system

Abstract

The system according to this embodiment aims to provide an AI conversation service using voice input and voice output. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives voice input. The analysis unit analyzes the voice input received by the reception unit. The generation unit generates a response based on the voice input analyzed by the analysis unit. The output unit outputs the response generated by the generation unit as voice.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, an AI conversation service using voice input and voice output has not been sufficiently provided, and there is room for improvement.

[0005] The system according to an embodiment aims to provide an AI conversation service using voice input and voice output.

Means for Solving the Problems

[0006] The system according to an embodiment includes a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives voice input. The analysis unit analyzes the voice input received by the reception unit. The generation unit generates a response based on the voice input analyzed by the analysis unit. The output unit outputs the response generated by the generation unit as voice. [Effects of the Invention]

[0007] The system according to this embodiment can provide an AI conversation service using voice input and voice output. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. 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. Also, the database 24 and the communication I / F 26 are 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).

[0019] 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The voice-only AI conversation service according to an embodiment of the present invention is a system that uses a generating AI to analyze voice input, generate an appropriate response, and output it as voice. This system is started when the user launches a smartphone app once and displays the chat screen. The user inputs a question by voice, for example, "What's the weather like today?" This voice input is analyzed by the generating AI, and an appropriate response is generated. For example, a response such as "The weather is sunny today" is generated. This response is output as voice. This allows the user to converse with the AI ​​using only voice. Furthermore, the user can select a conversation mode, for example, "Talkative," "Normal," or "Quiet." The generating AI adjusts the frequency and content of the conversation according to the selected mode. The generating AI can also display URL information as needed. For example, if the user asks a question such as "Tell me about nearby restaurants," the generating AI can display the URL of an appropriate restaurant. This mechanism allows the user to converse with the AI ​​using only voice by simply launching their smartphone once. In addition, the selection of a conversation mode allows for conversations tailored to the user's preferences. Furthermore, by displaying URL information as needed, the service can provide users with useful information. This allows the voice-only AI conversation service to analyze the user's voice input, generate appropriate responses, and output them as voice.

[0029] The voice-only AI conversation service according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives voice input. Voice input includes, but is not limited to, natural language or command voices. The reception unit receives voice input using, for example, the microphone of a smartphone. The reception unit can also receive voice input in real time. Furthermore, the reception unit can record the voice input and analyze it later. For example, the reception unit receives voice input when the user speaks into the microphone of a smartphone. The analysis unit analyzes the voice input received by the reception unit. For example, the analysis may use, but is not limited to, speech recognition technology or natural language processing technology. For example, the analysis unit converts the voice input into text data using speech recognition technology. The analysis unit can also analyze the meaning of the voice input using natural language processing technology. Furthermore, the analysis unit can understand the context of the voice input and extract information to generate an appropriate response. For example, the analysis unit converts the voice input into text data using speech recognition technology and analyzes that text data using natural language processing technology. The generation unit generates a response based on the voice input analyzed by the analysis unit. The response may include, but is not limited to, voice responses or text responses. For example, the generation unit may use a generation AI to generate an appropriate response to voice input. The generation unit can also use a generation AI to generate accurate answers to user questions. Furthermore, the generation unit may use a generation AI to generate responses that provide relevant information. For example, the generation unit may use a generation AI to generate an appropriate response to voice input and output that response as voice data. The output unit outputs the response generated by the generation unit as voice. For voice output, for example, speech synthesis technology may be used, but is not limited to this example. For example, the output unit may use speech synthesis technology to convert the generated response into voice data and output it through a speaker. The output unit may also output the generated response in high-quality voice. Furthermore, the output unit may output the generated response as voice in real time.For example, the output unit converts the response generated using speech synthesis technology into audio data and outputs it in real time through the speaker. As a result, the voice-only AI conversation service according to this embodiment can analyze the user's voice input, generate an appropriate response, and output it as audio.

[0030] The reception unit accepts voice input. Voice input includes, but is not limited to, natural language and command voices. The reception unit accepts voice input using, for example, the microphone of a smartphone. Specifically, smartphone microphones are highly sensitive and have noise-canceling capabilities to remove ambient noise, enabling clear voice input. The reception unit can also accept voice input in real time. This means that voice data is sent to the system the moment the user speaks, and processing begins immediately. Furthermore, the reception unit can record the voice input and analyze it later. For example, voice input is accepted when the user speaks into the microphone of their smartphone. The recorded voice data is stored on a cloud server and can be accessed later by the analysis unit as needed. This allows for detailed analysis later, even if real-time processing is difficult. In addition, the reception unit can use voice filtering technology to remove background noise and improve voice clarity in order to improve the quality of voice input. This allows the reception unit to accept user voice input with high accuracy and improve the overall performance of the system.

[0031] The analysis unit analyzes the voice input received by the reception unit. Analysis may utilize, but is not limited to, speech recognition technology or natural language processing technology. Specifically, the analysis unit converts voice input into text data using speech recognition technology. Speech recognition technology employs deep learning models to achieve high-precision speech recognition. For example, speech recognition models are trained using large amounts of voice data and corresponding text data, enabling them to handle various accents and speaking styles. The analysis unit can also analyze the meaning of voice input using natural language processing technology. Natural language processing technology uses algorithms to understand context and intent from text data, accurately grasping the user's intent. Furthermore, the analysis unit can extract information to understand the context of the voice input and generate appropriate responses. For example, the analysis unit converts voice input into text data using speech recognition technology and then analyzes that text data using natural language processing technology. This allows the analysis unit to accurately understand the user's intent and provide the necessary foundational information for generating appropriate responses. Additionally, the analysis unit can leverage past conversation history and user profile information to generate more personalized responses. This allows the analysis unit to analyze the user's voice input with high accuracy, improving the overall response accuracy of the system.

[0032] The generation unit generates responses based on the speech input analyzed by the analysis unit. These responses may include, but are not limited to, speech or text responses. Specifically, the generation unit uses generative AI to generate appropriate responses to speech input. The generative AI uses natural language generation techniques to generate appropriate responses to user questions and requests. For example, the generative AI can use a large, pre-trained language model to generate natural conversations based on the user's intent. The generation unit can also use generative AI to generate accurate answers to user questions. For example, the generative AI can search for relevant information in response to a user's question and generate an appropriate answer. Furthermore, the generation unit can use generative AI to generate responses that provide relevant information. For example, the generation unit uses generative AI to generate appropriate responses to speech input and outputs these responses as speech data. The generation unit can use algorithms to generate optimal responses, taking into account the user's intent and context, and provide the user with natural and useful information. Furthermore, the generation unit can evaluate the generated responses and modify them as needed to improve their quality. This allows the generation unit to produce high-quality responses to user voice input, improving the overall user experience of the system.

[0033] The output unit outputs the response generated by the generation unit as audio. This output may involve, but is not limited to, speech synthesis technology. Specifically, the output unit converts the response generated using speech synthesis technology into audio data and outputs it through a speaker. Speech synthesis technology uses algorithms to convert text data into natural-sounding speech, achieving high-quality audio output. For example, speech synthesis technology can adjust the intonation and rhythm of speech to generate natural-sounding utterances. The output unit can also output the generated response in high-quality audio, allowing the user to receive clear and easily understandable audio responses. Furthermore, the output unit can output the generated response in real time. For example, the output unit converts the response generated using speech synthesis technology into audio data and outputs it in real time through a speaker. This allows the user to receive responses immediately, enabling smooth conversation. Additionally, to improve the quality of the audio output, the output unit can use speech filtering technology to remove noise and enhance speech clarity. This allows the output unit to provide users with high-quality audio responses and improve the overall user experience of the system.

[0034] The mode selection unit can adjust the frequency and content of conversations according to the conversation mode selected by the user. For example, if the user selects the "talkative" mode, the mode selection unit will increase the frequency of conversations and provide detailed information. It can also provide standard conversation frequency and content if the user selects the "normal" mode. Furthermore, if the user selects the "less talkative" mode, the mode selection unit can reduce the frequency of conversations and provide concise information. For example, if the user selects the "talkative" mode, the mode selection unit can converse once an hour and provide detailed information. If the user selects the "normal" mode, the mode selection unit can converse once every two hours and provide standard information. If the user selects the "less talkative" mode, the mode selection unit can converse once every three hours and provide concise information. This allows for conversations tailored to the user's preferences.

[0035] The information display unit can display URL information as needed. For example, if a user asks a question like "Tell me about nearby restaurants," the information display unit will display the URL of an appropriate restaurant. It can also display the URL of a relevant news article if a user asks a question like "Tell me about the latest news." Furthermore, if a user asks a question like "Tell me about movies you recommend," the information display unit can display the URL of a movie review site. This allows the system to provide users with useful information.

[0036] The analysis unit can analyze voice input and generate an appropriate response. For example, the analysis unit can convert voice input into text data using speech recognition technology. Furthermore, the analysis unit can analyze the meaning of voice input using natural language processing technology. In addition, the analysis unit can understand the context of the voice input and extract information necessary to generate an appropriate response. For example, the analysis unit converts voice input into text data using speech recognition technology and then analyzes that text data using natural language processing technology. This allows the analysis unit to analyze voice input and generate an appropriate response.

[0037] The generation unit can generate responses using a generation AI. For example, the generation unit can use the generation AI to generate appropriate responses to voice input. Furthermore, the generation unit can use the generation AI to generate accurate answers to user questions. In addition, the generation unit can use the generation AI to generate responses that provide relevant information. For example, the generation unit uses the generation AI to generate appropriate responses to voice input and outputs those responses as voice data. Thus, the generation unit can generate responses using a generation AI.

[0038] The output unit can output the generated response as audio. For example, the output unit can convert the generated response using speech synthesis technology into audio data and output it through a speaker. The output unit can also output the generated response in high-quality audio. Furthermore, the output unit can output the generated response as audio in real time. For example, the output unit can convert the generated response using speech synthesis technology into audio data and output it through a speaker in real time. This allows the output unit to output the generated response as audio.

[0039] The reception unit can analyze the user's past voice input history and select the optimal reception method. For example, the reception unit can prioritize receiving voice commands that the user has frequently used in the past. Furthermore, the reception unit can predict commands to be used during specific time periods based on the user's past voice input history and accept those commands. In addition, the reception unit can analyze the user's past voice input history and propose the most efficient reception method. For example, the reception unit can prioritize receiving voice commands that the user has frequently used in the past. The reception unit can also predict commands to be used during specific time periods based on the user's past voice input history and accept those commands. The reception unit can also analyze the user's past voice input history and propose the most efficient reception method. This allows the reception unit to analyze the user's past voice input history and select the optimal reception method.

[0040] The reception unit can filter out the user's current ambient noise to remove noise when receiving voice input. For example, if the user is in a noisy environment, the reception unit can filter out ambient noise to remove noise and make the voice input clearer. Also, if the user is in a quiet environment, the reception unit can minimize the filtering of ambient noise to improve the accuracy of the voice input. Furthermore, if the user is on the move when making voice input, the reception unit can filter out wind noise and car noise to remove noise. For example, if the user is in a noisy environment, the reception unit can filter out ambient noise to remove noise and make the voice input clearer. Also, if the user is in a quiet environment, the reception unit can minimize the filtering of ambient noise to improve the accuracy of the voice input. Also, if the user is on the move when making voice input, the reception unit can filter out wind noise and car noise to remove noise. This allows the system to filter out the user's current ambient noise to remove noise when receiving voice input.

[0041] The reception system can prioritize receiving voice input based on the user's geographical location. For example, if the user is in a specific location, the reception system will prioritize receiving voice input related to that location. Furthermore, if the user is traveling, the reception system can prioritize receiving voice input related to their travel destination. Additionally, if the user is at home, the reception system can prioritize receiving voice input related to their home. This allows the system to prioritize receiving voice input based on the user's geographical location.

[0042] The reception system can analyze the user's social media activity when receiving voice input and receive relevant voice input. For example, the reception system can prioritize receiving voice input related to topics the user is discussing on social media. It can also prioritize receiving voice input related to accounts the user follows on social media. Furthermore, it can prioritize receiving voice input related to information the user has shared on social media. This allows the system to analyze the user's social media activity and receive relevant voice input.

[0043] The analysis unit can adjust the level of detail in its analysis of voice input based on the importance of the input content. For example, the analysis unit performs detailed analysis for important questions to generate highly accurate responses. It can also perform standard analysis for general questions to generate quick responses. Furthermore, it can perform rapid analysis for urgent questions to generate immediate responses. This allows the level of detail in the analysis to be adjusted based on the importance of the input content.

[0044] The analysis unit can apply different analysis algorithms depending on the category of the input content when analyzing voice input. For example, for questions about the weather, the analysis unit can apply an analysis algorithm based on weather forecast data. It can also apply an analysis algorithm based on restaurant reviews for questions about restaurants. Furthermore, it can apply an analysis algorithm based on the latest news data for questions about news. This allows for the application of different analysis algorithms depending on the category of the input content.

[0045] The analysis unit can determine the priority of analysis based on the timing of input submission when analyzing voice input. For example, the analysis unit can prioritize the analysis of the most recent voice input to generate a quick response. It can also sequentially analyze past voice inputs to generate an appropriate response. Furthermore, the analysis unit can prioritize the analysis of urgent voice inputs to generate an immediate response. This allows the analysis priority to be determined based on the timing of input submission.

[0046] The analysis unit can adjust the order of analysis based on the relevance of the input content when analyzing voice input. For example, the analysis unit can prioritize the analysis of highly relevant voice inputs and generate appropriate responses. It can also postpone the analysis of less relevant voice inputs. Furthermore, the analysis unit can group voice inputs of the same category together to efficiently generate responses. This allows the analysis order to be adjusted based on the relevance of the input content.

[0047] The generation unit can adjust the level of detail in the response based on the importance of the input content when generating the response. For example, the generation unit generates a detailed response for important questions. It can also generate a standard response for general questions. Furthermore, it can generate a rapid response for urgent questions. For example, the generation unit generates a detailed response for important questions. It can also generate a standard response for general questions. It can also generate a rapid response for urgent questions. This allows the level of detail in the response to be adjusted based on the importance of the input content.

[0048] The generation unit can apply different generation algorithms depending on the category of the input content when generating responses. For example, for questions about the weather, the generation unit can apply a generation algorithm based on weather forecast data. It can also apply a generation algorithm based on restaurant reviews for questions about restaurants. Furthermore, it can apply a generation algorithm based on the latest news data for questions about news. This allows for the application of different generation algorithms depending on the category of the input content.

[0049] The generation unit can determine the priority of responses based on the timing of input submission when generating responses. For example, the generation unit can prioritize responses to the most recent voice input. It can also sequentially generate responses to past voice inputs. Furthermore, the generation unit can prioritize responses to urgent voice inputs. This allows the system to determine the priority of responses based on the timing of input submission.

[0050] The generation unit can adjust the order of responses based on the relevance of the input content during response generation. For example, the generation unit can prioritize generating responses for highly relevant voice inputs. It can also delay generating responses for less relevant voice inputs. Furthermore, the generation unit can generate responses for voice inputs of the same category all at once. For example, the generation unit can prioritize generating responses for highly relevant voice inputs. It can also delay generating responses for less relevant voice inputs. It can also generate responses for voice inputs of the same category all at once. This allows the order of responses to be adjusted based on the relevance of the input content.

[0051] The output unit can adjust the level of detail in the output based on the importance of the response. For example, the output unit will provide detailed audio output for important responses. It can also provide standard audio output for general responses. Furthermore, it can provide rapid audio output for urgent responses. This allows the level of detail in the output to be adjusted based on the importance of the response.

[0052] The output unit can apply different output algorithms depending on the category of the response content when outputting audio. For example, the output unit can apply an output algorithm based on weather forecast data to responses related to the weather. It can also apply an output algorithm based on restaurant reviews to responses related to restaurants. Furthermore, it can apply an output algorithm based on the latest news data to responses related to news. This allows for the application of different output algorithms depending on the category of the response content.

[0053] The output unit can determine the priority of output based on the timing of response submission when outputting audio. For example, the output unit prioritizes outputting the most recent response. It can also output past responses sequentially. Furthermore, the output unit can prioritize outputting urgent responses. This allows the output priority to be determined based on the timing of response submission.

[0054] The output unit can adjust the order of output based on the relevance of the response content when outputting audio. For example, the output unit can prioritize outputting highly relevant responses. It can also delay outputting less relevant responses. Furthermore, the output unit can group responses of the same category together for output. This allows the output order to be adjusted based on the relevance of the response content.

[0055] The mode selection unit can suggest the optimal mode by referring to the user's past conversation history when selecting a mode. For example, if the user has frequently used the "talkative" mode in the past, the mode selection unit will suggest that mode. It can also suggest the "less talkative" mode if the user has used that mode in the past. Furthermore, the mode selection unit can predict and suggest the optimal mode based on the user's past conversation history. For example, if the user has frequently used the "talkative" mode in the past, the mode selection unit will suggest that mode. It can also suggest the "less talkative" mode if the user has used that mode in the past. The mode selection unit can also predict and suggest the optimal mode based on the user's past conversation history. This allows the system to suggest the optimal mode by referring to the user's past conversation history.

[0056] The mode selection unit can suggest the optimal mode based on the user's current environment information when selecting a mode. For example, if the user is in a quiet environment, the mode selection unit can suggest the "talkative" mode. It can also suggest the "less talkative" mode if the user is in a noisy environment. Furthermore, it can suggest the "normal" mode if the user is in a normal environment. This allows the system to suggest the optimal mode based on the user's current environment information.

[0057] The information display unit can display the most relevant information by referencing the user's past search history when displaying URL information. For example, the information display unit prioritizes displaying information that the user has frequently searched for in the past. It can also display highly relevant information based on the user's past search history. Furthermore, the information display unit can analyze the user's past search history and display the most appropriate information. This allows the system to display the most relevant information by referencing the user's past search history.

[0058] The information display unit can display highly relevant information based on the user's geographical location when displaying URL information. For example, if the user is in a specific location, the information display unit will display information related to that location. Furthermore, if the user is traveling, the information display unit can display information related to their travel destination. Additionally, if the user is at home, the information display unit can display information related to their home. This allows the display of highly relevant information based on the user's geographical location.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The reception system can predict the optimal response when receiving a user's voice input by referring to the user's past conversation history. For example, if a user has frequently asked a particular question in the past, the system will prioritize preparing a response to that question. The reception system can also predict commands to be used at specific times based on the user's past conversation history and process them accordingly. Furthermore, the reception system can analyze the user's past conversation history and suggest the most efficient way to process the call. This allows for efficient processing by predicting the optimal response based on the user's past conversation history.

[0061] The information display unit can display highly relevant information based on the user's geographical location. For example, if the user is in a specific location, it can display information related to that location. If the user is traveling, it can also display information related to their travel destination. Furthermore, if the user is at home, it can display information related to their home. This allows the display of highly relevant information based on the user's geographical location.

[0062] The analysis unit can apply different analysis algorithms to voice input depending on the category of the input content. For example, a question about the weather can be analyzed using an analysis algorithm based on weather forecast data. Similarly, a question about restaurants can be analyzed using an analysis algorithm based on restaurant reviews. Furthermore, a question about news can be analyzed using an analysis algorithm based on the latest news data. This allows for the application of different analysis algorithms depending on the category of the input content.

[0063] The output unit can adjust the level of detail in the output based on the importance of the response. For example, it can provide detailed audio output for important responses, standard audio output for general responses, and rapid audio output for urgent responses. This allows for adjustment of the level of detail in the output based on the importance of the response.

[0064] The analysis unit can determine the priority of analysis based on the timing of input submission when analyzing voice input. For example, it can prioritize the analysis of the most recent voice input to generate a quick response. It can also sequentially analyze past voice inputs to generate an appropriate response. Furthermore, it can prioritize the analysis of urgent voice inputs to generate an immediate response. This allows the system to determine the priority of analysis based on the timing of input submission.

[0065] The generation unit can adjust the level of detail in the response based on the importance of the input content during response generation. For example, it can generate a detailed response for important questions, a standard response for general questions, and a rapid response for urgent questions. This allows the level of detail in the response to be adjusted based on the importance of the input content.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The reception desk accepts voice input. Voice input can include natural language and command voices. For example, voice input can be accepted using a smartphone's microphone. It is also possible to accept voice input in real time or to record it and analyze it later. Step 2: The analysis unit analyzes the voice input received by the reception unit. Speech recognition technology and natural language processing technology are used for the analysis. For example, speech recognition technology is used to convert the voice input into text data, and that text data is analyzed using natural language processing technology. Furthermore, it is also possible to understand the context of the voice input and extract information to generate an appropriate response. Step 3: The generation unit generates a response based on the voice input analyzed by the analysis unit. The response may include voice responses or text responses. For example, the generation AI can be used to generate an appropriate response to voice input, producing responses that provide accurate answers to the user's questions or relevant information. Step 4: The output unit outputs the response generated by the generation unit as audio. Speech synthesis technology is used for audio output. For example, the response generated using speech synthesis technology can be converted into audio data and output in real time through a speaker.

[0068] (Example of form 2) The voice-only AI conversation service according to an embodiment of the present invention is a system that uses a generating AI to analyze voice input, generate an appropriate response, and output it as voice. This system is started when the user launches a smartphone app once and displays the chat screen. The user inputs a question by voice, for example, "What's the weather like today?" This voice input is analyzed by the generating AI, and an appropriate response is generated. For example, a response such as "The weather is sunny today" is generated. This response is output as voice. This allows the user to converse with the AI ​​using only voice. Furthermore, the user can select a conversation mode, for example, "Talkative," "Normal," or "Quiet." The generating AI adjusts the frequency and content of the conversation according to the selected mode. The generating AI can also display URL information as needed. For example, if the user asks a question such as "Tell me about nearby restaurants," the generating AI can display the URL of an appropriate restaurant. This mechanism allows the user to converse with the AI ​​using only voice by simply launching their smartphone once. In addition, the selection of a conversation mode allows for conversations tailored to the user's preferences. Furthermore, by displaying URL information as needed, the service can provide users with useful information. This allows the voice-only AI conversation service to analyze the user's voice input, generate appropriate responses, and output them as voice.

[0069] The voice-only AI conversation service according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives voice input. Voice input includes, but is not limited to, natural language or command voices. The reception unit receives voice input using, for example, the microphone of a smartphone. The reception unit can also receive voice input in real time. Furthermore, the reception unit can record the voice input and analyze it later. For example, the reception unit receives voice input when the user speaks into the microphone of a smartphone. The analysis unit analyzes the voice input received by the reception unit. For example, the analysis may use, but is not limited to, speech recognition technology or natural language processing technology. For example, the analysis unit converts the voice input into text data using speech recognition technology. The analysis unit can also analyze the meaning of the voice input using natural language processing technology. Furthermore, the analysis unit can understand the context of the voice input and extract information to generate an appropriate response. For example, the analysis unit converts the voice input into text data using speech recognition technology and analyzes that text data using natural language processing technology. The generation unit generates a response based on the voice input analyzed by the analysis unit. The response may include, but is not limited to, voice responses or text responses. For example, the generation unit may use a generation AI to generate an appropriate response to voice input. The generation unit can also use a generation AI to generate accurate answers to user questions. Furthermore, the generation unit may use a generation AI to generate responses that provide relevant information. For example, the generation unit may use a generation AI to generate an appropriate response to voice input and output that response as voice data. The output unit outputs the response generated by the generation unit as voice. For voice output, for example, speech synthesis technology may be used, but is not limited to this example. For example, the output unit may use speech synthesis technology to convert the generated response into voice data and output it through a speaker. The output unit may also output the generated response in high-quality voice. Furthermore, the output unit may output the generated response as voice in real time.For example, the output unit converts the response generated using speech synthesis technology into audio data and outputs it in real time through the speaker. As a result, the voice-only AI conversation service according to this embodiment can analyze the user's voice input, generate an appropriate response, and output it as audio.

[0070] The reception unit accepts voice input. Voice input includes, but is not limited to, natural language and command voices. The reception unit accepts voice input using, for example, the microphone of a smartphone. Specifically, smartphone microphones are highly sensitive and have noise-canceling capabilities to remove ambient noise, enabling clear voice input. The reception unit can also accept voice input in real time. This means that voice data is sent to the system the moment the user speaks, and processing begins immediately. Furthermore, the reception unit can record the voice input and analyze it later. For example, voice input is accepted when the user speaks into the microphone of their smartphone. The recorded voice data is stored on a cloud server and can be accessed later by the analysis unit as needed. This allows for detailed analysis later, even if real-time processing is difficult. In addition, the reception unit can use voice filtering technology to remove background noise and improve voice clarity in order to improve the quality of voice input. This allows the reception unit to accept user voice input with high accuracy and improve the overall performance of the system.

[0071] The analysis unit analyzes the voice input received by the reception unit. Analysis may utilize, but is not limited to, speech recognition technology or natural language processing technology. Specifically, the analysis unit converts voice input into text data using speech recognition technology. Speech recognition technology employs deep learning models to achieve high-precision speech recognition. For example, speech recognition models are trained using large amounts of voice data and corresponding text data, enabling them to handle various accents and speaking styles. The analysis unit can also analyze the meaning of voice input using natural language processing technology. Natural language processing technology uses algorithms to understand context and intent from text data, accurately grasping the user's intent. Furthermore, the analysis unit can extract information to understand the context of the voice input and generate appropriate responses. For example, the analysis unit converts voice input into text data using speech recognition technology and then analyzes that text data using natural language processing technology. This allows the analysis unit to accurately understand the user's intent and provide the necessary foundational information for generating appropriate responses. Additionally, the analysis unit can leverage past conversation history and user profile information to generate more personalized responses. This allows the analysis unit to analyze the user's voice input with high accuracy, improving the overall response accuracy of the system.

[0072] The generation unit generates responses based on the speech input analyzed by the analysis unit. These responses may include, but are not limited to, speech or text responses. Specifically, the generation unit uses generative AI to generate appropriate responses to speech input. The generative AI uses natural language generation techniques to generate appropriate responses to user questions and requests. For example, the generative AI can use a large, pre-trained language model to generate natural conversations based on the user's intent. The generation unit can also use generative AI to generate accurate answers to user questions. For example, the generative AI can search for relevant information in response to a user's question and generate an appropriate answer. Furthermore, the generation unit can use generative AI to generate responses that provide relevant information. For example, the generation unit uses generative AI to generate appropriate responses to speech input and outputs these responses as speech data. The generation unit can use algorithms to generate optimal responses, taking into account the user's intent and context, and provide the user with natural and useful information. Furthermore, the generation unit can evaluate the generated responses and modify them as needed to improve their quality. This allows the generation unit to produce high-quality responses to user voice input, improving the overall user experience of the system.

[0073] The output unit outputs the response generated by the generation unit as audio. This output may involve, but is not limited to, speech synthesis technology. Specifically, the output unit converts the response generated using speech synthesis technology into audio data and outputs it through a speaker. Speech synthesis technology uses algorithms to convert text data into natural-sounding speech, achieving high-quality audio output. For example, speech synthesis technology can adjust the intonation and rhythm of speech to generate natural-sounding utterances. The output unit can also output the generated response in high-quality audio, allowing the user to receive clear and easily understandable audio responses. Furthermore, the output unit can output the generated response in real time. For example, the output unit converts the response generated using speech synthesis technology into audio data and outputs it in real time through a speaker. This allows the user to receive responses immediately, enabling smooth conversation. Additionally, to improve the quality of the audio output, the output unit can use speech filtering technology to remove noise and enhance speech clarity. This allows the output unit to provide users with high-quality audio responses and improve the overall user experience of the system.

[0074] The mode selection unit can adjust the frequency and content of conversations according to the conversation mode selected by the user. For example, if the user selects the "talkative" mode, the mode selection unit will increase the frequency of conversations and provide detailed information. It can also provide standard conversation frequency and content if the user selects the "normal" mode. Furthermore, if the user selects the "less talkative" mode, the mode selection unit can reduce the frequency of conversations and provide concise information. For example, if the user selects the "talkative" mode, the mode selection unit can converse once an hour and provide detailed information. If the user selects the "normal" mode, the mode selection unit can converse once every two hours and provide standard information. If the user selects the "less talkative" mode, the mode selection unit can converse once every three hours and provide concise information. This allows for conversations tailored to the user's preferences.

[0075] The information display unit can display URL information as needed. For example, if a user asks a question like "Tell me about nearby restaurants," the information display unit will display the URL of an appropriate restaurant. It can also display the URL of a relevant news article if a user asks a question like "Tell me about the latest news." Furthermore, if a user asks a question like "Tell me about movies you recommend," the information display unit can display the URL of a movie review site. This allows the system to provide users with useful information.

[0076] The analysis unit can analyze voice input and generate an appropriate response. For example, the analysis unit can convert voice input into text data using speech recognition technology. Furthermore, the analysis unit can analyze the meaning of voice input using natural language processing technology. In addition, the analysis unit can understand the context of the voice input and extract information necessary to generate an appropriate response. For example, the analysis unit converts voice input into text data using speech recognition technology and then analyzes that text data using natural language processing technology. This allows the analysis unit to analyze voice input and generate an appropriate response.

[0077] The generation unit can generate responses using a generation AI. For example, the generation unit can use the generation AI to generate appropriate responses to voice input. Furthermore, the generation unit can use the generation AI to generate accurate answers to user questions. In addition, the generation unit can use the generation AI to generate responses that provide relevant information. For example, the generation unit uses the generation AI to generate appropriate responses to voice input and outputs those responses as voice data. Thus, the generation unit can generate responses using a generation AI.

[0078] The output unit can output the generated response as audio. For example, the output unit can convert the generated response using speech synthesis technology into audio data and output it through a speaker. The output unit can also output the generated response in high-quality audio. Furthermore, the output unit can output the generated response as audio in real time. For example, the output unit can convert the generated response using speech synthesis technology into audio data and output it through a speaker in real time. This allows the output unit to output the generated response as audio.

[0079] The reception system can estimate the user's emotions and adjust the timing of voice input reception based on the estimated emotions. For example, if the user is stressed, the reception system can delay the timing of voice input reception to provide time to relax. Conversely, if the user is relaxed, the reception system can speed up the timing of voice input reception to facilitate smooth conversation. Furthermore, if the user is in a hurry, the reception system can make the timing of voice input reception immediate to enable a quick response. For example, if the user is stressed, the reception system can delay the timing of voice input reception to provide time to relax. If the user is relaxed, the reception system can speed up the timing of voice input reception to facilitate smooth conversation. If the user is in a hurry, the reception system can make the timing of voice input reception immediate to enable a quick response. This allows the timing of voice input reception to be adjusted according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0080] The reception unit can analyze the user's past voice input history and select the optimal reception method. For example, the reception unit can prioritize receiving voice commands that the user has frequently used in the past. Furthermore, the reception unit can predict commands to be used during specific time periods based on the user's past voice input history and accept those commands. In addition, the reception unit can analyze the user's past voice input history and propose the most efficient reception method. For example, the reception unit can prioritize receiving voice commands that the user has frequently used in the past. The reception unit can also predict commands to be used during specific time periods based on the user's past voice input history and accept those commands. The reception unit can also analyze the user's past voice input history and propose the most efficient reception method. This allows the reception unit to analyze the user's past voice input history and select the optimal reception method.

[0081] The reception unit can filter out the user's current ambient noise to remove noise when receiving voice input. For example, if the user is in a noisy environment, the reception unit can filter out ambient noise to remove noise and make the voice input clearer. Also, if the user is in a quiet environment, the reception unit can minimize the filtering of ambient noise to improve the accuracy of the voice input. Furthermore, if the user is on the move when making voice input, the reception unit can filter out wind noise and car noise to remove noise. For example, if the user is in a noisy environment, the reception unit can filter out ambient noise to remove noise and make the voice input clearer. Also, if the user is in a quiet environment, the reception unit can minimize the filtering of ambient noise to improve the accuracy of the voice input. Also, if the user is on the move when making voice input, the reception unit can filter out wind noise and car noise to remove noise. This allows the system to filter out the user's current ambient noise to remove noise when receiving voice input.

[0082] The reception system can estimate the user's emotions and determine the priority of voice input to be received based on the estimated emotions. For example, if the user is nervous, the reception system will prioritize important voice input. If the user is relaxed, the reception system can also prioritize general voice input. Furthermore, if the user is in a hurry, the reception system can also prioritize urgent voice input. For example, if the user is nervous, the reception system will prioritize important voice input. If the user is relaxed, the reception system can also prioritize general voice input. If the user is in a hurry, the reception system can also prioritize urgent voice input. This allows the system to determine the priority of voice input to be received according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0083] The reception system can prioritize receiving voice input based on the user's geographical location. For example, if the user is in a specific location, the reception system will prioritize receiving voice input related to that location. Furthermore, if the user is traveling, the reception system can prioritize receiving voice input related to their travel destination. Additionally, if the user is at home, the reception system can prioritize receiving voice input related to their home. This allows the system to prioritize receiving voice input based on the user's geographical location.

[0084] The reception system can analyze the user's social media activity when receiving voice input and receive relevant voice input. For example, the reception system can prioritize receiving voice input related to topics the user is discussing on social media. It can also prioritize receiving voice input related to accounts the user follows on social media. Furthermore, it can prioritize receiving voice input related to information the user has shared on social media. This allows the system to analyze the user's social media activity and receive relevant voice input.

[0085] The analysis unit can estimate the user's emotions and adjust the voice input analysis method based on the estimated user emotions. For example, if the user is relaxed, the analysis unit can perform a detailed analysis and generate a highly accurate response. Furthermore, if the user is in a hurry, the analysis unit can perform a rapid analysis and generate an immediate response. Additionally, if the user is excited, the analysis unit can perform an emotion-sensitive analysis and generate an appropriate response. This allows the voice input analysis method to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0086] The analysis unit can adjust the level of detail in its analysis of voice input based on the importance of the input content. For example, the analysis unit performs detailed analysis for important questions to generate highly accurate responses. It can also perform standard analysis for general questions to generate quick responses. Furthermore, it can perform rapid analysis for urgent questions to generate immediate responses. This allows the level of detail in the analysis to be adjusted based on the importance of the input content.

[0087] The analysis unit can apply different analysis algorithms depending on the category of the input content when analyzing voice input. For example, for questions about the weather, the analysis unit can apply an analysis algorithm based on weather forecast data. It can also apply an analysis algorithm based on restaurant reviews for questions about restaurants. Furthermore, it can apply an analysis algorithm based on the latest news data for questions about news. This allows for the application of different analysis algorithms depending on the category of the input content.

[0088] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, if the user is nervous, the analysis unit will prioritize analyzing important voice input. It can also prioritize analyzing general voice input if the user is relaxed. Furthermore, if the user is in a hurry, the analysis unit can prioritize analyzing urgent voice input. This allows the analysis priority to be determined according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0089] The analysis unit can determine the priority of analysis based on the timing of input submission when analyzing voice input. For example, the analysis unit can prioritize the analysis of the most recent voice input to generate a quick response. It can also sequentially analyze past voice inputs to generate an appropriate response. Furthermore, the analysis unit can prioritize the analysis of urgent voice inputs to generate an immediate response. This allows the analysis priority to be determined based on the timing of input submission.

[0090] The analysis unit can adjust the order of analysis based on the relevance of the input content when analyzing voice input. For example, the analysis unit can prioritize the analysis of highly relevant voice inputs and generate appropriate responses. It can also postpone the analysis of less relevant voice inputs. Furthermore, the analysis unit can group voice inputs of the same category together to efficiently generate responses. This allows the analysis order to be adjusted based on the relevance of the input content.

[0091] The generation unit can estimate the user's emotions and adjust the response generation method based on the estimated user emotions. For example, if the user is relaxed, the generation unit can generate a detailed response. It can also generate a concise response if the user is in a hurry. Furthermore, if the user is excited, the generation unit can generate an emotion-sensitive response. This allows the response generation method to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The generation unit can adjust the level of detail in the response based on the importance of the input content when generating the response. For example, the generation unit generates a detailed response for important questions. It can also generate a standard response for general questions. Furthermore, it can generate a rapid response for urgent questions. For example, the generation unit generates a detailed response for important questions. It can also generate a standard response for general questions. It can also generate a rapid response for urgent questions. This allows the level of detail in the response to be adjusted based on the importance of the input content.

[0093] The generation unit can apply different generation algorithms depending on the category of the input content when generating responses. For example, for questions about the weather, the generation unit can apply a generation algorithm based on weather forecast data. It can also apply a generation algorithm based on restaurant reviews for questions about restaurants. Furthermore, it can apply a generation algorithm based on the latest news data for questions about news. This allows for the application of different generation algorithms depending on the category of the input content.

[0094] The generation unit can estimate the user's emotions and adjust the length of the response based on the estimated emotions. For example, if the user is relaxed, the generation unit will generate a longer response. It can also generate a shorter response if the user is in a hurry. Furthermore, if the user is excited, the generation unit can generate an emotionally sensitive response. This allows the response length to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The generation unit can determine the priority of responses based on the timing of input submission when generating responses. For example, the generation unit can prioritize responses to the most recent voice input. It can also sequentially generate responses to past voice inputs. Furthermore, the generation unit can prioritize responses to urgent voice inputs. This allows the system to determine the priority of responses based on the timing of input submission.

[0096] The generation unit can adjust the order of responses based on the relevance of the input content during response generation. For example, the generation unit can prioritize generating responses for highly relevant voice inputs. It can also delay generating responses for less relevant voice inputs. Furthermore, the generation unit can generate responses for voice inputs of the same category all at once. For example, the generation unit can prioritize generating responses for highly relevant voice inputs. It can also delay generating responses for less relevant voice inputs. It can also generate responses for voice inputs of the same category all at once. This allows the order of responses to be adjusted based on the relevance of the input content.

[0097] The output unit can estimate the user's emotions and adjust the way it expresses the voice output based on the estimated emotions. For example, if the user is nervous, the output unit will output in a calm voice. It can also output in a cheerful voice if the user is relaxed. Furthermore, if the user is in a hurry, the output unit can output quickly and concisely. This allows the expression of the voice output to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The output unit can adjust the level of detail in the output based on the importance of the response. For example, the output unit will provide detailed audio output for important responses. It can also provide standard audio output for general responses. Furthermore, it can provide rapid audio output for urgent responses. This allows the level of detail in the output to be adjusted based on the importance of the response.

[0099] The output unit can apply different output algorithms depending on the category of the response content when outputting audio. For example, the output unit can apply an output algorithm based on weather forecast data to responses related to the weather. It can also apply an output algorithm based on restaurant reviews to responses related to restaurants. Furthermore, it can apply an output algorithm based on the latest news data to responses related to news. This allows for the application of different output algorithms depending on the category of the response content.

[0100] The output unit can estimate the user's emotions and determine the priority of audio output based on the estimated emotions. For example, if the user is tense, the output unit will prioritize important audio output. It can also prioritize general audio output if the user is relaxed. Furthermore, if the user is in a hurry, the output unit can prioritize urgent audio output. This allows the system to prioritize audio output according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0101] The output unit can determine the priority of output based on the timing of response submission when outputting audio. For example, the output unit prioritizes outputting the most recent response. It can also output past responses sequentially. Furthermore, the output unit can prioritize outputting urgent responses. This allows the output priority to be determined based on the timing of response submission.

[0102] The output unit can adjust the order of output based on the relevance of the response content when outputting audio. For example, the output unit can prioritize outputting highly relevant responses. It can also delay outputting less relevant responses. Furthermore, the output unit can group responses of the same category together for output. This allows the output order to be adjusted based on the relevance of the response content.

[0103] The mode selection unit can estimate the user's emotions and present conversation mode options based on the estimated emotions. For example, if the user is relaxed, the mode selection unit may suggest the "talkative" mode. It can also suggest the "less talkative" mode if the user is focused. Furthermore, it can suggest the "normal" mode if the user is in a normal state. This allows the system to present conversation mode options according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The mode selection unit can suggest the optimal mode by referring to the user's past conversation history when selecting a mode. For example, if the user has frequently used the "talkative" mode in the past, the mode selection unit will suggest that mode. It can also suggest the "less talkative" mode if the user has used that mode in the past. Furthermore, the mode selection unit can predict and suggest the optimal mode based on the user's past conversation history. For example, if the user has frequently used the "talkative" mode in the past, the mode selection unit will suggest that mode. It can also suggest the "less talkative" mode if the user has used that mode in the past. The mode selection unit can also predict and suggest the optimal mode based on the user's past conversation history. This allows the system to suggest the optimal mode by referring to the user's past conversation history.

[0105] The mode selection unit can estimate the user's emotions and determine the priority of mode selection based on the estimated emotions. For example, if the user is relaxed, the mode selection unit will prioritize suggesting the "talkative" mode. If the user is focused, the mode selection unit can also prioritize suggesting the "quiet" mode. Furthermore, if the user is in a normal state, the mode selection unit can also prioritize suggesting the "normal" mode. For example, if the user is relaxed, the mode selection unit will prioritize suggesting the "talkative" mode. If the user is focused, the mode selection unit can also prioritize suggesting the "quiet" mode. If the user is in a normal state, the mode selection unit can also prioritize suggesting the "normal" mode. This allows the system to determine the priority of mode selection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0106] The mode selection unit can suggest the optimal mode based on the user's current environment information when selecting a mode. For example, if the user is in a quiet environment, the mode selection unit can suggest the "talkative" mode. It can also suggest the "less talkative" mode if the user is in a noisy environment. Furthermore, it can suggest the "normal" mode if the user is in a normal environment. This allows the system to suggest the optimal mode based on the user's current environment information.

[0107] The information display unit can estimate the user's emotions and determine the priority of URL information to display based on the estimated emotions. For example, if the user is relaxed, the information display unit will prioritize displaying highly relevant URL information. It can also prioritize displaying important URL information if the user is in a hurry. Furthermore, if the user is excited, the information display unit can prioritize displaying emotionally sensitive URL information. This allows the system to determine the priority of URL information to display according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] The information display unit can display the most relevant information by referencing the user's past search history when displaying URL information. For example, the information display unit prioritizes displaying information that the user has frequently searched for in the past. It can also display highly relevant information based on the user's past search history. Furthermore, the information display unit can analyze the user's past search history and display the most appropriate information. This allows the system to display the most relevant information by referencing the user's past search history.

[0109] The information display unit can estimate the user's emotions and adjust the format of the information displayed based on the estimated emotions. For example, if the user is relaxed, the information display unit can display detailed information. If the user is in a hurry, the information display unit can also display concise information. Furthermore, if the user is excited, the information display unit can also display visually stimulating information. For example, if the user is relaxed, the information display unit can display detailed information. If the user is in a hurry, the information display unit can also display concise information. If the user is excited, the information display unit can also display visually stimulating information. This allows the format of the information displayed to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0110] The information display unit can display highly relevant information based on the user's geographical location when displaying URL information. For example, if the user is in a specific location, the information display unit will display information related to that location. Furthermore, if the user is traveling, the information display unit can display information related to their travel destination. Additionally, if the user is at home, the information display unit can display information related to their home. This allows the display of highly relevant information based on the user's geographical location.

[0111] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0112] The reception system can predict the optimal response when receiving a user's voice input by referring to the user's past conversation history. For example, if a user has frequently asked a particular question in the past, the system will prioritize preparing a response to that question. The reception system can also predict commands to be used at specific times based on the user's past conversation history and process them accordingly. Furthermore, the reception system can analyze the user's past conversation history and suggest the most efficient way to process the call. This allows for efficient processing by predicting the optimal response based on the user's past conversation history.

[0113] The mode selection unit can estimate the user's emotions and present conversation mode options based on those emotions. For example, if the user is relaxed, it can suggest the "talkative" mode. If the user is focused, it can suggest the "less talkative" mode. Furthermore, if the user is in a normal state, it can suggest the "normal" mode. This allows the system to present conversation mode options according to the user's emotions.

[0114] The information display unit can display highly relevant information based on the user's geographical location. For example, if the user is in a specific location, it can display information related to that location. If the user is traveling, it can also display information related to their travel destination. Furthermore, if the user is at home, it can display information related to their home. This allows the display of highly relevant information based on the user's geographical location.

[0115] The analysis unit can apply different analysis algorithms to voice input depending on the category of the input content. For example, a question about the weather can be analyzed using an analysis algorithm based on weather forecast data. Similarly, a question about restaurants can be analyzed using an analysis algorithm based on restaurant reviews. Furthermore, a question about news can be analyzed using an analysis algorithm based on the latest news data. This allows for the application of different analysis algorithms depending on the category of the input content.

[0116] The generation unit can estimate the user's emotions and adjust the response generation method based on the estimated emotions. For example, if the user is relaxed, it can generate a detailed response. If the user is in a hurry, it can generate a concise response. Furthermore, if the user is excited, it can generate an emotionally sensitive response. This allows the response generation method to be adjusted according to the user's emotions.

[0117] The output unit can adjust the level of detail in the output based on the importance of the response. For example, it can provide detailed audio output for important responses, standard audio output for general responses, and rapid audio output for urgent responses. This allows for adjustment of the level of detail in the output based on the importance of the response.

[0118] The reception system can estimate the user's emotions and adjust the timing of voice input reception based on those estimates. For example, if the user is stressed, the voice input reception timing can be delayed to give them time to relax. Conversely, if the user is relaxed, the voice input reception timing can be sped up to facilitate smooth conversation. Furthermore, if the user is in a hurry, the voice input reception timing can be made immediate to enable a quick response. In this way, the timing of voice input reception can be adjusted according to the user's emotions.

[0119] The analysis unit can determine the priority of analysis based on the timing of input submission when analyzing voice input. For example, it can prioritize the analysis of the most recent voice input to generate a quick response. It can also sequentially analyze past voice inputs to generate an appropriate response. Furthermore, it can prioritize the analysis of urgent voice inputs to generate an immediate response. This allows the system to determine the priority of analysis based on the timing of input submission.

[0120] The generation unit can adjust the level of detail in the response based on the importance of the input content during response generation. For example, it can generate a detailed response for important questions, a standard response for general questions, and a rapid response for urgent questions. This allows the level of detail in the response to be adjusted based on the importance of the input content.

[0121] The output unit can estimate the user's emotions and adjust the way it expresses the voice output based on those emotions. For example, if the user is nervous, it can output in a calm voice. If the user is relaxed, it can output in a cheerful voice. Furthermore, if the user is in a hurry, it can output quickly and concisely. In this way, the way it expresses the voice output can be adjusted according to the user's emotions.

[0122] The following briefly describes the processing flow for example form 2.

[0123] Step 1: The reception desk accepts voice input. Voice input can include natural language and command voices. For example, voice input can be accepted using a smartphone's microphone. It is also possible to accept voice input in real time or to record it and analyze it later. Step 2: The analysis unit analyzes the voice input received by the reception unit. Speech recognition technology and natural language processing technology are used for the analysis. For example, speech recognition technology is used to convert the voice input into text data, and that text data is analyzed using natural language processing technology. Furthermore, it is also possible to understand the context of the voice input and extract information to generate an appropriate response. Step 3: The generation unit generates a response based on the voice input analyzed by the analysis unit. The response may include voice responses or text responses. For example, the generation AI can be used to generate an appropriate response to voice input, producing responses that provide accurate answers to the user's questions or relevant information. Step 4: The output unit outputs the response generated by the generation unit as audio. Speech synthesis technology is used for audio output. For example, the response generated using speech synthesis technology can be converted into audio data and output in real time through a speaker.

[0124] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0125] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0126] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0127] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, output unit, mode selection unit, and information display unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 38B of the smart device 14. The analysis unit analyzes the voice input using the specific processing unit 290 of the data processing unit 12. The generation unit generates an appropriate response using the specific processing unit 290 of the data processing unit 12. The output unit outputs the response in voice using the speaker 40B of the smart device 14. The mode selection unit sets a conversation mode according to the user's selection using the control unit 46A of the smart device 14. The information display unit displays URL information using the display 40A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0128] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0129] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0130] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0131] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0132] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0134] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0135] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0136] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0137] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0138] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0139] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0140] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0141] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0142] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0143] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, output unit, mode selection unit, and information display unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 238 of the smart glasses 214. The analysis unit analyzes the voice input using the identification processing unit 290 of the data processing unit 12. The generation unit generates an appropriate response using the identification processing unit 290 of the data processing unit 12. The output unit outputs the response in voice using the speaker 240 of the smart glasses 214. The mode selection unit sets a conversation mode according to the user's selection using the control unit 46A of the smart glasses 214. The information display unit displays URL information using the display of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0144] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0145] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0146] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0147] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0148] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0150] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0151] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0152] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0153] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0154] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0155] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0156] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0157] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0158] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0159] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, output unit, mode selection unit, and information display unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 238 of the headset terminal 314. The analysis unit analyzes the voice input using the specific processing unit 290 of the data processing unit 12. The generation unit generates an appropriate response using the specific processing unit 290 of the data processing unit 12. The output unit outputs the response in voice using the speaker 240 of the headset terminal 314. The mode selection unit sets a conversation mode according to the user's selection using the control unit 46A of the headset terminal 314. The information display unit displays URL information using the display 343 of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0160] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0161] As shown in Figure 7, the 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.

[0162] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0163] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0164] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0165] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0166] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0167] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0168] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0169] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0170] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0171] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0172] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0173] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0174] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0175] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0176] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, output unit, mode selection unit, and information display unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 238 of the robot 414. The analysis unit analyzes the voice input using the specific processing unit 290 of the data processing unit 12. The generation unit generates an appropriate response using the specific processing unit 290 of the data processing unit 12. The output unit outputs the response in voice using the speaker 240 of the robot 414. The mode selection unit sets a conversation mode according to the user's selection using the control unit 46A of the robot 414. The information display unit displays URL information using the display of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0177] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0178] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0179] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0180] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0181] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0182] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0183] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0184] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0185] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0186] 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.

[0187] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0188] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0189] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0190] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0191] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0192] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0193] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0194] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0195] (Note 1) A reception desk that accepts voice input, An analysis unit analyzes the voice input received by the reception unit, A generation unit that generates a response based on the audio input analyzed by the analysis unit, The system includes an output unit that outputs the response generated by the generation unit as sound. A system characterized by the following features. (Note 2) Equipped with a mode selection unit, The frequency and content of conversations are adjusted according to the conversation mode selected by the user. The system described in Appendix 1, characterized by the features described herein. (Note 3) Equipped with an information display unit, Display URL information as needed. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned analysis unit, It analyzes voice input and generates appropriate responses. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is Generative AI generates responses. The system described in Appendix 1, characterized by the features described herein. (Note 6) The output unit is, Output the generated response as audio. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of voice input acceptance based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is The system analyzes the user's past voice input history and selects the optimal reception method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving voice input, the system filters out the user's current ambient noise to remove unwanted sounds. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is It estimates the user's emotions and determines the priority of voice input to accept based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving voice input, the system prioritizes accepting voice input that is highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving voice input, the system analyzes the user's social media activity and accepts relevant voice input. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the voice input analysis method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, When analyzing voice input, the level of detail in the analysis is adjusted based on the importance of the input content. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, When analyzing voice input, different analysis algorithms are applied depending on the category of the input content. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, The system estimates the user's emotions and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, When analyzing voice input, the analysis priority is determined based on when the input content was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, When analyzing voice input, the order of analysis is adjusted based on the relevance of the input content. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is It estimates the user's emotions and adjusts the response generation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is When generating a response, adjust the level of detail in the response based on the importance of the input. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating a response, different generation algorithms are applied depending on the category of the input content. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is It estimates the user's emotions and adjusts the length of the response based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is When generating a response, the priority of the response is determined based on when the input content was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is When generating responses, the order of responses is adjusted based on the relevance of the input content. The system described in Appendix 1, characterized by the features described herein. (Note 25) The output unit is, It estimates the user's emotions and adjusts the way the voice output is expressed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The output unit is, When outputting audio, the level of detail in the output is adjusted based on the importance of the response. The system described in Appendix 1, characterized by the features described herein. (Note 27) The output unit is, When outputting audio, different output algorithms are applied depending on the category of the response. The system described in Appendix 1, characterized by the features described herein. (Note 28) The output unit is, It estimates the user's emotions and determines the priority of voice output based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The output unit is, When outputting audio, the output priority is determined based on when the response was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The output unit is, When outputting audio, the order of output is adjusted based on the relevance of the response content. The system described in Appendix 1, characterized by the features described herein. (Note 31) The mode selection unit is, It estimates the user's emotions and presents chat mode options based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The mode selection unit is, When selecting a mode, the system suggests the optimal mode by referring to the user's past conversation history. The system described in Appendix 2, characterized by the features described herein. (Note 33) The mode selection unit is, It estimates the user's emotions and determines the priority of mode selection based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The mode selection unit is, When selecting a mode, the system will suggest the optimal mode based on the user's current environment information. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned information display unit is It estimates the user's sentiment and determines the priority of URL information to display based on the estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned information display unit is When displaying URL information, the system refers to the user's past search history to display the most relevant information. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned information display unit is It estimates the user's emotions and adjusts the format of the information displayed based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned information display unit is When displaying URL information, the system will display more relevant information based on the user's geographical location. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0196] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that accepts voice input, An analysis unit analyzes the voice input received by the reception unit, A generation unit that generates a response based on the audio input analyzed by the analysis unit, The system includes an output unit that outputs the response generated by the generation unit as sound. A system characterized by the following features.

2. Equipped with a mode selection unit, The frequency and content of conversations are adjusted according to the conversation mode selected by the user. The system according to feature 1.

3. Equipped with an information display unit, Display URL information as needed. The system according to feature 1.

4. The aforementioned analysis unit, Analyzes voice input and generates appropriate responses. The system according to feature 1.

5. The generating unit is Generating responses using AI. The system according to feature 1.

6. The output unit is, Output the generated response as audio. The system according to feature 1.

7. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of voice input acceptance based on the estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is The system analyzes the user's past voice input history and selects the optimal reception method. The system according to feature 1.

9. The aforementioned reception unit is When receiving voice input, the system filters out the user's current ambient noise to remove unwanted sounds. The system according to feature 1.

10. The aforementioned reception unit is It estimates the user's emotions and determines the priority of voice input to accept based on the estimated emotions. The system according to feature 1.

Images