System

Abstract

A system is provided.SOLUTION: A system comprising: voice input means; conversion means for converting voice data into text data; generation means for generating manipulation guidance from the text data using a generative model; and output means for outputting the generated manipulation guidance by voice.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] Elderly people often find it difficult to operate smartphones, resulting in a digital divide. This problem has become even more serious with the trend toward nuclear families and longer life expectancies. Furthermore, especially in times of disaster, delays in obtaining information increase the risk of disasters, so rapid information acquisition is essential. Therefore, it is urgent to enable elderly people to use smartphones easily and without stress, and solutions are needed to achieve this. [Means for solving the problem]

[0005] This invention is a system that includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance aloud. When a user provides voice input, the system acquires the voice and converts it into text data. Next, the system uses the generative model to generate appropriate operation guidance based on the user's question and outputs it aloud. This procedure can help elderly people easily understand how to operate smartphones and bridge the digital divide.

[0006] The "voice input means" is a means for acquiring the user's voice as digital data.

[0007] The "conversion means" is a means for converting voice data into text data.

[0008] The "generation means" is a means for generating operation guidance from text data using a generative model.

[0009] A "generative model" is a model that uses a pre-trained dialogue model to analyze text data and generate appropriate responses.

[0010] The "output means" is a means for outputting the generated operation guidance to the user as voice. [Brief explanation of the drawings]

[0011] [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

[0012] 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.

[0013] First, the terms used in the following description will be explained.

[0014] 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).

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] The system of the present invention includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance by voice. Below, the processing of the system program will be explained in natural language.

[0033] Voice input means

[0034] The user speaks a question into the smartphone's microphone, and this voice is captured as digital data by the voice input means.

[0035] Speech-to-text

[0036] The device analyzes the acquired voice data and converts it into text data using a voice recognition library. In this step, the voice recognition library analyzes the voice data and generates text data such as "Tell me how to use this app."

[0037] Generate operation guides

[0038] The server receives the generated text data and analyzes it using a pre-trained generative model. The generative model is an interactive AI model that generates appropriate operation guidance based on the generated text data. For example, if a user asks, "How do I use this app?", the server generates operation guidance such as, "To use this app, tap this icon on the home screen."

[0039] Guide audio output

[0040] The device converts the generated operation guide into audio data using a text-to-speech engine and outputs it audibly to the user, allowing the user to actually receive the operation guide in audio, making it easier for them to understand how to operate the smartphone.

[0041] Specific examples

[0042] For example, if a user asks "How do I use this app?", the following happens:

[0043] 1. The user speaks a question into the smartphone microphone.

[0044] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0045] 3. The server uses the generative model to analyze this text data and generate an instruction guide such as, "To use this app, tap this icon on the home screen."

[0046] 4. The device converts the generated operation guide into voice data and outputs it to the user.

[0047] This system allows elderly people to easily understand how to operate smartphones, making it an effective means of bridging the digital divide.

[0048] The processing flow will be explained below.

[0049] Step 1:

[0050] The user speaks their question into the smartphone's microphone. The voice input means captures the user's voice and stores the voice data in digital format.

[0051] Step 2:

[0052] The device uses a speech recognition library to convert the acquired voice data into text data. The speech recognition library analyzes the voice signal and generates corresponding text data. Text in the format "Tell me how to use this app" is generated.

[0053] Step 3:

[0054] The terminal sends the converted text data to the server, which receives the text data and prepares it for analysis.

[0055] Step 4:

[0056] The server uses a pre-trained interactive generative model to analyze the text data and generate appropriate operation guides. Based on the user's question, the generative model generates operation guide text such as "To use this app, tap this icon on the home screen."

[0057] Step 5:

[0058] The server transmits the generated operation guide text to the terminal, which processes the received operation guide text and prepares for voice output.

[0059] Step 6:

[0060] The device uses a text-to-speech engine to convert the operation guide text into voice data, which is then converted into a format that is easy for the user to hear.

[0061] Step 7:

[0062] The terminal reproduces the generated audio data through the audio output means so that the user can hear it, thereby enabling the user to receive the smartphone operation guide by audio.

[0063] Example 1

[0064] 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."

[0065] There is a need to overcome the difficulties faced by elderly and technology-inexperienced users when learning how to operate electronic devices, including smartphones. Conventional methods require users to refer to user manuals or web pages, which can be burdensome for users. Furthermore, text-only instructions are difficult to understand and are difficult to translate into actual operation. To address these challenges, an intuitive and easy-to-use operation guidance system using voice input is needed.

[0066] 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.

[0067] In this invention, the server includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance by voice. This allows a user to receive operation guidance by voice in real time by simply asking a question by voice, making it easy to understand how to operate a smartphone or the like.

[0068] "Audio input means" refers to devices and techniques for capturing user-generated audio into a device.

[0069] The "conversion means for converting voice data into text data" refers to software and hardware technology for analyzing acquired voice data and converting it into corresponding text data.

[0070] A "generative model" is an artificial intelligence system that uses pre-trained algorithms to generate specific outputs based on input data.

[0071] The "generation means" refers to a technique and device for generating an appropriate operation guide based on text data.

[0072] The "output means" refers to a device and technology for providing the generated operation guide to the user as audio data.

[0073] A "text-to-speech engine" is software and technology that synthesizes text data into natural-sounding speech and outputs it.

[0074] A "voice recognition library" is a collection of software that has the function of analyzing voice data and converting it into text data.

[0075] A "dialogue model" is an artificial intelligence system designed to generate appropriate responses through dialogue with a user.

[0076] The system of the present invention includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance by voice. The processing of the system program will be specifically described below.

[0077] In an embodiment of the system, a user speaks a question into a microphone on a device such as a smartphone or tablet. For example, they may say, "Tell me how to use this app." This causes a voice input means to capture voice data in digital form. The device then uses a speech recognition library, such as the Google Speech-to-Text API, to convert the captured voice data into text data. The conversion means analyzes the speech waveform, breaks it down into phonemes, and maps them to text data.

[0078] The device then sends the converted text data to the server. The server analyzes the text data using a pre-trained generative AI model (e.g., OpenAI's GPT-3) and generates an appropriate operation guide. This generation method is an algorithm that understands the user's intent based on the text data and generates the most appropriate operation guide. An example of a prompt sentence is, "If the user says, 'Tell me how to use this app,' what kind of operation guide should be generated?" Based on this, the server generates an operation guide such as, "To use this app, tap this icon on the home screen."

[0079] Finally, the device converts the generated operation guide into voice data using a text-to-speech engine (e.g., Amazon Polly) and outputs it audibly to the user. This output means allows the user to receive the operation guide as voice, making it easier for them to understand how to operate the smartphone.

[0080] For example, if a user asks "How do I use this app?", the following process occurs:

[0081] 1. The user speaks a question into the smartphone microphone.

[0082] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0083] 3. The server uses the generative AI model to analyze this text data and generate an operation guide such as, "To use this app, tap this icon on the home screen."

[0084] 4. The device converts the generated operation guide into voice data and outputs it to the user.

[0085] This system allows even elderly people and users who are not familiar with technology to easily understand how to operate a smartphone. In this way, the voice guidance system greatly improves user convenience.

[0086] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0087] Step 1: Getting voice input

[0088] The user speaks a question into the smartphone's microphone, and this voice is captured as digital data by the voice input means.

[0089] Input: User spoken words

[0090] What it does: An audio input method captures audio in digital form.

[0091] Output: Digital audio data

[0092] Step 2: Convert audio data to text

[0093] The terminal analyzes the acquired voice data using a voice recognition library (for example, Google Speech-to-Text API) and converts it into text data.

[0094] Input: Digital audio data

[0095] How it works: The device analyzes the audio waveform, breaks it down into phonemes, and maps them to text data.

[0096] Output: Text data in the format "Tell me how to use this app"

[0097] Step 3: Send text data

[0098] The terminal transmits the converted text data to the server.

[0099] Input: Text data in the format "Tell me how to use this app"

[0100] Operation: The device sends text data to the server via the network.

[0101] Output: Text data sent to the server

[0102] Step 4: Generate the guide

[0103] The server analyzes the received text data using a generative model (e.g., OpenAI's GPT-3) and generates appropriate operation guides.

[0104] Input: Text data in the format "Tell me how to use this app"

[0105] How it works: The generative model analyzes the text data and generates a guide based on the prompt: "If a user says 'Teach me how to use this app,' what kind of guide should be generated?"

[0106] Output: Operation guide such as "To use this app, tap this icon on the home screen."

[0107] Step 5: Sending the guide

[0108] The server transmits the generated operation guide to the terminal.

[0109] Input: Instructions such as "To use this app, tap this icon on the home screen."

[0110] Operation: The server sends the operation guide to the terminal via the network.

[0111] Output: Operation guide delivered to the device

[0112] Step 6: Audio output of operation guide

[0113] The device converts the received operation guide into voice data using a text-to-speech engine (e.g., Amazon Polly) and outputs it audibly to the user.

[0114] Input: Instructions such as "To use this app, tap this icon on the home screen."

[0115] Operation: The device converts the text data of the operation guide into voice data using a speech synthesis engine.

[0116] Output: Audio data that the user can hear (operation guide)

[0117] The above is the specific processing flow of the system. This system allows users to easily ask questions by voice and receive operation guidance in response to those questions by voice.

[0118] (Application example 1)

[0119] 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."

[0120] There is a problem in that it is difficult for workers in factories to quickly obtain information on how to use operating machines correctly and on maintenance management. Conventional methods require manuals and face-to-face training, which takes time and effort, and also increases the risk of operating incorrectly. This can reduce work efficiency and compromise safety.

[0121] 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.

[0122] In this invention, the server includes a voice input means, a conversion means for converting voice data into text data, and a generation means for generating operation guidance from the text data using a generative model, thereby enabling the server to provide appropriate operation instructions and operation guidance in real time by voice based on the worker's voice questions.

[0123] "Voice input means" is a device for acquiring voice uttered by a user and storing it as digital data.

[0124] The "conversion means" is a device or software that has the function of converting acquired voice data into text data.

[0125] The "generation means" is a device or software that has the function of generating an appropriate operation guide from text data.

[0126] The "output means" is a device or software that converts the generated operation guide into audio data and provides it to the user as audio.

[0127] "Work machines" refer to various types of machinery and equipment used in factories, and are devices for automation and machine control to improve work efficiency.

[0128] "Workers" are people who operate work machines and perform various tasks in a factory.

[0129] "Real-time" means that data is processed and output immediately, without delay.

[0130] A "conversational AI model" is an artificial intelligence model that generates appropriate responses in natural language in response to user input.

[0131] A system for implementing the present invention is configured as follows.

[0132] Voice input means

[0133] The user speaks a question into a microphone mounted on the work machine. This voice is captured as digital data by a voice input means. A commercially available microphone or voice collection device can be used as the voice input means.

[0134] Speech-to-text

[0135] The device analyzes the acquired voice data and converts it into text data using a voice recognition library. In this step, the voice recognition library can use services such as "Google Cloud Speech-to-Text." This library analyzes the voice data and generates text data such as "Please tell me how to maintain this machine."

[0136] Generate operation guides

[0137] The server receives the generated text data and analyzes it using a pre-trained generative model. A conversational AI model such as OpenAI's GPT-4 is used as the generative model. This generative model generates appropriate operation guidance based on the text data. For example, it provides specific instructions such as, "First, turn off the machine and then remove the cover. Next, clean the dust inside."

[0138] Guide audio output

[0139] The device uses a text-to-speech engine to convert the generated operation guide into audio data and output it audibly to the user. The text-to-speech engine can be "Amazon Polly" or similar.

[0140] Specific examples

[0141] For example, if a worker asks, "Tell me how to maintain this machine," the process goes like this:

[0142] 1. The worker speaks a question into the microphone on the work machine.

[0143] 2. The device receives the voice data and converts it into text data such as "Please tell me how to maintain this machine."

[0144] 3. The server uses the generative model to analyze this text data and generate an operation guide that reads, "First, turn off the machine and then remove the cover. Next, clean the dust that has accumulated inside."

[0145] 4. The terminal converts the generated operation guide into audio data and outputs it to the worker.

[0146] Prompt Sentence Examples

[0147] The following is an example of a prompt sentence that generates an appropriate operation guide for a dialogue when a worker asks, "Tell me how to maintain this machine."

[0148] markdown

[0149] Please generate an appropriate operation guide for the following dialogue when the user asks, "Please tell me how to maintain this machine."

[0150] Q: How do I maintain this machine?

[0151] Answer: First, turn off the machine and then remove the cover. Then, clean the dust accumulated inside. For detailed instructions, please refer to the following website:

[0152] This system allows workers to receive quick and accurate operation instructions and maintenance guides via voice input and output, improving work efficiency and reducing the risk of operational errors.

[0153] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0154] Step 1:

[0155] The user speaks a question into the microphone of the work machine. This voice is acquired as digital data by the voice input means. Specifically, when the user says, "Please tell me how to maintain this machine," the voice data is input into the terminal via the microphone.

[0156] Step 2:

[0157] The device converts the acquired voice data into text data using a speech recognition library. Specifically, the device calls the Google Cloud Speech-to-Text API and converts the voice data into text data such as "Please tell me how to maintain this machine." During this conversion process, the voice data is analyzed and the corresponding text is generated.

[0158] Step 3:

[0159] The terminal transmits the generated text data to the server. Specifically, the text data is sent to the server as an HTTP request. This data transmission continues until the server receives it.

[0160] Step 4:

[0161] The server analyzes the received text data using a pre-trained generative AI model to generate appropriate operation guidance. Specifically, the server uses OpenAI's GPT-4 model to generate operation guidance such as "First, turn off the machine and then remove the cover. Next, clean the dust that has accumulated inside" in response to the received text data "Please tell me how to maintain this machine." In this generation process, a dialogue generation model operates based on the input text and outputs the corresponding guidance.

[0162] Step 5:

[0163] The server sends the generated operation guide to the terminal. Specifically, the generated text data is returned to the terminal as an HTTP response. This data transmission continues until the terminal receives it.

[0164] Step 6:

[0165] The device converts the generated operation guide into audio data using a text-to-speech engine. Specifically, the device calls Amazon Polly to convert the text data of the operation guide into audio data. During this conversion process, the text is analyzed and the corresponding audio is generated.

[0166] Step 7:

[0167] The terminal outputs the generated audio data to the user through a speaker. Specifically, the audio data reaches the user's ears from the speaker. This audio output allows the user to receive the operation guide by audio.

[0168] 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.

[0169] The system of this invention includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, an output means for outputting the generated operation guidance by voice, and an emotion engine for recognizing the user's emotions. Below, the processing of the system program will be explained in natural language.

[0170] Voice input means

[0171] The user speaks their question into the smartphone's microphone, and the voice input means captures the user's voice and stores the voice data in digital format.

[0172] Speech-to-text

[0173] The device analyzes the acquired voice data and converts it into text data using a speech recognition library. The speech recognition library analyzes the voice signal and generates text in the format of "Tell me how to use this app."

[0174] emotion recognition

[0175] The device uses an emotion engine to recognize the user's emotions from the voice or text data, for example, determining whether the user is distressed, angry, or happy based on the tone and content of the voice.

[0176] Generate operation guides

[0177] The server receives the generated text data and the recognized user emotion and analyzes it using a pre-trained generative model. The generative model is an interactive AI model that generates emotion-sensitive operation guidance such as "To use this app, tap this icon on the home screen" based on the text data and emotion information.

[0178] Guide audio output

[0179] The device converts the generated operation guide text into audio data using a text-to-speech engine and outputs it audibly to the user. At this time, the tone and expression of the generated guide are adjusted to match the user's emotions.

[0180] Specific examples

[0181] For example, if a user asks "How do I use this app?" and speaks in a confused tone:

[0182] 1. The user speaks a question into the smartphone microphone.

[0183] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0184] 3. The device uses an emotion engine to analyze the user's problem.

[0185] 4. The server uses the generative model to generate an operation guide based on the text data and the user's confusion: "We'll explain it in simple terms. To use this app, tap this icon on the home screen."

[0186] 5. The device converts the generated operation guide into voice data and outputs it to the user in a gentle tone.

[0187] This system allows elderly people to receive appropriate support in how to operate their smartphones based on their emotions, and to receive information in a format that is easier to understand.

[0188] The processing flow will be explained below.

[0189] Step 1:

[0190] The user speaks a question into the smartphone's microphone, and the user's voice is captured as digital voice data by the voice input means.

[0191] Step 2:

[0192] The voice data acquired by the device is analyzed using a voice recognition library and converted into text data. The voice signal is analyzed and the text data "Teach me how to use this app" is generated.

[0193] Step 3:

[0194] The device uses the emotion engine to recognize the user's emotion from the acquired and converted voice data and text data, for example, recognizing that the user is in a difficult state from the tone and content of the voice.

[0195] Step 4:

[0196] The device sends the converted text data and the recognized user emotion information to the server, which then receives the necessary data and prepares to proceed to the next step.

[0197] Step 5:

[0198] The server uses a pre-trained interactive generative model to analyze the text data and emotional information sent and generate appropriate operation guidance. For example, the generative model generates operation guidance such as, "To use this app, tap this icon on the home screen."

[0199] Step 6:

[0200] The server sends the generated operation guide to the terminal, which receives the guide and prepares for voice output.

[0201] Step 7:

[0202] The device uses a text-to-speech engine to convert the operation guide text into voice data, and the generated operation guide is converted into voice in a tone that takes into consideration the user's emotions.

[0203] Step 8:

[0204] The terminal reproduces the generated voice data through the voice output means so that the user can hear it. For example, if the user is recognized as having trouble, guidance is provided in a gentle tone.

[0205] Through this step, the system provides smartphone operation guidance in a way that takes the user's emotions into consideration, helping elderly people to easily understand how to operate the smartphone.

[0206] Example 2

[0207] 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."

[0208] In conventional voice assistant systems, the function of converting user questions from voice to text and providing information based on that text often ignores emotions, which can increase user stress and dissatisfaction. Furthermore, there is a lack of guidance that takes emotions into consideration, particularly for elderly users and those who require technical support, resulting in a poor user experience.

[0209] 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 a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, an output means for outputting the generated operation guidance by voice, and an emotion recognition means for recognizing the emotion of the user. This allows the system to provide guidance that takes into consideration the emotion of the user, and enables even elderly users and users who require technical support to use the system smoothly and without stress.

[0210] "Voice input means" refers to equipment or software for acquiring user speech as voice data.

[0211] "Conversion means for converting voice data into text data" refers to software or a library that analyzes acquired voice data and converts it into corresponding text data.

[0212] A "generative model" refers to an AI model that uses a pre-trained algorithm to generate sentences such as operation guides from text data.

[0213] "Generation means for generating operation guide" refers to a function or software that uses a generative model to generate a guide that helps the user with operation from text data.

[0214] The "output means for outputting the generated operation guide as audio" refers to a device or software that converts the generated operation guide into audio data and outputs it in a form that can be heard by the user.

[0215] "Emotion recognition means for recognizing user emotions" refers to algorithms or software for analyzing and recognizing user emotions from voice data or text data.

[0216] MODE FOR CARRYING OUT THE INVENTION

[0217] A system for implementing the present invention includes the following components:

[0218] Voice input means

[0219] The user speaks their question using a device with a microphone (e.g., a smartphone or tablet), and the voice input means captures the voice and stores it in digital format.

[0220] A conversion means for converting voice data into text data

[0221] The device then uses a speech recognition library such as the Google Cloud Speech-to-Text API to analyze the captured voice data and convert it into text data. The voice signal is analyzed and text is generated in the form of a message such as "Tell me how to use this app."

[0222] emotion recognition means

[0223] The device uses an emotion engine such as IBM Watson Tone Analyzer to recognize the user's emotions from the analyzed text or voice data, determining whether the user is distressed, angry, or happy based on the tone and content of the voice.

[0224] A method for generating operation guides

[0225] The server receives the generated text data and the recognized user emotion data and analyzes it using a generative AI model such as OpenAI GPT-3. Based on the text data and emotion information, the generative AI model generates emotion-sensitive operation guidance such as "To use this app, tap this icon on the home screen."

[0226] An output means for outputting the generated operation guide in voice form.

[0227] The device then sends the generated guide text to a text-to-speech engine such as Amazon Polly, which converts it into speech data. This speech data is then output to the smartphone speaker for the user to hear, with the tone and expression adjusted to match the user's emotions.

[0228] Specific examples

[0229] For example, if a user asks "How do I use this app?" and speaks in a confused tone:

[0230] 1. The user speaks a question into the smartphone microphone.

[0231] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0232] 3. The device uses IBM Watson Tone Analyzer to analyze the user's problem.

[0233] 4. The server uses OpenAI GPT-3 to generate an operation guide based on the text data and the user's confusion: "We'll explain it in simple terms. To use this app, tap this icon on the home screen."

[0234] 5. The device sends the generated operation guide to Amazon Polly, which converts it into voice data in a gentle tone and finally outputs it to the user through the smartphone speaker.

[0235] Prompt Sentence Examples

[0236] Here are some example prompts to input to a generative AI model:

[0237] "Take a question uttered by a user in a confused tone and generate a how-to guide that explains how to use the app in a straightforward and friendly tone."

[0238] This system allows elderly people and users who require technical support to receive guidance that takes their emotions into consideration, making it easier for them to use the system.

[0239] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0240] Step 1: Voice Input

[0241] The user speaks a question into the smartphone's microphone. The voice input means captures the voice and stores it in digital format. Specifically, the user picks up the smartphone and asks, "Tell me how to use this app." The smartphone's microphone captures the voice data and temporarily stores it.

[0242] Input: User's spoken utterance

[0243] Output: Digital audio data

[0244] Step 2: Convert audio data to text

[0245] The device uses a speech recognition library such as the Google Cloud Speech-to-Text API to analyze the audio data and convert it into text. The library analyzes the audio signal and generates the corresponding text data.

[0246] Specifically, the device sends voice data to the Google Cloud Speech-to-Text API and receives text data such as "Teach me how to use this app." The device then stores this text data.

[0247] Input: Digital audio data

[0248] Output: Text data of "Tell me how to use this app"

[0249] Step 3: Emotion Recognition

[0250] The device uses an emotion engine such as IBM Watson Tone Analyzer to recognize the user's emotion from text data or voice data. The emotion recognition means analyzes the content of the text and the tone of the voice to generate user emotion information.

[0251] Specifically, the device sends text data to the IBM Watson Tone Analyzer, labels it with the emotion "distressed," and receives the results. The device then stores the emotion recognition results.

[0252] Input: Text data of "Teach me how to use this app"

[0253] Output: User's emotion (e.g. "I'm in trouble")

[0254] Step 4: Generate the guide

[0255] The server receives the text data and emotion recognition results and generates operation instructions using a generative AI model such as OpenAI GPT-3. The generative model analyzes the text data and emotion information and generates specific operation instructions that take emotions into consideration.

[0256] Specifically, the device sends text and emotion data to the server, which then sends the data to the OpenAI GPT-3 API. The generative AI model generates an operation guide, such as "We'll explain it in simple terms. To use this app, tap this icon on the home screen," and the server sends it back to the device.

[0257] Input: Text data, user emotion information

[0258] Output: Emotionally sensitive operation guide text

[0259] Step 5: Audio guide output

[0260] The device sends the generated operation guide text to a text-to-speech engine such as Amazon Polly, which converts it into speech data. The speech engine converts the text into speech data, and the device outputs the speech to the user.

[0261] Specifically, the device sends the operation guide text to Amazon Polly, which converts it into voice data in a gentle tone and finally outputs it to the user through the smartphone speaker.

[0262] Input: Emotionally sensitive guide text

[0263] Output: Audio data (gentle tone)

[0264] Through the above processing steps, users are given appropriate support in how to operate their smartphones according to their emotions, and can receive information in a more understandable format.

[0265] (Application example 2)

[0266] 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."

[0267] In logistics centers, there is insufficient support for staff to work efficiently. There is also a lack of means to help staff deal with situations that cause confusion or stress. There is a need for real-time work guidance based on voice input and support that responds to staff emotions.

[0268] 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.

[0269] In this invention, the server includes a voice input means, a means for converting voice data into text data, a means for generating operation guidance from the text data using a generative model, a means for outputting the generated operation guidance by voice, an emotion recognition means for recognizing a user's emotion, and a means for controlling a robot that supports the work of staff at the logistics center. This enables the staff at the logistics center to receive appropriate operation guidance by voice depending on the situation in which they feel confused or stressed.

[0270] "Voice input means" refers to a device that acquires a user's voice data and converts it into digital form.

[0271] The "conversion means for converting voice data into text data" is a function for analyzing acquired voice data and generating corresponding text data.

[0272] A "generative model" is an algorithm that generates appropriate operation guides and outputs from text data based on pre-trained data.

[0273] The "generation means" is a process for generating operation guidance from text data using a generative model.

[0274] The "output means for outputting voice" is a function that converts the generated text data into voice data and presents it to the user.

[0275] "Emotion recognition means" is a technology that analyzes voice data or text data and recognizes the emotional state of the user.

[0276] A "robot that supports staff work at a logistics center" is a robot designed to support workers at a logistics center, and has the ability to provide voice instructions and work guides.

[0277] The system of the present invention is constructed by combining the following hardware and software: First, a microphone is used as a voice input means, and the user inputs voice instructions. This voice data is converted into text data using a voice recognition library (e.g., speech_recognition library).

[0278] The server then receives the text data and analyzes the user's emotions using emotion recognition, using the pipeline function of the transformers library. This allows the server to obtain emotional information such as whether the user is distressed, angry, or happy.

[0279] Furthermore, the server uses a generative model (e.g., GPT-3) to generate operation guidance based on text data and emotional information. This generative model is a pre-trained dialogue model and can provide guidance that takes the user's emotions into consideration. The generated operation guidance is converted into voice data using the gTTS library as an output means and presented to the user.

[0280] Specifically, the process is as follows:

[0281] 1. A user speaks into the microphone, "How can I check the availability of this item? I'm having trouble."

[0282] 2. The device receives the voice data and converts it into text data such as "How can I check the stock of this product?"

[0283] 3. The device uses an emotion engine to recognize that the user is confused.

[0284] 4. The server uses a generative model (GPT-3) to generate an operation guide based on the text data and the user's confusion.

[0285] 5. The device converts the generated operation guide into voice data and outputs to the user in a friendly tone, "To check your inventory, first tap this icon, then open the inventory menu."

[0286] Example prompt sentence:

[0287] When a user is confused, generate a task guide based on the following text: How do I check the availability of this product?

[0288] This allows logistics center staff to receive appropriate work guidance in real time, enabling them to carry out their work efficiently.In addition, the guidance provided takes into consideration the user's emotions, which is expected to reduce stress and confusion.

[0289] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0290] Step 1:

[0291] The user inputs speech.

[0292] Input: User's spoken instructions (e.g., "How do I check the availability of this item? I'm having trouble.").

[0293] Operation: Audio data is picked up by the device's microphone and converted into digital form.

[0294] Output: Audio data in digital format.

[0295] Step 2:

[0296] Convert the audio data into text data.

[0297] Input: Audio data in digital format.

[0298] Operation: The device uses a voice recognition library to analyze the voice data and generate text data.

[0299] Output: Text data (e.g., "How do I check the stock of this item?").

[0300] Step 3:

[0301] Recognize user emotions.

[0302] Input: Text data.

[0303] Operation: The device uses emotion recognition means (the pipeline function of the transformers library) to analyze text data and recognize the user's emotions.

[0304] Output: User's emotional state (e.g., confusion).

[0305] Step 4:

[0306] Generate operation guide.

[0307] Input: Text data and user emotion information.

[0308] Operation: The server uses a generative model (GPT-3) to generate an operation guide based on the text data and the user's emotional information. The prompt sentence is input to the generative model, and the operation guide is obtained as generated text.

[0309] Output: The generated instructions (e.g. "To check your inventory, first tap this icon, then open the inventory menu").

[0310] Step 5:

[0311] Outputs operation guides in voice.

[0312] Input: The generated instruction text.

[0313] Operation: The device uses a text-to-speech engine (gTTS) to convert text data into voice data, which is then output through the speaker.

[0314] Output: Audio guide.

[0315] Through the above process, logistics center staff can receive appropriate operational guidance in real time via voice.

[0316] 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.

[0317] 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.

[0318] 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.

[0319] [Second embodiment]

[0320] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0321] 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.

[0322] 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).

[0323] 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.

[0324] 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.

[0325] 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).

[0326] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0327] 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.

[0328] 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.

[0329] 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.

[0330] 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.

[0331] 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."

[0332] The system of the present invention includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance by voice. Below, the processing of the system program will be explained in natural language.

[0333] Voice input means

[0334] The user speaks a question into the smartphone's microphone, and this voice is captured as digital data by the voice input means.

[0335] Speech-to-text

[0336] The device analyzes the acquired voice data and converts it into text data using a voice recognition library. In this step, the voice recognition library analyzes the voice data and generates text data such as "Tell me how to use this app."

[0337] Generate operation guides

[0338] The server receives the generated text data and analyzes it using a pre-trained generative model. The generative model is an interactive AI model that generates appropriate operation guidance based on the generated text data. For example, if a user asks, "How do I use this app?", the server generates operation guidance such as, "To use this app, tap this icon on the home screen."

[0339] Guide audio output

[0340] The device converts the generated operation guide into audio data using a text-to-speech engine and outputs it audibly to the user, allowing the user to actually receive the operation guide in audio, making it easier for them to understand how to operate the smartphone.

[0341] Specific examples

[0342] For example, if a user asks "How do I use this app?", the following happens:

[0343] 1. The user speaks a question into the smartphone microphone.

[0344] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0345] 3. The server uses the generative model to analyze this text data and generate an instruction guide such as, "To use this app, tap this icon on the home screen."

[0346] 4. The device converts the generated operation guide into voice data and outputs it to the user.

[0347] This system allows elderly people to easily understand how to operate smartphones, making it an effective means of bridging the digital divide.

[0348] The processing flow will be explained below.

[0349] Step 1:

[0350] The user speaks their question into the smartphone's microphone. The voice input means captures the user's voice and stores the voice data in digital format.

[0351] Step 2:

[0352] The device uses a speech recognition library to convert the acquired voice data into text data. The speech recognition library analyzes the voice signal and generates corresponding text data. Text in the format "Tell me how to use this app" is generated.

[0353] Step 3:

[0354] The terminal sends the converted text data to the server, which receives the text data and prepares it for analysis.

[0355] Step 4:

[0356] The server uses a pre-trained interactive generative model to analyze the text data and generate appropriate operation guides. Based on the user's question, the generative model generates operation guide text such as "To use this app, tap this icon on the home screen."

[0357] Step 5:

[0358] The server transmits the generated operation guide text to the terminal, which processes the received operation guide text and prepares for voice output.

[0359] Step 6:

[0360] The device uses a text-to-speech engine to convert the operation guide text into voice data, which is then converted into a format that is easy for the user to hear.

[0361] Step 7:

[0362] The terminal reproduces the generated audio data through the audio output means so that the user can hear it, thereby enabling the user to receive the smartphone operation guide by audio.

[0363] Example 1

[0364] 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."

[0365] There is a need to overcome the difficulties faced by elderly and technology-inexperienced users when learning how to operate electronic devices, including smartphones. Conventional methods require users to refer to user manuals or web pages, which can be burdensome for users. Furthermore, text-only instructions are difficult to understand and are difficult to translate into actual operation. To address these challenges, an intuitive and easy-to-use operation guidance system using voice input is needed.

[0366] 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.

[0367] In this invention, the server includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance by voice. This allows a user to receive operation guidance by voice in real time by simply asking a question by voice, making it easy to understand how to operate a smartphone or the like.

[0368] "Audio input means" refers to devices and techniques for capturing user-generated audio into a device.

[0369] The "conversion means for converting voice data into text data" refers to software and hardware technology for analyzing acquired voice data and converting it into corresponding text data.

[0370] A "generative model" is an artificial intelligence system that uses pre-trained algorithms to generate specific outputs based on input data.

[0371] The "generation means" refers to a technique and device for generating an appropriate operation guide based on text data.

[0372] The "output means" refers to a device and technology for providing the generated operation guide to the user as audio data.

[0373] A "text-to-speech engine" is software and technology that synthesizes text data into natural-sounding speech and outputs it.

[0374] A "voice recognition library" is a collection of software that has the function of analyzing voice data and converting it into text data.

[0375] A "dialogue model" is an artificial intelligence system designed to generate appropriate responses through dialogue with a user.

[0376] The system of the present invention includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance by voice. The processing of the system program will be specifically described below.

[0377] In an embodiment of the system, a user speaks a question into a microphone on a device such as a smartphone or tablet. For example, they may say, "Tell me how to use this app." This causes a voice input means to capture voice data in digital form. The device then uses a speech recognition library, such as the Google Speech-to-Text API, to convert the captured voice data into text data. The conversion means analyzes the speech waveform, breaks it down into phonemes, and maps them to text data.

[0378] The device then sends the converted text data to the server. The server analyzes the text data using a pre-trained generative AI model (e.g., OpenAI's GPT-3) and generates an appropriate operation guide. This generation method is an algorithm that understands the user's intent based on the text data and generates the most appropriate operation guide. An example of a prompt sentence is, "If the user says, 'Tell me how to use this app,' what kind of operation guide should be generated?" Based on this, the server generates an operation guide such as, "To use this app, tap this icon on the home screen."

[0379] Finally, the device converts the generated operation guide into voice data using a text-to-speech engine (e.g., Amazon Polly) and outputs it audibly to the user. This output means allows the user to receive the operation guide as voice, making it easier for them to understand how to operate the smartphone.

[0380] For example, if a user asks "How do I use this app?", the following process occurs:

[0381] 1. The user speaks a question into the smartphone microphone.

[0382] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0383] 3. The server uses the generative AI model to analyze this text data and generate an operation guide such as, "To use this app, tap this icon on the home screen."

[0384] 4. The device converts the generated operation guide into voice data and outputs it to the user.

[0385] This system allows even elderly people and users who are not familiar with technology to easily understand how to operate a smartphone. In this way, the voice guidance system greatly improves user convenience.

[0386] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0387] Step 1: Getting voice input

[0388] The user speaks a question into the smartphone's microphone, and this voice is captured as digital data by the voice input means.

[0389] Input: User spoken words

[0390] What it does: An audio input method captures audio in digital form.

[0391] Output: Digital audio data

[0392] Step 2: Convert audio data to text

[0393] The terminal analyzes the acquired voice data using a voice recognition library (for example, Google Speech-to-Text API) and converts it into text data.

[0394] Input: Digital audio data

[0395] How it works: The device analyzes the audio waveform, breaks it down into phonemes, and maps them to text data.

[0396] Output: Text data in the format "Tell me how to use this app"

[0397] Step 3: Send text data

[0398] The terminal transmits the converted text data to the server.

[0399] Input: Text data in the format "Tell me how to use this app"

[0400] Operation: The device sends text data to the server via the network.

[0401] Output: Text data sent to the server

[0402] Step 4: Generate the guide

[0403] The server analyzes the received text data using a generative model (e.g., OpenAI's GPT-3) and generates appropriate operation guides.

[0404] Input: Text data in the format "Tell me how to use this app"

[0405] How it works: The generative model analyzes the text data and generates a guide based on the prompt: "If a user says 'Teach me how to use this app,' what kind of guide should be generated?"

[0406] Output: Operation guide such as "To use this app, tap this icon on the home screen."

[0407] Step 5: Sending the guide

[0408] The server transmits the generated operation guide to the terminal.

[0409] Input: Instructions such as "To use this app, tap this icon on the home screen."

[0410] Operation: The server sends the operation guide to the terminal via the network.

[0411] Output: Operation guide delivered to the device

[0412] Step 6: Audio output of operation guide

[0413] The device converts the received operation guide into voice data using a text-to-speech engine (e.g., Amazon Polly) and outputs it audibly to the user.

[0414] Input: Instructions such as "To use this app, tap this icon on the home screen."

[0415] Operation: The device converts the text data of the operation guide into voice data using a speech synthesis engine.

[0416] Output: Audio data that the user can hear (operation guide)

[0417] The above is the specific processing flow of the system. This system allows users to easily ask questions by voice and receive operation guidance in response to those questions by voice.

[0418] (Application example 1)

[0419] 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."

[0420] There is a problem in that it is difficult for workers in factories to quickly obtain information on how to use operating machines correctly and on maintenance management. Conventional methods require manuals and face-to-face training, which takes time and effort, and also increases the risk of operating incorrectly. This can reduce work efficiency and compromise safety.

[0421] 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.

[0422] In this invention, the server includes a voice input means, a conversion means for converting voice data into text data, and a generation means for generating operation guidance from the text data using a generative model, thereby enabling the server to provide appropriate operation instructions and operation guidance in real time by voice based on the worker's voice questions.

[0423] "Voice input means" is a device for acquiring voice uttered by a user and storing it as digital data.

[0424] The "conversion means" is a device or software that has the function of converting acquired voice data into text data.

[0425] The "generation means" is a device or software that has the function of generating an appropriate operation guide from text data.

[0426] The "output means" is a device or software that converts the generated operation guide into audio data and provides it to the user as audio.

[0427] "Work machines" refer to various types of machinery and equipment used in factories, and are devices for automation and machine control to improve work efficiency.

[0428] "Workers" are people who operate work machines and perform various tasks in a factory.

[0429] "Real-time" means that data is processed and output immediately, without delay.

[0430] A "conversational AI model" is an artificial intelligence model that generates appropriate responses in natural language in response to user input.

[0431] A system for implementing the present invention is configured as follows.

[0432] Voice input means

[0433] The user speaks a question into a microphone mounted on the work machine. This voice is captured as digital data by a voice input means. A commercially available microphone or voice collection device can be used as the voice input means.

[0434] Speech-to-text

[0435] The device analyzes the acquired voice data and converts it into text data using a voice recognition library. In this step, the voice recognition library can use services such as "Google Cloud Speech-to-Text." This library analyzes the voice data and generates text data such as "Please tell me how to maintain this machine."

[0436] Generate operation guides

[0437] The server receives the generated text data and analyzes it using a pre-trained generative model. A conversational AI model such as OpenAI's GPT-4 is used as the generative model. This generative model generates appropriate operation guidance based on the text data. For example, it provides specific instructions such as, "First, turn off the machine and then remove the cover. Next, clean the dust inside."

[0438] Guide audio output

[0439] The device uses a text-to-speech engine to convert the generated operation guide into audio data and output it audibly to the user. The text-to-speech engine can be "Amazon Polly" or similar.

[0440] Specific examples

[0441] For example, if a worker asks, "Tell me how to maintain this machine," the process goes like this:

[0442] 1. The worker speaks a question into the microphone on the work machine.

[0443] 2. The device receives the voice data and converts it into text data such as "Please tell me how to maintain this machine."

[0444] 3. The server uses the generative model to analyze this text data and generate an operation guide that reads, "First, turn off the machine and then remove the cover. Next, clean the dust that has accumulated inside."

[0445] 4. The terminal converts the generated operation guide into audio data and outputs it to the worker.

[0446] Prompt Sentence Examples

[0447] The following is an example of a prompt sentence that generates an appropriate operation guide for a dialogue when a worker asks, "Tell me how to maintain this machine."

[0448] markdown

[0449] Please generate an appropriate operation guide for the following dialogue when the user asks, "Please tell me how to maintain this machine."

[0450] Q: How do I maintain this machine?

[0451] Answer: First, turn off the machine and then remove the cover. Then, clean the dust accumulated inside. For detailed instructions, please refer to the following website:

[0452] This system allows workers to receive quick and accurate operation instructions and maintenance guides via voice input and output, improving work efficiency and reducing the risk of operational errors.

[0453] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0454] Step 1:

[0455] The user speaks a question into the microphone of the work machine. This voice is acquired as digital data by the voice input means. Specifically, when the user says, "Please tell me how to maintain this machine," the voice data is input into the terminal via the microphone.

[0456] Step 2:

[0457] The device converts the acquired voice data into text data using a speech recognition library. Specifically, the device calls the Google Cloud Speech-to-Text API and converts the voice data into text data such as "Please tell me how to maintain this machine." During this conversion process, the voice data is analyzed and the corresponding text is generated.

[0458] Step 3:

[0459] The terminal transmits the generated text data to the server. Specifically, the text data is sent to the server as an HTTP request. This data transmission continues until the server receives it.

[0460] Step 4:

[0461] The server analyzes the received text data using a pre-trained generative AI model to generate appropriate operation guidance. Specifically, the server uses OpenAI's GPT-4 model to generate operation guidance such as "First, turn off the machine and then remove the cover. Next, clean the dust that has accumulated inside" in response to the received text data "Please tell me how to maintain this machine." In this generation process, a dialogue generation model operates based on the input text and outputs the corresponding guidance.

[0462] Step 5:

[0463] The server sends the generated operation guide to the terminal. Specifically, the generated text data is returned to the terminal as an HTTP response. This data transmission continues until the terminal receives it.

[0464] Step 6:

[0465] The device converts the generated operation guide into audio data using a text-to-speech engine. Specifically, the device calls Amazon Polly to convert the text data of the operation guide into audio data. During this conversion process, the text is analyzed and the corresponding audio is generated.

[0466] Step 7:

[0467] The terminal outputs the generated audio data to the user through a speaker. Specifically, the audio data reaches the user's ears from the speaker. This audio output allows the user to receive the operation guide by audio.

[0468] 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.

[0469] The system of this invention includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, an output means for outputting the generated operation guidance by voice, and an emotion engine for recognizing the user's emotions. Below, the processing of the system program will be explained in natural language.

[0470] Voice input means

[0471] The user speaks their question into the smartphone's microphone, and the voice input means captures the user's voice and stores the voice data in digital format.

[0472] Speech-to-text

[0473] The device analyzes the acquired voice data and converts it into text data using a speech recognition library. The speech recognition library analyzes the voice signal and generates text in the format of "Tell me how to use this app."

[0474] emotion recognition

[0475] The device uses an emotion engine to recognize the user's emotions from the voice or text data, for example, determining whether the user is distressed, angry, or happy based on the tone and content of the voice.

[0476] Generate operation guides

[0477] The server receives the generated text data and the recognized user emotion and analyzes it using a pre-trained generative model. The generative model is an interactive AI model that generates emotion-sensitive operation guidance such as "To use this app, tap this icon on the home screen" based on the text data and emotion information.

[0478] Guide audio output

[0479] The device converts the generated operation guide text into audio data using a text-to-speech engine and outputs it audibly to the user. At this time, the tone and expression of the generated guide are adjusted to match the user's emotions.

[0480] Specific examples

[0481] For example, if a user asks "How do I use this app?" and speaks in a confused tone:

[0482] 1. The user speaks a question into the smartphone microphone.

[0483] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0484] 3. The device uses an emotion engine to analyze the user's problem.

[0485] 4. The server uses the generative model to generate an operation guide based on the text data and the user's confusion: "We'll explain it in simple terms. To use this app, tap this icon on the home screen."

[0486] 5. The device converts the generated operation guide into voice data and outputs it to the user in a gentle tone.

[0487] This system allows elderly people to receive appropriate support in how to operate their smartphones based on their emotions, and to receive information in a format that is easier to understand.

[0488] The processing flow will be explained below.

[0489] Step 1:

[0490] The user speaks a question into the smartphone's microphone, and the user's voice is captured as digital voice data by the voice input means.

[0491] Step 2:

[0492] The voice data acquired by the device is analyzed using a voice recognition library and converted into text data. The voice signal is analyzed and the text data "Teach me how to use this app" is generated.

[0493] Step 3:

[0494] The device uses the emotion engine to recognize the user's emotion from the acquired and converted voice data and text data, for example, recognizing that the user is in a difficult state from the tone and content of the voice.

[0495] Step 4:

[0496] The device sends the converted text data and the recognized user emotion information to the server, which then receives the necessary data and prepares to proceed to the next step.

[0497] Step 5:

[0498] The server uses a pre-trained interactive generative model to analyze the text data and emotional information sent and generate appropriate operation guidance. For example, the generative model generates operation guidance such as, "To use this app, tap this icon on the home screen."

[0499] Step 6:

[0500] The server sends the generated operation guide to the terminal, which receives the guide and prepares for voice output.

[0501] Step 7:

[0502] The device uses a text-to-speech engine to convert the operation guide text into voice data, and the generated operation guide is converted into voice in a tone that takes into consideration the user's emotions.

[0503] Step 8:

[0504] The terminal reproduces the generated voice data through the voice output means so that the user can hear it. For example, if the user is recognized as having trouble, guidance is provided in a gentle tone.

[0505] Through this step, the system provides smartphone operation guidance in a way that takes the user's emotions into consideration, helping elderly people to easily understand how to operate the smartphone.

[0506] Example 2

[0507] 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."

[0508] In conventional voice assistant systems, the function of converting user questions from voice to text and providing information based on that text often ignores emotions, which can increase user stress and dissatisfaction. Furthermore, there is a lack of guidance that takes emotions into consideration, particularly for elderly users and those who require technical support, resulting in a poor user experience.

[0509] 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 a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, an output means for outputting the generated operation guidance by voice, and an emotion recognition means for recognizing the emotion of the user. This allows the system to provide guidance that takes into consideration the emotion of the user, and enables even elderly users and users who require technical support to use the system smoothly and without stress.

[0510] "Voice input means" refers to equipment or software for acquiring user speech as voice data.

[0511] "Conversion means for converting voice data into text data" refers to software or a library that analyzes acquired voice data and converts it into corresponding text data.

[0512] A "generative model" refers to an AI model that uses a pre-trained algorithm to generate sentences such as operation guides from text data.

[0513] "Generation means for generating operation guide" refers to a function or software that uses a generative model to generate a guide that helps the user with operation from text data.

[0514] The "output means for outputting the generated operation guide as audio" refers to a device or software that converts the generated operation guide into audio data and outputs it in a form that can be heard by the user.

[0515] "Emotion recognition means for recognizing user emotions" refers to algorithms or software for analyzing and recognizing user emotions from voice data or text data.

[0516] MODE FOR CARRYING OUT THE INVENTION

[0517] A system for implementing the present invention includes the following components:

[0518] Voice input means

[0519] The user speaks their question using a device with a microphone (e.g., a smartphone or tablet), and the voice input means captures the voice and stores it in digital format.

[0520] A conversion means for converting voice data into text data

[0521] The device then uses a speech recognition library such as the Google Cloud Speech-to-Text API to analyze the captured voice data and convert it into text data. The voice signal is analyzed and text is generated in the form of a message such as "Tell me how to use this app."

[0522] emotion recognition means

[0523] The device uses an emotion engine such as IBM Watson Tone Analyzer to recognize the user's emotions from the analyzed text or voice data, determining whether the user is distressed, angry, or happy based on the tone and content of the voice.

[0524] A method for generating operation guides

[0525] The server receives the generated text data and the recognized user emotion data and analyzes it using a generative AI model such as OpenAI GPT-3. Based on the text data and emotion information, the generative AI model generates emotion-sensitive operation guidance such as "To use this app, tap this icon on the home screen."

[0526] An output means for outputting the generated operation guide in voice form.

[0527] The device then sends the generated guide text to a text-to-speech engine such as Amazon Polly, which converts it into speech data. This speech data is then output to the smartphone speaker for the user to hear, with the tone and expression adjusted to match the user's emotions.

[0528] Specific examples

[0529] For example, if a user asks "How do I use this app?" and speaks in a confused tone:

[0530] 1. The user speaks a question into the smartphone microphone.

[0531] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0532] 3. The device uses IBM Watson Tone Analyzer to analyze the user's problem.

[0533] 4. The server uses OpenAI GPT-3 to generate an operation guide based on the text data and the user's confusion: "We'll explain it in simple terms. To use this app, tap this icon on the home screen."

[0534] 5. The device sends the generated operation guide to Amazon Polly, which converts it into voice data in a gentle tone and finally outputs it to the user through the smartphone speaker.

[0535] Prompt Sentence Examples

[0536] Here are some example prompts to input to a generative AI model:

[0537] "Take a question uttered by a user in a confused tone and generate a how-to guide that explains how to use the app in a straightforward and friendly tone."

[0538] This system allows elderly people and users who require technical support to receive guidance that takes their emotions into consideration, making it easier for them to use the system.

[0539] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0540] Step 1: Voice Input

[0541] The user speaks a question into the smartphone's microphone. The voice input means captures the voice and stores it in digital format. Specifically, the user picks up the smartphone and asks, "Tell me how to use this app." The smartphone's microphone captures the voice data and temporarily stores it.

[0542] Input: User's spoken utterance

[0543] Output: Digital audio data

[0544] Step 2: Convert audio data to text

[0545] The device uses a speech recognition library such as the Google Cloud Speech-to-Text API to analyze the audio data and convert it into text. The library analyzes the audio signal and generates the corresponding text data.

[0546] Specifically, the device sends voice data to the Google Cloud Speech-to-Text API and receives text data such as "Teach me how to use this app." The device then stores this text data.

[0547] Input: Digital audio data

[0548] Output: Text data of "Tell me how to use this app"

[0549] Step 3: Emotion Recognition

[0550] The device uses an emotion engine such as IBM Watson Tone Analyzer to recognize the user's emotion from text data or voice data. The emotion recognition means analyzes the content of the text and the tone of the voice to generate user emotion information.

[0551] Specifically, the device sends text data to the IBM Watson Tone Analyzer, labels it with the emotion "distressed," and receives the results. The device then stores the emotion recognition results.

[0552] Input: Text data of "Teach me how to use this app"

[0553] Output: User's emotion (e.g. "I'm in trouble")

[0554] Step 4: Generate the guide

[0555] The server receives the text data and emotion recognition results and generates operation instructions using a generative AI model such as OpenAI GPT-3. The generative model analyzes the text data and emotion information and generates specific operation instructions that take emotions into consideration.

[0556] Specifically, the device sends text and emotion data to the server, which then sends the data to the OpenAI GPT-3 API. The generative AI model generates an operation guide, such as "We'll explain it in simple terms. To use this app, tap this icon on the home screen," and the server sends it back to the device.

[0557] Input: Text data, user emotion information

[0558] Output: Emotionally sensitive operation guide text

[0559] Step 5: Audio guide output

[0560] The device sends the generated operation guide text to a text-to-speech engine such as Amazon Polly, which converts it into speech data. The speech engine converts the text into speech data, and the device outputs the speech to the user.

[0561] Specifically, the device sends the operation guide text to Amazon Polly, which converts it into voice data in a gentle tone and finally outputs it to the user through the smartphone speaker.

[0562] Input: Emotionally sensitive guide text

[0563] Output: Audio data (gentle tone)

[0564] Through the above processing steps, users are given appropriate support in how to operate their smartphones according to their emotions, and can receive information in a more understandable format.

[0565] (Application example 2)

[0566] 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."

[0567] In logistics centers, there is insufficient support for staff to work efficiently. There is also a lack of means to help staff deal with situations that cause confusion or stress. There is a need for real-time work guidance based on voice input and support that responds to staff emotions.

[0568] 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.

[0569] In this invention, the server includes a voice input means, a means for converting voice data into text data, a means for generating operation guidance from the text data using a generative model, a means for outputting the generated operation guidance by voice, an emotion recognition means for recognizing a user's emotion, and a means for controlling a robot that supports the work of staff at the logistics center. This enables the staff at the logistics center to receive appropriate operation guidance by voice depending on the situation in which they feel confused or stressed.

[0570] "Voice input means" refers to a device that acquires a user's voice data and converts it into digital form.

[0571] The "conversion means for converting voice data into text data" is a function for analyzing acquired voice data and generating corresponding text data.

[0572] A "generative model" is an algorithm that generates appropriate operation guides and outputs from text data based on pre-trained data.

[0573] The "generation means" is a process for generating operation guidance from text data using a generative model.

[0574] The "output means for outputting voice" is a function that converts the generated text data into voice data and presents it to the user.

[0575] "Emotion recognition means" is a technology that analyzes voice data or text data and recognizes the emotional state of the user.

[0576] A "robot that supports staff work at a logistics center" is a robot designed to support workers at a logistics center, and has the ability to provide voice instructions and work guides.

[0577] The system of the present invention is constructed by combining the following hardware and software: First, a microphone is used as a voice input means, and the user inputs voice instructions. This voice data is converted into text data using a voice recognition library (e.g., speech_recognition library).

[0578] The server then receives the text data and analyzes the user's emotions using emotion recognition, using the pipeline function of the transformers library. This allows the server to obtain emotional information such as whether the user is distressed, angry, or happy.

[0579] Furthermore, the server uses a generative model (e.g., GPT-3) to generate operation guidance based on text data and emotional information. This generative model is a pre-trained dialogue model and can provide guidance that takes the user's emotions into consideration. The generated operation guidance is converted into voice data using the gTTS library as an output means and presented to the user.

[0580] Specifically, the process is as follows:

[0581] 1. A user speaks into the microphone, "How can I check the availability of this item? I'm having trouble."

[0582] 2. The device receives the voice data and converts it into text data such as "How can I check the stock of this product?"

[0583] 3. The device uses an emotion engine to recognize that the user is confused.

[0584] 4. The server uses a generative model (GPT-3) to generate an operation guide based on the text data and the user's confusion.

[0585] 5. The device converts the generated operation guide into voice data and outputs to the user in a friendly tone, "To check your inventory, first tap this icon, then open the inventory menu."

[0586] Example prompt sentence:

[0587] When a user is confused, generate a task guide based on the following text: How do I check the availability of this product?

[0588] This allows logistics center staff to receive appropriate work guidance in real time, enabling them to carry out their work efficiently.In addition, the guidance provided takes into consideration the user's emotions, which is expected to reduce stress and confusion.

[0589] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0590] Step 1:

[0591] The user inputs speech.

[0592] Input: User's spoken instructions (e.g., "How do I check the availability of this item? I'm having trouble.").

[0593] Operation: Audio data is picked up by the device's microphone and converted into digital form.

[0594] Output: Audio data in digital format.

[0595] Step 2:

[0596] Convert the audio data into text data.

[0597] Input: Audio data in digital format.

[0598] Operation: The device uses a voice recognition library to analyze the voice data and generate text data.

[0599] Output: Text data (e.g., "How do I check the stock of this item?").

[0600] Step 3:

[0601] Recognize user emotions.

[0602] Input: Text data.

[0603] Operation: The device uses emotion recognition means (the pipeline function of the transformers library) to analyze text data and recognize the user's emotions.

[0604] Output: User's emotional state (e.g., confusion).

[0605] Step 4:

[0606] Generate operation guide.

[0607] Input: Text data and user emotion information.

[0608] Operation: The server uses a generative model (GPT-3) to generate an operation guide based on the text data and the user's emotional information. The prompt sentence is input to the generative model, and the operation guide is obtained as generated text.

[0609] Output: The generated instructions (e.g. "To check your inventory, first tap this icon, then open the inventory menu").

[0610] Step 5:

[0611] Outputs operation guides in voice.

[0612] Input: The generated instruction text.

[0613] Operation: The device uses a text-to-speech engine (gTTS) to convert text data into voice data, which is then output through the speaker.

[0614] Output: Audio guide.

[0615] Through the above process, logistics center staff can receive appropriate operational guidance in real time via voice.

[0616] 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.

[0617] 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.

[0618] 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.

[0619] [Third embodiment]

[0620] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0621] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0622] 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).

[0623] 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.

[0624] 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.

[0625] 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).

[0626] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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."

[0632] The system of the present invention includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance by voice. Below, the processing of the system program will be explained in natural language.

[0633] Voice input means

[0634] The user speaks a question into the smartphone's microphone, and this voice is captured as digital data by the voice input means.

[0635] Speech-to-text

[0636] The device analyzes the acquired voice data and converts it into text data using a voice recognition library. In this step, the voice recognition library analyzes the voice data and generates text data such as "Tell me how to use this app."

[0637] Generate operation guides

[0638] The server receives the generated text data and analyzes it using a pre-trained generative model. The generative model is an interactive AI model that generates appropriate operation guidance based on the generated text data. For example, if a user asks, "How do I use this app?", the server generates operation guidance such as, "To use this app, tap this icon on the home screen."

[0639] Guide audio output

[0640] The device converts the generated operation guide into audio data using a text-to-speech engine and outputs it audibly to the user, allowing the user to actually receive the operation guide in audio, making it easier for them to understand how to operate the smartphone.

[0641] Specific examples

[0642] For example, if a user asks "How do I use this app?", the following happens:

[0643] 1. The user speaks a question into the smartphone microphone.

[0644] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0645] 3. The server uses the generative model to analyze this text data and generate an instruction guide such as, "To use this app, tap this icon on the home screen."

[0646] 4. The device converts the generated operation guide into voice data and outputs it to the user.

[0647] This system allows elderly people to easily understand how to operate smartphones, making it an effective means of bridging the digital divide.

[0648] The processing flow will be explained below.

[0649] Step 1:

[0650] The user speaks their question into the smartphone's microphone. The voice input means captures the user's voice and stores the voice data in digital format.

[0651] Step 2:

[0652] The device uses a speech recognition library to convert the acquired voice data into text data. The speech recognition library analyzes the voice signal and generates corresponding text data. Text in the format "Tell me how to use this app" is generated.

[0653] Step 3:

[0654] The terminal sends the converted text data to the server, which receives the text data and prepares it for analysis.

[0655] Step 4:

[0656] The server uses a pre-trained interactive generative model to analyze the text data and generate appropriate operation guides. Based on the user's question, the generative model generates operation guide text such as "To use this app, tap this icon on the home screen."

[0657] Step 5:

[0658] The server transmits the generated operation guide text to the terminal, which processes the received operation guide text and prepares for voice output.

[0659] Step 6:

[0660] The device uses a text-to-speech engine to convert the operation guide text into voice data, which is then converted into a format that is easy for the user to hear.

[0661] Step 7:

[0662] The terminal reproduces the generated audio data through the audio output means so that the user can hear it, thereby enabling the user to receive the smartphone operation guide by audio.

[0663] Example 1

[0664] 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."

[0665] There is a need to overcome the difficulties faced by elderly and technology-inexperienced users when learning how to operate electronic devices, including smartphones. Conventional methods require users to refer to user manuals or web pages, which can be burdensome for users. Furthermore, text-only instructions are difficult to understand and are difficult to translate into actual operation. To address these challenges, an intuitive and easy-to-use operation guidance system using voice input is needed.

[0666] 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.

[0667] In this invention, the server includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance by voice. This allows a user to receive operation guidance by voice in real time by simply asking a question by voice, making it easy to understand how to operate a smartphone or the like.

[0668] "Audio input means" refers to devices and techniques for capturing user-generated audio into a device.

[0669] The "conversion means for converting voice data into text data" refers to software and hardware technology for analyzing acquired voice data and converting it into corresponding text data.

[0670] A "generative model" is an artificial intelligence system that uses pre-trained algorithms to generate specific outputs based on input data.

[0671] The "generation means" refers to a technique and device for generating an appropriate operation guide based on text data.

[0672] The "output means" refers to a device and technology for providing the generated operation guide to the user as audio data.

[0673] A "text-to-speech engine" is software and technology that synthesizes text data into natural-sounding speech and outputs it.

[0674] A "voice recognition library" is a collection of software that has the function of analyzing voice data and converting it into text data.

[0675] A "dialogue model" is an artificial intelligence system designed to generate appropriate responses through dialogue with a user.

[0676] The system of the present invention includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance by voice. The processing of the system program will be specifically described below.

[0677] In an embodiment of the system, a user speaks a question into a microphone on a device such as a smartphone or tablet. For example, they may say, "Tell me how to use this app." This causes a voice input means to capture voice data in digital form. The device then uses a speech recognition library, such as the Google Speech-to-Text API, to convert the captured voice data into text data. The conversion means analyzes the speech waveform, breaks it down into phonemes, and maps them to text data.

[0678] The device then sends the converted text data to the server. The server analyzes the text data using a pre-trained generative AI model (e.g., OpenAI's GPT-3) and generates an appropriate operation guide. This generation method is an algorithm that understands the user's intent based on the text data and generates the most appropriate operation guide. An example of a prompt sentence is, "If the user says, 'Tell me how to use this app,' what kind of operation guide should be generated?" Based on this, the server generates an operation guide such as, "To use this app, tap this icon on the home screen."

[0679] Finally, the device converts the generated operation guide into voice data using a text-to-speech engine (e.g., Amazon Polly) and outputs it audibly to the user. This output means allows the user to receive the operation guide as voice, making it easier for them to understand how to operate the smartphone.

[0680] For example, if a user asks "How do I use this app?", the following process occurs:

[0681] 1. The user speaks a question into the smartphone microphone.

[0682] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0683] 3. The server uses the generative AI model to analyze this text data and generate an operation guide such as, "To use this app, tap this icon on the home screen."

[0684] 4. The device converts the generated operation guide into voice data and outputs it to the user.

[0685] This system allows even elderly people and users who are not familiar with technology to easily understand how to operate a smartphone. In this way, the voice guidance system greatly improves user convenience.

[0686] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0687] Step 1: Getting voice input

[0688] The user speaks a question into the smartphone's microphone, and this voice is captured as digital data by the voice input means.

[0689] Input: User spoken words

[0690] What it does: An audio input method captures audio in digital form.

[0691] Output: Digital audio data

[0692] Step 2: Convert audio data to text

[0693] The terminal analyzes the acquired voice data using a voice recognition library (for example, Google Speech-to-Text API) and converts it into text data.

[0694] Input: Digital audio data

[0695] How it works: The device analyzes the audio waveform, breaks it down into phonemes, and maps them to text data.

[0696] Output: Text data in the format "Tell me how to use this app"

[0697] Step 3: Send text data

[0698] The terminal transmits the converted text data to the server.

[0699] Input: Text data in the format "Tell me how to use this app"

[0700] Operation: The device sends text data to the server via the network.

[0701] Output: Text data sent to the server

[0702] Step 4: Generate the guide

[0703] The server analyzes the received text data using a generative model (e.g., OpenAI's GPT-3) and generates appropriate operation guides.

[0704] Input: Text data in the format "Tell me how to use this app"

[0705] How it works: The generative model analyzes the text data and generates a guide based on the prompt: "If a user says 'Teach me how to use this app,' what kind of guide should be generated?"

[0706] Output: Operation guide such as "To use this app, tap this icon on the home screen."

[0707] Step 5: Sending the guide

[0708] The server transmits the generated operation guide to the terminal.

[0709] Input: Instructions such as "To use this app, tap this icon on the home screen."

[0710] Operation: The server sends the operation guide to the terminal via the network.

[0711] Output: Operation guide delivered to the device

[0712] Step 6: Audio output of operation guide

[0713] The device converts the received operation guide into voice data using a text-to-speech engine (e.g., Amazon Polly) and outputs it audibly to the user.

[0714] Input: Instructions such as "To use this app, tap this icon on the home screen."

[0715] Operation: The device converts the text data of the operation guide into voice data using a speech synthesis engine.

[0716] Output: Audio data that the user can hear (operation guide)

[0717] The above is the specific processing flow of the system. This system allows users to easily ask questions by voice and receive operation guidance in response to those questions by voice.

[0718] (Application example 1)

[0719] 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."

[0720] There is a problem in that it is difficult for workers in factories to quickly obtain information on how to use operating machines correctly and on maintenance management. Conventional methods require manuals and face-to-face training, which takes time and effort, and also increases the risk of operating incorrectly. This can reduce work efficiency and compromise safety.

[0721] 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.

[0722] In this invention, the server includes a voice input means, a conversion means for converting voice data into text data, and a generation means for generating operation guidance from the text data using a generative model, thereby enabling the server to provide appropriate operation instructions and operation guidance in real time by voice based on the worker's voice questions.

[0723] "Voice input means" is a device for acquiring voice uttered by a user and storing it as digital data.

[0724] The "conversion means" is a device or software that has the function of converting acquired voice data into text data.

[0725] The "generation means" is a device or software that has the function of generating an appropriate operation guide from text data.

[0726] The "output means" is a device or software that converts the generated operation guide into audio data and provides it to the user as audio.

[0727] "Work machines" refer to various types of machinery and equipment used in factories, and are devices for automation and machine control to improve work efficiency.

[0728] "Workers" are people who operate work machines and perform various tasks in a factory.

[0729] "Real-time" means that data is processed and output immediately, without delay.

[0730] A "conversational AI model" is an artificial intelligence model that generates appropriate responses in natural language in response to user input.

[0731] A system for implementing the present invention is configured as follows.

[0732] Voice input means

[0733] The user speaks a question into a microphone mounted on the work machine. This voice is captured as digital data by a voice input means. A commercially available microphone or voice collection device can be used as the voice input means.

[0734] Speech-to-text

[0735] The device analyzes the acquired voice data and converts it into text data using a voice recognition library. In this step, the voice recognition library can use services such as "Google Cloud Speech-to-Text." This library analyzes the voice data and generates text data such as "Please tell me how to maintain this machine."

[0736] Generate operation guides

[0737] The server receives the generated text data and analyzes it using a pre-trained generative model. A conversational AI model such as OpenAI's GPT-4 is used as the generative model. This generative model generates appropriate operation guidance based on the text data. For example, it provides specific instructions such as, "First, turn off the machine and then remove the cover. Next, clean the dust inside."

[0738] Guide audio output

[0739] The device uses a text-to-speech engine to convert the generated operation guide into audio data and output it audibly to the user. The text-to-speech engine can be "Amazon Polly" or similar.

[0740] Specific examples

[0741] For example, if a worker asks, "Tell me how to maintain this machine," the process goes like this:

[0742] 1. The worker speaks a question into the microphone on the work machine.

[0743] 2. The device receives the voice data and converts it into text data such as "Please tell me how to maintain this machine."

[0744] 3. The server uses the generative model to analyze this text data and generate an operation guide that reads, "First, turn off the machine and then remove the cover. Next, clean the dust that has accumulated inside."

[0745] 4. The terminal converts the generated operation guide into audio data and outputs it to the worker.

[0746] Prompt Sentence Examples

[0747] The following is an example of a prompt sentence that generates an appropriate operation guide for a dialogue when a worker asks, "Tell me how to maintain this machine."

[0748] markdown

[0749] Please generate an appropriate operation guide for the following dialogue when the user asks, "Please tell me how to maintain this machine."

[0750] Q: How do I maintain this machine?

[0751] Answer: First, turn off the machine and then remove the cover. Then, clean the dust accumulated inside. For detailed instructions, please refer to the following website:

[0752] This system allows workers to receive quick and accurate operation instructions and maintenance guides via voice input and output, improving work efficiency and reducing the risk of operational errors.

[0753] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0754] Step 1:

[0755] The user speaks a question into the microphone of the work machine. This voice is acquired as digital data by the voice input means. Specifically, when the user says, "Please tell me how to maintain this machine," the voice data is input into the terminal via the microphone.

[0756] Step 2:

[0757] The device converts the acquired voice data into text data using a speech recognition library. Specifically, the device calls the Google Cloud Speech-to-Text API and converts the voice data into text data such as "Please tell me how to maintain this machine." During this conversion process, the voice data is analyzed and the corresponding text is generated.

[0758] Step 3:

[0759] The terminal transmits the generated text data to the server. Specifically, the text data is sent to the server as an HTTP request. This data transmission continues until the server receives it.

[0760] Step 4:

[0761] The server analyzes the received text data using a pre-trained generative AI model to generate appropriate operation guidance. Specifically, the server uses OpenAI's GPT-4 model to generate operation guidance such as "First, turn off the machine and then remove the cover. Next, clean the dust that has accumulated inside" in response to the received text data "Please tell me how to maintain this machine." In this generation process, a dialogue generation model operates based on the input text and outputs the corresponding guidance.

[0762] Step 5:

[0763] The server sends the generated operation guide to the terminal. Specifically, the generated text data is returned to the terminal as an HTTP response. This data transmission continues until the terminal receives it.

[0764] Step 6:

[0765] The device converts the generated operation guide into audio data using a text-to-speech engine. Specifically, the device calls Amazon Polly to convert the text data of the operation guide into audio data. During this conversion process, the text is analyzed and the corresponding audio is generated.

[0766] Step 7:

[0767] The terminal outputs the generated audio data to the user through a speaker. Specifically, the audio data reaches the user's ears from the speaker. This audio output allows the user to receive the operation guide by audio.

[0768] 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.

[0769] The system of this invention includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, an output means for outputting the generated operation guidance by voice, and an emotion engine for recognizing the user's emotions. Below, the processing of the system program will be explained in natural language.

[0770] Voice input means

[0771] The user speaks their question into the smartphone's microphone, and the voice input means captures the user's voice and stores the voice data in digital format.

[0772] Speech-to-text

[0773] The device analyzes the acquired voice data and converts it into text data using a speech recognition library. The speech recognition library analyzes the voice signal and generates text in the format of "Tell me how to use this app."

[0774] emotion recognition

[0775] The device uses an emotion engine to recognize the user's emotions from the voice or text data, for example, determining whether the user is distressed, angry, or happy based on the tone and content of the voice.

[0776] Generate operation guides

[0777] The server receives the generated text data and the recognized user emotion and analyzes it using a pre-trained generative model. The generative model is an interactive AI model that generates emotion-sensitive operation guidance such as "To use this app, tap this icon on the home screen" based on the text data and emotion information.

[0778] Guide audio output

[0779] The device converts the generated operation guide text into audio data using a text-to-speech engine and outputs it audibly to the user. At this time, the tone and expression of the generated guide are adjusted to match the user's emotions.

[0780] Specific examples

[0781] For example, if a user asks "How do I use this app?" and speaks in a confused tone:

[0782] 1. The user speaks a question into the smartphone microphone.

[0783] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0784] 3. The device uses an emotion engine to analyze the user's problem.

[0785] 4. The server uses the generative model to generate an operation guide based on the text data and the user's confusion: "We'll explain it in simple terms. To use this app, tap this icon on the home screen."

[0786] 5. The device converts the generated operation guide into voice data and outputs it to the user in a gentle tone.

[0787] This system allows elderly people to receive appropriate support in how to operate their smartphones based on their emotions, and to receive information in a format that is easier to understand.

[0788] The processing flow will be explained below.

[0789] Step 1:

[0790] The user speaks a question into the smartphone's microphone, and the user's voice is captured as digital voice data by the voice input means.

[0791] Step 2:

[0792] The voice data acquired by the device is analyzed using a voice recognition library and converted into text data. The voice signal is analyzed and the text data "Teach me how to use this app" is generated.

[0793] Step 3:

[0794] The device uses the emotion engine to recognize the user's emotion from the acquired and converted voice data and text data, for example, recognizing that the user is in a difficult state from the tone and content of the voice.

[0795] Step 4:

[0796] The device sends the converted text data and the recognized user emotion information to the server, which then receives the necessary data and prepares to proceed to the next step.

[0797] Step 5:

[0798] The server uses a pre-trained interactive generative model to analyze the text data and emotional information sent and generate appropriate operation guidance. For example, the generative model generates operation guidance such as, "To use this app, tap this icon on the home screen."

[0799] Step 6:

[0800] The server sends the generated operation guide to the terminal, which receives the guide and prepares for voice output.

[0801] Step 7:

[0802] The device uses a text-to-speech engine to convert the operation guide text into voice data, and the generated operation guide is converted into voice in a tone that takes into consideration the user's emotions.

[0803] Step 8:

[0804] The terminal reproduces the generated voice data through the voice output means so that the user can hear it. For example, if the user is recognized as having trouble, guidance is provided in a gentle tone.

[0805] Through this step, the system provides smartphone operation guidance in a way that takes the user's emotions into consideration, helping elderly people to easily understand how to operate the smartphone.

[0806] Example 2

[0807] 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."

[0808] In conventional voice assistant systems, the function of converting user questions from voice to text and providing information based on that text often ignores emotions, which can increase user stress and dissatisfaction. Furthermore, there is a lack of guidance that takes emotions into consideration, particularly for elderly users and those who require technical support, resulting in a poor user experience.

[0809] 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 a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, an output means for outputting the generated operation guidance by voice, and an emotion recognition means for recognizing the emotion of the user. This allows the system to provide guidance that takes into consideration the emotion of the user, and enables even elderly users and users who require technical support to use the system smoothly and without stress.

[0810] "Voice input means" refers to equipment or software for acquiring user speech as voice data.

[0811] "Conversion means for converting voice data into text data" refers to software or a library that analyzes acquired voice data and converts it into corresponding text data.

[0812] A "generative model" refers to an AI model that uses a pre-trained algorithm to generate sentences such as operation guides from text data.

[0813] "Generation means for generating operation guide" refers to a function or software that uses a generative model to generate a guide that helps the user with operation from text data.

[0814] The "output means for outputting the generated operation guide as audio" refers to a device or software that converts the generated operation guide into audio data and outputs it in a form that can be heard by the user.

[0815] "Emotion recognition means for recognizing user emotions" refers to algorithms or software for analyzing and recognizing user emotions from voice data or text data.

[0816] MODE FOR CARRYING OUT THE INVENTION

[0817] A system for implementing the present invention includes the following components:

[0818] Voice input means

[0819] The user speaks their question using a device with a microphone (e.g., a smartphone or tablet), and the voice input means captures the voice and stores it in digital format.

[0820] A conversion means for converting voice data into text data

[0821] The device then uses a speech recognition library such as the Google Cloud Speech-to-Text API to analyze the captured voice data and convert it into text data. The voice signal is analyzed and text is generated in the form of a message such as "Tell me how to use this app."

[0822] emotion recognition means

[0823] The device uses an emotion engine such as IBM Watson Tone Analyzer to recognize the user's emotions from the analyzed text or voice data, determining whether the user is distressed, angry, or happy based on the tone and content of the voice.

[0824] A method for generating operation guides

[0825] The server receives the generated text data and the recognized user emotion data and analyzes it using a generative AI model such as OpenAI GPT-3. Based on the text data and emotion information, the generative AI model generates emotion-sensitive operation guidance such as "To use this app, tap this icon on the home screen."

[0826] An output means for outputting the generated operation guide in voice form.

[0827] The device then sends the generated guide text to a text-to-speech engine such as Amazon Polly, which converts it into speech data. This speech data is then output to the smartphone speaker for the user to hear, with the tone and expression adjusted to match the user's emotions.

[0828] Specific examples

[0829] For example, if a user asks "How do I use this app?" and speaks in a confused tone:

[0830] 1. The user speaks a question into the smartphone microphone.

[0831] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0832] 3. The device uses IBM Watson Tone Analyzer to analyze the user's problem.

[0833] 4. The server uses OpenAI GPT-3 to generate an operation guide based on the text data and the user's confusion: "We'll explain it in simple terms. To use this app, tap this icon on the home screen."

[0834] 5. The device sends the generated operation guide to Amazon Polly, which converts it into voice data in a gentle tone and finally outputs it to the user through the smartphone speaker.

[0835] Prompt Sentence Examples

[0836] Here are some example prompts to input to a generative AI model:

[0837] "Take a question uttered by a user in a confused tone and generate a how-to guide that explains how to use the app in a straightforward and friendly tone."

[0838] This system allows elderly people and users who require technical support to receive guidance that takes their emotions into consideration, making it easier for them to use the system.

[0839] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0840] Step 1: Voice Input

[0841] The user speaks a question into the smartphone's microphone. The voice input means captures the voice and stores it in digital format. Specifically, the user picks up the smartphone and asks, "Tell me how to use this app." The smartphone's microphone captures the voice data and temporarily stores it.

[0842] Input: User's spoken utterance

[0843] Output: Digital audio data

[0844] Step 2: Convert audio data to text

[0845] The device uses a speech recognition library such as the Google Cloud Speech-to-Text API to analyze the audio data and convert it into text. The library analyzes the audio signal and generates the corresponding text data.

[0846] Specifically, the device sends voice data to the Google Cloud Speech-to-Text API and receives text data such as "Teach me how to use this app." The device then stores this text data.

[0847] Input: Digital audio data

[0848] Output: Text data of "Tell me how to use this app"

[0849] Step 3: Emotion Recognition

[0850] The device uses an emotion engine such as IBM Watson Tone Analyzer to recognize the user's emotion from text data or voice data. The emotion recognition means analyzes the content of the text and the tone of the voice to generate user emotion information.

[0851] Specifically, the device sends text data to the IBM Watson Tone Analyzer, labels it with the emotion "distressed," and receives the results. The device then stores the emotion recognition results.

[0852] Input: Text data of "Teach me how to use this app"

[0853] Output: User's emotion (e.g. "I'm in trouble")

[0854] Step 4: Generate the guide

[0855] The server receives the text data and emotion recognition results and generates operation instructions using a generative AI model such as OpenAI GPT-3. The generative model analyzes the text data and emotion information and generates specific operation instructions that take emotions into consideration.

[0856] Specifically, the device sends text and emotion data to the server, which then sends the data to the OpenAI GPT-3 API. The generative AI model generates an operation guide, such as "We'll explain it in simple terms. To use this app, tap this icon on the home screen," and the server sends it back to the device.

[0857] Input: Text data, user emotion information

[0858] Output: Emotionally sensitive operation guide text

[0859] Step 5: Audio guide output

[0860] The device sends the generated operation guide text to a text-to-speech engine such as Amazon Polly, which converts it into speech data. The speech engine converts the text into speech data, and the device outputs the speech to the user.

[0861] Specifically, the device sends the operation guide text to Amazon Polly, which converts it into voice data in a gentle tone and finally outputs it to the user through the smartphone speaker.

[0862] Input: Emotionally sensitive guide text

[0863] Output: Audio data (gentle tone)

[0864] Through the above processing steps, users are given appropriate support in how to operate their smartphones according to their emotions, and can receive information in a more understandable format.

[0865] (Application example 2)

[0866] 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."

[0867] In logistics centers, there is insufficient support for staff to work efficiently. There is also a lack of means to help staff deal with situations that cause confusion or stress. There is a need for real-time work guidance based on voice input and support that responds to staff emotions.

[0868] 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.

[0869] In this invention, the server includes a voice input means, a means for converting voice data into text data, a means for generating operation guidance from the text data using a generative model, a means for outputting the generated operation guidance by voice, an emotion recognition means for recognizing a user's emotion, and a means for controlling a robot that supports the work of staff at the logistics center. This enables the staff at the logistics center to receive appropriate operation guidance by voice depending on the situation in which they feel confused or stressed.

[0870] "Voice input means" refers to a device that acquires a user's voice data and converts it into digital form.

[0871] The "conversion means for converting voice data into text data" is a function for analyzing acquired voice data and generating corresponding text data.

[0872] A "generative model" is an algorithm that generates appropriate operation guides and outputs from text data based on pre-trained data.

[0873] The "generation means" is a process for generating operation guidance from text data using a generative model.

[0874] The "output means for outputting voice" is a function that converts the generated text data into voice data and presents it to the user.

[0875] "Emotion recognition means" is a technology that analyzes voice data or text data and recognizes the emotional state of the user.

[0876] A "robot that supports staff work at a logistics center" is a robot designed to support workers at a logistics center, and has the ability to provide voice instructions and work guides.

[0877] The system of the present invention is constructed by combining the following hardware and software: First, a microphone is used as a voice input means, and the user inputs voice instructions. This voice data is converted into text data using a voice recognition library (e.g., speech_recognition library).

[0878] The server then receives the text data and analyzes the user's emotions using emotion recognition, using the pipeline function of the transformers library. This allows the server to obtain emotional information such as whether the user is distressed, angry, or happy.

[0879] Furthermore, the server uses a generative model (e.g., GPT-3) to generate operation guidance based on text data and emotional information. This generative model is a pre-trained dialogue model and can provide guidance that takes the user's emotions into consideration. The generated operation guidance is converted into voice data using the gTTS library as an output means and presented to the user.

[0880] Specifically, the process is as follows:

[0881] 1. A user speaks into the microphone, "How can I check the availability of this item? I'm having trouble."

[0882] 2. The device receives the voice data and converts it into text data such as "How can I check the stock of this product?"

[0883] 3. The device uses an emotion engine to recognize that the user is confused.

[0884] 4. The server uses a generative model (GPT-3) to generate an operation guide based on the text data and the user's confusion.

[0885] 5. The device converts the generated operation guide into voice data and outputs to the user in a friendly tone, "To check your inventory, first tap this icon, then open the inventory menu."

[0886] Example prompt sentence:

[0887] When a user is confused, generate a task guide based on the following text: How do I check the availability of this product?

[0888] This allows logistics center staff to receive appropriate work guidance in real time, enabling them to carry out their work efficiently.In addition, the guidance provided takes into consideration the user's emotions, which is expected to reduce stress and confusion.

[0889] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0890] Step 1:

[0891] The user inputs speech.

[0892] Input: User's spoken instructions (e.g., "How do I check the availability of this item? I'm having trouble.").

[0893] Operation: Audio data is picked up by the device's microphone and converted into digital form.

[0894] Output: Audio data in digital format.

[0895] Step 2:

[0896] Convert the audio data into text data.

[0897] Input: Audio data in digital format.

[0898] Operation: The device uses a voice recognition library to analyze the voice data and generate text data.

[0899] Output: Text data (e.g., "How do I check the stock of this item?").

[0900] Step 3:

[0901] Recognize user emotions.

[0902] Input: Text data.

[0903] Operation: The device uses emotion recognition means (the pipeline function of the transformers library) to analyze text data and recognize the user's emotions.

[0904] Output: User's emotional state (e.g., confusion).

[0905] Step 4:

[0906] Generate operation guide.

[0907] Input: Text data and user emotion information.

[0908] Operation: The server uses a generative model (GPT-3) to generate an operation guide based on the text data and the user's emotional information. The prompt sentence is input to the generative model, and the operation guide is obtained as generated text.

[0909] Output: The generated instructions (e.g. "To check your inventory, first tap this icon, then open the inventory menu").

[0910] Step 5:

[0911] Outputs operation guides in voice.

[0912] Input: The generated instruction text.

[0913] Operation: The device uses a text-to-speech engine (gTTS) to convert text data into voice data, which is then output through the speaker.

[0914] Output: Audio guide.

[0915] Through the above process, logistics center staff can receive appropriate operational guidance in real time via voice.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] [Fourth embodiment]

[0920] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0921] 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.

[0922] 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).

[0923] 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.

[0924] 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.

[0925] 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).

[0926] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0927] 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.

[0928] 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.

[0929] 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.

[0930] 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.

[0931] 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.

[0932] 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."

[0933] The system of the present invention includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance by voice. Below, the processing of the system program will be explained in natural language.

[0934] Voice input means

[0935] The user speaks a question into the smartphone's microphone, and this voice is captured as digital data by the voice input means.

[0936] Speech-to-text

[0937] The device analyzes the acquired voice data and converts it into text data using a voice recognition library. In this step, the voice recognition library analyzes the voice data and generates text data such as "Tell me how to use this app."

[0938] Generate operation guides

[0939] The server receives the generated text data and analyzes it using a pre-trained generative model. The generative model is an interactive AI model that generates appropriate operation guidance based on the generated text data. For example, if a user asks, "How do I use this app?", the server generates operation guidance such as, "To use this app, tap this icon on the home screen."

[0940] Guide audio output

[0941] The device converts the generated operation guide into audio data using a text-to-speech engine and outputs it audibly to the user, allowing the user to actually receive the operation guide in audio, making it easier for them to understand how to operate the smartphone.

[0942] Specific examples

[0943] For example, if a user asks "How do I use this app?", the following happens:

[0944] 1. The user speaks a question into the smartphone microphone.

[0945] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0946] 3. The server uses the generative model to analyze this text data and generate an instruction guide such as, "To use this app, tap this icon on the home screen."

[0947] 4. The device converts the generated operation guide into voice data and outputs it to the user.

[0948] This system allows elderly people to easily understand how to operate smartphones, making it an effective means of bridging the digital divide.

[0949] The processing flow will be explained below.

[0950] Step 1:

[0951] The user speaks their question into the smartphone's microphone. The voice input means captures the user's voice and stores the voice data in digital format.

[0952] Step 2:

[0953] The device uses a speech recognition library to convert the acquired voice data into text data. The speech recognition library analyzes the voice signal and generates corresponding text data. Text in the format "Tell me how to use this app" is generated.

[0954] Step 3:

[0955] The terminal sends the converted text data to the server, which receives the text data and prepares it for analysis.

[0956] Step 4:

[0957] The server uses a pre-trained interactive generative model to analyze the text data and generate appropriate operation guides. Based on the user's question, the generative model generates operation guide text such as "To use this app, tap this icon on the home screen."

[0958] Step 5:

[0959] The server transmits the generated operation guide text to the terminal, which processes the received operation guide text and prepares for voice output.

[0960] Step 6:

[0961] The device uses a text-to-speech engine to convert the operation guide text into voice data, which is then converted into a format that is easy for the user to hear.

[0962] Step 7:

[0963] The terminal reproduces the generated audio data through the audio output means so that the user can hear it, thereby enabling the user to receive the smartphone operation guide by audio.

[0964] Example 1

[0965] 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."

[0966] There is a need to overcome the difficulties faced by elderly and technology-inexperienced users when learning how to operate electronic devices, including smartphones. Conventional methods require users to refer to user manuals or web pages, which can be burdensome for users. Furthermore, text-only instructions are difficult to understand and are difficult to translate into actual operation. To address these challenges, an intuitive and easy-to-use operation guidance system using voice input is needed.

[0967] 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.

[0968] In this invention, the server includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance by voice. This allows a user to receive operation guidance by voice in real time by simply asking a question by voice, making it easy to understand how to operate a smartphone or the like.

[0969] "Audio input means" refers to devices and techniques for capturing user-generated audio into a device.

[0970] The "conversion means for converting voice data into text data" refers to software and hardware technology for analyzing acquired voice data and converting it into corresponding text data.

[0971] A "generative model" is an artificial intelligence system that uses pre-trained algorithms to generate specific outputs based on input data.

[0972] The "generation means" refers to a technique and device for generating an appropriate operation guide based on text data.

[0973] The "output means" refers to a device and technology for providing the generated operation guide to the user as audio data.

[0974] A "text-to-speech engine" is software and technology that synthesizes text data into natural-sounding speech and outputs it.

[0975] A "voice recognition library" is a collection of software that has the function of analyzing voice data and converting it into text data.

[0976] A "dialogue model" is an artificial intelligence system designed to generate appropriate responses through dialogue with a user.

[0977] The system of the present invention includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, and an output means for outputting the generated operation guidance by voice. The processing of the system program will be specifically described below.

[0978] In an embodiment of the system, a user speaks a question into a microphone on a device such as a smartphone or tablet. For example, they may say, "Tell me how to use this app." This causes a voice input means to capture voice data in digital form. The device then uses a speech recognition library, such as the Google Speech-to-Text API, to convert the captured voice data into text data. The conversion means analyzes the speech waveform, breaks it down into phonemes, and maps them to text data.

[0979] The device then sends the converted text data to the server. The server analyzes the text data using a pre-trained generative AI model (e.g., OpenAI's GPT-3) and generates an appropriate operation guide. This generation method is an algorithm that understands the user's intent based on the text data and generates the most appropriate operation guide. An example of a prompt sentence is, "If the user says, 'Tell me how to use this app,' what kind of operation guide should be generated?" Based on this, the server generates an operation guide such as, "To use this app, tap this icon on the home screen."

[0980] Finally, the device converts the generated operation guide into voice data using a text-to-speech engine (e.g., Amazon Polly) and outputs it audibly to the user. This output means allows the user to receive the operation guide as voice, making it easier for them to understand how to operate the smartphone.

[0981] For example, if a user asks "How do I use this app?", the following process occurs:

[0982] 1. The user speaks a question into the smartphone microphone.

[0983] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[0984] 3. The server uses the generative AI model to analyze this text data and generate an operation guide such as, "To use this app, tap this icon on the home screen."

[0985] 4. The device converts the generated operation guide into voice data and outputs it to the user.

[0986] This system allows even elderly people and users who are not familiar with technology to easily understand how to operate a smartphone. In this way, the voice guidance system greatly improves user convenience.

[0987] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0988] Step 1: Getting voice input

[0989] The user speaks a question into the smartphone's microphone, and this voice is captured as digital data by the voice input means.

[0990] Input: User spoken words

[0991] What it does: An audio input method captures audio in digital form.

[0992] Output: Digital audio data

[0993] Step 2: Convert audio data to text

[0994] The terminal analyzes the acquired voice data using a voice recognition library (for example, Google Speech-to-Text API) and converts it into text data.

[0995] Input: Digital audio data

[0996] How it works: The device analyzes the audio waveform, breaks it down into phonemes, and maps them to text data.

[0997] Output: Text data in the format "Tell me how to use this app"

[0998] Step 3: Send text data

[0999] The terminal transmits the converted text data to the server.

[1000] Input: Text data in the format "Tell me how to use this app"

[1001] Operation: The device sends text data to the server via the network.

[1002] Output: Text data sent to the server

[1003] Step 4: Generate the guide

[1004] The server analyzes the received text data using a generative model (e.g., OpenAI's GPT-3) and generates appropriate operation guides.

[1005] Input: Text data in the format "Tell me how to use this app"

[1006] How it works: The generative model analyzes the text data and generates a guide based on the prompt: "If a user says 'Teach me how to use this app,' what kind of guide should be generated?"

[1007] Output: Operation guide such as "To use this app, tap this icon on the home screen."

[1008] Step 5: Sending the guide

[1009] The server transmits the generated operation guide to the terminal.

[1010] Input: Instructions such as "To use this app, tap this icon on the home screen."

[1011] Operation: The server sends the operation guide to the terminal via the network.

[1012] Output: Operation guide delivered to the device

[1013] Step 6: Audio output of operation guide

[1014] The device converts the received operation guide into voice data using a text-to-speech engine (e.g., Amazon Polly) and outputs it audibly to the user.

[1015] Input: Instructions such as "To use this app, tap this icon on the home screen."

[1016] Operation: The device converts the text data of the operation guide into voice data using a speech synthesis engine.

[1017] Output: Audio data that the user can hear (operation guide)

[1018] The above is the specific processing flow of the system. This system allows users to easily ask questions by voice and receive operation guidance in response to those questions by voice.

[1019] (Application example 1)

[1020] 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."

[1021] There is a problem in that it is difficult for workers in factories to quickly obtain information on how to use operating machines correctly and on maintenance management. Conventional methods require manuals and face-to-face training, which takes time and effort, and also increases the risk of operating incorrectly. This can reduce work efficiency and compromise safety.

[1022] 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.

[1023] In this invention, the server includes a voice input means, a conversion means for converting voice data into text data, and a generation means for generating operation guidance from the text data using a generative model, thereby enabling the server to provide appropriate operation instructions and operation guidance in real time by voice based on the worker's voice questions.

[1024] "Voice input means" is a device for acquiring voice uttered by a user and storing it as digital data.

[1025] The "conversion means" is a device or software that has the function of converting acquired voice data into text data.

[1026] The "generation means" is a device or software that has the function of generating an appropriate operation guide from text data.

[1027] The "output means" is a device or software that converts the generated operation guide into audio data and provides it to the user as audio.

[1028] "Work machines" refer to various types of machinery and equipment used in factories, and are devices for automation and machine control to improve work efficiency.

[1029] "Workers" are people who operate work machines and perform various tasks in a factory.

[1030] "Real-time" means that data is processed and output immediately, without delay.

[1031] A "conversational AI model" is an artificial intelligence model that generates appropriate responses in natural language in response to user input.

[1032] A system for implementing the present invention is configured as follows.

[1033] Voice input means

[1034] The user speaks a question into a microphone mounted on the work machine. This voice is captured as digital data by a voice input means. A commercially available microphone or voice collection device can be used as the voice input means.

[1035] Speech-to-text

[1036] The device analyzes the acquired voice data and converts it into text data using a voice recognition library. In this step, the voice recognition library can use services such as "Google Cloud Speech-to-Text." This library analyzes the voice data and generates text data such as "Please tell me how to maintain this machine."

[1037] Generate operation guides

[1038] The server receives the generated text data and analyzes it using a pre-trained generative model. A conversational AI model such as OpenAI's GPT-4 is used as the generative model. This generative model generates appropriate operation guidance based on the text data. For example, it provides specific instructions such as, "First, turn off the machine and then remove the cover. Next, clean the dust inside."

[1039] Guide audio output

[1040] The device uses a text-to-speech engine to convert the generated operation guide into audio data and output it audibly to the user. The text-to-speech engine can be "Amazon Polly" or similar.

[1041] Specific examples

[1042] For example, if a worker asks, "Tell me how to maintain this machine," the process goes like this:

[1043] 1. The worker speaks a question into the microphone on the work machine.

[1044] 2. The device receives the voice data and converts it into text data such as "Please tell me how to maintain this machine."

[1045] 3. The server uses the generative model to analyze this text data and generate an operation guide that reads, "First, turn off the machine and then remove the cover. Next, clean the dust that has accumulated inside."

[1046] 4. The terminal converts the generated operation guide into audio data and outputs it to the worker.

[1047] Prompt Sentence Examples

[1048] The following is an example of a prompt sentence that generates an appropriate operation guide for a dialogue when a worker asks, "Tell me how to maintain this machine."

[1049] markdown

[1050] Please generate an appropriate operation guide for the following dialogue when the user asks, "Please tell me how to maintain this machine."

[1051] Q: How do I maintain this machine?

[1052] Answer: First, turn off the machine and then remove the cover. Then, clean the dust accumulated inside. For detailed instructions, please refer to the following website:

[1053] This system allows workers to receive quick and accurate operation instructions and maintenance guides via voice input and output, improving work efficiency and reducing the risk of operational errors.

[1054] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1055] Step 1:

[1056] The user speaks a question into the microphone of the work machine. This voice is acquired as digital data by the voice input means. Specifically, when the user says, "Please tell me how to maintain this machine," the voice data is input into the terminal via the microphone.

[1057] Step 2:

[1058] The device converts the acquired voice data into text data using a speech recognition library. Specifically, the device calls the Google Cloud Speech-to-Text API and converts the voice data into text data such as "Please tell me how to maintain this machine." During this conversion process, the voice data is analyzed and the corresponding text is generated.

[1059] Step 3:

[1060] The terminal transmits the generated text data to the server. Specifically, the text data is sent to the server as an HTTP request. This data transmission continues until the server receives it.

[1061] Step 4:

[1062] The server analyzes the received text data using a pre-trained generative AI model to generate appropriate operation guidance. Specifically, the server uses OpenAI's GPT-4 model to generate operation guidance such as "First, turn off the machine and then remove the cover. Next, clean the dust that has accumulated inside" in response to the received text data "Please tell me how to maintain this machine." In this generation process, a dialogue generation model operates based on the input text and outputs the corresponding guidance.

[1063] Step 5:

[1064] The server sends the generated operation guide to the terminal. Specifically, the generated text data is returned to the terminal as an HTTP response. This data transmission continues until the terminal receives it.

[1065] Step 6:

[1066] The device converts the generated operation guide into audio data using a text-to-speech engine. Specifically, the device calls Amazon Polly to convert the text data of the operation guide into audio data. During this conversion process, the text is analyzed and the corresponding audio is generated.

[1067] Step 7:

[1068] The terminal outputs the generated audio data to the user through a speaker. Specifically, the audio data reaches the user's ears from the speaker. This audio output allows the user to receive the operation guide by audio.

[1069] 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.

[1070] The system of this invention includes a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, an output means for outputting the generated operation guidance by voice, and an emotion engine for recognizing the user's emotions. Below, the processing of the system program will be explained in natural language.

[1071] Voice input means

[1072] The user speaks their question into the smartphone's microphone, and the voice input means captures the user's voice and stores the voice data in digital format.

[1073] Speech-to-text

[1074] The device analyzes the acquired voice data and converts it into text data using a speech recognition library. The speech recognition library analyzes the voice signal and generates text in the format of "Tell me how to use this app."

[1075] emotion recognition

[1076] The device uses an emotion engine to recognize the user's emotions from the voice or text data, for example, determining whether the user is distressed, angry, or happy based on the tone and content of the voice.

[1077] Generate operation guides

[1078] The server receives the generated text data and the recognized user emotion and analyzes it using a pre-trained generative model. The generative model is an interactive AI model that generates emotion-sensitive operation guidance such as "To use this app, tap this icon on the home screen" based on the text data and emotion information.

[1079] Guide audio output

[1080] The device converts the generated operation guide text into audio data using a text-to-speech engine and outputs it audibly to the user. At this time, the tone and expression of the generated guide are adjusted to match the user's emotions.

[1081] Specific examples

[1082] For example, if a user asks "How do I use this app?" and speaks in a confused tone:

[1083] 1. The user speaks a question into the smartphone microphone.

[1084] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[1085] 3. The device uses an emotion engine to analyze the user's problem.

[1086] 4. The server uses the generative model to generate an operation guide based on the text data and the user's confusion: "We'll explain it in simple terms. To use this app, tap this icon on the home screen."

[1087] 5. The device converts the generated operation guide into voice data and outputs it to the user in a gentle tone.

[1088] This system allows elderly people to receive appropriate support in how to operate their smartphones based on their emotions, and to receive information in a format that is easier to understand.

[1089] The processing flow will be explained below.

[1090] Step 1:

[1091] The user speaks a question into the smartphone's microphone, and the user's voice is captured as digital voice data by the voice input means.

[1092] Step 2:

[1093] The voice data acquired by the device is analyzed using a voice recognition library and converted into text data. The voice signal is analyzed and the text data "Teach me how to use this app" is generated.

[1094] Step 3:

[1095] The device uses the emotion engine to recognize the user's emotion from the acquired and converted voice data and text data, for example, recognizing that the user is in a difficult state from the tone and content of the voice.

[1096] Step 4:

[1097] The device sends the converted text data and the recognized user emotion information to the server, which then receives the necessary data and prepares to proceed to the next step.

[1098] Step 5:

[1099] The server uses a pre-trained interactive generative model to analyze the text data and emotional information sent and generate appropriate operation guidance. For example, the generative model generates operation guidance such as, "To use this app, tap this icon on the home screen."

[1100] Step 6:

[1101] The server sends the generated operation guide to the terminal, which receives the guide and prepares for voice output.

[1102] Step 7:

[1103] The device uses a text-to-speech engine to convert the operation guide text into voice data, and the generated operation guide is converted into voice in a tone that takes into consideration the user's emotions.

[1104] Step 8:

[1105] The terminal reproduces the generated voice data through the voice output means so that the user can hear it. For example, if the user is recognized as having trouble, guidance is provided in a gentle tone.

[1106] Through this step, the system provides smartphone operation guidance in a way that takes the user's emotions into consideration, helping elderly people to easily understand how to operate the smartphone.

[1107] Example 2

[1108] 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."

[1109] In conventional voice assistant systems, the function of converting user questions from voice to text and providing information based on that text often ignores emotions, which can increase user stress and dissatisfaction. Furthermore, there is a lack of guidance that takes emotions into consideration, particularly for elderly users and those who require technical support, resulting in a poor user experience.

[1110] 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 a voice input means, a conversion means for converting voice data into text data, a generation means for generating operation guidance from the text data using a generative model, an output means for outputting the generated operation guidance by voice, and an emotion recognition means for recognizing the emotion of the user. This allows the system to provide guidance that takes into consideration the emotion of the user, and enables even elderly users and users who require technical support to use the system smoothly and without stress.

[1111] "Voice input means" refers to equipment or software for acquiring user speech as voice data.

[1112] "Conversion means for converting voice data into text data" refers to software or a library that analyzes acquired voice data and converts it into corresponding text data.

[1113] A "generative model" refers to an AI model that uses a pre-trained algorithm to generate sentences such as operation guides from text data.

[1114] "Generation means for generating operation guide" refers to a function or software that uses a generative model to generate a guide that helps the user with operation from text data.

[1115] The "output means for outputting the generated operation guide as audio" refers to a device or software that converts the generated operation guide into audio data and outputs it in a form that can be heard by the user.

[1116] "Emotion recognition means for recognizing user emotions" refers to algorithms or software for analyzing and recognizing user emotions from voice data or text data.

[1117] MODE FOR CARRYING OUT THE INVENTION

[1118] A system for implementing the present invention includes the following components:

[1119] Voice input means

[1120] The user speaks their question using a device with a microphone (e.g., a smartphone or tablet), and the voice input means captures the voice and stores it in digital format.

[1121] A conversion means for converting voice data into text data

[1122] The device then uses a speech recognition library such as the Google Cloud Speech-to-Text API to analyze the captured voice data and convert it into text data. The voice signal is analyzed and text is generated in the form of a message such as "Tell me how to use this app."

[1123] emotion recognition means

[1124] The device uses an emotion engine such as IBM Watson Tone Analyzer to recognize the user's emotions from the analyzed text or voice data, determining whether the user is distressed, angry, or happy based on the tone and content of the voice.

[1125] A method for generating operation guides

[1126] The server receives the generated text data and the recognized user emotion data and analyzes it using a generative AI model such as OpenAI GPT-3. Based on the text data and emotion information, the generative AI model generates emotion-sensitive operation guidance such as "To use this app, tap this icon on the home screen."

[1127] An output means for outputting the generated operation guide in voice form.

[1128] The device then sends the generated guide text to a text-to-speech engine such as Amazon Polly, which converts it into speech data. This speech data is then output to the smartphone speaker for the user to hear, with the tone and expression adjusted to match the user's emotions.

[1129] Specific examples

[1130] For example, if a user asks "How do I use this app?" and speaks in a confused tone:

[1131] 1. The user speaks a question into the smartphone microphone.

[1132] 2. The device receives the voice data and converts it into text data such as "Tell me how to use this app."

[1133] 3. The device uses IBM Watson Tone Analyzer to analyze the user's problem.

[1134] 4. The server uses OpenAI GPT-3 to generate an operation guide based on the text data and the user's confusion: "We'll explain it in simple terms. To use this app, tap this icon on the home screen."

[1135] 5. The device sends the generated operation guide to Amazon Polly, which converts it into voice data in a gentle tone and finally outputs it to the user through the smartphone speaker.

[1136] Prompt Sentence Examples

[1137] Here are some example prompts to input to a generative AI model:

[1138] "Take a question uttered by a user in a confused tone and generate a how-to guide that explains how to use the app in a straightforward and friendly tone."

[1139] This system allows elderly people and users who require technical support to receive guidance that takes their emotions into consideration, making it easier for them to use the system.

[1140] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1141] Step 1: Voice Input

[1142] The user speaks a question into the smartphone's microphone. The voice input means captures the voice and stores it in digital format. Specifically, the user picks up the smartphone and asks, "Tell me how to use this app." The smartphone's microphone captures the voice data and temporarily stores it.

[1143] Input: User's spoken utterance

[1144] Output: Digital audio data

[1145] Step 2: Convert audio data to text

[1146] The device uses a speech recognition library such as the Google Cloud Speech-to-Text API to analyze the audio data and convert it into text. The library analyzes the audio signal and generates the corresponding text data.

[1147] Specifically, the device sends voice data to the Google Cloud Speech-to-Text API and receives text data such as "Teach me how to use this app." The device then stores this text data.

[1148] Input: Digital audio data

[1149] Output: Text data of "Tell me how to use this app"

[1150] Step 3: Emotion Recognition

[1151] The device uses an emotion engine such as IBM Watson Tone Analyzer to recognize the user's emotion from text data or voice data. The emotion recognition means analyzes the content of the text and the tone of the voice to generate user emotion information.

[1152] Specifically, the device sends text data to the IBM Watson Tone Analyzer, labels it with the emotion "distressed," and receives the results. The device then stores the emotion recognition results.

[1153] Input: Text data of "Teach me how to use this app"

[1154] Output: User's emotion (e.g. "I'm in trouble")

[1155] Step 4: Generate the guide

[1156] The server receives the text data and emotion recognition results and generates operation instructions using a generative AI model such as OpenAI GPT-3. The generative model analyzes the text data and emotion information and generates specific operation instructions that take emotions into consideration.

[1157] Specifically, the device sends text and emotion data to the server, which then sends the data to the OpenAI GPT-3 API. The generative AI model generates an operation guide, such as "We'll explain it in simple terms. To use this app, tap this icon on the home screen," and the server sends it back to the device.

[1158] Input: Text data, user emotion information

[1159] Output: Emotionally sensitive operation guide text

[1160] Step 5: Audio guide output

[1161] The device sends the generated operation guide text to a text-to-speech engine such as Amazon Polly, which converts it into speech data. The speech engine converts the text into speech data, and the device outputs the speech to the user.

[1162] Specifically, the device sends the operation guide text to Amazon Polly, which converts it into voice data in a gentle tone and finally outputs it to the user through the smartphone speaker.

[1163] Input: Emotionally sensitive guide text

[1164] Output: Audio data (gentle tone)

[1165] Through the above processing steps, users are given appropriate support in how to operate their smartphones according to their emotions, and can receive information in a more understandable format.

[1166] (Application example 2)

[1167] 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."

[1168] In logistics centers, there is insufficient support for staff to work efficiently. There is also a lack of means to help staff deal with situations that cause confusion or stress. There is a need for real-time work guidance based on voice input and support that responds to staff emotions.

[1169] 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.

[1170] In this invention, the server includes a voice input means, a means for converting voice data into text data, a means for generating operation guidance from the text data using a generative model, a means for outputting the generated operation guidance by voice, an emotion recognition means for recognizing a user's emotion, and a means for controlling a robot that supports the work of staff at the logistics center. This enables the staff at the logistics center to receive appropriate operation guidance by voice depending on the situation in which they feel confused or stressed.

[1171] "Voice input means" refers to a device that acquires a user's voice data and converts it into digital form.

[1172] The "conversion means for converting voice data into text data" is a function for analyzing acquired voice data and generating corresponding text data.

[1173] A "generative model" is an algorithm that generates appropriate operation guides and outputs from text data based on pre-trained data.

[1174] The "generation means" is a process for generating operation guidance from text data using a generative model.

[1175] The "output means for outputting voice" is a function that converts the generated text data into voice data and presents it to the user.

[1176] "Emotion recognition means" is a technology that analyzes voice data or text data and recognizes the emotional state of the user.

[1177] A "robot that supports staff work at a logistics center" is a robot designed to support workers at a logistics center, and has the ability to provide voice instructions and work guides.

[1178] The system of the present invention is constructed by combining the following hardware and software: First, a microphone is used as a voice input means, and the user inputs voice instructions. This voice data is converted into text data using a voice recognition library (e.g., speech_recognition library).

[1179] The server then receives the text data and analyzes the user's emotions using emotion recognition, using the pipeline function of the transformers library. This allows the server to obtain emotional information such as whether the user is distressed, angry, or happy.

[1180] Furthermore, the server uses a generative model (e.g., GPT-3) to generate operation guidance based on text data and emotional information. This generative model is a pre-trained dialogue model and can provide guidance that takes the user's emotions into consideration. The generated operation guidance is converted into voice data using the gTTS library as an output means and presented to the user.

[1181] Specifically, the process is as follows:

[1182] 1. A user speaks into the microphone, "How can I check the availability of this item? I'm having trouble."

[1183] 2. The device receives the voice data and converts it into text data such as "How can I check the stock of this product?"

[1184] 3. The device uses an emotion engine to recognize that the user is confused.

[1185] 4. The server uses a generative model (GPT-3) to generate an operation guide based on the text data and the user's confusion.

[1186] 5. The device converts the generated operation guide into voice data and outputs to the user in a friendly tone, "To check your inventory, first tap this icon, then open the inventory menu."

[1187] Example prompt sentence:

[1188] When a user is confused, generate a task guide based on the following text: How do I check the availability of this product?

[1189] This allows logistics center staff to receive appropriate work guidance in real time, enabling them to carry out their work efficiently.In addition, the guidance provided takes into consideration the user's emotions, which is expected to reduce stress and confusion.

[1190] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1191] Step 1:

[1192] The user inputs speech.

[1193] Input: User's spoken instructions (e.g., "How do I check the availability of this item? I'm having trouble.").

[1194] Operation: Audio data is picked up by the device's microphone and converted into digital form.

[1195] Output: Audio data in digital format.

[1196] Step 2:

[1197] Convert the audio data into text data.

[1198] Input: Audio data in digital format.

[1199] Operation: The device uses a voice recognition library to analyze the voice data and generate text data.

[1200] Output: Text data (e.g., "How do I check the stock of this item?").

[1201] Step 3:

[1202] Recognize user emotions.

[1203] Input: Text data.

[1204] Operation: The device uses emotion recognition means (the pipeline function of the transformers library) to analyze text data and recognize the user's emotions.

[1205] Output: User's emotional state (e.g., confusion).

[1206] Step 4:

[1207] Generate operation guide.

[1208] Input: Text data and user emotion information.

[1209] Operation: The server uses a generative model (GPT-3) to generate an operation guide based on the text data and the user's emotional information. The prompt sentence is input to the generative model, and the operation guide is obtained as generated text.

[1210] Output: The generated instructions (e.g. "To check your inventory, first tap this icon, then open the inventory menu").

[1211] Step 5:

[1212] Outputs operation guides in voice.

[1213] Input: The generated instruction text.

[1214] Operation: The device uses a text-to-speech engine (gTTS) to convert text data into voice data, which is then output through the speaker.

[1215] Output: Audio guide.

[1216] Through the above process, logistics center staff can receive appropriate operational guidance in real time via voice.

[1217] 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.

[1218] 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.

[1219] 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 robot 414.

[1220] 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.

[1221] 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.

[1222] 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.

[1223] 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).

[1224] 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.

[1225] 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."

[1226] 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.

[1227] 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).

[1228] 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.

[1229] 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.

[1230] 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.

[1231] 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.

[1232] 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.

[1233] 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.

[1234] 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.

[1235] 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.

[1236] 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.

[1237] 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.

[1238] The following is further disclosed regarding the above embodiment.

[1239] (Claim 1)

[1240] A voice input means;

[1241] A conversion means for converting voice data into text data;

[1242] a generation means for generating an operation guide from text data using a generative model;

[1243] an output means for outputting the generated operation guide as voice;

[1244] A system including:

[1245] (Claim 2)

[1246] 10. The system of claim 1, further comprising means for converting voice data into text data in real time.

[1247] (Claim 3)

[1248] 10. The system of claim 1, wherein the generative model is a pre-trained dialogue model.

[1249] "Example 1"

[1250] (Claim 1)

[1251] A voice input means;

[1252] A conversion means for converting voice data into text data;

[1253] a generation means for generating an operation guide from text data using a generative model;

[1254] an output means for outputting the generated operation guide as voice;

[1255] A system including:

[1256] (Claim 2)

[1257] 10. The system of claim 1, further comprising means for converting voice data into text data in real time.

[1258] (Claim 3)

[1259] 10. The system of claim 1, wherein the generative model is a pre-trained dialogue model.

[1260] (Claim 4)

[1261] 10. The system of claim 1, further comprising means for analyzing the text data to generate an appropriate operation guide.

[1262] (Claim 5)

[1263] The system according to claim 1, further comprising means for converting the generated operation guide into audio data using a text-to-speech engine and outputting the audio data.

[1264] (Claim 6)

[1265] 10. The system of claim 1, further comprising means for converting voice data into text data using a voice recognition library.

[1266] "Application Example 1"

[1267] (Claim 1)

[1268] A voice input means;

[1269] A conversion means for converting voice data into text data;

[1270] a generation means for generating an operation guide from text data using a generative model;

[1271] an output means for outputting the generated operation guide as voice;

[1272] a means for providing audio work instructions based on questions from a worker, the means being mounted on the work machine;

[1273] A system including:

[1274] (Claim 2)

[1275] 10. The system of claim 1, further comprising means for converting voice data into text data in real time.

[1276] (Claim 3)

[1277] 2. The system of claim 1, wherein the generative model is a pre-trained conversational AI model that is installed on a work machine and provides work instructions via voice based on questions from the worker.

[1278] "Example 2: Combining Emotion Engines"

[1279] (Claim 1)

[1280] A voice input means;

[1281] A conversion means for converting voice data into text data;

[1282] a generation means for generating an operation guide from text data using a generative model;

[1283] an output means for outputting the generated operation guide as voice;

[1284] emotion recognition means for recognizing an emotion of a user;

[1285] A system including:

[1286] (Claim 2)

[1287] 10. The system of claim 1, further comprising means for converting voice data into text data in real time.

[1288] (Claim 3)

[1289] 10. The system of claim 1, wherein the generative model is a pre-trained dialogue model, and the generated operation guide has its expression and tone adjusted based on the user's emotions.

[1290] "Application example 2 when combining emotion engines"

[1291] (Claim 1)

[1292] A voice input means;

[1293] A conversion means for converting voice data into text data;

[1294] a generation means for generating an operation guide from text data using a generative model;

[1295] an output means for outputting the generated operation guide as voice;

[1296] emotion recognition means for recognizing an emotion of a user;

[1297] A means for controlling a robot that assists staff in the logistics center;

[1298] A system including:

[1299] (Claim 2)

[1300] 10. The system of claim 1, further comprising means for converting voice data into text data in real time.

[1301] (Claim 3)

[1302] 10. The system of claim 1, wherein the generative model is a pre-trained dialogue model. [Explanation of symbols]

[1303] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A voice input means; A conversion means for converting voice data into text data; a generation means for generating an operation guide from text data using a generative model; an output means for outputting the generated operation guide as voice; A system including:

2. 10. The system of claim 1, further comprising means for converting voice data to text data in real time.

3. The system of claim 1 , wherein the generative model is a pre-trained dialogue model.

Images