System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving input data from a user; means for analyzing the input data by natural language processing; means for determining a need of the user based on a result of the analysis; means for selecting an appropriate hospitality action from a Japanese hospitality action database; means for generating the selected hospitality action as a specific action or message; and means for providing the generated action or message to the user.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] Modern AI systems lack human-like qualities and local culture and customs, resulting in mechanical, emotionless responses. To solve this problem, it is important to accurately understand the user's needs and provide appropriate hospitality behavior based on those needs. This invention aims to improve the user experience by using generative AI that incorporates the unique Japanese spirit of "omotenashi" (hospitality) to provide warm, rather than mechanical, responses. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for receiving input data from a user, a means for analyzing the input data using natural language processing, a means for determining the user's needs based on the analysis results, a means for selecting appropriate hospitality actions from a database of Japanese hospitality actions, a means for generating specific actions and messages based on the selected hospitality actions, and a means for providing the generated actions and messages to the user. Furthermore, the present invention may include a means for converting voice input into text, and a means for displaying or providing the generated actions and messages to the user by voice. This configuration enables a warm and welcoming response that meets the user's needs.

[0006] "User" refers to a person who uses the system.

[0007] "Input data" is information provided by a user to a system, including information in the form of text, audio, images, etc.

[0008] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0009] "Analysis" is the process of understanding the content of input data and extracting meaning and intent.

[0010] "Needs" refers to the services, information, and responses that users are looking for.

[0011] The "Hospitality Behavior Database" is a database that records behaviors and responses based on Japanese-specific customer service and etiquette.

[0012] "Hospitality behavior" refers to specific actions or responses taken toward users in the course of service or customer service.

[0013] An "action" refers to a specific operation or behavior that a system performs.

[0014] "Message" refers to information or a response provided by the system to the user.

[0015] "Generation" is the process by which the system creates new actions and messages based on input data and analysis results.

[0016] "Providing" refers to communicating system-generated actions and messages to the user. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] System Overview

[0039] This invention is a system that includes a generative AI that understands user needs and provides the uniquely Japanese "omotenashi" hospitality. This system receives input data from users, analyzes the data, and selects and generates appropriate hospitality actions to provide warm and welcoming service to users.

[0040] A natural language description of the program's operation

[0041] Input from the user

[0042] The user inputs voice or text into the device. For example, the user might say, "Please tell me what dishes you recommend." The device receives this voice input and converts it into text data using its voice recognition function.

[0043] Sending data

[0044] The device sends the converted text data to the server, which receives it and passes it to a natural language processing (NLP) module.

[0045] Data analysis

[0046] The server's NLP module analyzes the text data. This analysis allows it to understand the meaning and intent behind the user's statements and identify the information and actions the user is seeking. For example, it can understand a user's need to know what dishes they recommend.

[0047] Choosing actions based on needs

[0048] Based on the analysis results, the server selects an appropriate hospitality action from a database of hospitality actions specific to Japan, such as "recommending dishes."

[0049] Action and message generation

[0050] The server generates specific actions and messages based on the selected behavior. The generated messages provide appropriate information to the user and realize a warm and friendly response. For example, it generates a message such as "Our recommendation is seasonal fresh fish sashimi."

[0051] Responding to the user

[0052] The generated message is sent from the server to the terminal, which receives it and provides it to the user by displaying or speaking it. In addition, in the case of a customer service robot, it performs an appropriate physical action (e.g., smiling or exchanging business cards).

[0053] Specific examples

[0054] Example 1: Restaurant service robot

[0055] 1. User Input

[0056] A user speaks to a customer service robot installed in a restaurant and asks, "What dishes do you recommend?"

[0057] The terminal (robot) receives this voice and converts it into text using voice recognition.

[0058] 2. Data submission and analysis

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

[0060] The server receives the data and analyzes it using a natural language processing module.

[0061] The server determines that the user's need is "I want to know recommended dishes."

[0062] 3. Action selection and generation

[0063] Based on the analysis results, the server selects the action of "suggesting recommended dishes" from the hospitality action database.

[0064] Generate a message saying, "Our recommendation is sashimi made from fresh seasonal fish."

[0065] 4. Responding to the User

[0066] The server sends the generated message to the terminal.

[0067] The terminal (robot) announces in voice, "Our recommendation is sashimi made from fresh seasonal fish," and shows a smiling face.

[0068] In this way, the present invention makes it possible to improve the user experience by embodying the uniquely Japanese hospitality using generative AI.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] The user inputs input data (text or voice) into the device. For example, in a restaurant, the user might say, "Please tell me what dishes you recommend." The device receives this voice.

[0072] Step 2:

[0073] The voice data received by the device is passed to the voice recognition module, which converts it into text, and the converted text data is sent to the server.

[0074] Step 3:

[0075] The server receives the text data, passes it to a natural language processing (NLP) module, and analyzes the text data.

[0076] Step 4:

[0077] The server's NLP module analyzes the context and meaning of the text data to identify the user's needs, such as "I want to know what dishes are recommended."

[0078] Step 5:

[0079] Based on the analysis results, the server sends a query to the Japanese hospitality behavior database to search for an appropriate hospitality behavior. For example, it selects the behavior of "recommending dishes."

[0080] Step 6:

[0081] The server generates specific actions and messages based on the selected hospitality behavior. For example, it generates a message such as, "Our recommendation is fresh seasonal fish sashimi."

[0082] Step 7:

[0083] The server sends the generated messages and action data to the terminal, which receives this data.

[0084] Step 8:

[0085] The device receives a message from the server and displays it to the user via voice or display. For example, a customer service robot might say, "Our recommendation is sashimi made with fresh seasonal fish," and then physically move to smile.

[0086] Through these steps, the system can provide appropriate hospitality according to the user's needs and realize human-like responses.

[0087] Example 1

[0088] 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."

[0089] Conventional customer service systems have had difficulty effectively responding to the diverse needs of users, and it has been particularly difficult to embody the uniquely Japanese spirit of "omotenashi" (hospitality). Furthermore, the process of converting voice input into text and then analyzing it is complicated, which reduces the efficiency and accuracy of the entire system.

[0090] 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.

[0091] In this invention, the server includes means for receiving input data from a user, means for converting the input data into text data by speech recognition, means for analyzing the text data by natural language processing, means for determining the user's needs based on the analysis results, means for selecting an appropriate action from a hospitality action database, means for generating the selected action as a specific action or message, and means for providing the generated action or message to the user. This makes it possible to respond quickly and accurately to the user's needs and embody the uniquely Japanese "omotenashi" hospitality.

[0092] "Means for receiving input data from a user" refers to a function including devices and software for capturing input information such as voice or text from a user.

[0093] "Means for converting input data into text data using voice recognition" refers to a function for converting voice input into text format, which utilizes voice recognition software or an API.

[0094] "Means for analyzing text data using natural language processing" refers to a function that uses natural language processing technology to analyze received text data and understand its content.

[0095] "Means for determining user needs based on analysis results" refers to a function that identifies user requests and expectations based on analysis results from natural language processing.

[0096] "Means for selecting appropriate actions from a hospitality action database" refers to a function that selects the most appropriate action from a database that records hospitality actions based on the analysis results.

[0097] "Means for generating selected behaviors as specific actions or messages" refers to the function for converting selected hospitality behaviors into specific actions or messages.

[0098] The "means for providing the generated action or message to the user" is a function for presenting the generated action or message to the user, and uses a display, speaker, or the like.

[0099] This invention is a system that includes a generative AI that understands user needs and provides the uniquely Japanese "omotenashi" hospitality. This system is realized by combining technical elements such as voice recognition, natural language processing technology, customer service robots, and a hospitality behavior database.

[0100] Hardware and Software Configuration

[0101] The main components of the system are:

[0102] Terminal

[0103] 1. Audio input device: Equipped with a microphone to receive the user's audio input.

[0104] 2. Speech Recognition Software: We use speech recognition software, such as the Google® Speech-to-Text API, to convert voice input into text data.

[0105] 3. Communication module: Equipped with a communication means for transmitting text data to a server using a Wi-Fi module.

[0106] server

[0107] 1. Natural Language Processing (NLP) module: Utilizes OpenAI's GPT-4 (registered trademark) to analyze text data and understand user intent.

[0108] 2. Action selection module: Based on the analyzed needs, an appropriate action is selected from the hospitality action database.

[0109] 3. Generation module: Generates the selected behavior as a specific action or message.

[0110] Customer Service Robot

[0111] 1. Audio output device: A speaker for presenting the generated message to the user.

[0112] 2. Display device: A display for showing a smile or other visual expression of hospitality.

[0113] 3. Motion control system: A control system for executing pre-programmed physical movements (e.g., bowing movements).

[0114] Specific operation of the system

[0115] Input from the user

[0116] The user inputs a question into the terminal by voice or text. For example, the user might say, "What dishes do you recommend?"

[0117] Text Conversion

[0118] The device uses a microphone to receive the user's voice and converts it into text using the Google Speech-to-Text API. The converted text data is temporarily stored in the device's memory and then sent to the server via the Wi-Fi module.

[0119] Data analysis

[0120] The server passes the received text data to the NLP module, which uses GPT-4 to analyze the data, understanding the user's intent and identifying the information and actions the user is seeking.

[0121] Action selection and message generation

[0122] Based on the analysis results, an appropriate action is selected from the hospitality behavior database. GPT-4 is then used again to convert the selected action into a specific action or message. For example, a message such as "Our recommendation is seasonal fresh fish sashimi" is generated.

[0123] Responding to the user

[0124] The generated message is sent from the server to the terminal. The terminal (customer service robot) uses this message to provide voice guidance through the speaker, display a smiley face icon on the display, and execute a bow using the robot's motion control system.

[0125] Specific examples

[0126] Restaurant service robot

[0127] 1. User input: The user speaks to a customer service robot installed in a restaurant, saying, "What dishes do you recommend?"

[0128] 2. Text conversion: The device (robot) receives this voice and converts it into text using a speech recognition function (Google Speech-to-Text API).

[0129] 3. Data transmission and analysis: The converted text data is sent to the server, where it is analyzed using an NLP module (GPT-4). The server determines that the user's need is "I want to know what dishes are recommended."

[0130] 4. Action selection and generation: Based on the analysis results, the server selects the action of "suggesting recommended dishes" from the hospitality action database and generates a message saying, "Our recommendation is seasonal fresh fish sashimi."

[0131] 5. Responding to the user: The generated message is sent to the terminal, which then announces in voice, "Our recommendation is sashimi made from fresh seasonal fish," displays a smiley face icon on the display, and the robot performs a bow.

[0132] This system allows users to intuitively obtain information through voice input and receive warm service. As a specific example, it can improve the user experience in restaurant settings.

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] A detailed explanation of the program's processing flow

[0135] Step 1: Input from the user

[0136] Specific operation: The user inputs a question into the terminal by voice. For example, the user utters, "Please tell me what dishes you recommend."

[0137] Input: User-uttered voice data

[0138] Output: Audio data

[0139] Step 2: Voice Recognition

[0140] Specific operation: The device receives voice data using the built-in microphone and converts the voice data into text data using voice recognition software (e.g., Google Speech-to-Text API).

[0141] Input: Received audio data

[0142] Data processing: Text conversion using speech recognition

[0143] Output: Text data

[0144] Step 3: Send text data

[0145] Specific operation: The terminal sends the converted text data to the server via the Wi-Fi module. For security reasons, the transmission uses the HTTPS protocol.

[0146] Input: Text data

[0147] Output: Text data sent to the server

[0148] Step 4: Analyzing the text data

[0149] Specific operation: The server passes the received text data to an NLP module (e.g., GPT-4) for natural language processing, which analyzes the user's intent and identifies their needs.

[0150] Input: Received text data

[0151] Data Computing: Analysis with Natural Language Processing

[0152] Output: Analysis results that identify user needs

[0153] Step 5: Choose an action

[0154] Specific operation: Based on the analysis results, the server selects an appropriate action from the hospitality action database. Example: It selects the action of "recommending dishes."

[0155] Input: Analysis results

[0156] Data calculation: Action selection from a hospitality action database

[0157] Output: Selected behavioral data

[0158] Step 6: Creating Actions and Messages

[0159] Specific behavior: The server uses an NLP module (e.g., GPT-4) again to generate a specific action or message based on the selected behavior. Example: Generate a message such as "Our recommendation is seasonal fresh fish sashimi."

[0160] Input: Selected behavioral data

[0161] Data arithmetic: Action and message generation by NLP modules

[0162] Output: Generated messages and actions

[0163] Step 7: Respond to the user

[0164] Specific behavior: The generated message and action are sent from the server to the terminal. The terminal (customer service robot) provides voice guidance through a speaker, displays a smiley face icon on the display, and performs a physical action (e.g., bowing).

[0165] Input: Generated message and action

[0166] Output: Audio response to the user, visual display, physical action

[0167] In this way, each processing step works in cooperation with the other, providing a system that provides a warm and welcoming response to users.

[0168] (Application example 1)

[0169] 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."

[0170] The challenge is to improve the quality of customer service in brick-and-mortar stores and provide a warmer hospitality experience. In today's brick-and-mortar stores, staff are often too busy to provide high-quality hospitality to each and every customer, so it is necessary to utilize technology to achieve efficient, high-quality customer service.

[0171] 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.

[0172] In this invention, the server includes means for receiving input data from a user, means for analyzing the input data using natural language processing, means for determining the user's needs based on the analysis results, means for selecting an appropriate hospitality action from a hospitality action database, means for generating the selected hospitality action as a specific action or message, means for providing the generated action or message to the user, and means for displaying the generated action or message in real time via smart glasses, thereby enabling staff at a physical store to perform appropriate hospitality actions in real time and provide high-quality, warm service to each individual customer.

[0173] "Means for receiving input data from a user" refers to a device that allows a user to input data such as voice or text, and a function for receiving that data.

[0174] "Means for analyzing input data using natural language processing" refers to a system that uses natural language processing technology to analyze the content of received user input data and understand its meaning and intent.

[0175] "Means for determining user needs based on analysis results" refers to algorithms and related systems for determining what users want based on analysis results obtained through natural language processing.

[0176] "Means for selecting appropriate hospitality actions from a hospitality action database" refers to a system that selects appropriate actions from a pre-prepared hospitality action database in order to identify the action that best suits the user's needs.

[0177] "Means for generating selected hospitality behaviors as specific actions and messages" refers to a system that concretizes the selected hospitality behaviors and generates messages and actions to actually convey to users.

[0178] The term "means for providing the generated action or message to the user" refers to a device or system for communicating the generated action or message to the user.

[0179] "Means for displaying generated actions and messages in real time via smart glasses" refers to a system that uses smart glasses to visually display generated actions and messages in real time.

[0180] This invention is a system that includes generative AI to understand user needs and provide the unique Japanese "omotenashi" (hospitality). This system supports store staff using smart glasses to take appropriate hospitality actions toward customers.

[0181] Hardware Configuration

[0182] The system includes the following major components:

[0183] Smart glasses (e.g., Google Glass (registered trademark), Vuzix Blade)

[0184] Audio input device (microphone)

[0185] Data Processing Server

[0186] Software Configuration

[0187] The software and technologies used are as follows:

[0188] Speech recognition libraries (e.g., speech_recognition module)

[0189] Natural Language Processing API (NLP Generation AI API)

[0190] Smart Glasses Control API

[0191] User input and data submission

[0192] A user (customer) speaks a question or request to a store staff member in a physical store. The voice input device (microphone) captures this voice, and the smart glasses convert it into text data. This text data is sent to a data processing server.

[0193] Analyzing data and determining needs

[0194] The data processing server passes the received text data to a natural language processing API, which analyzes the content. Based on the analysis results, it identifies customer needs and determines the necessary information and actions.

[0195] Selection and generation of hospitality behavior

[0196] The server selects appropriate hospitality actions from the hospitality action database and generates specific messages and actions, which are displayed to store staff via smart glasses.

[0197] Responses to customers and examples

[0198] Staff wearing smart glasses receive the generated messages and instructions in real time and respond appropriately to the customer. For example, if a customer asks, "What's on the lunch menu today?", the staff member's smart glasses will display a message saying, "Our lunch menu is the steak set of the day," and the staff member will then verbally convey that message.

[0199] Prompt Sentence Examples

[0200] "A customer has requested the lunch menu. Please generate an appropriate response."

[0201] This system enables store staff to take appropriate hospitality actions in real time, providing high-quality, warm service to each and every customer.

[0202] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0203] Step 1:

[0204] The user speaks a question or request. The user's input is captured by a microphone as voice data. The input data is voice information and includes the customer's question or request.

[0205] Step 2:

[0206] The device (smart glasses) converts the voice data into text data. This conversion is performed using a speech recognition library (e.g., speech_recognition). Specifically, the voice data is obtained as text data.

[0207] Step 3:

[0208] The terminal sends the converted text data to the server. This transmission is performed via network communication, and the text data arrives at the server. The input is the text data, and the output is the transmission result to the server.

[0209] Step 4:

[0210] The server passes the received text data to a natural language processing API, which analyzes the data. The input is text data, and through analysis, it understands the customer's needs and intentions. The output is the analysis results.

[0211] Step 5:

[0212] The server determines the customer's needs based on the analysis results. Based on the determined needs, it selects an appropriate hospitality action. The specific operation is to compare the analysis results with a hospitality action database. The input is the analysis results, and the output is the selected hospitality action.

[0213] Step 6:

[0214] The server generates the selected hospitality behavior as a specific message or action. This generation is performed using a generative AI model. The input is the selected hospitality behavior, and the output is a specific message or action.

[0215] Step 7:

[0216] The server sends the generated messages and actions to the device (smart glasses). This transmission is also done via network communication. The input is the generated messages and actions, and the output is the transmission result to the device.

[0217] Step 8:

[0218] The terminal displays messages and actions received to staff in real time. Messages are visually provided to staff via the smart glasses display. The input is the received message or action, and the output is the display to staff.

[0219] Step 9:

[0220] Staff members respond to customers based on messages and instructions displayed on the smart glasses. Specific actions include providing appropriate verbal responses and guidance. The input is the information displayed on the smart glasses, and the output is the response to the customer.

[0221] 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.

[0222] System Overview

[0223] This invention is a generative AI system equipped with an emotion engine that recognizes user emotions, and provides the uniquely Japanese "omotenashi" hospitality. It analyzes input data from users, understands their needs and emotions, selects appropriate omotenashi actions, and provides generated actions and messages to users.

[0224] A natural language description of the program's operation

[0225] Input from the user

[0226] The user provides text or voice input data to the device. For example, the user might say, "What dishes do you recommend?" The device receives this speech and converts it into text data using a voice recognition module.

[0227] Sending data

[0228] The device sends the converted text data to the server, which receives it and passes it to a natural language processing (NLP) module for analysis.

[0229] Data analysis

[0230] The server's NLP module analyzes the text data to understand its context and meaning. Through this analysis, the server identifies the user's needs. For example, the server determines that the user wants to know what dishes are recommended.

[0231] User Emotion Recognition

[0232] The emotion engine installed on the server recognizes the user's emotions from the input data. For example, it recognizes the user's emotions such as excitement, interest, or distress from the tone and content of the voice when the user speaks.

[0233] Choosing actions based on needs and emotions

[0234] The server selects an appropriate action from a database of Japanese hospitality actions based on the analysis results and emotion recognition results. For example, if the user is excited, it can select an action that calms and explains things.

[0235] Action and message generation

[0236] The server generates specific actions and messages based on the selected hospitality behaviors. For example, it generates a message such as, "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy."

[0237] Responding to the user

[0238] The generated message and action data are sent from the server to the device. The device receives this data and provides it to the user via voice or screen display. In the case of a customer service robot, it also performs appropriate physical actions (for example, smiling and explaining).

[0239] Specific examples

[0240] Example 1: Restaurant service robot

[0241] 1. User Input

[0242] A user speaks to a customer service robot installed in a restaurant and asks, "What dishes do you recommend?"

[0243] The terminal (robot) receives this voice and converts it into text using voice recognition.

[0244] 2. Data submission and analysis

[0245] The terminal transmits the text data to the server.

[0246] The server receives the data and analyzes it using a natural language processing (NLP) module.

[0247] The server determines that the user's need is "I want to know recommended dishes."

[0248] 3. User Emotion Recognition

[0249] The emotion engine installed on the server recognizes the user's emotion from the tone and content of the voice. For example, it recognizes that the user is excited.

[0250] 4. Action Selection and Generation

[0251] Based on the analysis results and emotion recognition results, the server selects the action of "suggesting recommended dishes" from the hospitality action database.

[0252] Generate a message saying, "Our recommendation is sashimi made from fresh seasonal fish. Please relax and enjoy."

[0253] 5. Responding to the User

[0254] The server sends the generated message to the terminal.

[0255] The terminal (robot) announces in voice, "Our recommendation is sashimi made from fresh seasonal fish. Please relax and enjoy," and then shows a smiling face.

[0256] In this way, the present invention, combined with an emotion recognition engine, can provide appropriate hospitality based on the user's needs and emotions, enabling more human-like responses and greatly improving the user experience.

[0257] The processing flow will be explained below.

[0258] Step 1:

[0259] The user provides input data (text or voice) to the device. For example, the user might say, "What dishes do you recommend?" The device receives this voice.

[0260] Step 2:

[0261] The voice data received by the device is passed to the voice recognition module, which converts it into text, and the converted text data is sent to the server.

[0262] Step 3:

[0263] The server receives the text data, passes it to a natural language processing (NLP) module, and analyzes the text data.

[0264] Step 4:

[0265] The server's NLP module analyzes the context and meaning of the text data to identify the user's needs, such as "I want to know what dishes are recommended."

[0266] Step 5:

[0267] The server sends the analyzed text data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes the user's emotions, such as excitement, interest, or distress, from the tone and phrasing of the input data.

[0268] Step 6:

[0269] The server integrates the analysis results from NLP and the emotion recognition results from the emotion engine to determine the overall needs and emotions of the user.

[0270] Step 7:

[0271] Based on the results of the server's overall judgment, it searches for appropriate actions from a database of Japanese hospitality actions. For example, if the user is excited, it will select an action that calmly explains the situation.

[0272] Step 8:

[0273] Based on the hospitality behavior selected by the server, specific actions and messages are generated. For example, a message such as "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy."

[0274] Step 9:

[0275] The server sends the generated messages and action data to the terminal, which receives the data.

[0276] Step 10:

[0277] The device provides the user with the message received from the server. If the robot is providing voice guidance, it will smile and say, "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy." It may also perform other physical actions.

[0278] Through these steps, the system provides appropriate hospitality actions based on the user's needs and emotions, realizing human-like responses.

[0279] Example 2

[0280] 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."

[0281] Conventional customer service systems have difficulty accurately understanding user needs and providing appropriate responses. Furthermore, they are unable to respond in a way that takes into account the user's emotions, which can result in a poor user experience. It has been particularly difficult to provide responses that reflect the uniquely Japanese spirit of "omotenashi" hospitality.

[0282] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving user input data, means for analyzing the input data by natural language processing, means for determining the user's needs based on the analysis results, means for recognizing the user's emotions, means for selecting appropriate hospitality actions based on the user's needs and emotions, means for generating the selected hospitality actions as specific actions and messages, and means for providing the generated actions and messages to the user. This enables a service that takes into consideration both the user's needs and emotions, thereby realizing the uniquely Japanese "omotenashi" (hospitality).

[0283] "Means for receiving input data from a user" refers to a technology or device that receives text or voice data provided by a user at a terminal and incorporates it into the system.

[0284] "Means for analyzing input data using natural language processing" refers to the process of analyzing received text data using natural language processing technology to understand its context and meaning.

[0285] "Means for determining user needs based on analysis results" refers to methods and technologies for identifying what a user is looking for based on the analysis results obtained through natural language processing.

[0286] "Means for recognizing user emotions" refers to technology that determines a user's emotional state from data input by the user, voice tone, etc.

[0287] "Means for selecting appropriate hospitality actions based on the user's needs and emotions" refers to technology that takes into account the user's needs and emotions and selects the most appropriate response or action from a database.

[0288] "Means for generating specific actions and messages from selected hospitality behaviors" refers to the process of creating specific actions and messages to be provided to users based on the selected behaviors.

[0289] "Means for providing the generated action or message to the user" refers to a technology or device that provides the generated message or action to the user by sound, display, or physical action.

[0290] The present invention is a generative AI system that analyzes input data from a user and provides the unique Japanese "omotenashi" hospitality. Specific embodiments for carrying out the present invention will be described below.

[0291] System configuration

[0292] This system mainly consists of the following hardware and software:

[0293] A device for receiving user input (e.g., a customer service robot or smartphone)

[0294] Server for analyzing and generating input data

[0295] Natural Language Processing (NLP) modules (e.g., "spaCy")

[0296] Speech recognition module (e.g. "Google Speech-to-Text")

[0297] Emotion recognition engine (e.g., "IBM Watson (registered trademark) Tone Analyzer")

[0298] Generative AI model (e.g., "GPT-3 (registered trademark)")

[0299] Speech synthesis modules (e.g., "Google Text-to-Speech")

[0300] User Input

[0301] The user inputs information into the device by voice or text. For example, the user might say, "Please tell me what dishes you recommend." The device is equipped with a microphone and keyboard, through which it receives voice and text data. In the case of voice input, the device's voice recognition module is used to convert it into text data in real time.

[0302] Data transmission and analysis

[0303] The device sends text data to the server using the HTTP protocol. The server then uses the natural language processing (NLP) module "spaCy" to analyze the text data and understand its context and meaning. For example, from a request such as "What dishes do you recommend?", the server identifies the user's need as "I want to know what dishes you recommend."

[0304] emotion recognition

[0305] The server's emotion recognition engine, IBM Watson Tone Analyzer, uses the analyzed text data and voice tone to recognize the user's emotions. For example, the tone of the text and the pitch of the voice can determine whether the user is excited, interested, or confused.

[0306] Selection of hospitality actions

[0307] The server selects an appropriate hospitality behavior from the hospitality behavior database based on the analysis results and emotion recognition results. For example, if the user is excited and wants to know what dishes they recommend, the server selects an action that calmly explains the situation.

[0308] Action and Message Generation

[0309] The server uses the generative AI model "GPT-3" to generate specific actions and messages based on the selected hospitality behavior. For example, it generates a message such as "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy."

[0310] Responding to the user

[0311] The generated actions and messages are sent from the server to the device, which then plays the messages aloud using the voice synthesis module "Google Text-to-Speech."The customer service robot also performs the necessary gestures and smiles along with the generated messages.

[0312] Specific examples

[0313] Example prompt sentence:

[0314] 1. The user types to the customer service robot, "Please tell me what dish you recommend."

[0315] 2. The robot performs voice recognition and sends the text data to the server.

[0316] 3. The server analyzes the data and determines that the user's need is to "know recommended dishes."

[0317] 4. The emotion recognition engine recognizes the user's state of excitement.

[0318] 5. Select calm explanation behaviors from the hospitality behavior database.

[0319] 6. The generative AI model generates the message, "Our recommendation is fresh, seasonal fish sashimi. Please relax and enjoy."

[0320] 7. The robot will guide you with voice and show a smiling face.

[0321] In this way, the present invention can provide a service that takes into consideration both the needs and feelings of the user, and can realize the uniquely Japanese "omotenashi" hospitality.

[0322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0323] Step 1:

[0324] The user inputs information into the device by voice or text. Specifically, the user says, "Please tell me what dishes you recommend." The input is acquired as voice data from the microphone and converted into text data by the device's voice recognition module. This converted text data is passed on to the next process. The input data is voice data, and the output data is text data.

[0325] Step 2:

[0326] The device sends the text data obtained by speech recognition to the server. Specifically, the text data is sent to the server as an HTTP request specifying an endpoint. The input data is the text data, and the output data is an HTTP request to the server.

[0327] Step 3:

[0328] The server receives an HTTP request and extracts the text data. The text data is then passed to a natural language processing module for contextual and semantic analysis. Specifically, the NLP module "spaCy" is used. The input data is the text data, and the output data is the analysis results. The analysis results include tokenized text and keywords.

[0329] Step 4:

[0330] The server identifies the user's needs based on the analysis results. For example, from the phrase "recommended dishes," it determines that the user's need is "I want to know recommended dishes." The input data is the analysis results, and the output data is the user's needs information.

[0331] Step 5:

[0332] The emotion recognition engine installed on the server recognizes emotions from the user's input data (voice and text). For example, it uses IBM Watson Tone Analyzer to identify the user's emotional state, such as whether they are excited or troubled. The input data is text data and voice data, and the output data is the emotion recognition results.

[0333] Step 6:

[0334] The server selects an appropriate hospitality action based on the user's needs and emotion recognition results. It searches for the most appropriate action from a database of Japanese hospitality actions and selects an action such as "explain calmly." The input data are the needs information and emotion recognition results, and the output data is the selected hospitality action.

[0335] Step 7:

[0336] The server generates a specific message based on the selected hospitality behavior. Using the generative AI model "GPT-3," it generates a message such as "Our recommendation is seasonal fresh fish sashimi. Please relax and enjoy." The input data are the selected hospitality behaviors, and the output data is the generated message.

[0337] Step 8:

[0338] The generated message is sent from the server to the terminal. Specifically, the server sends the message to the terminal as an HTTP response. The input data is the generated message, and the output data is the HTTP response to the terminal.

[0339] Step 9:

[0340] The device provides the received message to the user. It uses the speech synthesis module "Google Text-to-Speech" to play back the message aloud. In the case of a customer service robot, it also performs appropriate facial expressions and gestures. The input data is the received message, and the output data is voice and physical gestures.

[0341] Through the above process, it becomes possible to provide hospitality that takes into account the user's needs and emotions. This series of steps results in a more human-like response and an improved user experience.

[0342] (Application example 2)

[0343] 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."

[0344] Food delivery services lack personalized suggestions based on user emotions, resulting in a uniform user experience and a lack of hospitality. This often results in users not receiving satisfactory suggestions, which can lead to a decrease in the frequency of service use.

[0345] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0346] In this invention, the server includes means for receiving input data from a user, means for analyzing the input data using natural language processing, means for determining the user's needs based on the analysis results, means for recognizing the user's emotions from the input data, means for selecting appropriate hospitality actions from a Japanese hospitality action database, means for generating specific actions and messages from the selected hospitality actions, and means for providing the generated actions and messages to the user. This enables personalized suggestions based on the user's emotions and needs, thereby improving the user experience.

[0347] A "means for receiving input data from a user" is a device or software component through which a user provides input data such as voice or text.

[0348] The "means for analyzing input data using natural language processing" is a software module for analyzing received input data and understanding its context and meaning.

[0349] The "means for determining user needs based on the analysis results" refers to logic or algorithms for identifying what the user wants from the analyzed data.

[0350] The "means for recognizing user emotions from input data" refers to a software module or algorithm for determining user emotions from the tone and content of input data.

[0351] The "means for selecting appropriate hospitality behavior from a database of Japanese hospitality behavior" is a software module that includes a database and selection logic for selecting optimal behavior based on the user's needs and emotions.

[0352] The "means for generating the selected hospitality behavior as a specific action or message" is a software module that converts the selected behavior into a specific action or message to be presented to the user.

[0353] The "means for providing the generated action or message to the user" is a device or software component for providing the generated action or message to the user in the form of audio, text, video, or the like.

[0354] System Overview

[0355] The system for implementing this invention is a generative AI system with an emotion engine that recognizes user emotions. This system can incorporate the Japanese spirit of hospitality into food delivery services and provide personalized suggestions to users.

[0356] Hardware and Software Configuration

[0357] 1. Hardware:

[0358] Smartphone (iOS / ANDROID (registered trademark))

[0359] Server (cloud-based)

[0360] 2. Software:

[0361] Speech recognition modules (e.g., Google Cloud Speech-to-Text API)

[0362] Natural Language Processing (NLP) modules (e.g., spaCy, Transformers)

[0363] Emotion recognition engine (e.g., Microsoft® Azure® Emotion API)

[0364] Hospitality behavior database (e.g., database such as PostgreSQL)

[0365] Processing flow

[0366] 1. User Input:

[0367] A user opens a food delivery app and speaks or texts, "What are your specials for tonight?"

[0368] The smartphone app receives this input, and in the case of voice input, converts it into text data using a voice recognition module (Google Cloud Speech-to-Text API).

[0369] 2. Data transmission and analysis:

[0370] The smartphone sends the text data to the server.

[0371] On the server, an NLP module (spaCy or Transformers) analyzes this data and determines what the user wants, for example, "What are some recommended dishes?"

[0372] 3. User Emotion Recognition:

[0373] The server uses an emotion recognition engine (Microsoft Azure Emotion API) to recognize the user's emotions from the analyzed data. For example, it determines that the user is feeling stressed.

[0374] 4. Action selection and generation:

[0375] Based on the analysis results and emotion recognition results, the server selects appropriate actions from a database of Japanese hospitality behaviors.

[0376] As a specific example, we select the action of "suggesting dishes that reduce stress" and generate a message such as "Our recommendation is chicken soup made with herbs that have a relaxing effect. Please enjoy."

[0377] 5. Response to the user:

[0378] The server generates a message and sends it to the smartphone app.

[0379] A smartphone app provides this message to the user via voice or text and displays an appropriate visual (such as an image of a dish).

[0380] Specific examples

[0381] When a user speaks to the app and says, "What are your dish recommendations?", the following happens:

[0382] 1. Speech recognition result (Google Cloud Speech-to-Text API):

[0383] "What dishes do you recommend?"

[0384] 2. Analysis results (spaCy NLP module):

[0385] {

[0386] "intent": "recommendation",

[0387] "target": "cooking"

[0388] }

[0389] 3. Emotion recognition results (Microsoft Azure Emotion API):

[0390] {

[0391] "emotion": "stress"

[0392] }

[0393] 4. Final Response:

[0394] "Our recommendation is the chicken soup with herbs, which has a relaxing effect. Enjoy."

[0395] By implementing this invention, personalized suggestions based on the user's emotions and needs can be made, improving the user experience.

[0396] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0397] Step 1:

[0398] A user opens a food delivery app and speaks or texts, "What are your specials for tonight?"

[0399] Input: User voice or text data.

[0400] Output: The audio data (in the case of speech input) or directly the text data (in the case of text input) that is passed to the speech recognition module.

[0401] Specific action: The user presses the microphone button on the smartphone app screen and speaks, or enters text into the text field.

[0402] Step 2:

[0403] The device (smartphone) receives voice input and converts the voice into text using a speech recognition module (Google Cloud Speech-to-Text API).

[0404] Input: Audio data.

[0405] Output: The converted text data.

[0406] Specific operation: The voice recognition module converts the voice data into text data, and the converted text data is stored in the terminal.

[0407] Step 3:

[0408] The terminal transmits the converted text data to the server.

[0409] Input: Text data.

[0410] Output: Send to server.

[0411] Specific operation: The smartphone app sends text data to the server as an API request.

[0412] Step 4:

[0413] The server receives the text data and analyzes it using an NLP module (spaCy or Transformers) to identify the user's needs.

[0414] Input: Text data.

[0415] Output: Identified need (e.g., "I'd like some food recommendations").

[0416] What it does: The NLP module analyzes text data, understands context and meaning, and determines the user's needs.

[0417] Step 5:

[0418] The server uses an emotion recognition engine (Microsoft Azure Emotion API) to recognize the user's emotions from the input data.

[0419] Input: Text data.

[0420] Output: Perceived emotion (e.g., "stressed").

[0421] Specific operation: The emotion recognition engine analyzes the user's emotions based on features such as text data and voice tone, and obtains a judgment result.

[0422] Step 6:

[0423] Based on the analysis results and emotion recognition results, the server selects appropriate actions from a database of Japanese hospitality actions.

[0424] Input: Analysis results and emotion recognition results.

[0425] Output: Selected hospitality behavior (e.g., "Suggest a dish that reduces stress").

[0426] Specific operation: The logic in the server searches and selects the optimal action from the database based on the analysis results and emotion recognition results.

[0427] Step 7:

[0428] The server generates specific actions and messages based on the selected hospitality behaviors.

[0429] Input: Selected hospitality behaviors.

[0430] Output: The generated message (e.g., "Our specialty is our relaxing herbal chicken soup. Enjoy.").

[0431] Specific operation: The server's generative AI model generates an appropriate message based on the given prompt (e.g., "Suggest a dish that has a relaxing effect").

[0432] Step 8:

[0433] The server generates a message and sends it to the terminal.

[0434] Input: The generated message.

[0435] Output: Send to terminal.

[0436] Specific operation: The server sends the generated message as an API response to the smartphone app.

[0437] Step 9:

[0438] The device provides the received message to the user via voice or text and displays an appropriate image (such as an image of a dish).

[0439] Input: The generated message.

[0440] Output: The audio or text and video presented to the user.

[0441] What it does: The smartphone app displays the message on the screen, reads it aloud, and displays a related video on the screen.

[0442] 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.

[0443] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0444] 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.

[0445] [Second embodiment]

[0446] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0447] 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.

[0448] 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).

[0449] 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.

[0450] 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.

[0451] 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).

[0452] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0453] 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.

[0454] 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.

[0455] 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.

[0456] 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.

[0457] 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."

[0458] System Overview

[0459] This invention is a system that includes a generative AI that understands user needs and provides the uniquely Japanese "omotenashi" hospitality. This system receives input data from users, analyzes the data, and selects and generates appropriate hospitality actions to provide warm and welcoming service to users.

[0460] A natural language description of the program's operation

[0461] Input from the user

[0462] The user inputs voice or text into the device. For example, the user might say, "Please tell me what dishes you recommend." The device receives this voice input and converts it into text data using its voice recognition function.

[0463] Sending data

[0464] The device sends the converted text data to the server, which receives it and passes it to a natural language processing (NLP) module.

[0465] Data analysis

[0466] The server's NLP module analyzes the text data. This analysis allows it to understand the meaning and intent behind the user's statements and identify the information and actions the user is seeking. For example, it can understand a user's need to know what dishes they recommend.

[0467] Choosing actions based on needs

[0468] Based on the analysis results, the server selects an appropriate hospitality action from a database of hospitality actions specific to Japan, such as "recommending dishes."

[0469] Action and message generation

[0470] The server generates specific actions and messages based on the selected behavior. The generated messages provide appropriate information to the user and realize a warm and friendly response. For example, it generates a message such as "Our recommendation is seasonal fresh fish sashimi."

[0471] Responding to the user

[0472] The generated message is sent from the server to the terminal, which receives it and provides it to the user by displaying or speaking it. In addition, in the case of a customer service robot, it performs an appropriate physical action (e.g., smiling or exchanging business cards).

[0473] Specific examples

[0474] Example 1: Restaurant service robot

[0475] 1. User Input

[0476] A user speaks to a customer service robot installed in a restaurant and asks, "What dishes do you recommend?"

[0477] The terminal (robot) receives this voice and converts it into text using voice recognition.

[0478] 2. Data submission and analysis

[0479] The terminal transmits the text data to the server.

[0480] The server receives the data and analyzes it using a natural language processing module.

[0481] The server determines that the user's need is "I want to know recommended dishes."

[0482] 3. Action selection and generation

[0483] Based on the analysis results, the server selects the action of "suggesting recommended dishes" from the hospitality action database.

[0484] Generate a message saying, "Our recommendation is sashimi made from fresh seasonal fish."

[0485] 4. Responding to the User

[0486] The server sends the generated message to the terminal.

[0487] The terminal (robot) announces in voice, "Our recommendation is sashimi made from fresh seasonal fish," and shows a smiling face.

[0488] In this way, the present invention makes it possible to improve the user experience by embodying the uniquely Japanese hospitality using generative AI.

[0489] The processing flow will be explained below.

[0490] Step 1:

[0491] The user inputs input data (text or voice) into the device. For example, in a restaurant, the user might say, "Please tell me what dishes you recommend." The device receives this voice.

[0492] Step 2:

[0493] The voice data received by the device is passed to the voice recognition module, which converts it into text, and the converted text data is sent to the server.

[0494] Step 3:

[0495] The server receives the text data, passes it to a natural language processing (NLP) module, and analyzes the text data.

[0496] Step 4:

[0497] The server's NLP module analyzes the context and meaning of the text data to identify the user's needs, such as "I want to know what dishes are recommended."

[0498] Step 5:

[0499] Based on the analysis results, the server sends a query to the Japanese hospitality behavior database to search for an appropriate hospitality behavior. For example, it selects the behavior of "recommending dishes."

[0500] Step 6:

[0501] The server generates specific actions and messages based on the selected hospitality behavior. For example, it generates a message such as, "Our recommendation is fresh seasonal fish sashimi."

[0502] Step 7:

[0503] The server sends the generated messages and action data to the terminal, which receives this data.

[0504] Step 8:

[0505] The device receives a message from the server and displays it to the user via voice or display. For example, a customer service robot might say, "Our recommendation is sashimi made with fresh seasonal fish," and then physically move to smile.

[0506] Through these steps, the system can provide appropriate hospitality according to the user's needs and realize human-like responses.

[0507] Example 1

[0508] 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."

[0509] Conventional customer service systems have had difficulty effectively responding to the diverse needs of users, and it has been particularly difficult to embody the uniquely Japanese spirit of "omotenashi" (hospitality). Furthermore, the process of converting voice input into text and then analyzing it is complicated, which reduces the efficiency and accuracy of the entire system.

[0510] 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.

[0511] In this invention, the server includes means for receiving input data from a user, means for converting the input data into text data by speech recognition, means for analyzing the text data by natural language processing, means for determining the user's needs based on the analysis results, means for selecting an appropriate action from a hospitality action database, means for generating the selected action as a specific action or message, and means for providing the generated action or message to the user. This makes it possible to respond quickly and accurately to the user's needs and embody the uniquely Japanese "omotenashi" hospitality.

[0512] "Means for receiving input data from a user" refers to a function including devices and software for capturing input information such as voice or text from a user.

[0513] "Means for converting input data into text data using voice recognition" refers to a function for converting voice input into text format, which utilizes voice recognition software or an API.

[0514] "Means for analyzing text data using natural language processing" refers to a function that uses natural language processing technology to analyze received text data and understand its content.

[0515] "Means for determining user needs based on analysis results" refers to a function that identifies user requests and expectations based on analysis results from natural language processing.

[0516] "Means for selecting appropriate actions from a hospitality action database" refers to a function that selects the most appropriate action from a database that records hospitality actions based on the analysis results.

[0517] "Means for generating selected behaviors as specific actions or messages" refers to the function for converting selected hospitality behaviors into specific actions or messages.

[0518] The "means for providing the generated action or message to the user" is a function for presenting the generated action or message to the user, and uses a display, speaker, or the like.

[0519] This invention is a system that includes a generative AI that understands user needs and provides the uniquely Japanese "omotenashi" hospitality. This system is realized by combining technical elements such as voice recognition, natural language processing technology, customer service robots, and a hospitality behavior database.

[0520] Hardware and Software Configuration

[0521] The main components of the system are:

[0522] Terminal

[0523] 1. Audio input device: Equipped with a microphone to receive the user's audio input.

[0524] 2. Speech Recognition Software: We use speech recognition software such as the Google Speech-to-Text API to convert voice input into text data.

[0525] 3. Communication module: Equipped with a communication means for transmitting text data to a server using a Wi-Fi module.

[0526] server

[0527] 1. Natural Language Processing (NLP) module: Uses OpenAI's GPT-4 to analyze text data and understand user intent.

[0528] 2. Action selection module: Based on the analyzed needs, an appropriate action is selected from the hospitality action database.

[0529] 3. Generation module: Generates the selected behavior as a specific action or message.

[0530] Customer Service Robot

[0531] 1. Audio output device: A speaker for presenting the generated message to the user.

[0532] 2. Display device: A display for showing a smile or other visual expression of hospitality.

[0533] 3. Motion control system: A control system for executing pre-programmed physical movements (e.g., bowing movements).

[0534] Specific operation of the system

[0535] Input from the user

[0536] The user inputs a question into the terminal by voice or text. For example, the user might say, "What dishes do you recommend?"

[0537] Text Conversion

[0538] The device uses a microphone to receive the user's voice and converts it into text using the Google Speech-to-Text API. The converted text data is temporarily stored in the device's memory and then sent to the server via the Wi-Fi module.

[0539] Data analysis

[0540] The server passes the received text data to the NLP module, which uses GPT-4 to analyze the data, understanding the user's intent and identifying the information and actions the user is seeking.

[0541] Action selection and message generation

[0542] Based on the analysis results, an appropriate action is selected from the hospitality behavior database. GPT-4 is then used again to convert the selected action into a specific action or message. For example, a message such as "Our recommendation is seasonal fresh fish sashimi" is generated.

[0543] Responding to the user

[0544] The generated message is sent from the server to the terminal. The terminal (customer service robot) uses this message to provide voice guidance through the speaker, display a smiley face icon on the display, and execute a bow using the robot's motion control system.

[0545] Specific examples

[0546] Restaurant service robot

[0547] 1. User input: The user speaks to a customer service robot installed in a restaurant, saying, "What dishes do you recommend?"

[0548] 2. Text conversion: The device (robot) receives this voice and converts it into text using a speech recognition function (Google Speech-to-Text API).

[0549] 3. Data transmission and analysis: The converted text data is sent to the server, where it is analyzed using an NLP module (GPT-4). The server determines that the user's need is "I want to know what dishes are recommended."

[0550] 4. Action selection and generation: Based on the analysis results, the server selects the action of "suggesting recommended dishes" from the hospitality action database and generates a message saying, "Our recommendation is seasonal fresh fish sashimi."

[0551] 5. Responding to the user: The generated message is sent to the terminal, which then announces in voice, "Our recommendation is sashimi made from fresh seasonal fish," displays a smiley face icon on the display, and the robot performs a bow.

[0552] This system allows users to intuitively obtain information through voice input and receive warm service. As a specific example, it can improve the user experience in restaurant settings.

[0553] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0554] A detailed explanation of the program's processing flow

[0555] Step 1: Input from the user

[0556] Specific operation: The user inputs a question into the terminal by voice. For example, the user utters, "Please tell me what dishes you recommend."

[0557] Input: User-uttered voice data

[0558] Output: Audio data

[0559] Step 2: Voice Recognition

[0560] Specific operation: The device receives voice data using the built-in microphone and converts the voice data into text data using voice recognition software (e.g., Google Speech-to-Text API).

[0561] Input: Received audio data

[0562] Data processing: Text conversion using speech recognition

[0563] Output: Text data

[0564] Step 3: Send text data

[0565] Specific operation: The terminal sends the converted text data to the server via the Wi-Fi module. For security reasons, the transmission uses the HTTPS protocol.

[0566] Input: Text data

[0567] Output: Text data sent to the server

[0568] Step 4: Analyzing the text data

[0569] Specific operation: The server passes the received text data to an NLP module (e.g., GPT-4) for natural language processing, which analyzes the user's intent and identifies their needs.

[0570] Input: Received text data

[0571] Data Computing: Analysis with Natural Language Processing

[0572] Output: Analysis results that identify user needs

[0573] Step 5: Choose an action

[0574] Specific operation: Based on the analysis results, the server selects an appropriate action from the hospitality action database. Example: It selects the action of "recommending dishes."

[0575] Input: Analysis results

[0576] Data calculation: Action selection from a hospitality action database

[0577] Output: Selected behavioral data

[0578] Step 6: Creating Actions and Messages

[0579] Specific behavior: The server uses an NLP module (e.g., GPT-4) again to generate a specific action or message based on the selected behavior. Example: Generate a message such as "Our recommendation is seasonal fresh fish sashimi."

[0580] Input: Selected behavioral data

[0581] Data arithmetic: Action and message generation by NLP modules

[0582] Output: Generated messages and actions

[0583] Step 7: Respond to the user

[0584] Specific behavior: The generated message and action are sent from the server to the terminal. The terminal (customer service robot) provides voice guidance through a speaker, displays a smiley face icon on the display, and performs a physical action (e.g., bowing).

[0585] Input: Generated message and action

[0586] Output: Audio response to the user, visual display, physical action

[0587] In this way, each processing step works in cooperation with the other, providing a system that provides a warm and welcoming response to users.

[0588] (Application example 1)

[0589] 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."

[0590] The challenge is to improve the quality of customer service in brick-and-mortar stores and provide a warmer hospitality experience. In today's brick-and-mortar stores, staff are often too busy to provide high-quality hospitality to each and every customer, so it is necessary to utilize technology to achieve efficient, high-quality customer service.

[0591] 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.

[0592] In this invention, the server includes means for receiving input data from a user, means for analyzing the input data using natural language processing, means for determining the user's needs based on the analysis results, means for selecting an appropriate hospitality action from a hospitality action database, means for generating the selected hospitality action as a specific action or message, means for providing the generated action or message to the user, and means for displaying the generated action or message in real time via smart glasses, thereby enabling staff at a physical store to perform appropriate hospitality actions in real time and provide high-quality, warm service to each individual customer.

[0593] "Means for receiving input data from a user" refers to a device that allows a user to input data such as voice or text, and a function for receiving that data.

[0594] "Means for analyzing input data using natural language processing" refers to a system that uses natural language processing technology to analyze the content of received user input data and understand its meaning and intent.

[0595] "Means for determining user needs based on analysis results" refers to algorithms and related systems for determining what users want based on analysis results obtained through natural language processing.

[0596] "Means for selecting appropriate hospitality actions from a hospitality action database" refers to a system that selects appropriate actions from a pre-prepared hospitality action database in order to identify the action that best suits the user's needs.

[0597] "Means for generating selected hospitality behaviors as specific actions and messages" refers to a system that concretizes the selected hospitality behaviors and generates messages and actions to actually convey to users.

[0598] The term "means for providing the generated action or message to the user" refers to a device or system for communicating the generated action or message to the user.

[0599] "Means for displaying generated actions and messages in real time via smart glasses" refers to a system that uses smart glasses to visually display generated actions and messages in real time.

[0600] This invention is a system that includes generative AI to understand user needs and provide the unique Japanese "omotenashi" hospitality. This system supports store staff using smart glasses to take appropriate hospitality actions toward customers.

[0601] Hardware Configuration

[0602] The system includes the following major components:

[0603] Smart glasses (e.g. Google Glass, Vuzix Blade)

[0604] Audio input device (microphone)

[0605] Data Processing Server

[0606] Software Configuration

[0607] The software and technologies used are as follows:

[0608] Speech recognition libraries (e.g., speech_recognition module)

[0609] Natural Language Processing API (NLP Generation AI API)

[0610] Smart Glasses Control API

[0611] User input and data submission

[0612] A user (customer) speaks a question or request to a store staff member in a physical store. The voice input device (microphone) captures this voice, and the smart glasses convert it into text data. This text data is sent to a data processing server.

[0613] Analyzing data and determining needs

[0614] The data processing server passes the received text data to a natural language processing API, which analyzes the content. Based on the analysis results, it identifies customer needs and determines the necessary information and actions.

[0615] Selection and generation of hospitality behavior

[0616] The server selects appropriate hospitality actions from the hospitality action database and generates specific messages and actions, which are displayed to store staff via smart glasses.

[0617] Responses to customers and examples

[0618] Staff wearing smart glasses receive the generated messages and instructions in real time and respond appropriately to the customer. For example, if a customer asks, "What's on the lunch menu today?", the staff member's smart glasses will display a message saying, "Our lunch menu is the steak set of the day," and the staff member will then verbally convey that message.

[0619] Prompt Sentence Examples

[0620] "A customer has requested the lunch menu. Please generate an appropriate response."

[0621] This system enables store staff to take appropriate hospitality actions in real time, providing high-quality, warm service to each and every customer.

[0622] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0623] Step 1:

[0624] The user speaks a question or request. The user's input is captured by a microphone as voice data. The input data is voice information and includes the customer's question or request.

[0625] Step 2:

[0626] The device (smart glasses) converts the voice data into text data. This conversion is performed using a speech recognition library (e.g., speech_recognition). Specifically, the voice data is obtained as text data.

[0627] Step 3:

[0628] The terminal sends the converted text data to the server. This transmission is performed via network communication, and the text data arrives at the server. The input is the text data, and the output is the transmission result to the server.

[0629] Step 4:

[0630] The server passes the received text data to a natural language processing API, which analyzes the data. The input is text data, and through analysis, it understands the customer's needs and intentions. The output is the analysis results.

[0631] Step 5:

[0632] The server determines the customer's needs based on the analysis results. Based on the determined needs, it selects an appropriate hospitality action. The specific operation is to compare the analysis results with a hospitality action database. The input is the analysis results, and the output is the selected hospitality action.

[0633] Step 6:

[0634] The server generates the selected hospitality behavior as a specific message or action. This generation is performed using a generative AI model. The input is the selected hospitality behavior, and the output is a specific message or action.

[0635] Step 7:

[0636] The server sends the generated messages and actions to the device (smart glasses). This transmission is also done via network communication. The input is the generated messages and actions, and the output is the transmission result to the device.

[0637] Step 8:

[0638] The terminal displays messages and actions received to staff in real time. Messages are visually provided to staff via the smart glasses display. The input is the received message or action, and the output is the display to staff.

[0639] Step 9:

[0640] Staff members respond to customers based on messages and instructions displayed on the smart glasses. Specific actions include providing appropriate verbal responses and guidance. The input is the information displayed on the smart glasses, and the output is the response to the customer.

[0641] 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.

[0642] System Overview

[0643] This invention is a generative AI system equipped with an emotion engine that recognizes user emotions, and provides the uniquely Japanese "omotenashi" hospitality. It analyzes input data from users, understands their needs and emotions, selects appropriate omotenashi actions, and provides generated actions and messages to users.

[0644] A natural language description of the program's operation

[0645] Input from the user

[0646] The user provides text or voice input data to the device. For example, the user might say, "What dishes do you recommend?" The device receives this speech and converts it into text data using a voice recognition module.

[0647] Sending data

[0648] The device sends the converted text data to the server, which receives it and passes it to a natural language processing (NLP) module for analysis.

[0649] Data analysis

[0650] The server's NLP module analyzes the text data to understand its context and meaning. Through this analysis, the server identifies the user's needs. For example, the server determines that the user wants to know what dishes are recommended.

[0651] User Emotion Recognition

[0652] The emotion engine installed on the server recognizes the user's emotions from the input data. For example, it recognizes the user's emotions such as excitement, interest, or distress from the tone and content of the voice when the user speaks.

[0653] Choosing actions based on needs and emotions

[0654] The server selects an appropriate action from a database of Japanese hospitality actions based on the analysis results and emotion recognition results. For example, if the user is excited, it can select an action that calms and explains things.

[0655] Action and message generation

[0656] The server generates specific actions and messages based on the selected hospitality behaviors. For example, it generates a message such as, "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy."

[0657] Responding to the user

[0658] The generated message and action data are sent from the server to the device. The device receives this data and provides it to the user via voice or screen display. In the case of a customer service robot, it also performs appropriate physical actions (for example, smiling and explaining).

[0659] Specific examples

[0660] Example 1: Restaurant service robot

[0661] 1. User Input

[0662] A user speaks to a customer service robot installed in a restaurant and asks, "What dishes do you recommend?"

[0663] The terminal (robot) receives this voice and converts it into text using voice recognition.

[0664] 2. Data submission and analysis

[0665] The terminal transmits the text data to the server.

[0666] The server receives the data and analyzes it using a natural language processing (NLP) module.

[0667] The server determines that the user's need is "I want to know recommended dishes."

[0668] 3. User Emotion Recognition

[0669] The emotion engine installed on the server recognizes the user's emotion from the tone and content of the voice. For example, it recognizes that the user is excited.

[0670] 4. Action Selection and Generation

[0671] Based on the analysis results and emotion recognition results, the server selects the action of "suggesting recommended dishes" from the hospitality action database.

[0672] Generate a message saying, "Our recommendation is sashimi made from fresh seasonal fish. Please relax and enjoy."

[0673] 5. Responding to the User

[0674] The server sends the generated message to the terminal.

[0675] The terminal (robot) announces in voice, "Our recommendation is sashimi made from fresh seasonal fish. Please relax and enjoy," and then shows a smiling face.

[0676] In this way, the present invention, combined with an emotion recognition engine, can provide appropriate hospitality based on the user's needs and emotions, enabling more human-like responses and greatly improving the user experience.

[0677] The processing flow will be explained below.

[0678] Step 1:

[0679] The user provides input data (text or voice) to the device. For example, the user might say, "What dishes do you recommend?" The device receives this voice.

[0680] Step 2:

[0681] The voice data received by the device is passed to the voice recognition module, which converts it into text, and the converted text data is sent to the server.

[0682] Step 3:

[0683] The server receives the text data, passes it to a natural language processing (NLP) module, and analyzes the text data.

[0684] Step 4:

[0685] The server's NLP module analyzes the context and meaning of the text data to identify the user's needs, such as "I want to know what dishes are recommended."

[0686] Step 5:

[0687] The server sends the analyzed text data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes the user's emotions, such as excitement, interest, or distress, from the tone and phrasing of the input data.

[0688] Step 6:

[0689] The server integrates the analysis results from NLP and the emotion recognition results from the emotion engine to determine the overall needs and emotions of the user.

[0690] Step 7:

[0691] Based on the results of the server's overall judgment, it searches for appropriate actions from a database of Japanese hospitality actions. For example, if the user is excited, it will select an action that calmly explains the situation.

[0692] Step 8:

[0693] Based on the hospitality behavior selected by the server, specific actions and messages are generated. For example, a message such as "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy."

[0694] Step 9:

[0695] The server sends the generated messages and action data to the terminal, which receives the data.

[0696] Step 10:

[0697] The device provides the user with the message received from the server. If the robot is providing voice guidance, it will smile and say, "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy." It may also perform other physical actions.

[0698] Through these steps, the system provides appropriate hospitality actions based on the user's needs and emotions, realizing human-like responses.

[0699] Example 2

[0700] 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."

[0701] Conventional customer service systems have difficulty accurately understanding user needs and providing appropriate responses. Furthermore, they are unable to respond in a way that takes into account the user's emotions, which can result in a poor user experience. It has been particularly difficult to provide responses that reflect the uniquely Japanese spirit of "omotenashi" hospitality.

[0702] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving user input data, means for analyzing the input data by natural language processing, means for determining the user's needs based on the analysis results, means for recognizing the user's emotions, means for selecting appropriate hospitality actions based on the user's needs and emotions, means for generating the selected hospitality actions as specific actions and messages, and means for providing the generated actions and messages to the user. This enables a service that takes into consideration both the user's needs and emotions, thereby realizing the uniquely Japanese "omotenashi" (hospitality).

[0703] "Means for receiving input data from a user" refers to a technology or device that receives text or voice data provided by a user at a terminal and incorporates it into the system.

[0704] "Means for analyzing input data using natural language processing" refers to the process of analyzing received text data using natural language processing technology to understand its context and meaning.

[0705] "Means for determining user needs based on analysis results" refers to methods and technologies for identifying what a user is looking for based on the analysis results obtained through natural language processing.

[0706] "Means for recognizing user emotions" refers to technology that determines a user's emotional state from data input by the user, voice tone, etc.

[0707] "Means for selecting appropriate hospitality actions based on the user's needs and emotions" refers to technology that takes into account the user's needs and emotions and selects the most appropriate response or action from a database.

[0708] "Means for generating specific actions and messages from selected hospitality behaviors" refers to the process of creating specific actions and messages to be provided to users based on the selected behaviors.

[0709] "Means for providing the generated action or message to the user" refers to a technology or device that provides the generated message or action to the user by sound, display, or physical action.

[0710] The present invention is a generative AI system that analyzes input data from a user and provides the unique Japanese "omotenashi" hospitality. Specific embodiments for carrying out the present invention will be described below.

[0711] System configuration

[0712] This system mainly consists of the following hardware and software:

[0713] A device for receiving user input (e.g., a customer service robot or smartphone)

[0714] Server for analyzing and generating input data

[0715] Natural Language Processing (NLP) modules (e.g., "spaCy")

[0716] Speech recognition module (e.g. "Google Speech-to-Text")

[0717] Emotion recognition engine (e.g., "IBM Watson Tone Analyzer")

[0718] Generative AI models (e.g., "GPT-3")

[0719] Speech synthesis modules (e.g., "Google Text-to-Speech")

[0720] User Input

[0721] The user inputs information into the device by voice or text. For example, the user might say, "Please tell me what dishes you recommend." The device is equipped with a microphone and keyboard, through which it receives voice and text data. In the case of voice input, the device's voice recognition module is used to convert it into text data in real time.

[0722] Data transmission and analysis

[0723] The device sends text data to the server using the HTTP protocol. The server then uses the natural language processing (NLP) module "spaCy" to analyze the text data and understand its context and meaning. For example, from a request such as "What dishes do you recommend?", the server identifies the user's need as "I want to know what dishes you recommend."

[0724] emotion recognition

[0725] The server's emotion recognition engine, IBM Watson Tone Analyzer, uses the analyzed text data and voice tone to recognize the user's emotions. For example, the tone of the text and the pitch of the voice can determine whether the user is excited, interested, or confused.

[0726] Selection of hospitality actions

[0727] The server selects an appropriate hospitality behavior from the hospitality behavior database based on the analysis results and emotion recognition results. For example, if the user is excited and wants to know what dishes they recommend, the server selects an action that calmly explains the situation.

[0728] Action and Message Generation

[0729] The server uses the generative AI model "GPT-3" to generate specific actions and messages based on the selected hospitality behavior. For example, it generates a message such as "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy."

[0730] Responding to the user

[0731] The generated actions and messages are sent from the server to the device, which then plays the messages aloud using the voice synthesis module "Google Text-to-Speech."The customer service robot also performs the necessary gestures and smiles along with the generated messages.

[0732] Specific examples

[0733] Example prompt sentence:

[0734] 1. The user types to the customer service robot, "Please tell me what dish you recommend."

[0735] 2. The robot performs voice recognition and sends the text data to the server.

[0736] 3. The server analyzes the data and determines that the user's need is to "know recommended dishes."

[0737] 4. The emotion recognition engine recognizes the user's state of excitement.

[0738] 5. Select calm explanation behaviors from the hospitality behavior database.

[0739] 6. The generative AI model generates the message, "Our recommendation is fresh, seasonal fish sashimi. Please relax and enjoy."

[0740] 7. The robot will guide you with voice and show a smiling face.

[0741] In this way, the present invention can provide a service that takes into consideration both the needs and feelings of the user, and can realize the uniquely Japanese "omotenashi" hospitality.

[0742] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0743] Step 1:

[0744] The user inputs information into the device by voice or text. Specifically, the user says, "Please tell me what dishes you recommend." The input is acquired as voice data from the microphone and converted into text data by the device's voice recognition module. This converted text data is passed on to the next process. The input data is voice data, and the output data is text data.

[0745] Step 2:

[0746] The device sends the text data obtained by speech recognition to the server. Specifically, the text data is sent to the server as an HTTP request specifying an endpoint. The input data is the text data, and the output data is an HTTP request to the server.

[0747] Step 3:

[0748] The server receives an HTTP request and extracts the text data. The text data is then passed to a natural language processing module for contextual and semantic analysis. Specifically, the NLP module "spaCy" is used. The input data is the text data, and the output data is the analysis results. The analysis results include tokenized text and keywords.

[0749] Step 4:

[0750] The server identifies the user's needs based on the analysis results. For example, from the phrase "recommended dishes," it determines that the user's need is "I want to know recommended dishes." The input data is the analysis results, and the output data is the user's needs information.

[0751] Step 5:

[0752] The emotion recognition engine installed on the server recognizes emotions from the user's input data (voice and text). For example, it uses IBM Watson Tone Analyzer to identify the user's emotional state, such as whether they are excited or troubled. The input data is text data and voice data, and the output data is the emotion recognition results.

[0753] Step 6:

[0754] The server selects an appropriate hospitality action based on the user's needs and emotion recognition results. It searches for the most appropriate action from a database of Japanese hospitality actions and selects an action such as "explain calmly." The input data are the needs information and emotion recognition results, and the output data is the selected hospitality action.

[0755] Step 7:

[0756] The server generates a specific message based on the selected hospitality behavior. Using the generative AI model "GPT-3," it generates a message such as "Our recommendation is seasonal fresh fish sashimi. Please relax and enjoy." The input data are the selected hospitality behaviors, and the output data is the generated message.

[0757] Step 8:

[0758] The generated message is sent from the server to the terminal. Specifically, the server sends the message to the terminal as an HTTP response. The input data is the generated message, and the output data is the HTTP response to the terminal.

[0759] Step 9:

[0760] The device provides the received message to the user. It uses the speech synthesis module "Google Text-to-Speech" to play back the message aloud. In the case of a customer service robot, it also performs appropriate facial expressions and gestures. The input data is the received message, and the output data is voice and physical gestures.

[0761] Through the above process, it becomes possible to provide hospitality that takes into account the user's needs and emotions. This series of steps results in a more human-like response and an improved user experience.

[0762] (Application example 2)

[0763] 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."

[0764] Food delivery services lack personalized suggestions based on user emotions, resulting in a uniform user experience and a lack of hospitality. This often results in users not receiving satisfactory suggestions, which can lead to a decrease in the frequency of service use.

[0765] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0766] In this invention, the server includes means for receiving input data from a user, means for analyzing the input data using natural language processing, means for determining the user's needs based on the analysis results, means for recognizing the user's emotions from the input data, means for selecting appropriate hospitality actions from a Japanese hospitality action database, means for generating specific actions and messages from the selected hospitality actions, and means for providing the generated actions and messages to the user. This enables personalized suggestions based on the user's emotions and needs, thereby improving the user experience.

[0767] A "means for receiving input data from a user" is a device or software component through which a user provides input data such as voice or text.

[0768] The "means for analyzing input data using natural language processing" is a software module for analyzing received input data and understanding its context and meaning.

[0769] The "means for determining user needs based on the analysis results" refers to logic or algorithms for identifying what the user wants from the analyzed data.

[0770] The "means for recognizing user emotions from input data" refers to a software module or algorithm for determining user emotions from the tone and content of input data.

[0771] The "means for selecting appropriate hospitality behavior from a database of Japanese hospitality behavior" is a software module that includes a database and selection logic for selecting optimal behavior based on the user's needs and emotions.

[0772] The "means for generating the selected hospitality behavior as a specific action or message" is a software module that converts the selected behavior into a specific action or message to be presented to the user.

[0773] The "means for providing the generated action or message to the user" is a device or software component for providing the generated action or message to the user in the form of audio, text, video, or the like.

[0774] System Overview

[0775] The system for implementing this invention is a generative AI system with an emotion engine that recognizes user emotions. This system can incorporate the Japanese spirit of hospitality into food delivery services and provide personalized suggestions to users.

[0776] Hardware and Software Configuration

[0777] 1. Hardware:

[0778] Smartphone (iOS / Android)

[0779] Server (cloud-based)

[0780] 2. Software:

[0781] Speech recognition modules (e.g., Google Cloud Speech-to-Text API)

[0782] Natural Language Processing (NLP) modules (e.g., spaCy, Transformers)

[0783] Emotion recognition engine (e.g. Microsoft Azure Emotion API)

[0784] Hospitality behavior database (e.g., database such as PostgreSQL)

[0785] Processing flow

[0786] 1. User Input:

[0787] A user opens a food delivery app and speaks or texts, "What are your specials for tonight?"

[0788] The smartphone app receives this input, and in the case of voice input, converts it into text data using a voice recognition module (Google Cloud Speech-to-Text API).

[0789] 2. Data transmission and analysis:

[0790] The smartphone sends the text data to the server.

[0791] On the server, an NLP module (spaCy or Transformers) analyzes this data and determines what the user wants, for example, "What are some recommended dishes?"

[0792] 3. User Emotion Recognition:

[0793] The server uses an emotion recognition engine (Microsoft Azure Emotion API) to recognize the user's emotions from the analyzed data. For example, it determines that the user is feeling stressed.

[0794] 4. Action selection and generation:

[0795] Based on the analysis results and emotion recognition results, the server selects appropriate actions from a database of Japanese hospitality behaviors.

[0796] As a specific example, we select the action of "suggesting dishes that reduce stress" and generate a message such as "Our recommendation is chicken soup made with herbs that have a relaxing effect. Please enjoy."

[0797] 5. Response to the user:

[0798] The server generates a message and sends it to the smartphone app.

[0799] A smartphone app provides this message to the user via voice or text and displays an appropriate visual (such as an image of a dish).

[0800] Specific examples

[0801] When a user speaks to the app and says, "What are your dish recommendations?", the following happens:

[0802] 1. Speech recognition result (Google Cloud Speech-to-Text API):

[0803] "What dishes do you recommend?"

[0804] 2. Analysis results (spaCy NLP module):

[0805] {

[0806] "intent": "recommendation",

[0807] "target": "cooking"

[0808] }

[0809] 3. Emotion recognition results (Microsoft Azure Emotion API):

[0810] {

[0811] "emotion": "stress"

[0812] }

[0813] 4. Final Response:

[0814] "Our recommendation is the chicken soup with herbs, which has a relaxing effect. Enjoy."

[0815] By implementing this invention, personalized suggestions based on the user's emotions and needs can be made, improving the user experience.

[0816] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0817] Step 1:

[0818] A user opens a food delivery app and speaks or texts, "What are your specials for tonight?"

[0819] Input: User voice or text data.

[0820] Output: The audio data (in the case of speech input) or directly the text data (in the case of text input) that is passed to the speech recognition module.

[0821] Specific action: The user presses the microphone button on the smartphone app screen and speaks, or enters text into the text field.

[0822] Step 2:

[0823] The device (smartphone) receives voice input and converts the voice into text using a speech recognition module (Google Cloud Speech-to-Text API).

[0824] Input: Audio data.

[0825] Output: The converted text data.

[0826] Specific operation: The voice recognition module converts the voice data into text data, and the converted text data is stored in the terminal.

[0827] Step 3:

[0828] The terminal transmits the converted text data to the server.

[0829] Input: Text data.

[0830] Output: Send to server.

[0831] Specific operation: The smartphone app sends text data to the server as an API request.

[0832] Step 4:

[0833] The server receives the text data and analyzes it using an NLP module (spaCy or Transformers) to identify the user's needs.

[0834] Input: Text data.

[0835] Output: Identified need (e.g., "I'd like some food recommendations").

[0836] What it does: The NLP module analyzes text data, understands context and meaning, and determines the user's needs.

[0837] Step 5:

[0838] The server uses an emotion recognition engine (Microsoft Azure Emotion API) to recognize the user's emotions from the input data.

[0839] Input: Text data.

[0840] Output: Perceived emotion (e.g., "stressed").

[0841] Specific operation: The emotion recognition engine analyzes the user's emotions based on features such as text data and voice tone, and obtains a judgment result.

[0842] Step 6:

[0843] Based on the analysis results and emotion recognition results, the server selects appropriate actions from a database of Japanese hospitality actions.

[0844] Input: Analysis results and emotion recognition results.

[0845] Output: Selected hospitality behavior (e.g., "Suggest a dish that reduces stress").

[0846] Specific operation: The logic in the server searches and selects the optimal action from the database based on the analysis results and emotion recognition results.

[0847] Step 7:

[0848] The server generates specific actions and messages based on the selected hospitality behaviors.

[0849] Input: Selected hospitality behaviors.

[0850] Output: The generated message (e.g., "Our specialty is our relaxing herbal chicken soup. Enjoy.").

[0851] Specific operation: The server's generative AI model generates an appropriate message based on the given prompt (e.g., "Suggest a dish that has a relaxing effect").

[0852] Step 8:

[0853] The server generates a message and sends it to the terminal.

[0854] Input: The generated message.

[0855] Output: Send to terminal.

[0856] Specific operation: The server sends the generated message as an API response to the smartphone app.

[0857] Step 9:

[0858] The device provides the received message to the user via voice or text and displays an appropriate image (such as an image of a dish).

[0859] Input: The generated message.

[0860] Output: The audio or text and video presented to the user.

[0861] What it does: The smartphone app displays the message on the screen, reads it aloud, and displays a related video on the screen.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] [Third embodiment]

[0866] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0867] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0868] 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).

[0869] 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.

[0870] 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.

[0871] 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).

[0872] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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."

[0878] System Overview

[0879] This invention is a system that includes a generative AI that understands user needs and provides the uniquely Japanese "omotenashi" hospitality. This system receives input data from users, analyzes the data, and selects and generates appropriate hospitality actions to provide warm and welcoming service to users.

[0880] A natural language description of the program's operation

[0881] Input from the user

[0882] The user inputs voice or text into the device. For example, the user might say, "Please tell me what dishes you recommend." The device receives this voice input and converts it into text data using its voice recognition function.

[0883] Sending data

[0884] The device sends the converted text data to the server, which receives it and passes it to a natural language processing (NLP) module.

[0885] Data analysis

[0886] The server's NLP module analyzes the text data. This analysis allows it to understand the meaning and intent behind the user's statements and identify the information and actions the user is seeking. For example, it can understand a user's need to know what dishes they recommend.

[0887] Choosing actions based on needs

[0888] Based on the analysis results, the server selects an appropriate hospitality action from a database of hospitality actions specific to Japan, such as "recommending dishes."

[0889] Action and message generation

[0890] The server generates specific actions and messages based on the selected behavior. The generated messages provide appropriate information to the user and realize a warm and friendly response. For example, it generates a message such as "Our recommendation is seasonal fresh fish sashimi."

[0891] Responding to the user

[0892] The generated message is sent from the server to the terminal, which receives it and provides it to the user by displaying or speaking it. In addition, in the case of a customer service robot, it performs an appropriate physical action (e.g., smiling or exchanging business cards).

[0893] Specific examples

[0894] Example 1: Restaurant service robot

[0895] 1. User Input

[0896] A user speaks to a customer service robot installed in a restaurant and asks, "What dishes do you recommend?"

[0897] The terminal (robot) receives this voice and converts it into text using voice recognition.

[0898] 2. Data submission and analysis

[0899] The terminal transmits the text data to the server.

[0900] The server receives the data and analyzes it using a natural language processing module.

[0901] The server determines that the user's need is "I want to know recommended dishes."

[0902] 3. Action selection and generation

[0903] Based on the analysis results, the server selects the action of "suggesting recommended dishes" from the hospitality action database.

[0904] Generate a message saying, "Our recommendation is sashimi made from fresh seasonal fish."

[0905] 4. Responding to the User

[0906] The server sends the generated message to the terminal.

[0907] The terminal (robot) announces in voice, "Our recommendation is sashimi made from fresh seasonal fish," and shows a smiling face.

[0908] In this way, the present invention makes it possible to improve the user experience by embodying the uniquely Japanese hospitality using generative AI.

[0909] The processing flow will be explained below.

[0910] Step 1:

[0911] The user inputs input data (text or voice) into the device. For example, in a restaurant, the user might say, "Please tell me what dishes you recommend." The device receives this voice.

[0912] Step 2:

[0913] The voice data received by the device is passed to the voice recognition module, which converts it into text, and the converted text data is sent to the server.

[0914] Step 3:

[0915] The server receives the text data, passes it to a natural language processing (NLP) module, and analyzes the text data.

[0916] Step 4:

[0917] The server's NLP module analyzes the context and meaning of the text data to identify the user's needs, such as "I want to know what dishes are recommended."

[0918] Step 5:

[0919] Based on the analysis results, the server sends a query to the Japanese hospitality behavior database to search for an appropriate hospitality behavior. For example, it selects the behavior of "recommending dishes."

[0920] Step 6:

[0921] The server generates specific actions and messages based on the selected hospitality behavior. For example, it generates a message such as, "Our recommendation is fresh seasonal fish sashimi."

[0922] Step 7:

[0923] The server sends the generated messages and action data to the terminal, which receives this data.

[0924] Step 8:

[0925] The device receives a message from the server and displays it to the user via voice or display. For example, a customer service robot might say, "Our recommendation is sashimi made with fresh seasonal fish," and then physically move to smile.

[0926] Through these steps, the system can provide appropriate hospitality according to the user's needs and realize human-like responses.

[0927] Example 1

[0928] 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."

[0929] Conventional customer service systems have had difficulty effectively responding to the diverse needs of users, and it has been particularly difficult to embody the uniquely Japanese spirit of "omotenashi" (hospitality). Furthermore, the process of converting voice input into text and then analyzing it is complicated, which reduces the efficiency and accuracy of the entire system.

[0930] 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.

[0931] In this invention, the server includes means for receiving input data from a user, means for converting the input data into text data by speech recognition, means for analyzing the text data by natural language processing, means for determining the user's needs based on the analysis results, means for selecting an appropriate action from a hospitality action database, means for generating the selected action as a specific action or message, and means for providing the generated action or message to the user. This makes it possible to respond quickly and accurately to the user's needs and embody the uniquely Japanese "omotenashi" hospitality.

[0932] "Means for receiving input data from a user" refers to a function including devices and software for capturing input information such as voice or text from a user.

[0933] "Means for converting input data into text data using voice recognition" refers to a function for converting voice input into text format, which utilizes voice recognition software or an API.

[0934] "Means for analyzing text data using natural language processing" refers to a function that uses natural language processing technology to analyze received text data and understand its content.

[0935] "Means for determining user needs based on analysis results" refers to a function that identifies user requests and expectations based on analysis results from natural language processing.

[0936] "Means for selecting appropriate actions from a hospitality action database" refers to a function that selects the most appropriate action from a database that records hospitality actions based on the analysis results.

[0937] "Means for generating selected behaviors as specific actions or messages" refers to the function for converting selected hospitality behaviors into specific actions or messages.

[0938] The "means for providing the generated action or message to the user" is a function for presenting the generated action or message to the user, and uses a display, speaker, or the like.

[0939] This invention is a system that includes a generative AI that understands user needs and provides the uniquely Japanese "omotenashi" hospitality. This system is realized by combining technical elements such as voice recognition, natural language processing technology, customer service robots, and a hospitality behavior database.

[0940] Hardware and Software Configuration

[0941] The main components of the system are:

[0942] Terminal

[0943] 1. Audio input device: Equipped with a microphone to receive the user's audio input.

[0944] 2. Speech Recognition Software: We use speech recognition software such as the Google Speech-to-Text API to convert voice input into text data.

[0945] 3. Communication module: Equipped with a communication means for transmitting text data to a server using a Wi-Fi module.

[0946] server

[0947] 1. Natural Language Processing (NLP) module: Uses OpenAI's GPT-4 to analyze text data and understand user intent.

[0948] 2. Action selection module: Based on the analyzed needs, an appropriate action is selected from the hospitality action database.

[0949] 3. Generation module: Generates the selected behavior as a specific action or message.

[0950] Customer Service Robot

[0951] 1. Audio output device: A speaker for presenting the generated message to the user.

[0952] 2. Display device: A display for showing a smile or other visual expression of hospitality.

[0953] 3. Motion control system: A control system for executing pre-programmed physical movements (e.g., bowing movements).

[0954] Specific operation of the system

[0955] Input from the user

[0956] The user inputs a question into the terminal by voice or text. For example, the user might say, "What dishes do you recommend?"

[0957] Text Conversion

[0958] The device uses a microphone to receive the user's voice and converts it into text using the Google Speech-to-Text API. The converted text data is temporarily stored in the device's memory and then sent to the server via the Wi-Fi module.

[0959] Data analysis

[0960] The server passes the received text data to the NLP module, which uses GPT-4 to analyze the data, understanding the user's intent and identifying the information and actions the user is seeking.

[0961] Action selection and message generation

[0962] Based on the analysis results, an appropriate action is selected from the hospitality behavior database. GPT-4 is then used again to convert the selected action into a specific action or message. For example, a message such as "Our recommendation is seasonal fresh fish sashimi" is generated.

[0963] Responding to the user

[0964] The generated message is sent from the server to the terminal. The terminal (customer service robot) uses this message to provide voice guidance through the speaker, display a smiley face icon on the display, and execute a bow using the robot's motion control system.

[0965] Specific examples

[0966] Restaurant service robot

[0967] 1. User input: The user speaks to a customer service robot installed in a restaurant, saying, "What dishes do you recommend?"

[0968] 2. Text conversion: The device (robot) receives this voice and converts it into text using a speech recognition function (Google Speech-to-Text API).

[0969] 3. Data transmission and analysis: The converted text data is sent to the server, where it is analyzed using an NLP module (GPT-4). The server determines that the user's need is "I want to know what dishes are recommended."

[0970] 4. Action selection and generation: Based on the analysis results, the server selects the action of "suggesting recommended dishes" from the hospitality action database and generates a message saying, "Our recommendation is seasonal fresh fish sashimi."

[0971] 5. Responding to the user: The generated message is sent to the terminal, which then announces in voice, "Our recommendation is sashimi made from fresh seasonal fish," displays a smiley face icon on the display, and the robot performs a bow.

[0972] This system allows users to intuitively obtain information through voice input and receive warm service. As a specific example, it can improve the user experience in restaurant settings.

[0973] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0974] A detailed explanation of the program's processing flow

[0975] Step 1: Input from the user

[0976] Specific operation: The user inputs a question into the terminal by voice. For example, the user utters, "Please tell me what dishes you recommend."

[0977] Input: User-uttered voice data

[0978] Output: Audio data

[0979] Step 2: Voice Recognition

[0980] Specific operation: The device receives voice data using the built-in microphone and converts the voice data into text data using voice recognition software (e.g., Google Speech-to-Text API).

[0981] Input: Received audio data

[0982] Data processing: Text conversion using speech recognition

[0983] Output: Text data

[0984] Step 3: Send text data

[0985] Specific operation: The terminal sends the converted text data to the server via the Wi-Fi module. For security reasons, the transmission uses the HTTPS protocol.

[0986] Input: Text data

[0987] Output: Text data sent to the server

[0988] Step 4: Analyzing the text data

[0989] Specific operation: The server passes the received text data to an NLP module (e.g., GPT-4) for natural language processing, which analyzes the user's intent and identifies their needs.

[0990] Input: Received text data

[0991] Data Computing: Analysis with Natural Language Processing

[0992] Output: Analysis results that identify user needs

[0993] Step 5: Choose an action

[0994] Specific operation: Based on the analysis results, the server selects an appropriate action from the hospitality action database. Example: It selects the action of "recommending dishes."

[0995] Input: Analysis results

[0996] Data calculation: Action selection from a hospitality action database

[0997] Output: Selected behavioral data

[0998] Step 6: Creating Actions and Messages

[0999] Specific behavior: The server uses an NLP module (e.g., GPT-4) again to generate a specific action or message based on the selected behavior. Example: Generate a message such as "Our recommendation is seasonal fresh fish sashimi."

[1000] Input: Selected behavioral data

[1001] Data arithmetic: Action and message generation by NLP modules

[1002] Output: Generated messages and actions

[1003] Step 7: Respond to the user

[1004] Specific behavior: The generated message and action are sent from the server to the terminal. The terminal (customer service robot) provides voice guidance through a speaker, displays a smiley face icon on the display, and performs a physical action (e.g., bowing).

[1005] Input: Generated message and action

[1006] Output: Audio response to the user, visual display, physical action

[1007] In this way, each processing step works in cooperation with the other, providing a system that provides a warm and welcoming response to users.

[1008] (Application example 1)

[1009] 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."

[1010] The challenge is to improve the quality of customer service in brick-and-mortar stores and provide a warmer hospitality experience. In today's brick-and-mortar stores, staff are often too busy to provide high-quality hospitality to each and every customer, so it is necessary to utilize technology to achieve efficient, high-quality customer service.

[1011] 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.

[1012] In this invention, the server includes means for receiving input data from a user, means for analyzing the input data using natural language processing, means for determining the user's needs based on the analysis results, means for selecting an appropriate hospitality action from a hospitality action database, means for generating the selected hospitality action as a specific action or message, means for providing the generated action or message to the user, and means for displaying the generated action or message in real time via smart glasses, thereby enabling staff at a physical store to perform appropriate hospitality actions in real time and provide high-quality, warm service to each individual customer.

[1013] "Means for receiving input data from a user" refers to a device that allows a user to input data such as voice or text, and a function for receiving that data.

[1014] "Means for analyzing input data using natural language processing" refers to a system that uses natural language processing technology to analyze the content of received user input data and understand its meaning and intent.

[1015] "Means for determining user needs based on analysis results" refers to algorithms and related systems for determining what users want based on analysis results obtained through natural language processing.

[1016] "Means for selecting appropriate hospitality actions from a hospitality action database" refers to a system that selects appropriate actions from a pre-prepared hospitality action database in order to identify the action that best suits the user's needs.

[1017] "Means for generating selected hospitality behaviors as specific actions and messages" refers to a system that concretizes the selected hospitality behaviors and generates messages and actions to actually convey to users.

[1018] The term "means for providing the generated action or message to the user" refers to a device or system for communicating the generated action or message to the user.

[1019] "Means for displaying generated actions and messages in real time via smart glasses" refers to a system that uses smart glasses to visually display generated actions and messages in real time.

[1020] This invention is a system that includes generative AI to understand user needs and provide the unique Japanese "omotenashi" hospitality. This system supports store staff using smart glasses to take appropriate hospitality actions toward customers.

[1021] Hardware Configuration

[1022] The system includes the following major components:

[1023] Smart glasses (e.g. Google Glass, Vuzix Blade)

[1024] Audio input device (microphone)

[1025] Data Processing Server

[1026] Software Configuration

[1027] The software and technologies used are as follows:

[1028] Speech recognition libraries (e.g., speech_recognition module)

[1029] Natural Language Processing API (NLP Generation AI API)

[1030] Smart Glasses Control API

[1031] User input and data submission

[1032] A user (customer) speaks a question or request to a store staff member in a physical store. The voice input device (microphone) captures this voice, and the smart glasses convert it into text data. This text data is sent to a data processing server.

[1033] Analyzing data and determining needs

[1034] The data processing server passes the received text data to a natural language processing API, which analyzes the content. Based on the analysis results, it identifies customer needs and determines the necessary information and actions.

[1035] Selection and generation of hospitality behavior

[1036] The server selects appropriate hospitality actions from the hospitality action database and generates specific messages and actions, which are displayed to store staff via smart glasses.

[1037] Responses to customers and examples

[1038] Staff wearing smart glasses receive the generated messages and instructions in real time and respond appropriately to the customer. For example, if a customer asks, "What's on the lunch menu today?", the staff member's smart glasses will display a message saying, "Our lunch menu is the steak set of the day," and the staff member will then verbally convey that message.

[1039] Prompt Sentence Examples

[1040] "A customer has requested the lunch menu. Please generate an appropriate response."

[1041] This system enables store staff to take appropriate hospitality actions in real time, providing high-quality, warm service to each and every customer.

[1042] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1043] Step 1:

[1044] The user speaks a question or request. The user's input is captured by a microphone as voice data. The input data is voice information and includes the customer's question or request.

[1045] Step 2:

[1046] The device (smart glasses) converts the voice data into text data. This conversion is performed using a speech recognition library (e.g., speech_recognition). Specifically, the voice data is obtained as text data.

[1047] Step 3:

[1048] The terminal sends the converted text data to the server. This transmission is performed via network communication, and the text data arrives at the server. The input is the text data, and the output is the transmission result to the server.

[1049] Step 4:

[1050] The server passes the received text data to a natural language processing API, which analyzes the data. The input is text data, and through analysis, it understands the customer's needs and intentions. The output is the analysis results.

[1051] Step 5:

[1052] The server determines the customer's needs based on the analysis results. Based on the determined needs, it selects an appropriate hospitality action. The specific operation is to compare the analysis results with a hospitality action database. The input is the analysis results, and the output is the selected hospitality action.

[1053] Step 6:

[1054] The server generates the selected hospitality behavior as a specific message or action. This generation is performed using a generative AI model. The input is the selected hospitality behavior, and the output is a specific message or action.

[1055] Step 7:

[1056] The server sends the generated messages and actions to the device (smart glasses). This transmission is also done via network communication. The input is the generated messages and actions, and the output is the transmission result to the device.

[1057] Step 8:

[1058] The terminal displays messages and actions received to staff in real time. Messages are visually provided to staff via the smart glasses display. The input is the received message or action, and the output is the display to staff.

[1059] Step 9:

[1060] Staff members respond to customers based on messages and instructions displayed on the smart glasses. Specific actions include providing appropriate verbal responses and guidance. The input is the information displayed on the smart glasses, and the output is the response to the customer.

[1061] 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.

[1062] System Overview

[1063] This invention is a generative AI system equipped with an emotion engine that recognizes user emotions, and provides the uniquely Japanese "omotenashi" hospitality. It analyzes input data from users, understands their needs and emotions, selects appropriate omotenashi actions, and provides generated actions and messages to users.

[1064] A natural language description of the program's operation

[1065] Input from the user

[1066] The user provides text or voice input data to the device. For example, the user might say, "What dishes do you recommend?" The device receives this speech and converts it into text data using a voice recognition module.

[1067] Sending data

[1068] The device sends the converted text data to the server, which receives it and passes it to a natural language processing (NLP) module for analysis.

[1069] Data analysis

[1070] The server's NLP module analyzes the text data to understand its context and meaning. Through this analysis, the server identifies the user's needs. For example, the server determines that the user wants to know what dishes are recommended.

[1071] User Emotion Recognition

[1072] The emotion engine installed on the server recognizes the user's emotions from the input data. For example, it recognizes the user's emotions such as excitement, interest, or distress from the tone and content of the voice when the user speaks.

[1073] Choosing actions based on needs and emotions

[1074] The server selects an appropriate action from a database of Japanese hospitality actions based on the analysis results and emotion recognition results. For example, if the user is excited, it can select an action that calms and explains things.

[1075] Action and message generation

[1076] The server generates specific actions and messages based on the selected hospitality behaviors. For example, it generates a message such as, "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy."

[1077] Responding to the user

[1078] The generated message and action data are sent from the server to the device. The device receives this data and provides it to the user via voice or screen display. In the case of a customer service robot, it also performs appropriate physical actions (for example, smiling and explaining).

[1079] Specific examples

[1080] Example 1: Restaurant service robot

[1081] 1. User Input

[1082] A user speaks to a customer service robot installed in a restaurant and asks, "What dishes do you recommend?"

[1083] The terminal (robot) receives this voice and converts it into text using voice recognition.

[1084] 2. Data submission and analysis

[1085] The terminal transmits the text data to the server.

[1086] The server receives the data and analyzes it using a natural language processing (NLP) module.

[1087] The server determines that the user's need is "I want to know recommended dishes."

[1088] 3. User Emotion Recognition

[1089] The emotion engine installed on the server recognizes the user's emotion from the tone and content of the voice. For example, it recognizes that the user is excited.

[1090] 4. Action Selection and Generation

[1091] Based on the analysis results and emotion recognition results, the server selects the action of "suggesting recommended dishes" from the hospitality action database.

[1092] Generate a message saying, "Our recommendation is sashimi made from fresh seasonal fish. Please relax and enjoy."

[1093] 5. Responding to the User

[1094] The server sends the generated message to the terminal.

[1095] The terminal (robot) announces in voice, "Our recommendation is sashimi made from fresh seasonal fish. Please relax and enjoy," and then shows a smiling face.

[1096] In this way, the present invention, combined with an emotion recognition engine, can provide appropriate hospitality based on the user's needs and emotions, enabling more human-like responses and greatly improving the user experience.

[1097] The processing flow will be explained below.

[1098] Step 1:

[1099] The user provides input data (text or voice) to the device. For example, the user might say, "What dishes do you recommend?" The device receives this voice.

[1100] Step 2:

[1101] The voice data received by the device is passed to the voice recognition module, which converts it into text, and the converted text data is sent to the server.

[1102] Step 3:

[1103] The server receives the text data, passes it to a natural language processing (NLP) module, and analyzes the text data.

[1104] Step 4:

[1105] The server's NLP module analyzes the context and meaning of the text data to identify the user's needs, such as "I want to know what dishes are recommended."

[1106] Step 5:

[1107] The server sends the analyzed text data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes the user's emotions, such as excitement, interest, or distress, from the tone and phrasing of the input data.

[1108] Step 6:

[1109] The server integrates the analysis results from NLP and the emotion recognition results from the emotion engine to determine the overall needs and emotions of the user.

[1110] Step 7:

[1111] Based on the results of the server's overall judgment, it searches for appropriate actions from a database of Japanese hospitality actions. For example, if the user is excited, it will select an action that calmly explains the situation.

[1112] Step 8:

[1113] Based on the hospitality behavior selected by the server, specific actions and messages are generated. For example, a message such as "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy."

[1114] Step 9:

[1115] The server sends the generated messages and action data to the terminal, which receives the data.

[1116] Step 10:

[1117] The device provides the user with the message received from the server. If the robot is providing voice guidance, it will smile and say, "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy." It may also perform other physical actions.

[1118] Through these steps, the system provides appropriate hospitality actions based on the user's needs and emotions, realizing human-like responses.

[1119] Example 2

[1120] 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."

[1121] Conventional customer service systems have difficulty accurately understanding user needs and providing appropriate responses. Furthermore, they are unable to respond in a way that takes into account the user's emotions, which can result in a poor user experience. It has been particularly difficult to provide responses that reflect the uniquely Japanese spirit of "omotenashi" hospitality.

[1122] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving user input data, means for analyzing the input data by natural language processing, means for determining the user's needs based on the analysis results, means for recognizing the user's emotions, means for selecting appropriate hospitality actions based on the user's needs and emotions, means for generating the selected hospitality actions as specific actions and messages, and means for providing the generated actions and messages to the user. This enables a service that takes into consideration both the user's needs and emotions, thereby realizing the uniquely Japanese "omotenashi" (hospitality).

[1123] "Means for receiving input data from a user" refers to a technology or device that receives text or voice data provided by a user at a terminal and incorporates it into the system.

[1124] "Means for analyzing input data using natural language processing" refers to the process of analyzing received text data using natural language processing technology to understand its context and meaning.

[1125] "Means for determining user needs based on analysis results" refers to methods and technologies for identifying what a user is looking for based on the analysis results obtained through natural language processing.

[1126] "Means for recognizing user emotions" refers to technology that determines a user's emotional state from data input by the user, voice tone, etc.

[1127] "Means for selecting appropriate hospitality actions based on the user's needs and emotions" refers to technology that takes into account the user's needs and emotions and selects the most appropriate response or action from a database.

[1128] "Means for generating specific actions and messages from selected hospitality behaviors" refers to the process of creating specific actions and messages to be provided to users based on the selected behaviors.

[1129] "Means for providing the generated action or message to the user" refers to a technology or device that provides the generated message or action to the user by sound, display, or physical action.

[1130] The present invention is a generative AI system that analyzes input data from a user and provides the unique Japanese "omotenashi" hospitality. Specific embodiments for carrying out the present invention will be described below.

[1131] System configuration

[1132] This system mainly consists of the following hardware and software:

[1133] A device for receiving user input (e.g., a customer service robot or smartphone)

[1134] Server for analyzing and generating input data

[1135] Natural Language Processing (NLP) modules (e.g., "spaCy")

[1136] Speech recognition module (e.g. "Google Speech-to-Text")

[1137] Emotion recognition engine (e.g., "IBM Watson Tone Analyzer")

[1138] Generative AI models (e.g., "GPT-3")

[1139] Speech synthesis modules (e.g., "Google Text-to-Speech")

[1140] User Input

[1141] The user inputs information into the device by voice or text. For example, the user might say, "Please tell me what dishes you recommend." The device is equipped with a microphone and keyboard, through which it receives voice and text data. In the case of voice input, the device's voice recognition module is used to convert it into text data in real time.

[1142] Data transmission and analysis

[1143] The device sends text data to the server using the HTTP protocol. The server then uses the natural language processing (NLP) module "spaCy" to analyze the text data and understand its context and meaning. For example, from a request such as "What dishes do you recommend?", the server identifies the user's need as "I want to know what dishes you recommend."

[1144] emotion recognition

[1145] The server's emotion recognition engine, IBM Watson Tone Analyzer, uses the analyzed text data and voice tone to recognize the user's emotions. For example, the tone of the text and the pitch of the voice can determine whether the user is excited, interested, or confused.

[1146] Selection of hospitality actions

[1147] The server selects an appropriate hospitality behavior from the hospitality behavior database based on the analysis results and emotion recognition results. For example, if the user is excited and wants to know what dishes they recommend, the server selects an action that calmly explains the situation.

[1148] Action and Message Generation

[1149] The server uses the generative AI model "GPT-3" to generate specific actions and messages based on the selected hospitality behavior. For example, it generates a message such as "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy."

[1150] Responding to the user

[1151] The generated actions and messages are sent from the server to the device, which then plays the messages aloud using the voice synthesis module "Google Text-to-Speech."The customer service robot also performs the necessary gestures and smiles along with the generated messages.

[1152] Specific examples

[1153] Example prompt sentence:

[1154] 1. The user types to the customer service robot, "Please tell me what dish you recommend."

[1155] 2. The robot performs voice recognition and sends the text data to the server.

[1156] 3. The server analyzes the data and determines that the user's need is to "know recommended dishes."

[1157] 4. The emotion recognition engine recognizes the user's state of excitement.

[1158] 5. Select calm explanation behaviors from the hospitality behavior database.

[1159] 6. The generative AI model generates the message, "Our recommendation is fresh, seasonal fish sashimi. Please relax and enjoy."

[1160] 7. The robot will guide you with voice and show a smiling face.

[1161] In this way, the present invention can provide a service that takes into consideration both the needs and feelings of the user, and can realize the uniquely Japanese "omotenashi" hospitality.

[1162] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1163] Step 1:

[1164] The user inputs information into the device by voice or text. Specifically, the user says, "Please tell me what dishes you recommend." The input is acquired as voice data from the microphone and converted into text data by the device's voice recognition module. This converted text data is passed on to the next process. The input data is voice data, and the output data is text data.

[1165] Step 2:

[1166] The device sends the text data obtained by speech recognition to the server. Specifically, the text data is sent to the server as an HTTP request specifying an endpoint. The input data is the text data, and the output data is an HTTP request to the server.

[1167] Step 3:

[1168] The server receives an HTTP request and extracts the text data. The text data is then passed to a natural language processing module for contextual and semantic analysis. Specifically, the NLP module "spaCy" is used. The input data is the text data, and the output data is the analysis results. The analysis results include tokenized text and keywords.

[1169] Step 4:

[1170] The server identifies the user's needs based on the analysis results. For example, from the phrase "recommended dishes," it determines that the user's need is "I want to know recommended dishes." The input data is the analysis results, and the output data is the user's needs information.

[1171] Step 5:

[1172] The emotion recognition engine installed on the server recognizes emotions from the user's input data (voice and text). For example, it uses IBM Watson Tone Analyzer to identify the user's emotional state, such as whether they are excited or troubled. The input data is text data and voice data, and the output data is the emotion recognition results.

[1173] Step 6:

[1174] The server selects an appropriate hospitality action based on the user's needs and emotion recognition results. It searches for the most appropriate action from a database of Japanese hospitality actions and selects an action such as "explain calmly." The input data are the needs information and emotion recognition results, and the output data is the selected hospitality action.

[1175] Step 7:

[1176] The server generates a specific message based on the selected hospitality behavior. Using the generative AI model "GPT-3," it generates a message such as "Our recommendation is seasonal fresh fish sashimi. Please relax and enjoy." The input data are the selected hospitality behaviors, and the output data is the generated message.

[1177] Step 8:

[1178] The generated message is sent from the server to the terminal. Specifically, the server sends the message to the terminal as an HTTP response. The input data is the generated message, and the output data is the HTTP response to the terminal.

[1179] Step 9:

[1180] The device provides the received message to the user. It uses the speech synthesis module "Google Text-to-Speech" to play back the message aloud. In the case of a customer service robot, it also performs appropriate facial expressions and gestures. The input data is the received message, and the output data is voice and physical gestures.

[1181] Through the above process, it becomes possible to provide hospitality that takes into account the user's needs and emotions. This series of steps results in a more human-like response and an improved user experience.

[1182] (Application example 2)

[1183] 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."

[1184] Food delivery services lack personalized suggestions based on user emotions, resulting in a uniform user experience and a lack of hospitality. This often results in users not receiving satisfactory suggestions, which can lead to a decrease in the frequency of service use.

[1185] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1186] In this invention, the server includes means for receiving input data from a user, means for analyzing the input data using natural language processing, means for determining the user's needs based on the analysis results, means for recognizing the user's emotions from the input data, means for selecting appropriate hospitality actions from a Japanese hospitality action database, means for generating specific actions and messages from the selected hospitality actions, and means for providing the generated actions and messages to the user. This enables personalized suggestions based on the user's emotions and needs, thereby improving the user experience.

[1187] A "means for receiving input data from a user" is a device or software component through which a user provides input data such as voice or text.

[1188] The "means for analyzing input data using natural language processing" is a software module for analyzing received input data and understanding its context and meaning.

[1189] The "means for determining user needs based on the analysis results" refers to logic or algorithms for identifying what the user wants from the analyzed data.

[1190] The "means for recognizing user emotions from input data" refers to a software module or algorithm for determining user emotions from the tone and content of input data.

[1191] The "means for selecting appropriate hospitality behavior from a database of Japanese hospitality behavior" is a software module that includes a database and selection logic for selecting optimal behavior based on the user's needs and emotions.

[1192] The "means for generating the selected hospitality behavior as a specific action or message" is a software module that converts the selected behavior into a specific action or message to be presented to the user.

[1193] The "means for providing the generated action or message to the user" is a device or software component for providing the generated action or message to the user in the form of audio, text, video, or the like.

[1194] System Overview

[1195] The system for implementing this invention is a generative AI system with an emotion engine that recognizes user emotions. This system can incorporate the Japanese spirit of hospitality into food delivery services and provide personalized suggestions to users.

[1196] Hardware and Software Configuration

[1197] 1. Hardware:

[1198] Smartphone (iOS / Android)

[1199] Server (cloud-based)

[1200] 2. Software:

[1201] Speech recognition modules (e.g., Google Cloud Speech-to-Text API)

[1202] Natural Language Processing (NLP) modules (e.g., spaCy, Transformers)

[1203] Emotion recognition engine (e.g. Microsoft Azure Emotion API)

[1204] Hospitality behavior database (e.g., database such as PostgreSQL)

[1205] Processing flow

[1206] 1. User Input:

[1207] A user opens a food delivery app and speaks or texts, "What are your specials for tonight?"

[1208] The smartphone app receives this input, and in the case of voice input, converts it into text data using a voice recognition module (Google Cloud Speech-to-Text API).

[1209] 2. Data transmission and analysis:

[1210] The smartphone sends the text data to the server.

[1211] On the server, an NLP module (spaCy or Transformers) analyzes this data and determines what the user wants, for example, "What are some recommended dishes?"

[1212] 3. User Emotion Recognition:

[1213] The server uses an emotion recognition engine (Microsoft Azure Emotion API) to recognize the user's emotions from the analyzed data. For example, it determines that the user is feeling stressed.

[1214] 4. Action selection and generation:

[1215] Based on the analysis results and emotion recognition results, the server selects appropriate actions from a database of Japanese hospitality behaviors.

[1216] As a specific example, we select the action of "suggesting dishes that reduce stress" and generate a message such as "Our recommendation is chicken soup made with herbs that have a relaxing effect. Please enjoy."

[1217] 5. Response to the user:

[1218] The server generates a message and sends it to the smartphone app.

[1219] A smartphone app provides this message to the user via voice or text and displays an appropriate visual (such as an image of a dish).

[1220] Specific examples

[1221] When a user speaks to the app and says, "What are your dish recommendations?", the following happens:

[1222] 1. Speech recognition result (Google Cloud Speech-to-Text API):

[1223] "What dishes do you recommend?"

[1224] 2. Analysis results (spaCy NLP module):

[1225] {

[1226] "intent": "recommendation",

[1227] "target": "cooking"

[1228] }

[1229] 3. Emotion recognition results (Microsoft Azure Emotion API):

[1230] {

[1231] "emotion": "stress"

[1232] }

[1233] 4. Final Response:

[1234] "Our recommendation is the chicken soup with herbs, which has a relaxing effect. Enjoy."

[1235] By implementing this invention, personalized suggestions based on the user's emotions and needs can be made, improving the user experience.

[1236] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1237] Step 1:

[1238] A user opens a food delivery app and speaks or texts, "What are your specials for tonight?"

[1239] Input: User voice or text data.

[1240] Output: The audio data (in the case of speech input) or directly the text data (in the case of text input) that is passed to the speech recognition module.

[1241] Specific action: The user presses the microphone button on the smartphone app screen and speaks, or enters text into the text field.

[1242] Step 2:

[1243] The device (smartphone) receives voice input and converts the voice into text using a speech recognition module (Google Cloud Speech-to-Text API).

[1244] Input: Audio data.

[1245] Output: The converted text data.

[1246] Specific operation: The voice recognition module converts the voice data into text data, and the converted text data is stored in the terminal.

[1247] Step 3:

[1248] The terminal transmits the converted text data to the server.

[1249] Input: Text data.

[1250] Output: Send to server.

[1251] Specific operation: The smartphone app sends text data to the server as an API request.

[1252] Step 4:

[1253] The server receives the text data and analyzes it using an NLP module (spaCy or Transformers) to identify the user's needs.

[1254] Input: Text data.

[1255] Output: Identified need (e.g., "I'd like some food recommendations").

[1256] What it does: The NLP module analyzes text data, understands context and meaning, and determines the user's needs.

[1257] Step 5:

[1258] The server uses an emotion recognition engine (Microsoft Azure Emotion API) to recognize the user's emotions from the input data.

[1259] Input: Text data.

[1260] Output: Perceived emotion (e.g., "stressed").

[1261] Specific operation: The emotion recognition engine analyzes the user's emotions based on features such as text data and voice tone, and obtains a judgment result.

[1262] Step 6:

[1263] Based on the analysis results and emotion recognition results, the server selects appropriate actions from a database of Japanese hospitality actions.

[1264] Input: Analysis results and emotion recognition results.

[1265] Output: Selected hospitality behavior (e.g., "Suggest a dish that reduces stress").

[1266] Specific operation: The logic in the server searches and selects the optimal action from the database based on the analysis results and emotion recognition results.

[1267] Step 7:

[1268] The server generates specific actions and messages based on the selected hospitality behaviors.

[1269] Input: Selected hospitality behaviors.

[1270] Output: The generated message (e.g., "Our specialty is our relaxing herbal chicken soup. Enjoy.").

[1271] Specific operation: The server's generative AI model generates an appropriate message based on the given prompt (e.g., "Suggest a dish that has a relaxing effect").

[1272] Step 8:

[1273] The server generates a message and sends it to the terminal.

[1274] Input: The generated message.

[1275] Output: Send to terminal.

[1276] Specific operation: The server sends the generated message as an API response to the smartphone app.

[1277] Step 9:

[1278] The device provides the received message to the user via voice or text and displays an appropriate image (such as an image of a dish).

[1279] Input: The generated message.

[1280] Output: The audio or text and video presented to the user.

[1281] What it does: The smartphone app displays the message on the screen, reads it aloud, and displays a related video on the screen.

[1282] 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.

[1283] 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.

[1284] 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.

[1285] [Fourth embodiment]

[1286] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1287] 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.

[1288] 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).

[1289] 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.

[1290] 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.

[1291] 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).

[1292] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1293] 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.

[1294] 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.

[1295] 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.

[1296] 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.

[1297] 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.

[1298] 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."

[1299] System Overview

[1300] This invention is a system that includes a generative AI that understands user needs and provides the uniquely Japanese "omotenashi" hospitality. This system receives input data from users, analyzes the data, and selects and generates appropriate hospitality actions to provide warm and welcoming service to users.

[1301] A natural language description of the program's operation

[1302] Input from the user

[1303] The user inputs voice or text into the device. For example, the user might say, "Please tell me what dishes you recommend." The device receives this voice input and converts it into text data using its voice recognition function.

[1304] Sending data

[1305] The device sends the converted text data to the server, which receives it and passes it to a natural language processing (NLP) module.

[1306] Data analysis

[1307] The server's NLP module analyzes the text data. This analysis allows it to understand the meaning and intent behind the user's statements and identify the information and actions the user is seeking. For example, it can understand a user's need to know what dishes they recommend.

[1308] Choosing actions based on needs

[1309] Based on the analysis results, the server selects an appropriate hospitality action from a database of hospitality actions specific to Japan, such as "recommending dishes."

[1310] Action and message generation

[1311] The server generates specific actions and messages based on the selected behavior. The generated messages provide appropriate information to the user and realize a warm and friendly response. For example, it generates a message such as "Our recommendation is seasonal fresh fish sashimi."

[1312] Responding to the user

[1313] The generated message is sent from the server to the terminal, which receives it and provides it to the user by displaying or speaking it. In addition, in the case of a customer service robot, it performs an appropriate physical action (e.g., smiling or exchanging business cards).

[1314] Specific examples

[1315] Example 1: Restaurant service robot

[1316] 1. User Input

[1317] A user speaks to a customer service robot installed in a restaurant and asks, "What dishes do you recommend?"

[1318] The terminal (robot) receives this voice and converts it into text using voice recognition.

[1319] 2. Data submission and analysis

[1320] The terminal transmits the text data to the server.

[1321] The server receives the data and analyzes it using a natural language processing module.

[1322] The server determines that the user's need is "I want to know recommended dishes."

[1323] 3. Action selection and generation

[1324] Based on the analysis results, the server selects the action of "suggesting recommended dishes" from the hospitality action database.

[1325] Generate a message saying, "Our recommendation is sashimi made from fresh seasonal fish."

[1326] 4. Responding to the User

[1327] The server sends the generated message to the terminal.

[1328] The terminal (robot) announces in voice, "Our recommendation is sashimi made from fresh seasonal fish," and shows a smiling face.

[1329] In this way, the present invention makes it possible to improve the user experience by embodying the uniquely Japanese hospitality using generative AI.

[1330] The processing flow will be explained below.

[1331] Step 1:

[1332] The user inputs input data (text or voice) into the device. For example, in a restaurant, the user might say, "Please tell me what dishes you recommend." The device receives this voice.

[1333] Step 2:

[1334] The voice data received by the device is passed to the voice recognition module, which converts it into text, and the converted text data is sent to the server.

[1335] Step 3:

[1336] The server receives the text data, passes it to a natural language processing (NLP) module, and analyzes the text data.

[1337] Step 4:

[1338] The server's NLP module analyzes the context and meaning of the text data to identify the user's needs, such as "I want to know what dishes are recommended."

[1339] Step 5:

[1340] Based on the analysis results, the server sends a query to the Japanese hospitality behavior database to search for an appropriate hospitality behavior. For example, it selects the behavior of "recommending dishes."

[1341] Step 6:

[1342] The server generates specific actions and messages based on the selected hospitality behavior. For example, it generates a message such as, "Our recommendation is fresh seasonal fish sashimi."

[1343] Step 7:

[1344] The server sends the generated messages and action data to the terminal, which receives this data.

[1345] Step 8:

[1346] The device receives a message from the server and displays it to the user via voice or display. For example, a customer service robot might say, "Our recommendation is sashimi made with fresh seasonal fish," and then physically move to smile.

[1347] Through these steps, the system can provide appropriate hospitality according to the user's needs and realize human-like responses.

[1348] Example 1

[1349] 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."

[1350] Conventional customer service systems have had difficulty effectively responding to the diverse needs of users, and it has been particularly difficult to embody the uniquely Japanese spirit of "omotenashi" (hospitality). Furthermore, the process of converting voice input into text and then analyzing it is complicated, which reduces the efficiency and accuracy of the entire system.

[1351] 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.

[1352] In this invention, the server includes means for receiving input data from a user, means for converting the input data into text data by speech recognition, means for analyzing the text data by natural language processing, means for determining the user's needs based on the analysis results, means for selecting an appropriate action from a hospitality action database, means for generating the selected action as a specific action or message, and means for providing the generated action or message to the user. This makes it possible to respond quickly and accurately to the user's needs and embody the uniquely Japanese "omotenashi" hospitality.

[1353] "Means for receiving input data from a user" refers to a function including devices and software for capturing input information such as voice or text from a user.

[1354] "Means for converting input data into text data using voice recognition" refers to a function for converting voice input into text format, which utilizes voice recognition software or an API.

[1355] "Means for analyzing text data using natural language processing" refers to a function that uses natural language processing technology to analyze received text data and understand its content.

[1356] "Means for determining user needs based on analysis results" refers to a function that identifies user requests and expectations based on analysis results from natural language processing.

[1357] "Means for selecting appropriate actions from a hospitality action database" refers to a function that selects the most appropriate action from a database that records hospitality actions based on the analysis results.

[1358] "Means for generating selected behaviors as specific actions or messages" refers to the function for converting selected hospitality behaviors into specific actions or messages.

[1359] The "means for providing the generated action or message to the user" is a function for presenting the generated action or message to the user, and uses a display, speaker, or the like.

[1360] This invention is a system that includes a generative AI that understands user needs and provides the uniquely Japanese "omotenashi" hospitality. This system is realized by combining technical elements such as voice recognition, natural language processing technology, customer service robots, and a hospitality behavior database.

[1361] Hardware and Software Configuration

[1362] The main components of the system are:

[1363] Terminal

[1364] 1. Audio input device: Equipped with a microphone to receive the user's audio input.

[1365] 2. Speech Recognition Software: We use speech recognition software such as the Google Speech-to-Text API to convert voice input into text data.

[1366] 3. Communication module: Equipped with a communication means for transmitting text data to a server using a Wi-Fi module.

[1367] server

[1368] 1. Natural Language Processing (NLP) module: Uses OpenAI's GPT-4 to analyze text data and understand user intent.

[1369] 2. Action selection module: Based on the analyzed needs, an appropriate action is selected from the hospitality action database.

[1370] 3. Generation module: Generates the selected behavior as a specific action or message.

[1371] Customer Service Robot

[1372] 1. Audio output device: A speaker for presenting the generated message to the user.

[1373] 2. Display device: A display for showing a smile or other visual expression of hospitality.

[1374] 3. Motion control system: A control system for executing pre-programmed physical movements (e.g., bowing movements).

[1375] Specific operation of the system

[1376] Input from the user

[1377] The user inputs a question into the terminal by voice or text. For example, the user might say, "What dishes do you recommend?"

[1378] Text Conversion

[1379] The device uses a microphone to receive the user's voice and converts it into text using the Google Speech-to-Text API. The converted text data is temporarily stored in the device's memory and then sent to the server via the Wi-Fi module.

[1380] Data analysis

[1381] The server passes the received text data to the NLP module, which uses GPT-4 to analyze the data, understanding the user's intent and identifying the information and actions the user is seeking.

[1382] Action selection and message generation

[1383] Based on the analysis results, an appropriate action is selected from the hospitality behavior database. GPT-4 is then used again to convert the selected action into a specific action or message. For example, a message such as "Our recommendation is seasonal fresh fish sashimi" is generated.

[1384] Responding to the user

[1385] The generated message is sent from the server to the terminal. The terminal (customer service robot) uses this message to provide voice guidance through the speaker, display a smiley face icon on the display, and execute a bow using the robot's motion control system.

[1386] Specific examples

[1387] Restaurant service robot

[1388] 1. User input: The user speaks to a customer service robot installed in a restaurant, saying, "What dishes do you recommend?"

[1389] 2. Text conversion: The device (robot) receives this voice and converts it into text using a speech recognition function (Google Speech-to-Text API).

[1390] 3. Data transmission and analysis: The converted text data is sent to the server, where it is analyzed using an NLP module (GPT-4). The server determines that the user's need is "I want to know what dishes are recommended."

[1391] 4. Action selection and generation: Based on the analysis results, the server selects the action of "suggesting recommended dishes" from the hospitality action database and generates a message saying, "Our recommendation is seasonal fresh fish sashimi."

[1392] 5. Responding to the user: The generated message is sent to the terminal, which then announces in voice, "Our recommendation is sashimi made from fresh seasonal fish," displays a smiley face icon on the display, and the robot performs a bow.

[1393] This system allows users to intuitively obtain information through voice input and receive warm service. As a specific example, it can improve the user experience in restaurant settings.

[1394] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1395] A detailed explanation of the program's processing flow

[1396] Step 1: Input from the user

[1397] Specific operation: The user inputs a question into the terminal by voice. For example, the user utters, "Please tell me what dishes you recommend."

[1398] Input: User-uttered voice data

[1399] Output: Audio data

[1400] Step 2: Voice Recognition

[1401] Specific operation: The device receives voice data using the built-in microphone and converts the voice data into text data using voice recognition software (e.g., Google Speech-to-Text API).

[1402] Input: Received audio data

[1403] Data processing: Text conversion using speech recognition

[1404] Output: Text data

[1405] Step 3: Send text data

[1406] Specific operation: The terminal sends the converted text data to the server via the Wi-Fi module. For security reasons, the transmission uses the HTTPS protocol.

[1407] Input: Text data

[1408] Output: Text data sent to the server

[1409] Step 4: Analyzing the text data

[1410] Specific operation: The server passes the received text data to an NLP module (e.g., GPT-4) for natural language processing, which analyzes the user's intent and identifies their needs.

[1411] Input: Received text data

[1412] Data Computing: Analysis with Natural Language Processing

[1413] Output: Analysis results that identify user needs

[1414] Step 5: Choose an action

[1415] Specific operation: Based on the analysis results, the server selects an appropriate action from the hospitality action database. Example: It selects the action of "recommending dishes."

[1416] Input: Analysis results

[1417] Data calculation: Action selection from a hospitality action database

[1418] Output: Selected behavioral data

[1419] Step 6: Creating Actions and Messages

[1420] Specific behavior: The server uses an NLP module (e.g., GPT-4) again to generate a specific action or message based on the selected behavior. Example: Generate a message such as "Our recommendation is seasonal fresh fish sashimi."

[1421] Input: Selected behavioral data

[1422] Data arithmetic: Action and message generation by NLP modules

[1423] Output: Generated messages and actions

[1424] Step 7: Respond to the user

[1425] Specific behavior: The generated message and action are sent from the server to the terminal. The terminal (customer service robot) provides voice guidance through a speaker, displays a smiley face icon on the display, and performs a physical action (e.g., bowing).

[1426] Input: Generated message and action

[1427] Output: Audio response to the user, visual display, physical action

[1428] In this way, each processing step works in cooperation with the other, providing a system that provides a warm and welcoming response to users.

[1429] (Application example 1)

[1430] 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."

[1431] The challenge is to improve the quality of customer service in brick-and-mortar stores and provide a warmer hospitality experience. In today's brick-and-mortar stores, staff are often too busy to provide high-quality hospitality to each and every customer, so it is necessary to utilize technology to achieve efficient, high-quality customer service.

[1432] 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.

[1433] In this invention, the server includes means for receiving input data from a user, means for analyzing the input data using natural language processing, means for determining the user's needs based on the analysis results, means for selecting an appropriate hospitality action from a hospitality action database, means for generating the selected hospitality action as a specific action or message, means for providing the generated action or message to the user, and means for displaying the generated action or message in real time via smart glasses, thereby enabling staff at a physical store to perform appropriate hospitality actions in real time and provide high-quality, warm service to each individual customer.

[1434] "Means for receiving input data from a user" refers to a device that allows a user to input data such as voice or text, and a function for receiving that data.

[1435] "Means for analyzing input data using natural language processing" refers to a system that uses natural language processing technology to analyze the content of received user input data and understand its meaning and intent.

[1436] "Means for determining user needs based on analysis results" refers to algorithms and related systems for determining what users want based on analysis results obtained through natural language processing.

[1437] "Means for selecting appropriate hospitality actions from a hospitality action database" refers to a system that selects appropriate actions from a pre-prepared hospitality action database in order to identify the action that best suits the user's needs.

[1438] "Means for generating selected hospitality behaviors as specific actions and messages" refers to a system that concretizes the selected hospitality behaviors and generates messages and actions to actually convey to users.

[1439] The term "means for providing the generated action or message to the user" refers to a device or system for communicating the generated action or message to the user.

[1440] "Means for displaying generated actions and messages in real time via smart glasses" refers to a system that uses smart glasses to visually display generated actions and messages in real time.

[1441] This invention is a system that includes generative AI to understand user needs and provide the unique Japanese "omotenashi" hospitality. This system supports store staff using smart glasses to take appropriate hospitality actions toward customers.

[1442] Hardware Configuration

[1443] The system includes the following major components:

[1444] Smart glasses (e.g. Google Glass, Vuzix Blade)

[1445] Audio input device (microphone)

[1446] Data Processing Server

[1447] Software Configuration

[1448] The software and technologies used are as follows:

[1449] Speech recognition libraries (e.g., speech_recognition module)

[1450] Natural Language Processing API (NLP Generation AI API)

[1451] Smart Glasses Control API

[1452] User input and data submission

[1453] A user (customer) speaks a question or request to a store staff member in a physical store. The voice input device (microphone) captures this voice, and the smart glasses convert it into text data. This text data is sent to a data processing server.

[1454] Analyzing data and determining needs

[1455] The data processing server passes the received text data to a natural language processing API, which analyzes the content. Based on the analysis results, it identifies customer needs and determines the necessary information and actions.

[1456] Selection and generation of hospitality behavior

[1457] The server selects appropriate hospitality actions from the hospitality action database and generates specific messages and actions, which are displayed to store staff via smart glasses.

[1458] Responses to customers and examples

[1459] Staff wearing smart glasses receive the generated messages and instructions in real time and respond appropriately to the customer. For example, if a customer asks, "What's on the lunch menu today?", the staff member's smart glasses will display a message saying, "Our lunch menu is the steak set of the day," and the staff member will then verbally convey that message.

[1460] Prompt Sentence Examples

[1461] "A customer has requested the lunch menu. Please generate an appropriate response."

[1462] This system enables store staff to take appropriate hospitality actions in real time, providing high-quality, warm service to each and every customer.

[1463] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1464] Step 1:

[1465] The user speaks a question or request. The user's input is captured by a microphone as voice data. The input data is voice information and includes the customer's question or request.

[1466] Step 2:

[1467] The device (smart glasses) converts the voice data into text data. This conversion is performed using a speech recognition library (e.g., speech_recognition). Specifically, the voice data is obtained as text data.

[1468] Step 3:

[1469] The terminal sends the converted text data to the server. This transmission is performed via network communication, and the text data arrives at the server. The input is the text data, and the output is the transmission result to the server.

[1470] Step 4:

[1471] The server passes the received text data to a natural language processing API, which analyzes the data. The input is text data, and through analysis, it understands the customer's needs and intentions. The output is the analysis results.

[1472] Step 5:

[1473] The server determines the customer's needs based on the analysis results. Based on the determined needs, it selects an appropriate hospitality action. The specific operation is to compare the analysis results with a hospitality action database. The input is the analysis results, and the output is the selected hospitality action.

[1474] Step 6:

[1475] The server generates the selected hospitality behavior as a specific message or action. This generation is performed using a generative AI model. The input is the selected hospitality behavior, and the output is a specific message or action.

[1476] Step 7:

[1477] The server sends the generated messages and actions to the device (smart glasses). This transmission is also done via network communication. The input is the generated messages and actions, and the output is the transmission result to the device.

[1478] Step 8:

[1479] The terminal displays messages and actions received to staff in real time. Messages are visually provided to staff via the smart glasses display. The input is the received message or action, and the output is the display to staff.

[1480] Step 9:

[1481] Staff members respond to customers based on messages and instructions displayed on the smart glasses. Specific actions include providing appropriate verbal responses and guidance. The input is the information displayed on the smart glasses, and the output is the response to the customer.

[1482] 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.

[1483] System Overview

[1484] This invention is a generative AI system equipped with an emotion engine that recognizes user emotions, and provides the uniquely Japanese "omotenashi" hospitality. It analyzes input data from users, understands their needs and emotions, selects appropriate omotenashi actions, and provides generated actions and messages to users.

[1485] A natural language description of the program's operation

[1486] Input from the user

[1487] The user provides text or voice input data to the device. For example, the user might say, "What dishes do you recommend?" The device receives this speech and converts it into text data using a voice recognition module.

[1488] Sending data

[1489] The device sends the converted text data to the server, which receives it and passes it to a natural language processing (NLP) module for analysis.

[1490] Data analysis

[1491] The server's NLP module analyzes the text data to understand its context and meaning. Through this analysis, the server identifies the user's needs. For example, the server determines that the user wants to know what dishes are recommended.

[1492] User Emotion Recognition

[1493] The emotion engine installed on the server recognizes the user's emotions from the input data. For example, it recognizes the user's emotions such as excitement, interest, or distress from the tone and content of the voice when the user speaks.

[1494] Choosing actions based on needs and emotions

[1495] The server selects an appropriate action from a database of Japanese hospitality actions based on the analysis results and emotion recognition results. For example, if the user is excited, it can select an action that calms and explains things.

[1496] Action and message generation

[1497] The server generates specific actions and messages based on the selected hospitality behaviors. For example, it generates a message such as, "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy."

[1498] Responding to the user

[1499] The generated message and action data are sent from the server to the device. The device receives this data and provides it to the user via voice or screen display. In the case of a customer service robot, it also performs appropriate physical actions (for example, smiling and explaining).

[1500] Specific examples

[1501] Example 1: Restaurant service robot

[1502] 1. User Input

[1503] A user speaks to a customer service robot installed in a restaurant and asks, "What dishes do you recommend?"

[1504] The terminal (robot) receives this voice and converts it into text using voice recognition.

[1505] 2. Data submission and analysis

[1506] The terminal transmits the text data to the server.

[1507] The server receives the data and analyzes it using a natural language processing (NLP) module.

[1508] The server determines that the user's need is "I want to know recommended dishes."

[1509] 3. User Emotion Recognition

[1510] The emotion engine installed on the server recognizes the user's emotion from the tone and content of the voice. For example, it recognizes that the user is excited.

[1511] 4. Action Selection and Generation

[1512] Based on the analysis results and emotion recognition results, the server selects the action of "suggesting recommended dishes" from the hospitality action database.

[1513] Generate a message saying, "Our recommendation is sashimi made from fresh seasonal fish. Please relax and enjoy."

[1514] 5. Responding to the User

[1515] The server sends the generated message to the terminal.

[1516] The terminal (robot) announces in voice, "Our recommendation is sashimi made from fresh seasonal fish. Please relax and enjoy," and then shows a smiling face.

[1517] In this way, the present invention, combined with an emotion recognition engine, can provide appropriate hospitality based on the user's needs and emotions, enabling more human-like responses and greatly improving the user experience.

[1518] The processing flow will be explained below.

[1519] Step 1:

[1520] The user provides input data (text or voice) to the device. For example, the user might say, "What dishes do you recommend?" The device receives this voice.

[1521] Step 2:

[1522] The voice data received by the device is passed to the voice recognition module, which converts it into text, and the converted text data is sent to the server.

[1523] Step 3:

[1524] The server receives the text data, passes it to a natural language processing (NLP) module, and analyzes the text data.

[1525] Step 4:

[1526] The server's NLP module analyzes the context and meaning of the text data to identify the user's needs, such as "I want to know what dishes are recommended."

[1527] Step 5:

[1528] The server sends the analyzed text data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes the user's emotions, such as excitement, interest, or distress, from the tone and phrasing of the input data.

[1529] Step 6:

[1530] The server integrates the analysis results from NLP and the emotion recognition results from the emotion engine to determine the overall needs and emotions of the user.

[1531] Step 7:

[1532] Based on the results of the server's overall judgment, it searches for appropriate actions from a database of Japanese hospitality actions. For example, if the user is excited, it will select an action that calmly explains the situation.

[1533] Step 8:

[1534] Based on the hospitality behavior selected by the server, specific actions and messages are generated. For example, a message such as "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy."

[1535] Step 9:

[1536] The server sends the generated messages and action data to the terminal, which receives the data.

[1537] Step 10:

[1538] The device provides the user with the message received from the server. If the robot is providing voice guidance, it will smile and say, "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy." It may also perform other physical actions.

[1539] Through these steps, the system provides appropriate hospitality actions based on the user's needs and emotions, realizing human-like responses.

[1540] Example 2

[1541] 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."

[1542] Conventional customer service systems have difficulty accurately understanding user needs and providing appropriate responses. Furthermore, they are unable to respond in a way that takes into account the user's emotions, which can result in a poor user experience. It has been particularly difficult to provide responses that reflect the uniquely Japanese spirit of "omotenashi" hospitality.

[1543] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving user input data, means for analyzing the input data by natural language processing, means for determining the user's needs based on the analysis results, means for recognizing the user's emotions, means for selecting appropriate hospitality actions based on the user's needs and emotions, means for generating the selected hospitality actions as specific actions and messages, and means for providing the generated actions and messages to the user. This enables a service that takes into consideration both the user's needs and emotions, thereby realizing the uniquely Japanese "omotenashi" (hospitality).

[1544] "Means for receiving input data from a user" refers to a technology or device that receives text or voice data provided by a user at a terminal and incorporates it into the system.

[1545] "Means for analyzing input data using natural language processing" refers to the process of analyzing received text data using natural language processing technology to understand its context and meaning.

[1546] "Means for determining user needs based on analysis results" refers to methods and technologies for identifying what a user is looking for based on the analysis results obtained through natural language processing.

[1547] "Means for recognizing user emotions" refers to technology that determines a user's emotional state from data input by the user, voice tone, etc.

[1548] "Means for selecting appropriate hospitality actions based on the user's needs and emotions" refers to technology that selects the most appropriate response or action from a database, taking into account the user's needs and emotions.

[1549] "Means for generating specific actions and messages from selected hospitality behaviors" refers to the process of creating specific actions and messages to be provided to users based on the selected behaviors.

[1550] "Means for providing the generated action or message to the user" refers to a technology or device that provides the generated message or action to the user by sound, display, or physical action.

[1551] The present invention is a generative AI system that analyzes input data from a user and provides the unique Japanese "omotenashi" hospitality. Specific embodiments for carrying out the present invention will be described below.

[1552] System configuration

[1553] This system mainly consists of the following hardware and software:

[1554] A device for receiving user input (e.g., a customer service robot or smartphone)

[1555] Server for analyzing and generating input data

[1556] Natural Language Processing (NLP) modules (e.g., "spaCy")

[1557] Speech recognition module (e.g. "Google Speech-to-Text")

[1558] Emotion recognition engine (e.g., "IBM Watson Tone Analyzer")

[1559] Generative AI models (e.g., "GPT-3")

[1560] Speech synthesis modules (e.g., "Google Text-to-Speech")

[1561] User Input

[1562] The user inputs information into the device by voice or text. For example, the user might say, "Please tell me what dishes you recommend." The device is equipped with a microphone and keyboard, through which it receives voice and text data. In the case of voice input, the device's voice recognition module is used to convert it into text data in real time.

[1563] Data transmission and analysis

[1564] The device sends text data to the server using the HTTP protocol. The server then uses the natural language processing (NLP) module "spaCy" to analyze the text data and understand its context and meaning. For example, from a request such as "What dishes do you recommend?", the server identifies the user's need as "I want to know what dishes you recommend."

[1565] emotion recognition

[1566] The server's emotion recognition engine, IBM Watson Tone Analyzer, uses the analyzed text data and voice tone to recognize the user's emotions. For example, the tone of the text and the pitch of the voice can determine whether the user is excited, interested, or confused.

[1567] Selection of hospitality actions

[1568] The server selects an appropriate hospitality behavior from the hospitality behavior database based on the analysis results and emotion recognition results. For example, if the user is excited and wants to know what dishes they recommend, the server selects an action that calmly explains the situation.

[1569] Action and Message Generation

[1570] The server uses the generative AI model "GPT-3" to generate specific actions and messages based on the selected hospitality behavior. For example, it generates a message such as "Our recommendation is fresh seasonal fish sashimi. Please relax and enjoy."

[1571] Responding to the user

[1572] The generated actions and messages are sent from the server to the device, which then plays the messages aloud using the voice synthesis module "Google Text-to-Speech."The customer service robot also performs the necessary gestures and smiles along with the generated messages.

[1573] Specific examples

[1574] Example prompt sentence:

[1575] 1. The user types to the customer service robot, "Please tell me what dish you recommend."

[1576] 2. The robot performs voice recognition and sends the text data to the server.

[1577] 3. The server analyzes the data and determines that the user's need is to "know recommended dishes."

[1578] 4. The emotion recognition engine recognizes the user's state of excitement.

[1579] 5. Select calm explanation behaviors from the hospitality behavior database.

[1580] 6. The generative AI model generates the message, "Our recommendation is fresh, seasonal fish sashimi. Please relax and enjoy."

[1581] 7. The robot will guide you with voice and show a smiling face.

[1582] In this way, the present invention can provide a service that takes into consideration both the needs and feelings of the user, and can realize the uniquely Japanese "omotenashi" hospitality.

[1583] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1584] Step 1:

[1585] The user inputs information into the device by voice or text. Specifically, the user says, "Please tell me what dishes you recommend." The input is acquired as voice data from the microphone and converted into text data by the device's voice recognition module. This converted text data is passed on to the next process. The input data is voice data, and the output data is text data.

[1586] Step 2:

[1587] The device sends the text data obtained by speech recognition to the server. Specifically, the text data is sent to the server as an HTTP request specifying an endpoint. The input data is the text data, and the output data is an HTTP request to the server.

[1588] Step 3:

[1589] The server receives an HTTP request and extracts the text data. The text data is then passed to a natural language processing module for contextual and semantic analysis. Specifically, the NLP module "spaCy" is used. The input data is the text data, and the output data is the analysis results. The analysis results include tokenized text and keywords.

[1590] Step 4:

[1591] The server identifies the user's needs based on the analysis results. For example, from the phrase "recommended dishes," it determines that the user's need is "I want to know recommended dishes." The input data is the analysis results, and the output data is the user's needs information.

[1592] Step 5:

[1593] The emotion recognition engine installed on the server recognizes emotions from the user's input data (voice and text). For example, it uses IBM Watson Tone Analyzer to identify the user's emotional state, such as whether they are excited or troubled. The input data is text data and voice data, and the output data is the emotion recognition results.

[1594] Step 6:

[1595] The server selects an appropriate hospitality action based on the user's needs and emotion recognition results. It searches for the most appropriate action from a database of Japanese hospitality actions and selects an action such as "explain calmly." The input data are the needs information and emotion recognition results, and the output data is the selected hospitality action.

[1596] Step 7:

[1597] The server generates a specific message based on the selected hospitality behavior. Using the generative AI model "GPT-3," it generates a message such as "Our recommendation is seasonal fresh fish sashimi. Please relax and enjoy." The input data are the selected hospitality behaviors, and the output data is the generated message.

[1598] Step 8:

[1599] The generated message is sent from the server to the terminal. Specifically, the server sends the message to the terminal as an HTTP response. The input data is the generated message, and the output data is the HTTP response to the terminal.

[1600] Step 9:

[1601] The device provides the received message to the user. It uses the speech synthesis module "Google Text-to-Speech" to play back the message aloud. In the case of a customer service robot, it also performs appropriate facial expressions and gestures. The input data is the received message, and the output data is voice and physical gestures.

[1602] Through the above process, it becomes possible to provide hospitality that takes into account the user's needs and emotions. This series of steps results in a more human-like response and an improved user experience.

[1603] (Application example 2)

[1604] 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."

[1605] Food delivery services lack personalized suggestions based on user emotions, resulting in a uniform user experience and a lack of hospitality. This often results in users not receiving satisfactory suggestions, which can lead to a decrease in the frequency of service use.

[1606] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1607] In this invention, the server includes means for receiving input data from a user, means for analyzing the input data using natural language processing, means for determining the user's needs based on the analysis results, means for recognizing the user's emotions from the input data, means for selecting appropriate hospitality actions from a Japanese hospitality action database, means for generating specific actions and messages from the selected hospitality actions, and means for providing the generated actions and messages to the user. This enables personalized suggestions based on the user's emotions and needs, thereby improving the user experience.

[1608] A "means for receiving input data from a user" is a device or software component through which a user provides input data such as voice or text.

[1609] The "means for analyzing input data using natural language processing" is a software module for analyzing received input data and understanding its context and meaning.

[1610] The "means for determining user needs based on the analysis results" refers to logic or algorithms for identifying what the user wants from the analyzed data.

[1611] The "means for recognizing user emotions from input data" refers to a software module or algorithm for determining user emotions from the tone and content of input data.

[1612] The "means for selecting appropriate hospitality behavior from a database of Japanese hospitality behavior" is a software module that includes a database and selection logic for selecting optimal behavior based on the user's needs and emotions.

[1613] The "means for generating the selected hospitality behavior as a specific action or message" is a software module that converts the selected behavior into a specific action or message to be presented to the user.

[1614] The "means for providing the generated action or message to the user" is a device or software component for providing the generated action or message to the user in the form of audio, text, video, or the like.

[1615] System Overview

[1616] The system for implementing this invention is a generative AI system with an emotion engine that recognizes user emotions. This system can incorporate the Japanese spirit of hospitality into food delivery services and provide personalized suggestions to users.

[1617] Hardware and Software Configuration

[1618] 1. Hardware:

[1619] Smartphone (iOS / Android)

[1620] Server (cloud-based)

[1621] 2. Software:

[1622] Speech recognition modules (e.g., Google Cloud Speech-to-Text API)

[1623] Natural Language Processing (NLP) modules (e.g., spaCy, Transformers)

[1624] Emotion recognition engine (e.g. Microsoft Azure Emotion API)

[1625] Hospitality behavior database (e.g., database such as PostgreSQL)

[1626] Processing flow

[1627] 1. User Input:

[1628] A user opens a food delivery app and speaks or texts, "What are your specials for tonight?"

[1629] The smartphone app receives this input, and in the case of voice input, converts it into text data using a voice recognition module (Google Cloud Speech-to-Text API).

[1630] 2. Data transmission and analysis:

[1631] The smartphone sends the text data to the server.

[1632] On the server, an NLP module (spaCy or Transformers) analyzes this data and determines what the user wants, for example, "What are some recommended dishes?"

[1633] 3. User Emotion Recognition:

[1634] The server uses an emotion recognition engine (Microsoft Azure Emotion API) to recognize the user's emotions from the analyzed data. For example, it determines that the user is feeling stressed.

[1635] 4. Action selection and generation:

[1636] Based on the analysis results and emotion recognition results, the server selects appropriate actions from a database of Japanese hospitality behaviors.

[1637] As a specific example, we select the action of "suggesting dishes that reduce stress" and generate a message such as "Our recommendation is chicken soup made with herbs that have a relaxing effect. Please enjoy."

[1638] 5. Response to the user:

[1639] The server generates a message and sends it to the smartphone app.

[1640] A smartphone app provides this message to the user via voice or text and displays an appropriate visual (such as an image of a dish).

[1641] Specific examples

[1642] When a user speaks to the app and says, "What are your dish recommendations?", the following happens:

[1643] 1. Speech recognition result (Google Cloud Speech-to-Text API):

[1644] "What dishes do you recommend?"

[1645] 2. Analysis results (spaCy NLP module):

[1646] {

[1647] "intent": "recommendation",

[1648] "target": "cooking"

[1649] }

[1650] 3. Emotion recognition results (Microsoft Azure Emotion API):

[1651] {

[1652] "emotion": "stress"

[1653] }

[1654] 4. Final Response:

[1655] "Our recommendation is the chicken soup with herbs, which has a relaxing effect. Enjoy."

[1656] By implementing this invention, personalized suggestions based on the user's emotions and needs can be made, improving the user experience.

[1657] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1658] Step 1:

[1659] A user opens a food delivery app and speaks or texts, "What are your specials for tonight?"

[1660] Input: User voice or text data.

[1661] Output: The audio data (in the case of speech input) or directly the text data (in the case of text input) that is passed to the speech recognition module.

[1662] Specific action: The user presses the microphone button on the smartphone app screen and speaks, or enters text into the text field.

[1663] Step 2:

[1664] The device (smartphone) receives voice input and converts the voice into text using a speech recognition module (Google Cloud Speech-to-Text API).

[1665] Input: Audio data.

[1666] Output: The converted text data.

[1667] Specific operation: The voice recognition module converts the voice data into text data, and the converted text data is stored in the terminal.

[1668] Step 3:

[1669] The terminal transmits the converted text data to the server.

[1670] Input: Text data.

[1671] Output: Send to server.

[1672] Specific operation: The smartphone app sends text data to the server as an API request.

[1673] Step 4:

[1674] The server receives the text data and analyzes it using an NLP module (spaCy or Transformers) to identify the user's needs.

[1675] Input: Text data.

[1676] Output: Identified need (e.g., "I'd like some food recommendations").

[1677] What it does: The NLP module analyzes text data, understands context and meaning, and determines the user's needs.

[1678] Step 5:

[1679] The server uses an emotion recognition engine (Microsoft Azure Emotion API) to recognize the user's emotions from the input data.

[1680] Input: Text data.

[1681] Output: Perceived emotion (e.g., "stressed").

[1682] Specific operation: The emotion recognition engine analyzes the user's emotions based on features such as text data and voice tone, and obtains a judgment result.

[1683] Step 6:

[1684] Based on the analysis results and emotion recognition results, the server selects appropriate actions from a database of Japanese hospitality actions.

[1685] Input: Analysis results and emotion recognition results.

[1686] Output: Selected hospitality behavior (e.g., "Suggest a dish that reduces stress").

[1687] Specific operation: The logic in the server searches and selects the optimal action from the database based on the analysis results and emotion recognition results.

[1688] Step 7:

[1689] The server generates specific actions and messages based on the selected hospitality behaviors.

[1690] Input: Selected hospitality behaviors.

[1691] Output: The generated message (e.g., "Our specialty is our relaxing herbal chicken soup. Enjoy.").

[1692] Specific operation: The server's generative AI model generates an appropriate message based on the given prompt (e.g., "Suggest a dish that has a relaxing effect").

[1693] Step 8:

[1694] The server generates a message and sends it to the terminal.

[1695] Input: The generated message.

[1696] Output: Send to terminal.

[1697] Specific operation: The server sends the generated message as an API response to the smartphone app.

[1698] Step 9:

[1699] The device provides the received message to the user via voice or text and displays an appropriate image (such as an image of a dish).

[1700] Input: The generated message.

[1701] Output: The audio or text and video presented to the user.

[1702] What it does: The smartphone app displays the message on the screen, reads it aloud, and displays a related video on the screen.

[1703] 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.

[1704] 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.

[1705] 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.

[1706] 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.

[1707] 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.

[1708] 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.

[1709] 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).

[1710] 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.

[1711] 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."

[1712] 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.

[1713] 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).

[1714] 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.

[1715] 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.

[1716] 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.

[1717] 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.

[1718] 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.

[1719] 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.

[1720] 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.

[1721] 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.

[1722] 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.

[1723] 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.

[1724] The following is further disclosed regarding the above embodiment.

[1725] (Claim 1)

[1726] means for receiving input data from a user;

[1727] means for analyzing input data by natural language processing;

[1728] a means for determining user needs based on the analysis results;

[1729] A method for selecting appropriate hospitality behaviors from a database of Japanese hospitality behaviors, and

[1730] A means to generate specific actions and messages based on the selected hospitality behaviors, and

[1731] a means for providing the generated actions and messages to a user;

[1732] A system including:

[1733] (Claim 2)

[1734] 10. The system of claim 1, further comprising means for converting voice input to text.

[1735] (Claim 3)

[1736] 10. The system of claim 1, further comprising means for displaying or audibly providing the generated action or message to the user.

[1737] "Example 1"

[1738] (Claim 1)

[1739] means for receiving input data from a user;

[1740] A means for converting input data into text data by speech recognition;

[1741] A means for analyzing text data using natural language processing;

[1742] a means for determining user needs based on the analysis results;

[1743] A means for selecting appropriate actions from a hospitality action database;

[1744] A means of generating specific actions and messages based on the selected behaviors;

[1745] a means for providing the generated actions and messages to a user;

[1746] A system including:

[1747] (Claim 2)

[1748] The system according to claim 1, wherein the generated actions and messages are displayed or audibly provided to the user.

[1749] (Claim 3)

[1750] The system according to claim 1, wherein the generated action is executed using a customer service robot.

[1751] "Application Example 1"

[1752] (Claim 1)

[1753] means for receiving input data from a user;

[1754] means for analyzing input data by natural language processing;

[1755] a means for determining user needs based on the analysis results;

[1756] A means for selecting appropriate hospitality behavior from a hospitality behavior database;

[1757] A means to generate specific actions and messages based on the selected hospitality behaviors, and

[1758] a means for providing the generated actions and messages to a user;

[1759] a means for displaying generated actions and messages in real time via the smart glasses;

[1760] A system including:

[1761] (Claim 2)

[1762] 10. The system of claim 1, further comprising means for converting voice input to text.

[1763] (Claim 3)

[1764] 10. The system of claim 1, further comprising means for displaying or audibly providing the generated action or message to the user.

[1765] "Example 2: Combining Emotion Engines"

[1766] (Claim 1)

[1767] means for receiving input data from a user;

[1768] means for analyzing input data by natural language processing;

[1769] a means for determining user needs based on the analysis results;

[1770] means for recognizing a user's emotion;

[1771] A means for selecting appropriate hospitality actions based on the user's needs and emotions;

[1772] A means to generate specific actions and messages based on the selected hospitality behaviors, and

[1773] a means for providing the generated actions and messages to a user;

[1774] A system including:

[1775] (Claim 2)

[1776] 10. The system of claim 1, further comprising means for converting voice input to text.

[1777] (Claim 3)

[1778] 10. The system of claim 1, further comprising means for displaying or audibly providing the generated action or message to the user.

[1779] "Application example 2 when combining emotion engines"

[1780] (Claim 1)

[1781] means for receiving input data from a user;

[1782] means for analyzing input data by natural language processing;

[1783] a means for determining user needs based on the analysis results;

[1784] means for recognizing a user's emotion from input data;

[1785] A method for selecting appropriate hospitality behaviors from the Japanese hospitality behavior database, and

[1786] A means to generate specific actions and messages based on the selected hospitality behaviors, and

[1787] a means for providing the generated actions and messages to a user;

[1788] A system including:

[1789] (Claim 2)

[1790] 10. The system of claim 1, further comprising means for converting voice input to text.

[1791] (Claim 3)

[1792] 10. The system of claim 1, further comprising means for displaying or audibly providing the generated action or message to the user. [Explanation of symbols]

[1793] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving input data from a user; means for analyzing input data by natural language processing; a means for determining user needs based on the analysis results; A method for selecting appropriate hospitality behaviors from a database of Japanese hospitality behaviors, and A means to generate specific actions and messages based on the selected hospitality behaviors, and a means for providing the generated actions and messages to a user; A system including:

2. 10. The system of claim 1, further comprising means for converting voice input to text.

3. 10. The system of claim 1, further comprising means for displaying or audibly providing the generated actions and messages to the user.

Images