying, "Don't forget to buy eggs and milk," and the device notifies the user.

[1032] Through the above process, this system provides information management and support functions that take the user's emotions into consideration, improving the quality of communication and information management within the home.

[1033] (Application example 2)

[1034] 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."

[1035] Conventional home conversation recording systems convert users' voices into text data and provide information management and reminder functions, but they only provide simple information without considering the user's emotional state. This has led to problems such as missing important information and failing to convey the nuances desired by the user. Furthermore, in certain application areas such as virtual stores, the systems lack the functionality to contribute to improving the user experience, and have not been able to sufficiently improve user satisfaction.

[1036] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving voice data 24 hours a day, 365 days a year, means for converting the received voice data into text data, means for saving the converted text data together with a timestamp, means for analyzing the saved text data and extracting important keywords and tasks, means for searching for text data related to a user's question and generating an answer, means for providing the generated answer to the user by voice, means for notifying the user of necessary reminder information, means for analyzing the user's emotions using emotion recognition technology, means for adjusting the tone of the answer based on the analyzed emotion, and means for providing detailed product information in a virtual store. This enables the provision of higher quality information and reminders that take the user's emotions into consideration.

[1037] "Means for receiving voice data 24 hours a day, 365 days a year" refers to equipment and software that constantly receives the user's voice and transmits it to the system.

[1038] "Means for converting received voice data into text data" refers to software or algorithms that convert voice received from a user into text information in real time.

[1039] "Means for saving the converted text data together with a timestamp" refers to equipment or software for adding time information to the converted text data and saving it in a database.

[1040] "Means of analyzing stored text data and extracting important keywords and tasks" refers to software that uses natural language processing technology to analyze and extract necessary information from stored text data.

[1041] "Means for searching text data related to a user's question and generating an answer" refers to software for searching a database for information related to a user's question and generating an appropriate answer.

[1042] The "means for providing the generated answer to the user by voice" refers to a speaker or voice output software for transmitting the generated answer to the user as voice.

[1043] "Means for notifying the user of necessary reminder information" refers to an alert or message issuing device for notifying the user of tasks or information set by the user.

[1044] "Means of analyzing user emotions using emotion recognition technology" refers to software or algorithms for inferring user emotions from voice data or text data.

[1045] "Means for adjusting the tone of a response based on the analyzed emotions" refers to technology or software for appropriately changing the wording or tone of a response depending on the user's emotions.

[1046] "Means for providing detailed product information within a virtual store" refers to a system or software for providing information about products that users want in a virtual store in text or audio format.

[1047] System Overview

[1048] This system receives voice data in real time, converts it into text data, analyzes it, saves it, recognizes the user's emotions, and provides information and reminders accordingly. It is primarily intended for use in the home, but can also be applied to virtual stores. The main components of the system include a voice data receiving device, a text conversion device, a natural language processing analysis engine, an emotion recognition engine, a database, and a reminder notification device.

[1049] Receiving and converting audio data

[1050] The device is installed in a home or virtual store and receives voice data 24 hours a day, 365 days a year. For example, this could be a smartphone or smart glasses. The received voice data is sent to a server in real time. The server uses a speech recognition API (e.g., Google Cloud Speech-to-Text API) to convert the voice data into text data.

[1051] Analyzing and storing text data

[1052] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing techniques, such as natural language processing libraries (e.g., SpaCy or NLTK). The extracted keywords and tasks are organized by category and stored in a database (e.g., MongoDB) with a timestamp.

[1053] emotion recognition

[1054] The server is equipped with an emotion recognition engine (e.g., IBM Watson Tone Analyzer) that analyzes the user's emotions from voice and text data. For example, a statement such as "This product is great" can be used to recognize the user's positive emotions. This emotional information is stored along with the text data and used for later information provision and reminders.

[1055] Real-time answers and reminders

[1056] For example, if a user asks, "What is this shirt made of?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text using a voice recognition API and searches a database for related text data. For example, it retrieves the material information of the relevant shirt from a product database, generates a response such as "This shirt is made of 100% cotton," and provides it to the user via the device. It is also possible to adjust the tone and content of the response based on emotion recognition information.

[1057] For reminder functions, the server periodically checks saved keywords and tasks and extracts information that requires a reminder. For example, if a user sets a meeting for tomorrow at 12 o'clock, the device will notify them at the specified time, saying, "It's almost time for the meeting." If the user is under stress, the notification tone will be softened.

[1058] Specific examples

[1059] When a user says, "I'd like to know more about this red dress," the device receives the voice and sends it to the server. The server converts the voice data into text, and an emotion recognition engine determines that the user is excited. It then searches a product database and generates detailed information about the corresponding dress. The generated information is provided as a spoken answer, such as, "The price of this red dress is XXX yen, and the material is YYY."

[1060] Example prompts for generative AI models

[1061] User: "I want to know more about this red dress."

[1062] Assistant: "What information are you looking for? Price, ingredients, reviews, etc."

[1063] In this way, this system has information management and support functions that take the user's emotions into consideration, providing a higher quality experience at home or in a virtual store.

[1064] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1065] Step 1:

[1066] When a user speaks at home or in a virtual store, the voice data is received by a device (such as a smartphone or smart glasses). The voice data contains the content of the user's speech and is sent to the server as "voice data."

[1067] Input: User's voice data

[1068] Output: Audio data sent to the server

[1069] Specific operation: When a user says, "I want to know more about this red dress," the smartphone or smart glasses receive it and send it to the server as voice data.

[1070] Step 2:

[1071] The server passes the received voice data to a speech recognition API and converts it into text data. This process uses speech recognition technologies such as the Google Cloud Speech-to-Text API. The converted text data contains the user's speech as text information.

[1072] Input: Received audio data

[1073] Output: Text data

[1074] Specific operation: The server calls the speech recognition API and converts the speech "I want to know more about this red dress" into text data "I want to know more about this red dress."

[1075] Step 3:

[1076] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing libraries (SpaCy and NLTK). The analyzed information is organized by cargo and stored in a database.

[1077] Input: Text data

[1078] Output: Parsed keywords and tasks

[1079] Specific operation: The server extracts important keywords such as "red dress" and "want to know" and stores them in the product information category.

[1080] Step 4:

[1081] The server uses an emotion recognition engine (IBM Watson Tone Analyzer) to analyze the user's emotions from the text data. The analyzed emotion information is saved in the form of, for example, "excitement."

[1082] Input: Text data

[1083] Output: Emotional information

[1084] Specific operation: The server recognizes the emotional state of "excitement" and assigns it to text data and saves it.

[1085] Step 5:

[1086] The server searches a database for text data related to the user's question and generates an answer, for example, by searching a product database to obtain detailed information about the relevant product.

[1087] Input: Text data as a user question

[1088] Output: The generated answer

[1089] Specific operation: The server searches for information related to "red dress" and generates an answer such as "The price of the red dress is XXX yen and the material is YYY."

[1090] Step 6:

[1091] The server adjusts the tone of the response based on the analyzed emotion information: if the emotion is "excited," the server sets the tone of the response to be more energetic.

[1092] Input: Generated answers, sentiment information

[1093] Output: Tone-adjusted answer

[1094] Specific behavior: The server sets the tone with an energetic "The price is XXX yen and the ingredients are YYY!"

[1095] Step 7:

[1096] The terminal provides the generated answer to the user by voice, and the answer is communicated to the user through the audio output device.

[1097] Input: Generated Answer

[1098] Output: Provides answers to the user via voice

[1099] Specific operation: Through a smartphone or smart glasses, a voice message is provided to the user saying, "This red dress costs XXX yen and is made of YYY material!"

[1100] Step 8:

[1101] The server periodically checks the reminder information set by the user and notifies the user of necessary information using a reminder notification device.

[1102] Input: Saved keywords or tasks

[1103] Output: Reminder notification

[1104] Specific operation: The server checks the reminder information that "there is a meeting at 12 o'clock tomorrow" and notifies the smartphone that "it's almost time for the meeting."

[1105] Prompt Sentence Examples

[1106] User: "I want to know more about this red dress."

[1107] Assistant: "What information are you looking for? Price, ingredients, reviews, etc."

[1108] Through the above processing steps, the system provides high-quality information and reminder functions that take the user's emotions into consideration.

[1109] 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.

[1110] 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.

[1111] 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.

[1112] [Fourth embodiment]

[1113] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1114] 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.

[1115] 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).

[1116] 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.

[1117] 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.

[1118] 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).

[1119] 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.

[1120] 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.

[1121] 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.

[1122] 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.

[1123] 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.

[1124] 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.

[1125] 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."

[1126] The system of the present invention records conversations within the home in real time, organizes necessary information, provides answers, and provides reminder functions. The system effectively supports information sharing within the home through the following functions: receiving and analyzing voice data, storing and searching text data, providing real-time answers to user questions, and sending reminder notifications.

[1127] Receiving and converting audio data

[1128] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. The received voice data is sent to a server in real time and converted into text data using voice recognition technology. For example, a user's statement, "What's for dinner tonight?" is received as voice data and converted into text data.

[1129] Analyzing and storing text data

[1130] The server analyzes the converted text data and extracts important keywords and tasks. Natural language processing technology is used for this analysis. The extracted keywords and tasks are organized by category and saved in a database with a timestamp. For example, a statement such as "I need to buy eggs and milk" is classified as a shopping list and saved in the database.

[1131] Real-time answers to user questions

[1132] When a user asks, "What did we have for dinner last night?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text and searches a database for related past conversation data. For example, if someone says something about dinner last night, the device generates an answer based on that information, such as "We had curry rice for dinner last night," and provides it to the user via the device.

[1133] Reminder function

[1134] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. For example, if a user says, "Don't forget to take out the trash tomorrow morning," the server prepares to notify the user of that information the next morning. At the specified time, the device will notify the user by voice, "Don't forget to take out the trash."

[1135] Specific examples

[1136] As a concrete example, consider the following usage scenario:

[1137] 1. A user says, "I need to buy eggs and milk tomorrow morning."

[1138] 2. The device receives this audio and sends it to the server.

[1139] 3. The server converts the speech into text, analyzes it, and stores it in a database.

[1140] 4. The next morning, the server retrieves the reminder information from the database and sends a voice notification to the terminal saying, "Don't forget to buy eggs and milk."

[1141] In this way, the system of the present invention provides innovative support for information management within the home by using real-time reception and text conversion of voice data, data analysis and storage, real-time answers to user questions, and reminder notification functions.

[1142] The processing flow will be explained below.

[1143] Step 1:

[1144] A user says, "I need to buy eggs and milk tomorrow morning."

[1145] Step 2:

[1146] The device receives the user's speech through the microphone, captures it as audio data, and temporarily stores it in a buffer.

[1147] Step 3:

[1148] The terminal packetizes the voice data stored in the buffer and transmits it to the server in real time.

[1149] Step 4:

[1150] The server converts the received voice data into text data using a voice recognition API.

[1151] Step 5:

[1152] The server analyzes the converted text data and extracts important keywords and tasks, such as buying "eggs" and "milk."

[1153] Step 6:

[1154] The server organizes the extracted keywords and tasks into categories and stores them in a database along with timestamps.

[1155] Step 7:

[1156] The next morning, the server periodically checks the stored database for reminder information.

[1157] Step 8:

[1158] The server extracts the relevant reminder information and identifies the task that needs to be reminded at the moment. In this case, "buy eggs and milk" is extracted as an important task.

[1159] Step 9:

[1160] The server generates a message based on the extracted reminder information and sends it to the terminal.

[1161] Step 10:

[1162] The terminal receives the sent reminder information and issues a voice message to the user saying "Don't forget to buy eggs and milk" at the specified time.

[1163] Step 11:

[1164] The user receives a reminder message and performs the specified task.

[1165] In this way, the system of the present invention supports information management in daily life by recording user comments in real time, analyzing and saving necessary information, and sending reminders at appropriate times.

[1166] Example 1

[1167] 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."

[1168] In modern homes, a large amount of information is exchanged on a daily basis, and there is a need to efficiently manage this information and provide necessary information in a timely manner. However, conventional systems have had difficulty recording, organizing, and searching household conversation information in real time, and providing immediate answers to user questions. In particular, problems arise with missing information within the home, such as sudden reminder notifications and confirmation of important tasks. This invention aims to solve these problems.

[1169] 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.

[1170] In this invention, the server includes means for converting voice data into text data in real time using voice recognition technology, means for analyzing the text data and extracting important keywords and tasks using natural language processing technology, means for storing and searching the text data organized by category in a database, and means for notifying users of reminder information by voice at specified times. This allows for efficient information management within the home, enabling quick answers to users' questions and timely reminder notifications.

[1171] "Audio data" refers to digital data such as human speech and environmental sounds collected via a voice input device such as a microphone.

[1172] "Text data" is character string data that is expressed as text by analyzing voice data using voice recognition technology.

[1173] A "timestamp" is information indicating the date and time when data was generated, and is a time marker that is saved together with the text data.

[1174] "Natural language processing technology" is a computer technology that analyzes text data to understand meaning and extract keywords.

[1175] A "database" is a digital recording system that allows for the systematic accumulation, management, and retrieval of text data and related information.

[1176] "Reminder information" is information for notifying the user at a specific time about a task or event that the user has set in advance.

[1177] "Answer generation" is a process of searching for information related to a user's question and creating an appropriate response based on that information.

[1178] "Real-time" refers to a situation in which processing or response occurs immediately without delay.

[1179] The system of the present invention is designed to record conversations within the home in real time, organize necessary information, provide answers, and provide reminder functions. Specific embodiments will be described below.

[1180] The system of the present invention is composed of a terminal installed in the home and a server installed on the cloud or in the home.

[1181] Receiving and converting audio data

[1182] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. The device's built-in microphone captures the user's speech and environmental sounds. For example, if a user says, "I have to take out the trash tomorrow," the voice data is recorded on the device via the microphone.

[1183] The received voice data is sent in real time to the server, which then uses voice recognition technology (e.g., Google Cloud Speech-to-Text API) to convert the voice data into text data.

[1184] Analyzing and storing text data

[1185] The server analyzes the converted text data and uses natural language processing technology (e.g., SpaCy) to extract important keywords and tasks. The analyzed text data is organized by category and stored in a database (e.g., MySQL) with a timestamp.

[1186] For example, if a user says, "I need to buy eggs and milk," this will be classified as a shopping list category and stored in the database.

[1187] Real-time answers to user questions

[1188] When a user asks, "What did we have for dinner last night?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text and searches a database for relevant past conversation data. For example, if someone says something about dinner last night, the device generates an answer based on that information, such as "We had curry rice for dinner last night," and provides it to the user via the device.

[1189] Reminder function

[1190] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. For example, if a user says, "Don't forget to take out the trash tomorrow morning," the server prepares to notify the user of that information the next morning. At the specified time, the device will notify the user by voice, "Don't forget to take out the trash."

[1191] Specific examples

[1192] As a concrete example, consider the following usage scenario:

[1193] 1. A user says, "I need to buy eggs and milk tomorrow morning."

[1194] 2. The device receives this audio and sends it to the server.

[1195] 3. The server converts the speech into text, analyzes it, and stores it in a database.

[1196] 4. The next morning, the server retrieves the reminder information from the database and sends a voice notification to the terminal saying, "Don't forget to buy eggs and milk."

[1197] In this way, the system of the present invention effectively supports information management within the home through real-time reception and text conversion of voice data, data analysis and storage, real-time answers to user questions, and reminder notification functions.

[1198] Prompt Sentence Examples

[1199] You can see how the system works by inputting prompts like the following into the generative AI model:

[1200] "Tell me what you had for dinner last night."

[1201] "Do you have any reminders set for tomorrow?"

[1202] "What items have you added to your shopping list this week?"

[1203] This makes it easy to check that the system is working as expected.

[1204] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1205] Step 1: Receiving audio data

[1206] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. It captures what the user says (input) and converts that voice data into a digital format in real time (output). For example, a microphone might capture someone saying, "I have to take out the trash tomorrow."

[1207] Specific behavior:

[1208] A microphone captures the user's voice.

[1209] The captured audio data is converted into a digital format within the device.

[1210] Step 2: Sending audio data

[1211] The device sends the received voice data to the server. The digital voice data (input) is transferred to the server via the Internet (output).

[1212] Specific behavior:

[1213] The terminal breaks down the voice data into packets and sends them to a server over the Internet.

[1214] The server receives the transmitted packets and reconstructs the audio data.

[1215] Step 3: Convert the audio data

[1216] The server converts the received voice data into text data using voice recognition technology. The voice data (input) is analyzed and converted into character string data (output).

[1217] Specific behavior:

[1218] The server performs voice analysis using voice recognition technology (e.g., Google Cloud Speech-to-Text API).

[1219] The analyzed voice data is output as text data.

[1220] Step 4: Analyzing the text data

[1221] The server analyzes the converted text data and extracts important keywords and tasks. The text data (input) is analyzed using natural language processing technology (e.g., SpaCy), and the extracted keywords and tasks (output) are stored in a database.

[1222] Specific behavior:

[1223] The server uses natural language processing technology to perform semantic analysis of the text data.

[1224] Important keywords (e.g., taking out the trash) are extracted.

[1225] The extracted keywords are organized into categories (e.g., housework reminders) and stored in a database.

[1226] Step 5: Generate answers to user questions

[1227] When a user asks, "What did I have for dinner last night?", the device receives the question as voice data (input) and sends it to the server, which converts the voice data into text, searches past conversation data, and generates a relevant answer (output).

[1228] Specific behavior:

[1229] The terminal transmits the voice data to the server.

[1230] The server converts the speech into text and searches the database.

[1231] Based on the search results, the answer "I had curry rice for dinner last night" is generated and sent to the device.

[1232] The terminal generates a response and provides it to the user as a voice.

[1233] Step 6: Execute the reminder function

[1234] The server periodically checks the saved keywords and tasks, extracts information that requires reminders, and generates notifications at specific times based on the information (input) and sends them to the device (output).

[1235] Specific behavior:

[1236] The server runs a scheduled job to check the stored data.

[1237] Reminder information is extracted and notification content is generated.

[1238] At the specified time, the server transmits the notification data to the terminal.

[1239] The device will notify you with a voice message saying, "Don't forget to take out the trash."

[1240] (Application example 1)

[1241] 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."

[1242] Communication between store clerks and customers in brick-and-mortar stores must be accurate and efficient. However, in reality, it is difficult for store clerks to accurately remember past conversations or to provide appropriate responses quickly. Furthermore, they tend to forget specific work tasks, which reduces work efficiency. To solve these problems, a system is needed that can record and analyze conversations between store clerks and customers in real time.

[1243] 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.

[1244] In this invention, the server includes means for receiving voice data 24 hours a day, 365 days a year, means for converting the received voice data into text data, means for saving the converted text data together with a timestamp, means for analyzing the saved text data and extracting important keywords and tasks, means for searching for text data related to a user's question and generating an answer, means for providing the generated answer to the user by voice, means for notifying the user of necessary reminder information, means for recording and analyzing conversations between a store clerk and a customer in real time, means for generating an appropriate answer based on past conversation data and providing it to the store clerk, and means for sending reminder notifications for specific tasks. This allows the store clerk to provide an appropriate answer based on past conversation data and receive reminders for specific work tasks.

[1245] "Audio data" refers to data that represents an audio signal in digital or analog form.

[1246] "Text data" refers to digital data expressed as character string information.

[1247] A "timestamp" is date and time information recorded for specific data.

[1248] A "server" is a computer system that processes and stores data over a network.

[1249] "Important keywords" are words or phrases that deserve special attention within the text data being analyzed.

[1250] A "task" is a task or action to achieve a specific purpose.

[1251] "User" means a person or individual who uses the System.

[1252] "Reminder information" refers to information that notifies or alerts the user to specific tasks or matters.

[1253] A "means" is a method or apparatus for achieving a particular function.

[1254] A "store associate" is an employee who provides services to customers in a physical store.

[1255] A "customer" is a person who visits a physical store and uses a product or service.

[1256] "Conversation data" refers to the content of a conversation that is recorded as voice data and analyzed.

[1257] "Real-time recording" means that there is little time delay and the audio data is recorded at the exact moment the conversation occurs.

[1258] "Means of analysis" refers to techniques and methods for analyzing the content of data and extracting meaning.

[1259] A "means for generating an answer" is a method or device for automatically generating an appropriate response from the analyzed data.

[1260] A "reminder notification" is a notification that notifies the user not to forget specific information or tasks.

[1261] The system for implementing the present invention includes a voice receiving terminal installed in a physical store, a server that performs text conversion and data analysis, a database, and a device that performs notifications.

[1262] 1. Receiving and converting audio data

[1263] The terminal is installed in the store and receives conversations between store staff and customers 24 hours a day, 365 days a year. This records all interactions within the store. The received voice data is sent to a server in real time and converted into text data using a speech recognition engine (e.g., TensorFlow or PyTorch).

[1264] 2. Analyzing and saving text data

[1265] The converted text data is then analyzed by the server. Natural language processing technology is used in this analysis to extract important keywords and tasks. The extracted keywords and tasks are then stored in a database with a timestamp using Elasticsearch. For example, if someone says, "Update sale information at 3 p.m.", it is organized and saved in the appropriate category.

[1266] 3. Real-time answers to user questions

[1267] When a store clerk asks through smart glasses or a smartphone, "What was the special sale information yesterday?", the server converts this voice data into text and uses Elasticsearch to search for related past conversation data. If a conversation about special sales information has been recorded in the past, the server generates an answer such as "Yesterday's special sale item was drinking water," and displays this information on the smart glasses or smartphone.

[1268] 4. Reminder function

[1269] The server periodically checks the saved keywords and tasks and extracts information that requires a reminder. For example, if the information is "We need to organize the shelves in preparation for tomorrow's opening," it will send a notification to the store clerk's smartphone at the specified time saying, "Please organize the shelves."

[1270] Specific examples

[1271] For example, consider the following usage scenario:

[1272] 1. A store clerk says, "We need to update the sale information at 3:00 PM."

[1273] 2. The device receives this audio and sends it to the server.

[1274] 3. The server converts the speech into text, analyzes it, and stores it in a database.

[1275] 4. At 3:00 p.m., the server retrieves the reminder information from the database and sends a voice notification to the terminal saying, "Please update your sale information."

[1276] Prompt Sentence Examples

[1277] Example: "What products were on sale yesterday?"

[1278] Sample answer: "There was a sale on drinking water yesterday."

[1279] The system of the present invention enables accurate and efficient communication between store staff and customers in physical stores, thereby improving business efficiency.

[1280] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1281] Step 1: Receiving audio data

[1282] The terminal is installed in the store and receives conversations between store staff and customers 24 hours a day, 365 days a year. The input is voice data, which the terminal receives in real time. The output is the voice data itself.

[1283] Step 2: Send and convert audio data

[1284] The device sends the received voice data to the server in real time. The server uses a speech recognition engine (e.g., TensorFlow or PyTorch) to convert the voice data into text data. The input is voice data, and the output is text data.

[1285] Step 3: Analyze and save the text data

[1286] The server analyzes the converted text data using natural language processing technology, extracts important keywords and tasks, and stores them in a database with a timestamp using Elasticsearch. The input is text data, and the data that is analyzed and classified is output. A timestamp is added to the stored data.

[1287] Step 4: Generate answers to user questions

[1288] A store clerk asks a question through smart glasses or a smartphone. The question is received as voice data and sent to a server. The server converts the voice to text and uses Elasticsearch to search relevant past conversation data. The input is the voice data (question) and the output is the search results. The server generates an appropriate answer and displays it on the smart glasses or smartphone.

[1289] Step 5: Execute the reminder function

[1290] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. At the specified time, a reminder notification is sent to the terminal or the store clerk's smartphone. The input is the task information saved in the database, and the output is the reminder notification. The notification is displayed on the smart glasses or smartphone.

[1291] Step 6: Providing responses and notifications

[1292] The server generates answers and provides them to the smart glasses or smartphone as text or voice, as well as reminder notifications. The input is the generated answers or reminder information, and the output is a notification message for the user.

[1293] As described above, the system of the present invention executes each step in a step-by-step manner, from receiving voice data to converting it into text, analyzing it, saving it, and then sending reminders and providing appropriate responses. This allows for accurate recording and analysis of communications between store staff and customers in physical stores, enabling efficient responses.

[1294] 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.

[1295] This invention is a system that records conversations within the home in real time and recognizes the user's emotions, thereby enabling more effective information organization, answer provision, and reminder functions.In addition to receiving and converting voice data, saving and analyzing text data, providing answers to user questions, and sending reminder notifications, the invention incorporates an emotion recognition engine, making it possible to respond based on the user's emotions.

[1296] Receiving and converting audio data

[1297] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. The received voice data is sent to a server in real time and converted into text data using voice recognition technology. For example, a user's statement such as "I need to buy eggs and milk tomorrow morning" is received as voice data and converted into text data.

[1298] Analyzing and storing text data

[1299] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing technology. The extracted keywords and tasks are organized by category and saved in a database with a timestamp. For example, "eggs" and "milk" are added to the "shopping" category.

[1300] emotion recognition

[1301] The server is equipped with an emotion engine that recognizes the user's emotions from the voice data. For example, it can infer the user's stress level from a statement such as "I have a meeting tomorrow, so I'm feeling stressed." This information is saved along with the text data and used to adjust future task priorities and response content.

[1302] Real-time answers to user questions

[1303] When a user asks, "What did you have for dinner last night?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text and searches a database for related past conversation data. For example, if the comment about last night's dinner was "curry rice," the device generates the answer "We had curry rice for dinner last night" and provides it to the user via the device. It is also possible to adjust the tone and content of the answer based on emotion recognition information.

[1304] Reminder function

[1305] The server periodically checks the saved keywords and tasks and extracts any information that requires a reminder. For example, if a task is set to "buy eggs and milk tomorrow morning," the server prepares to notify the user of that information the following morning. At the specified time, the device will notify the user with a voice message saying, "Don't forget to buy eggs and milk." If the user is under stress, the server will also adjust the tone of the notification to be softer.

[1306] Specific examples

[1307] As a concrete example, consider the following usage scenario:

[1308] 1. A user says, "I need to buy eggs and milk tomorrow morning."

[1309] 2. The device receives this audio and sends it to the server.

[1310] 3. The server converts the voice data into text, analyzes it, and stores it in a database.

[1311] 4. The server uses the emotion engine to recognize the user's emotion as "a little tired."

[1312] 5. The next morning, the server retrieves the reminder information from the database and generates a notification message in a soft tone, taking into account your emotional state, saying, "Don't forget to buy eggs and milk."

[1313] 6. The device will notify the user by voice, "Don't forget to buy eggs and milk."

[1314] In this way, the system of the present invention provides information management and support functions that take into account the user's emotions, thereby realizing higher quality communication and information management within the home.

[1315] The processing flow will be explained below.

[1316] Step 1:

[1317] A user says, "I need to buy eggs and milk tomorrow morning."

[1318] Step 2:

[1319] The device receives the user's speech through a microphone and captures it as voice data.

[1320] Step 3:

[1321] The device transmits the audio data to the server in real time.

[1322] Step 4:

[1323] The server converts the voice data into text data using a voice recognition API.

[1324] Step 5:

[1325] The server analyzes the text data and extracts the important keywords "egg" and "milk."

[1326] Step 6:

[1327] The server uses an emotion engine to analyze the user's emotions from the voice data and recognizes that the user is "feeling a little stressed."

[1328] Step 7:

[1329] The server organizes the extracted keywords and emotion data by category and stores them in a database along with a timestamp.

[1330] Step 8:

[1331] The next morning, the server periodically checks the stored database and extracts the information that needs to be reminded: "Buy eggs and milk."

[1332] Step 9:

[1333] The server takes emotion data into consideration when generating a notification message, where the tone is softened based on the emotion data.

[1334] Step 10:

[1335] The server sends the generated remind message to the terminal.

[1336] Step 11:

[1337] The device will then play a soft voice reminder message to the user saying, "Don't forget to buy eggs and milk."

[1338] Step 12:

[1339] The user receives a reminder message and performs the specified task.

[1340] Example 2

[1341] 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."

[1342] There is a demand for systems to effectively record and organize conversations within the home and provide necessary information in a timely manner. They are also expected to improve the user experience by understanding the user's emotions and responding accordingly. However, current systems lack sufficient functionality to meet these requirements, resulting in suboptimal information management and communication within the home. In particular, they lack the ability to recognize the user's emotions and provide information or reminders based on them.

[1343] 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.

[1344] In this invention, the server includes a means for converting voice data into text data, a means for analyzing text using natural language processing technology, and a means for recognizing emotions and saving them as data. By converting and analyzing voice data into text data and recognizing and saving emotions, the server can organize and provide information according to user needs. Furthermore, the content and tone of responses and reminders can be adjusted based on the user's emotions, enabling higher-quality information management and a better user experience.

[1345] "Audio data" is a recording of sounds, including the user's speech, captured within the home.

[1346] "Text data" is information obtained by converting voice data into a character string format.

[1347] A "timestamp" is information about the exact date and time when data was created or modified.

[1348] "Keywords" are important words or phrases extracted during text data analysis.

[1349] "Tasks" are user action plans or things to do that are derived from keywords.

[1350] "Emotion recognition" is a technology that determines a user's emotional state from voice data and text data.

[1351] "Natural language processing technology" is a set of computer technologies for analyzing, understanding, and generating human language.

[1352] A "database" is a system that systematically stores and manages text data and related information.

[1353] A "remind" is a notification that prompts the user to reconfirm a specific piece of information or task.

[1354] "Answer generation" is the process of providing appropriate information in response to a user's question.

[1355] This invention is a system that records conversations within the home in real time and recognizes the user's emotions to effectively organize information, provide answers, and provide reminder functions.In addition to receiving and converting voice data, saving and analyzing text data, providing answers to user questions, and sending reminder notifications, the system incorporates an emotion recognition engine, making it possible to respond based on the user's emotions.

[1356] Receiving and converting audio data

[1357] The device is installed in the home and receives voice data 24 hours a day, 365 days a year. A voice recognition device (e.g., a smart speaker with a microphone) is used to receive the voice data. The received voice data is sent to a server in real time and converted into text data using voice recognition software (e.g., a voice recognition API). For example, if a user says, "I need to buy eggs and milk tomorrow morning," this voice data is sent from the device to the server in real time and converted into text data.

[1358] Analyzing and storing text data

[1359] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing technology (e.g., a natural language processing library). The extracted keywords and tasks are organized by category and stored in a database with a timestamp. For example, the words "eggs" and "milk" uttered by the user are added to the "shopping" category.

[1360] emotion recognition

[1361] The server is equipped with an emotion recognition engine that can recognize the user's emotions from the voice data. For example, if a user says, "I'm stressed because I have a meeting tomorrow," the server analyzes this information and recognizes that the user is feeling stressed. This emotional information is saved along with the text data and used to adjust future task priorities and responses.

[1362] Real-time answers to user questions

[1363] When a user asks, "What did you have for dinner last night?", the device receives the voice and sends it to the server. The server converts the voice data into text and searches a database for related past conversation data. For example, if the user has recorded, "I had curry rice for dinner last night," the server generates a response, "I had curry rice for dinner last night," and notifies the user via the device. If necessary, the tone and content of the response can be adjusted based on emotion recognition information.

[1364] Reminder function

[1365] The server periodically checks the saved keywords and tasks and extracts tasks that require reminders. For example, if a user sets a task to "buy eggs and milk tomorrow morning," the server prepares to remind the user of this information the next morning. At the specified time, the server generates a reminder message saying, "Don't forget to buy eggs and milk," and notifies the user of this message by voice via the device. The tone of the message can also be adjusted taking into account the user's emotional state.

[1366] for example:

[1367] A user says, "I need to buy eggs and milk tomorrow morning."

[1368] The terminal receives this audio and sends it to the server.

[1369] The server converts the voice data into text, analyzes it, and stores it in a database.

[1370] The server uses an emotion recognition engine to recognize the user's emotion as "a little tired."

[1371] The next morning, the server retrieves the reminder information from the database and generates a notification message in a soft tone, taking into account the user's emotional state, saying, "Don't forget to buy eggs and milk."

[1372] The device will notify the user by voice, "Don't forget to buy eggs and milk."

[1373] This system provides information management and support functions that take the user's emotions into consideration, realizing high-quality communication and information management within the home.

[1374] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1375] Step 1:

[1376] The device receives voice 24 hours a day, 365 days a year. User speech is captured through a microphone as voice data input. This voice data is converted into digital format and sent to the server in real time. For example, if a user says, "I need to buy eggs and milk tomorrow morning," the voice data is captured and sent to the server.

[1377] Step 2:

[1378] The server converts the received voice data into text data. It receives the voice data as input, analyzes it using voice recognition software (e.g., a voice recognition API), and generates text data in the form of a string. The output is the text data, "I need to buy eggs and milk tomorrow morning."

[1379] Step 3:

[1380] The server analyzes the converted text data. It receives the text data as input and uses natural language processing technology (e.g., a natural language processing library) to extract important keywords and tasks. Specifically, it extracts nouns and verbs and identifies important words. The keywords "egg," "milk," and "buy" are extracted as output.

[1381] Step 4:

[1382] The server performs emotion recognition using the extracted keywords. It receives voice and text data as input and analyzes the user's emotions using an emotion recognition engine (e.g., emotion analysis API). Specifically, it analyzes the tone and context of the speech to determine emotional states such as stress and fatigue. The output identifies the emotional information "I'm a little tired."

[1383] Step 5:

[1384] The server stores the analyzed text data and emotional information in a database. It receives text data and emotional information as input and records them in the database along with a timestamp. Specifically, it organizes the data by category and adds "eggs" and "milk" to the "shopping" category.

[1385] Step 6:

[1386] When a user asks, "What was for dinner last night?", the device receives the question as voice data and sends it to the server. It receives voice data as input and forwards it to the server.

[1387] Step 7:

[1388] The server converts the received voice data back into text data and searches the database for related past conversation data. It obtains the newly converted text data as input. Specifically, it searches past records related to "dinner" and generates an answer such as "Last night's dinner was curry rice." It then generates the answer text as output.

[1389] Step 8:

[1390] The device plays back the answer sent from the server as voice. It receives the answer in text format as input and converts it into voice data using voice synthesis technology (e.g., voice synthesis API). Specifically, it notifies the user by voice, "I had curry rice for dinner last night."

[1391] Step 9:

[1392] The server periodically checks the set tasks and information that requires reminders, and prepares reminders in a timely manner. It references previously saved task information as input and checks the timing of the reminder. Specifically, if a task such as "Buy eggs and milk tomorrow morning" is set, it prepares that information.

[1393] Step 10:

[1394] When the specified time arrives, the server generates a reminder message and notifies the user via the device. It receives reminder task information as input and generates a message that takes emotional information into account. Specifically, it generates a gentle voice message saying, "Don't forget to buy eggs and milk," and the device notifies the user.

[1395] Through the above process, this system provides information management and support functions that take the user's emotions into consideration, improving the quality of communication and information management within the home.

[1396] (Application example 2)

[1397] 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."

[1398] Conventional home conversation recording systems convert users' voices into text data and provide information management and reminder functions, but they only provide simple information without considering the user's emotional state. This has led to problems such as missing important information and failing to convey the nuances desired by the user. Furthermore, in certain application areas such as virtual stores, the systems lack the functionality to contribute to improving the user experience, and have not been able to sufficiently improve user satisfaction.

[1399] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving voice data 24 hours a day, 365 days a year, means for converting the received voice data into text data, means for saving the converted text data together with a timestamp, means for analyzing the saved text data and extracting important keywords and tasks, means for searching for text data related to a user's question and generating an answer, means for providing the generated answer to the user by voice, means for notifying the user of necessary reminder information, means for analyzing the user's emotions using emotion recognition technology, means for adjusting the tone of the answer based on the analyzed emotion, and means for providing detailed product information in a virtual store. This enables the provision of higher quality information and reminders that take the user's emotions into consideration.

[1400] "Means for receiving voice data 24 hours a day, 365 days a year" refers to equipment and software that constantly receives the user's voice and transmits it to the system.

[1401] "Means for converting received voice data into text data" refers to software or algorithms that convert voice received from a user into text information in real time.

[1402] "Means for saving the converted text data together with a timestamp" refers to equipment or software for adding time information to the converted text data and saving it in a database.

[1403] "Means of analyzing stored text data and extracting important keywords and tasks" refers to software that uses natural language processing technology to analyze and extract necessary information from stored text data.

[1404] "Means for searching text data related to a user's question and generating an answer" refers to software for searching a database for information related to a user's question and generating an appropriate answer.

[1405] The "means for providing the generated answer to the user by voice" refers to a speaker or voice output software for transmitting the generated answer to the user as voice.

[1406] "Means for notifying the user of necessary reminder information" refers to an alert or message issuing device for notifying the user of tasks or information set by the user.

[1407] "Means of analyzing user emotions using emotion recognition technology" refers to software or algorithms for inferring user emotions from voice data or text data.

[1408] "Means for adjusting the tone of a response based on the analyzed emotions" refers to technology or software for appropriately changing the wording or tone of a response depending on the user's emotions.

[1409] "Means for providing detailed product information within a virtual store" refers to a system or software for providing information about products that users want in a virtual store in text or audio format.

[1410] System Overview

[1411] This system receives voice data in real time, converts it into text data, analyzes it, saves it, recognizes the user's emotions, and provides information and reminders accordingly. It is primarily intended for use in the home, but can also be applied to virtual stores. The main components of the system include a voice data receiving device, a text conversion device, a natural language processing analysis engine, an emotion recognition engine, a database, and a reminder notification device.

[1412] Receiving and converting audio data

[1413] The device is installed in a home or virtual store and receives voice data 24 hours a day, 365 days a year. For example, this could be a smartphone or smart glasses. The received voice data is sent to a server in real time. The server uses a speech recognition API (e.g., Google Cloud Speech-to-Text API) to convert the voice data into text data.

[1414] Analyzing and storing text data

[1415] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing techniques, such as natural language processing libraries (e.g., SpaCy or NLTK). The extracted keywords and tasks are organized by category and stored in a database (e.g., MongoDB) with a timestamp.

[1416] emotion recognition

[1417] The server is equipped with an emotion recognition engine (e.g., IBM Watson Tone Analyzer) that analyzes the user's emotions from voice and text data. For example, a statement such as "This product is great" can be used to recognize the user's positive emotions. This emotional information is stored along with the text data and used for later information provision and reminders.

[1418] Real-time answers and reminders

[1419] For example, if a user asks, "What is this shirt made of?", the device receives the question as voice data and sends it to the server. The server converts the voice data into text using a voice recognition API and searches a database for related text data. For example, it retrieves the material information of the relevant shirt from a product database, generates a response such as "This shirt is made of 100% cotton," and provides it to the user via the device. It is also possible to adjust the tone and content of the response based on emotion recognition information.

[1420] For reminder functions, the server periodically checks saved keywords and tasks and extracts information that requires a reminder. For example, if a user sets a meeting for tomorrow at 12 o'clock, the device will notify them at the specified time, saying, "It's almost time for the meeting." If the user is under stress, the notification tone will be softened.

[1421] Specific examples

[1422] When a user says, "I'd like to know more about this red dress," the device receives the voice and sends it to the server. The server converts the voice data into text, and an emotion recognition engine determines that the user is excited. It then searches a product database and generates detailed information about the corresponding dress. The generated information is provided as a spoken answer, such as, "The price of this red dress is XXX yen, and the material is YYY."

[1423] Example prompts for generative AI models

[1424] User: "I want to know more about this red dress."

[1425] Assistant: "What information are you looking for? Price, ingredients, reviews, etc."

[1426] In this way, this system has information management and support functions that take the user's emotions into consideration, providing a higher quality experience at home or in a virtual store.

[1427] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1428] Step 1:

[1429] When a user speaks at home or in a virtual store, the voice data is received by a device (such as a smartphone or smart glasses). The voice data contains the content of the user's speech and is sent to the server as "voice data."

[1430] Input: User's voice data

[1431] Output: Audio data sent to the server

[1432] Specific operation: When a user says, "I want to know more about this red dress," the smartphone or smart glasses receive it and send it to the server as voice data.

[1433] Step 2:

[1434] The server passes the received voice data to a speech recognition API and converts it into text data. This process uses speech recognition technologies such as the Google Cloud Speech-to-Text API. The converted text data contains the user's speech as text information.

[1435] Input: Received audio data

[1436] Output: Text data

[1437] Specific operation: The server calls the speech recognition API and converts the speech "I want to know more about this red dress" into text data "I want to know more about this red dress."

[1438] Step 3:

[1439] The server analyzes the converted text data and extracts important keywords and tasks. This analysis uses natural language processing libraries (SpaCy and NLTK). The analyzed information is organized by cargo and stored in a database.

[1440] Input: Text data

[1441] Output: Parsed keywords and tasks

[1442] Specific operation: The server extracts important keywords such as "red dress" and "want to know" and stores them in the product information category.

[1443] Step 4:

[1444] The server uses an emotion recognition engine (IBM Watson Tone Analyzer) to analyze the user's emotions from the text data. The analyzed emotion information is saved in the form of, for example, "excitement."

[1445] Input: Text data

[1446] Output: Emotional information

[1447] Specific operation: The server recognizes the emotional state of "excitement" and assigns it to text data and saves it.

[1448] Step 5:

[1449] The server searches a database for text data related to the user's question and generates an answer, for example, by searching a product database to obtain detailed information about the relevant product.

[1450] Input: Text data as a user question

[1451] Output: The generated answer

[1452] Specific operation: The server searches for information related to "red dress" and generates an answer such as "The price of the red dress is XXX yen and the material is YYY."

[1453] Step 6:

[1454] The server adjusts the tone of the response based on the analyzed emotion information: if the emotion is "excited," the server sets the tone of the response to be more energetic.

[1455] Input: Generated answers, sentiment information

[1456] Output: Tone-adjusted answer

[1457] Specific behavior: The server sets the tone with an energetic "The price is XXX yen and the ingredients are YYY!"

[1458] Step 7:

[1459] The terminal provides the generated answer to the user by voice, and the answer is communicated to the user through the audio output device.

[1460] Input: Generated Answer

[1461] Output: Provides answers to the user via voice

[1462] Specific operation: Through a smartphone or smart glasses, a voice message is provided to the user saying, "This red dress costs XXX yen and is made of YYY material!"

[1463] Step 8:

[1464] The server periodically checks the reminder information set by the user and notifies the user of necessary information using a reminder notification device.

[1465] Input: Saved keywords or tasks

[1466] Output: Reminder notification

[1467] Specific operation: The server checks the reminder information that "there is a meeting at 12 o'clock tomorrow" and notifies the smartphone that "it's almost time for the meeting."

[1468] Prompt Sentence Examples

[1469] User: "I want to know more about this red dress."

[1470] Assistant: "What information are you looking for? Price, ingredients, reviews, etc."

[1471] Through the above processing steps, the system provides high-quality information and reminder functions that take the user's emotions into consideration.

[1472] 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.

[1473] 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.

[1474] 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.

[1475] 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.

[1476] 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.

[1477] 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.

[1478] 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).

[1479] 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.

[1480] 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."

[1481] 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.

[1482] 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).

[1483] 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.

[1484] 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.

[1485] 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.

[1486] 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.

[1487] 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.

[1488] 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.

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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.

[1493] The following is further disclosed regarding the above embodiment.

[1494] (Claim 1)

[1495] A means of receiving voice data 24 hours a day, 365 days a year;

[1496] means for converting received voice data into text data;

[1497] A means for storing the converted text data together with a timestamp;

[1498] A method for analyzing saved text data and extracting important keywords and tasks.

[1499] means for searching text data related to a user's question and generating an answer;

[1500] means for audibly providing the generated answer to the user;

[1501] means for notifying the user of necessary reminder information;

[1502] A system including:

[1503] (Claim 2)

[1504] 2. The system according to claim 1, further comprising means for organizing and saving the analyzed keywords and tasks by category.

[1505] (Claim 3)

[1506] 10. The system of claim 1, further comprising means for providing the generated answers in real time.

[1507] "Example 1"

[1508] (Claim 1)

[1509] means for receiving audio data;

[1510] means for converting received voice data into text data;

[1511] A means for storing the converted text data together with a timestamp;

[1512] A method for analyzing saved text data and extracting important keywords and tasks.

[1513] means for searching text data related to a user's question and generating an answer;

[1514] means for audibly providing the generated answer to the user;

[1515] means for notifying a user of reminder information;

[1516] A means for converting voice data into text data in real time using voice recognition technology;

[1517] A means for analyzing text data using natural language processing technology;

[1518] A means to store and search text data organized by category in a database,

[1519] The system includes a means for notifying reminder information by voice at a specified time.

[1520] (Claim 2)

[1521] 2. The system according to claim 1, further comprising means for organizing and saving the analyzed keywords and tasks by category.

[1522] (Claim 3)

[1523] 10. The system of claim 1, further comprising means for providing the generated answers in real time.

[1524] "Application Example 1"

[1525] (Claim 1)

[1526] A means of receiving voice data 24 hours a day, 365 days a year;

[1527] means for converting received voice data into text data;

[1528] A means for storing the converted text data together with a timestamp;

[1529] A method for analyzing saved text data and extracting important keywords and tasks.

[1530] means for searching text data related to a user's question and generating an answer;

[1531] means for audibly providing the generated answer to the user;

[1532] means for notifying the user of necessary reminder information;

[1533] A means of recording and analyzing conversations between store clerks and customers in real time,

[1534] A means for generating appropriate responses based on past conversation data and providing them to store clerks;

[1535] A means to send reminders about specific tasks;

[1536] A system including:

[1537] (Claim 2)

[1538] 2. The system according to claim 1, further comprising means for organizing and saving the analyzed keywords and tasks by category.

[1539] (Claim 3)

[1540] 10. The system of claim 1, further comprising means for providing the generated answers in real time.

[1541] "Example 2: Combining Emotion Engines"

[1542] (Claim 1)

[1543] A means of receiving voice data 24 hours a day, 365 days a year;

[1544] means for converting received voice data into text data;

[1545] A means for storing the converted text data together with a timestamp;

[1546] A method for analyzing saved text data and extracting important keywords and tasks.

[1547] means for recognizing a user's emotion;

[1548] means for adjusting and storing text data based on emotion information;

[1549] means for searching text data related to a user's question and generating an answer;

[1550] means for audibly providing the generated answer to the user;

[1551] means for notifying the user of necessary reminder information;

[1552] A system including:

[1553] (Claim 2)

[1554] 2. The system according to claim 1, further comprising means for organizing and saving the analyzed keywords and tasks by category.

[1555] (Claim 3)

[1556] 10. The system of claim 1, further comprising means for providing the generated answers in real time.

[1557] "Application example 2 when combining emotion engines"

[1558] (Claim 1)

[1559] A means of receiving voice data 24 hours a day, 365 days a year;

[1560] means for converting received voice data into text data;

[1561] A means for storing the converted text data together with a timestamp;

[1562] A method for analyzing saved text data and extracting important keywords and tasks.

[1563] means for searching text data related to a user's question and generating an answer;

[1564] means for audibly providing the generated answer to the user;

[1565] means for notifying the user of necessary reminder information;

[1566] A means for analyzing a user's emotions using emotion recognition technology;

[1567] a means of adjusting the tone of the response based on the analyzed sentiment;

[1568] a means for providing detailed product information within the virtual store;

[1569] A system including:

[1570] (Claim 2)

[1571] 2. The system according to claim 1, further comprising means for organizing and saving the analyzed keywords and tasks by category.

[1572] (Claim 3)

[1573] 10. The system of claim 1, further comprising: means for providing generated answers in real time; and means for adjusting the content of the answers based on emotion recognition. [Explanation of symbols]

[1574] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving voice data 24 hours a day, 365 days a year; means for converting received voice data into text data; A means for storing the converted text data together with a timestamp; A method for analyzing saved text data and extracting important keywords and tasks. A means for searching text data related to a user's question and generating an answer; means for audibly providing the generated answer to the user; means for notifying the user of necessary reminder information; A system including:

2. 2. The system according to claim 1, further comprising means for organizing and saving the analyzed keywords and tasks by category.

3. 10. The system of claim 1, further comprising means for providing the generated answers in real time.

Images