System

Abstract

To provide a system for smoothly performing a voice conversation with a user who speaks in a dialect or who has a thick accent.SOLUTION: A system comprises: a reception part; an analysis part; a generation part; and an output part. The reception part receives voice input of a user. The analysis part analyzes the voice received on the reception part and interprets a dialect or an accent. The generation part generates a reply on the basis of a content analyzed by the analysis part. The output part outputs by voice, the reply generated by the generation part.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to conduct voice dialogue with users who spoke in strong dialects or accents, posing challenges for communication in nursing and welfare facilities.

[0005] The system according to the embodiment aims to smoothly carry out voice dialogue with a user who speaks in a dialect or with a strong accent. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives a voice input from a user. The analysis unit analyzes the voice received by the reception unit and understands dialects or accents. The generation unit generates a response based on the content analyzed by the analysis unit. The output unit outputs the response generated by the generation unit by voice. Effect of the Invention

[0007] The system according to the embodiment can smoothly carry out voice dialogue with a user who speaks in a dialect or with a strong accent. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[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. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

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

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The dialogue system according to the embodiment of the present invention introduces a dialogue robot or terminal for users in nursing care and welfare facilities. This dialogue system realizes the role of understanding dialects and accents and holding dialogues with the generation AI, especially for elderly users living in rural areas. The dialogue robot is responsible for input and output of voice, and solves the problem of conversations with caregivers due to strong accents and dialects. It also supports the problem of insufficient services being provided due to the recent shortage of caregivers. For example, when a user speaks to the dialogue robot, voice input is performed. This voice input is analyzed by the generation AI to understand dialects and accents. For example, the generation AI analyzes regional expressions such as dialects in the Tohoku region and Kansai dialect, and converts them into standard Japanese. This allows the user's words to be accurately understood. Next, the generation AI generates an appropriate response based on the analyzed content. For example, when a user speaks to the dialogue robot asking, "What did you eat today?", the generation AI generates a response such as, "I ate curry rice today." This response is output as voice through the dialogue robot. Furthermore, the generation AI can conduct dialogue according to the user's condition and needs. For example, if a user complains of feeling unwell, the generation AI will ask questions such as "What symptoms do you have?" and encourage appropriate responses. Also, if the user feels lonely, the generation AI will take care of the user's mind through dialogue such as "Has anything fun happened recently?" This mechanism can solve the problem of conversations with caregivers not being established and prevent a decline in the quality of services due to a shortage of caregivers. For example, even if a user speaks in a dialect or with a strong accent, the generation AI can accurately understand and respond appropriately, allowing the user to enjoy the conversation with peace of mind. In addition, the generation AI can grasp the user's condition and respond appropriately, reducing the burden on caregivers and improving the quality of services. As a result, the dialogue system can analyze the user's voice input, understand the dialect or accent, generate an appropriate response and output it as voice, thereby solving the problem of conversations with caregivers not being established.

[0029] The dialogue system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives a voice input from a user. The voice input from the user includes, for example, a dialect or accent, but is not limited to such an example. The reception unit collects voice using, for example, a microphone and converts it into digital data. The reception unit can also convert the voice data into text data using a voice recognition technology. For example, the reception unit analyzes the voice using voice recognition software and saves it as text data. The analysis unit uses a generation AI to analyze the voice received by the reception unit and understand the dialect or accent. The analysis is performed using, for example, a voice recognition algorithm or a machine learning technology, but is not limited to such an example. For example, the analysis unit learns the characteristics of the dialect or accent using a voice database to improve the analysis accuracy. The analysis unit can also estimate the user's emotions and reflect them in the analysis result. For example, the analysis unit estimates the user's emotions using voice tone or facial expression analysis technology and reflects them in the analysis result. The generation unit uses a generation AI to generate an appropriate response based on the contents analyzed by the analysis unit. The response is generated in, for example, a text format or a voice format, but is not limited to such examples. For example, the generation unit generates a response using a text generation AI (for example, LLM). The generation unit can also generate a dialogue according to the user's condition and needs. For example, the generation unit generates an appropriate question when the user complains of poor physical condition. The generation unit can also generate a dialogue to care for the user's mind when the user feels lonely. The output unit outputs the response generated by the generation unit by voice. The voice output is performed using, for example, a speaker, but is not limited to such examples. For example, the output unit converts text data into voice data using a voice synthesis technology and outputs it through a speaker. The output unit can also estimate the user's emotions and adjust the expression method of the voice output. For example, when the user is relaxed, the output unit outputs voice in a gentle voice. As a result, the dialogue system according to the embodiment can analyze the user's voice input, understand the dialect and accent, generate an appropriate response and output it by voice, thereby solving the problem of not being able to have a conversation with a caregiver.Some or all of the above-described processing in the output section may be performed using AI, for example, or may be performed without using AI.

[0030] The reception unit receives the voice input of the user. The voice input of the user includes, for example, dialects and accents, but is not limited to such examples. The reception unit, for example, uses a microphone to collect voice and convert it into digital data. Specifically, a high-sensitivity microphone is used to clearly collect the user's voice while reducing ambient noise. The collected voice data is subjected to noise removal and volume adjustment using digital signal processing technology, and is passed to the next process in an optimal state. The reception unit can also convert the voice data into text data using voice recognition technology. For example, the voice recognition software utilizes a voice recognition model using deep learning to convert the voice data into text data with high accuracy. At this time, a model that has been trained with various voice data in advance is used so that voices with dialects and accents can be accurately recognized. Furthermore, in order to improve the accuracy of voice recognition, it is also possible to accumulate the user's past voice data and speech patterns and build an individually optimized voice recognition model. As a result, the reception unit can accurately and quickly convert the user's voice input into digital data and provide it as an input to the next analysis unit.

[0031] The analysis unit uses the generation AI to analyze the voice received by the reception unit and understand the dialect or accent. The analysis is performed, for example, using a voice recognition algorithm or machine learning technology, but is not limited to such examples. Specifically, the analysis unit uses a voice database to learn the characteristics of the dialect or accent and improve the analysis accuracy. For example, the voice database includes voice samples of dialects and accents from all over the country, and the machine learning model learns the dialect and accent patterns based on this. The analysis unit can also estimate the user's emotions and reflect them in the analysis results. For example, the analysis unit estimates the user's emotions using voice tone and facial expression analysis technology and reflects them in the analysis results. Specifically, the analysis unit analyzes changes in voice tone, speech speed, volume fluctuations, etc. to estimate whether the user is angry, sad, or happy. Furthermore, the analysis unit can refer to the user's past speech history and behavior patterns to perform more accurate emotion estimation. This enables the analysis unit to analyze the user's voice input from multiple angles, understand dialects and accents, and accurately grasp the user's emotions and intentions.

[0032] The generation unit uses a generation AI to generate an appropriate response based on the contents analyzed by the analysis unit. The response is generated in, for example, a text format or a voice format, but is not limited to such examples. Specifically, the generation unit generates a response using a text generation AI (for example, LLM). The LLM has learned a large amount of text data and can generate a natural response according to the context. For example, if a user complains of poor health, the generation unit generates appropriate questions and advice to check the user's condition. The generation unit can also generate a dialogue according to the user's condition and needs. For example, if a user feels lonely, a dialogue that provides mental care can be generated. Specifically, the generation unit takes into account the user's emotional state and generates a response that includes words of encouragement and expressions of empathy. The generation unit can also refer to the user's past dialogue history to provide a consistent dialogue. This allows the generation unit to generate an appropriate response according to the user's needs and smoothly proceed with the dialogue with the user.

[0033] The output unit outputs the response generated by the generation unit as a voice. The voice output is performed, for example, using a speaker, but is not limited to such an example. Specifically, the output unit converts text data into voice data using a voice synthesis technology and outputs it through a speaker. For the voice synthesis technology, a voice synthesis model using deep learning is used to realize natural pronunciation and intonation. As a result, the generated response is output in a natural voice close to a human voice. The output unit can also estimate the user's emotions and adjust the expression method of the voice output. For example, when the user is relaxed, the output unit outputs voice in a calm voice. Conversely, when the user is nervous, the output unit can adjust the voice output to give a sense of security with a calm voice. Furthermore, the output unit can collect user feedback and continuously improve the quality of the voice output. For example, when a user is dissatisfied with the voice output, the voice synthesis model is retrained based on the feedback to realize a more natural and satisfying voice output. As a result, the output unit can provide the user with a high-quality voice response and improve satisfaction with the dialogue.

[0034] The analysis unit can understand dialects and accents by machine learning using a speech database. The speech database includes, for example, regional dialects and accents of a specific language, but is not limited to such examples. The analysis unit learns the characteristics of dialects and accents using the speech database, for example, to improve the analysis accuracy. For example, the analysis unit extracts the characteristics of dialects and accents from the speech database using supervised learning. The analysis unit can also discover dialect and accent patterns from the speech database using unsupervised learning. Furthermore, the analysis unit can adjust the model used to improve the analysis accuracy. For example, the analysis unit analyzes the speech database using a deep learning model to learn the characteristics of dialects and accents. As a result, the accuracy of understanding dialects and accents is improved by machine learning using the speech database. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0035] The generation unit can generate a dialogue based on the user's condition or needs. The user's condition or needs include, but are not limited to, for example, health condition, interests, and urgency. The generation unit generates a dialogue based on, for example, the user's health condition. For example, when the user complains of poor health, the generation unit generates an appropriate question. The generation unit can also generate a dialogue based on the user's interests. For example, when the user wants to talk about a hobby, the generation unit generates a dialogue related to the hobby. The generation unit can also generate a dialogue based on the user's urgency. For example, when the user needs emergency help, the generation unit generates a dialogue that responds quickly. This makes it possible to respond appropriately to the user by generating a dialogue according to the user's condition or needs. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0036] The generating unit can generate a question when the user complains of poor physical condition. Specific symptoms or conditions of poor physical condition include, for example, fever, headache, fatigue, etc., but are not limited to such examples. For example, when the user complains of fever, the generating unit generates a question such as "How high is your fever?" When the user complains of headache, the generating unit can also generate a question such as "Which part hurts?" When the user complains of fatigue, the generating unit can also generate a question such as "How long have you been tired for?" In this way, by generating an appropriate question when the user complains of poor physical condition, a quick response is possible. A part or all of the above-mentioned processing in the generating unit may be performed, for example, using AI, or may be performed without using AI.

[0037] The generation unit can generate a dialogue for providing care when the user feels lonely. Specific definitions and evaluation criteria for loneliness include, for example, self-reporting, results of a psychological test, and the like, but are not limited to such examples. For example, when the user complains of loneliness, the generation unit generates a dialogue such as "Has anything fun happened recently?". In addition, when the user feels lonely, the generation unit can also generate a dialogue such as "Do you want to talk to someone?". Furthermore, when the user feels lonely, the generation unit can also generate a dialogue such as "Is there anything I can help you with?". This makes it possible to care for the user's mind by generating a dialogue for providing care when the user feels lonely. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI.

[0038] The analysis unit can grasp the user's condition by facial expression recognition or data collection using a sensor. Specific techniques and methods of facial expression recognition include, for example, a face recognition algorithm, a sensor to be used, and the like, but are not limited to such examples. The analysis unit, for example, uses a face recognition algorithm to analyze the user's facial expression and grasp the state. The analysis unit can also collect the user's biometric data using a temperature sensor or a heart rate sensor to grasp the state. For example, the analysis unit measures the user's body temperature using a temperature sensor to grasp the state. The analysis unit can also measure the user's heart rate using a heart rate sensor to grasp the state. Furthermore, the analysis unit can adjust the frequency of data collection and grasp the user's state in real time. For example, the analysis unit collects data at regular time intervals and continuously monitors the user's state. This makes it possible to accurately grasp the user's state by facial expression recognition or data collection using a sensor. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0039] The reception unit can analyze the user's past dialogue history and select the optimal voice input method. For example, if the user has used voice input with preference in the past, the reception unit preferentially suggests voice input. In addition, if the user has used text input with preference in the past, the reception unit can also preferentially suggest text input. Furthermore, the reception unit can also suggest a voice input method suitable for a specific time period from the user's past dialogue history. In this way, the optimal voice input method can be selected by analyzing the user's past dialogue history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI.

[0040] The reception unit can perform filtering based on the user's current situation and field of interest at the time of voice input. For example, the reception unit receives only topics related to the user's current situation as voice input. The reception unit can also preferentially receive specific keywords based on the user's field of interest. Furthermore, the reception unit can filter appropriate voice input based on the user's current activity. This makes it possible to receive highly relevant voice input by filtering based on the user's current situation and field of interest. A part or all of the above-mentioned processing in the reception unit may be performed using AI, for example, or may be performed without using AI.

[0041] The reception unit can preferentially receive highly relevant inputs in consideration of the geographical location information of the user when inputting voice. For example, when the user is in a specific area, the reception unit preferentially receives voice inputs related to the area. In addition, when the user is traveling, the reception unit can also preferentially receive voice inputs related to the travel destination. Furthermore, when the user is at home, the reception unit can also preferentially receive voice inputs related to the home. In this way, by considering the geographical location information of the user, highly relevant voice inputs can be preferentially received. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI.

[0042] The reception unit can analyze the user's social media activity and receive related inputs at the time of voice input. The reception unit preferentially receives related voice inputs based on, for example, keywords frequently used by the user on social media. The reception unit can also analyze the user's social media activity and receive related topics as voice inputs. Furthermore, the reception unit can preferentially receive related voice inputs in consideration of the user's friendships on social media. In this way, by analyzing the user's social media activity, it is possible to preferentially receive related voice inputs. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI.

[0043] The analysis unit can adjust the update frequency of the speech database during analysis to reflect the latest dialects and accents. The analysis unit can, for example, periodically update the speech database to add new dialects and accents. The analysis unit can also preferentially add dialects and accents specific to the user's region to the database. Furthermore, the analysis unit can adjust the update frequency of the speech database based on user feedback. In this way, the latest dialects and accents can be reflected by adjusting the update frequency of the speech database. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or without using AI.

[0044] The analysis unit can improve the analysis accuracy by referring to the user's past speech patterns during analysis. The analysis unit, for example, analyzes the user's past speech patterns and grasps the characteristics of dialects and accents. The analysis unit can also adjust the analysis algorithm based on the user's past speech patterns. Furthermore, the analysis unit can also improve the accuracy of the analysis results by referring to the user's past speech patterns. As a result, the analysis accuracy is improved by referring to the user's past speech patterns. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI.

[0045] The analysis unit can improve the analysis accuracy by considering the geographical background of the user during analysis. The analysis unit can improve the analysis accuracy by considering, for example, a dialect or accent specific to the user's region. The analysis unit can also adjust the analysis algorithm based on the geographical background of the user. Furthermore, the analysis unit can also improve the accuracy of the analysis result by referring to the geographical background of the user. As a result, the analysis accuracy is improved by considering the geographical background of the user. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0046] The analysis unit can improve the accuracy of the analysis by referring to the user's related literature during the analysis. The analysis unit, for example, refers to the user's related literature to grasp the characteristics of the dialect or accent. The analysis unit can also adjust the analysis algorithm based on the user's related literature. Furthermore, the analysis unit can also improve the accuracy of the analysis result by referring to the user's related literature. As a result, the analysis accuracy is improved by referring to the user's related literature. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI.

[0047] The generation unit can adjust the level of detail of the response based on the user's state and needs when generating the response. For example, when the user requests detailed information, the generation unit generates a detailed response. Also, when the user requests concise information, the generation unit can generate a concise response. Furthermore, the generation unit can generate a response with an appropriate level of detail according to the user's state. This makes it possible to generate an optimal response for the user by adjusting the level of detail of the response based on the user's state and needs. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0048] The generation unit can apply different response algorithms depending on the user category when generating a response. For example, the generation unit applies a response algorithm for elderly people to generate an easy-to-understand response. The generation unit can also apply a response algorithm that corresponds to a dialect or accent specific to a region. Furthermore, the generation unit can also apply a response algorithm according to the needs of the user to generate an appropriate response. This makes it possible to generate an optimal response according to the user category. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI.

[0049] The generation unit can determine the priority of the response based on the time of the user's speech when generating the response. The generation unit determines the priority of the response based on, for example, the time when the user frequently spoke in the past. The generation unit can also generate an appropriate response preferentially according to the time of the user's speech. Furthermore, the generation unit can also generate an optimal response by taking into account the time of the user's speech. As a result, a more appropriate response can be generated by determining the priority of the response based on the time of the user's speech. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI.

[0050] The generation unit can adjust the order of responses based on the relevance of the user when generating responses. The generation unit preferentially generates highly relevant responses based on, for example, the user's past dialogue history. The generation unit can also preferentially generate highly relevant responses based on the user's current situation. Furthermore, the generation unit can also preferentially generate highly relevant responses based on the user's field of interest. This allows the order of responses to be adjusted based on the relevance of the user, thereby generating more appropriate responses. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0051] The output unit can select the optimal output method by referring to the user's past dialogue history when outputting voice. For example, the output unit preferentially selects a voice output method that the user has used in the past. The output unit can also select a voice output method suitable for a specific time period from the user's past dialogue history. Furthermore, the output unit can also select the optimal voice output method based on the user's past dialogue history. In this way, the optimal voice output method can be selected by referring to the user's past dialogue history. A part or all of the above-mentioned processing in the output unit may be performed, for example, using AI or may be performed without using AI.

[0052] The output unit can customize the means of output based on the current situation of the user when outputting audio. For example, when the user is in a quiet environment, the output unit outputs audio at a low volume. Also, when the user is in a noisy environment, the output unit can also output audio at a high volume. Furthermore, the output unit can customize the optimal audio output means according to the current situation of the user. As a result, by customizing the means of output based on the current situation of the user, more appropriate audio output can be performed. A part or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI.

[0053] The output unit can select the optimal output method in consideration of the geographical location information of the user when outputting audio. For example, when the user is in a specific area, the output unit prioritizes audio output related to the area. In addition, when the user is traveling, the output unit can also prioritize audio output related to the travel destination. Furthermore, when the user is at home, the output unit can also prioritize audio output related to the home. In this way, the optimal audio output method can be selected by considering the geographical location information of the user. A part or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI.

[0054] The output unit can analyze the user's social media activity and suggest a means of output when outputting voice. The output unit prioritizes related voice output based on, for example, keywords frequently used by the user on social media. The output unit can also analyze the user's social media activity and suggest related topics as voice output. Furthermore, the output unit can also prioritize related voice output in consideration of the user's friendships on social media. In this way, by analyzing the user's social media activity, related voice output can be prioritized. A part or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The generation unit can refer to the user's past dialogue history and generate a response based on topics that the user likes or is interested in. For example, if the user liked topics related to sports in the past, the generation unit can provide the latest news and information about sports. Also, if the user enjoys gardening as a hobby, the generation unit can provide gardening advice according to the season. Furthermore, the generation unit can select a topic suitable for a specific time period from the user's past dialogue history and generate a response. This makes it possible to provide a more personalized dialogue based on the user's past dialogue history.

[0057] The generating unit can monitor the user's health condition and provide health advice and information. For example, if the user measures his / her blood pressure regularly, the generating unit can provide appropriate advice based on the fluctuations in blood pressure. In addition, if the user complains of lack of exercise, the generating unit can also suggest simple exercises and stretching exercises. Furthermore, the generating unit can provide advice on nutritional balance based on the user's diet. This makes it possible to provide appropriate advice and information according to the user's health condition.

[0058] The analysis unit can analyze background sounds and environmental sounds in response to the user's voice input and estimate the user's current environment. For example, if the user's voice input includes birds chirping, the analysis unit can estimate that the user is outdoors and adjust the response. If the user's voice input includes the sound of a car, the analysis unit can estimate that the user is moving and can simplify the response. Furthermore, if the user's voice input includes an echo, the analysis unit can estimate that the user is in a large space and adjust the volume of the response. This can provide a more appropriate dialogue based on the user's current environment.

[0059] The generator can analyze the user's past dialogue history and generate a response based on the user's preferred dialogue style. For example, if the user has preferred humor in the past, the generator can generate a humorous response. If the user has preferred serious dialogue in the past, the generator can generate a response in a serious tone. Furthermore, if the user has preferred short dialogues in the past, the generator can generate a concise response. This allows for a more personalized dialogue to be provided based on the user's past dialogue history.

[0060] The generator can generate a response based on the user's current activity. For example, if the user is cooking, the generator can provide cooking advice and recipes. If the user is exercising, the generator can provide encouraging words about the exercise and suggestions for stretching. If the user is reading, the generator can provide impressions about the book and recommended books. This makes it possible to provide a more appropriate dialogue based on the user's current activity.

[0061] The process flow of the first embodiment will be briefly described below.

[0062] Step 1: The reception unit receives a voice input from a user. The user's voice input may include, but is not limited to, a dialect or accent. The reception unit may collect the voice using, for example, a microphone and convert it into digital data. The reception unit may also convert the voice data into text data using voice recognition technology. For example, the reception unit may analyze the voice using voice recognition software and save it as text data. Step 2: The analysis unit uses the generation AI to analyze the voice received by the reception unit and understand the dialect or accent. The analysis is performed, for example, using a voice recognition algorithm or machine learning technology, but is not limited to such examples. For example, the analysis unit uses a voice database to learn the characteristics of the dialect or accent and improve the analysis accuracy. The analysis unit can also estimate the user's emotions and reflect them in the analysis results. For example, the analysis unit estimates the user's emotions using voice tone and facial expression analysis technology and reflects them in the analysis results. Step 3: The generation unit uses a generation AI to generate an appropriate response based on the content analyzed by the analysis unit. The response is generated in, for example, text format or voice format, but is not limited to such examples. For example, the generation unit generates a response using a text generation AI (for example, LLM). The generation unit can also generate a dialogue according to the user's condition and needs. For example, when the user complains of poor health, the generation unit generates an appropriate question. When the user feels lonely, the generation unit can also generate a dialogue to provide mental care. Step 4: The output unit outputs the response generated by the generation unit by voice. The voice output is performed, for example, using a speaker, but is not limited to such an example. For example, the output unit converts text data into voice data using a voice synthesis technology and outputs it through the speaker. The output unit can also estimate the user's emotions and adjust the expression method of the voice output. For example, when the user is relaxed, the output unit outputs the voice in a gentle voice.

[0063] (Example 2) The dialogue system according to the embodiment of the present invention introduces a dialogue robot or terminal for users in nursing care and welfare facilities. This dialogue system realizes the role of understanding dialects and accents and holding dialogues with the generation AI, especially for elderly users living in rural areas. The dialogue robot is responsible for input and output of voice, and solves the problem of conversations with caregivers due to strong accents and dialects. It also supports the problem of insufficient services being provided due to the recent shortage of caregivers. For example, when a user speaks to the dialogue robot, voice input is performed. This voice input is analyzed by the generation AI to understand dialects and accents. For example, the generation AI analyzes regional expressions such as dialects in the Tohoku region and Kansai dialect, and converts them into standard Japanese. This allows the user's words to be accurately understood. Next, the generation AI generates an appropriate response based on the analyzed content. For example, when a user speaks to the dialogue robot asking, "What did you eat today?", the generation AI generates a response such as, "I ate curry rice today." This response is output as voice through the dialogue robot. Furthermore, the generation AI can conduct dialogue according to the user's condition and needs. For example, if a user complains of feeling unwell, the generation AI will ask questions such as "What symptoms do you have?" and encourage appropriate responses. Also, if the user feels lonely, the generation AI will take care of the user's mind through dialogue such as "Has anything fun happened recently?" This mechanism can solve the problem of conversations with caregivers not being established and prevent a decline in the quality of services due to a shortage of caregivers. For example, even if a user speaks in a dialect or with a strong accent, the generation AI can accurately understand and respond appropriately, allowing the user to enjoy the conversation with peace of mind. In addition, the generation AI can grasp the user's condition and respond appropriately, reducing the burden on caregivers and improving the quality of services. As a result, the dialogue system can analyze the user's voice input, understand the dialect or accent, generate an appropriate response and output it as voice, thereby solving the problem of conversations with caregivers not being established.

[0064] The dialogue system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives a voice input from a user. The voice input from the user includes, for example, a dialect or accent, but is not limited to such an example. The reception unit collects voice using, for example, a microphone and converts it into digital data. The reception unit can also convert the voice data into text data using a voice recognition technology. For example, the reception unit analyzes the voice using voice recognition software and saves it as text data. The analysis unit uses a generation AI to analyze the voice received by the reception unit and understand the dialect or accent. The analysis is performed using, for example, a voice recognition algorithm or a machine learning technology, but is not limited to such an example. For example, the analysis unit learns the characteristics of the dialect or accent using a voice database to improve the analysis accuracy. The analysis unit can also estimate the user's emotions and reflect them in the analysis result. For example, the analysis unit estimates the user's emotions using voice tone or facial expression analysis technology and reflects them in the analysis result. The generation unit uses a generation AI to generate an appropriate response based on the contents analyzed by the analysis unit. The response is generated in, for example, a text format or a voice format, but is not limited to such examples. For example, the generation unit generates a response using a text generation AI (for example, LLM). The generation unit can also generate a dialogue according to the user's condition and needs. For example, the generation unit generates an appropriate question when the user complains of poor physical condition. The generation unit can also generate a dialogue to care for the user's mind when the user feels lonely. The output unit outputs the response generated by the generation unit by voice. The voice output is performed using, for example, a speaker, but is not limited to such examples. For example, the output unit converts text data into voice data using a voice synthesis technology and outputs it through a speaker. The output unit can also estimate the user's emotions and adjust the expression method of the voice output. For example, when the user is relaxed, the output unit outputs voice in a gentle voice. As a result, the dialogue system according to the embodiment can analyze the user's voice input, understand the dialect and accent, generate an appropriate response and output it by voice, thereby solving the problem of not being able to have a conversation with a caregiver.Some or all of the above-described processing in the output section may be performed using AI, for example, or may be performed without using AI.

[0065] The reception unit receives the voice input of the user. The voice input of the user includes, for example, dialects and accents, but is not limited to such examples. The reception unit, for example, uses a microphone to collect voice and convert it into digital data. Specifically, a high-sensitivity microphone is used to clearly collect the user's voice while reducing ambient noise. The collected voice data is subjected to noise removal and volume adjustment using digital signal processing technology, and is passed to the next process in an optimal state. The reception unit can also convert the voice data into text data using voice recognition technology. For example, the voice recognition software utilizes a voice recognition model using deep learning to convert the voice data into text data with high accuracy. At this time, a model that has been trained with various voice data in advance is used so that voices with dialects and accents can be accurately recognized. Furthermore, in order to improve the accuracy of voice recognition, it is also possible to accumulate the user's past voice data and speech patterns and build an individually optimized voice recognition model. As a result, the reception unit can accurately and quickly convert the user's voice input into digital data and provide it as an input to the next analysis unit.

[0066] The analysis unit uses the generation AI to analyze the voice received by the reception unit and understand the dialect or accent. The analysis is performed, for example, using a voice recognition algorithm or machine learning technology, but is not limited to such examples. Specifically, the analysis unit uses a voice database to learn the characteristics of the dialect or accent and improve the analysis accuracy. For example, the voice database includes voice samples of dialects and accents from all over the country, and the machine learning model learns the dialect and accent patterns based on this. The analysis unit can also estimate the user's emotions and reflect them in the analysis results. For example, the analysis unit estimates the user's emotions using voice tone and facial expression analysis technology and reflects them in the analysis results. Specifically, the analysis unit analyzes changes in voice tone, speech speed, volume fluctuations, etc. to estimate whether the user is angry, sad, or happy. Furthermore, the analysis unit can refer to the user's past speech history and behavior patterns to perform more accurate emotion estimation. This enables the analysis unit to analyze the user's voice input from multiple angles, understand dialects and accents, and accurately grasp the user's emotions and intentions.

[0067] The generation unit uses a generation AI to generate an appropriate response based on the contents analyzed by the analysis unit. The response is generated in, for example, a text format or a voice format, but is not limited to such examples. Specifically, the generation unit generates a response using a text generation AI (for example, LLM). The LLM has learned a large amount of text data and can generate a natural response according to the context. For example, if a user complains of poor health, the generation unit generates appropriate questions and advice to check the user's condition. The generation unit can also generate a dialogue according to the user's condition and needs. For example, if a user feels lonely, a dialogue that provides mental care can be generated. Specifically, the generation unit takes into account the user's emotional state and generates a response that includes words of encouragement and expressions of empathy. The generation unit can also refer to the user's past dialogue history to provide a consistent dialogue. This allows the generation unit to generate an appropriate response according to the user's needs and smoothly proceed with the dialogue with the user.

[0068] The output unit outputs the response generated by the generation unit as a voice. The voice output is performed, for example, using a speaker, but is not limited to such an example. Specifically, the output unit converts text data into voice data using a voice synthesis technology and outputs it through a speaker. For the voice synthesis technology, a voice synthesis model using deep learning is used to realize natural pronunciation and intonation. As a result, the generated response is output in a natural voice close to a human voice. The output unit can also estimate the user's emotions and adjust the expression method of the voice output. For example, when the user is relaxed, the output unit outputs voice in a calm voice. Conversely, when the user is nervous, the output unit can adjust the voice output to give a sense of security with a calm voice. Furthermore, the output unit can collect user feedback and continuously improve the quality of the voice output. For example, when a user is dissatisfied with the voice output, the voice synthesis model is retrained based on the feedback to realize a more natural and satisfying voice output. As a result, the output unit can provide the user with a high-quality voice response and improve satisfaction with the dialogue.

[0069] The analysis unit can understand dialects and accents by machine learning using a speech database. The speech database includes, for example, regional dialects and accents of a specific language, but is not limited to such examples. The analysis unit learns the characteristics of dialects and accents using the speech database, for example, to improve the analysis accuracy. For example, the analysis unit extracts the characteristics of dialects and accents from the speech database using supervised learning. The analysis unit can also discover dialect and accent patterns from the speech database using unsupervised learning. Furthermore, the analysis unit can adjust the model used to improve the analysis accuracy. For example, the analysis unit analyzes the speech database using a deep learning model to learn the characteristics of dialects and accents. As a result, the accuracy of understanding dialects and accents is improved by machine learning using the speech database. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0070] The generation unit can generate a dialogue based on the user's condition or needs. The user's condition or needs include, but are not limited to, for example, health condition, interests, and urgency. The generation unit generates a dialogue based on, for example, the user's health condition. For example, when the user complains of poor health, the generation unit generates an appropriate question. The generation unit can also generate a dialogue based on the user's interests. For example, when the user wants to talk about a hobby, the generation unit generates a dialogue related to the hobby. The generation unit can also generate a dialogue based on the user's urgency. For example, when the user needs emergency help, the generation unit generates a dialogue that responds quickly. This makes it possible to respond appropriately to the user by generating a dialogue according to the user's condition or needs. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0071] The generating unit can generate a question when the user complains of poor physical condition. Specific symptoms or conditions of poor physical condition include, for example, fever, headache, fatigue, etc., but are not limited to such examples. For example, when the user complains of fever, the generating unit generates a question such as "How high is your fever?" When the user complains of headache, the generating unit can also generate a question such as "Which part hurts?" When the user complains of fatigue, the generating unit can also generate a question such as "How long have you been tired for?" In this way, by generating an appropriate question when the user complains of poor physical condition, a quick response is possible. A part or all of the above-mentioned processing in the generating unit may be performed, for example, using AI, or may be performed without using AI.

[0072] The generation unit can generate a dialogue for providing care when the user feels lonely. Specific definitions and evaluation criteria for loneliness include, for example, self-reporting, results of a psychological test, and the like, but are not limited to such examples. For example, when the user complains of loneliness, the generation unit generates a dialogue such as "Has anything fun happened recently?". In addition, when the user feels lonely, the generation unit can also generate a dialogue such as "Do you want to talk to someone?". Furthermore, when the user feels lonely, the generation unit can also generate a dialogue such as "Is there anything I can help you with?". This makes it possible to care for the user's mind by generating a dialogue for providing care when the user feels lonely. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI.

[0073] The analysis unit can grasp the user's condition by facial expression recognition or data collection using a sensor. Specific techniques and methods of facial expression recognition include, for example, a face recognition algorithm, a sensor to be used, and the like, but are not limited to such examples. The analysis unit, for example, uses a face recognition algorithm to analyze the user's facial expression and grasp the state. The analysis unit can also collect the user's biometric data using a temperature sensor or a heart rate sensor to grasp the state. For example, the analysis unit measures the user's body temperature using a temperature sensor to grasp the state. The analysis unit can also measure the user's heart rate using a heart rate sensor to grasp the state. Furthermore, the analysis unit can adjust the frequency of data collection and grasp the user's state in real time. For example, the analysis unit collects data at regular time intervals and continuously monitors the user's state. This makes it possible to accurately grasp the user's state by facial expression recognition or data collection using a sensor. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0074] The reception unit can estimate the user's emotion and adjust the timing of receiving the voice input based on the estimated emotion of the user. For example, when the user is excited, the reception unit delays the timing of receiving the voice input and waits until the user calms down. Also, when the user is relaxed, the reception unit can advance the timing of receiving the voice input to promote smooth dialogue. Furthermore, when the user feels anxious, the reception unit can adjust the timing of receiving the voice input to give the user a sense of security. In this way, by adjusting the timing of receiving the voice input based on the user's emotion, the voice input can be received at a more appropriate timing. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI.

[0075] The reception unit can analyze the user's past dialogue history and select the optimal voice input method. For example, if the user has used voice input with preference in the past, the reception unit preferentially suggests voice input. In addition, if the user has used text input with preference in the past, the reception unit can also preferentially suggest text input. Furthermore, the reception unit can also suggest a voice input method suitable for a specific time period from the user's past dialogue history. In this way, the optimal voice input method can be selected by analyzing the user's past dialogue history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI.

[0076] The reception unit can perform filtering based on the user's current situation and field of interest at the time of voice input. For example, the reception unit receives only topics related to the user's current situation as voice input. The reception unit can also preferentially receive specific keywords based on the user's field of interest. Furthermore, the reception unit can filter appropriate voice input based on the user's current activity. This makes it possible to receive highly relevant voice input by filtering based on the user's current situation and field of interest. A part or all of the above-mentioned processing in the reception unit may be performed using AI, for example, or may be performed without using AI.

[0077] The reception unit can estimate the user's emotion and determine the priority of the voice input to be received based on the estimated user's emotion. For example, when the user is excited, the reception unit preferentially receives a voice input with high urgency. In addition, when the user is relaxed, the reception unit can also preferentially receive a normal voice input. Furthermore, when the user is anxious, the reception unit can also preferentially receive a voice input that gives a sense of security. In this way, by determining the priority of the voice input based on the user's emotion, it is possible to preferentially receive a voice input with high urgency. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI.

[0078] The reception unit can preferentially receive highly relevant inputs in consideration of the geographical location information of the user when inputting voice. For example, when the user is in a specific area, the reception unit preferentially receives voice inputs related to the area. In addition, when the user is traveling, the reception unit can also preferentially receive voice inputs related to the travel destination. Furthermore, when the user is at home, the reception unit can also preferentially receive voice inputs related to the home. In this way, by considering the geographical location information of the user, highly relevant voice inputs can be preferentially received. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI.

[0079] The reception unit can analyze the user's social media activity and receive related inputs at the time of voice input. The reception unit preferentially receives related voice inputs based on, for example, keywords frequently used by the user on social media. The reception unit can also analyze the user's social media activity and receive related topics as voice inputs. Furthermore, the reception unit can preferentially receive related voice inputs in consideration of the user's friendships on social media. In this way, by analyzing the user's social media activity, it is possible to preferentially receive related voice inputs. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI.

[0080] The analysis unit can estimate the user's emotion and adjust the dialect or accent analysis method based on the estimated user's emotion. For example, when the user is excited, the analysis unit carefully analyzes the dialect or accent to avoid misunderstanding. The analysis unit can also apply a normal analysis method when the user is relaxed. Furthermore, when the user is feeling anxious, the analysis unit can check the analysis result and provide a sense of security. This improves the analysis accuracy by adjusting the dialect or accent analysis method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI.

[0081] The analysis unit can adjust the update frequency of the speech database during analysis to reflect the latest dialects and accents. The analysis unit can, for example, periodically update the speech database to add new dialects and accents. The analysis unit can also preferentially add dialects and accents specific to the user's region to the database. Furthermore, the analysis unit can adjust the update frequency of the speech database based on user feedback. In this way, the latest dialects and accents can be reflected by adjusting the update frequency of the speech database. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or without using AI.

[0082] The analysis unit can improve the analysis accuracy by referring to the user's past speech patterns during analysis. The analysis unit, for example, analyzes the user's past speech patterns and grasps the characteristics of dialects and accents. The analysis unit can also adjust the analysis algorithm based on the user's past speech patterns. Furthermore, the analysis unit can also improve the accuracy of the analysis results by referring to the user's past speech patterns. As a result, the analysis accuracy is improved by referring to the user's past speech patterns. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI.

[0083] The analysis unit can estimate the user's emotion and adjust the display method of the analysis result based on the estimated user's emotion. For example, when the user is nervous, the analysis unit provides a simple and highly visible display method. Furthermore, when the user is relaxed, the analysis unit can also provide a display method including detailed information. Furthermore, when the user is in a hurry, the analysis unit can also provide a display method that focuses on the main points. This allows for a display that is easy for the user to see by adjusting the display method of the analysis result based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI.

[0084] The analysis unit can improve the analysis accuracy by considering the geographical background of the user during analysis. The analysis unit can improve the analysis accuracy by considering, for example, a dialect or accent specific to the user's region. The analysis unit can also adjust the analysis algorithm based on the geographical background of the user. Furthermore, the analysis unit can also improve the accuracy of the analysis result by referring to the geographical background of the user. As a result, the analysis accuracy is improved by considering the geographical background of the user. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0085] The analysis unit can improve the accuracy of the analysis by referring to the user's related literature during the analysis. The analysis unit, for example, refers to the user's related literature to grasp the characteristics of the dialect or accent. The analysis unit can also adjust the analysis algorithm based on the user's related literature. Furthermore, the analysis unit can also improve the accuracy of the analysis result by referring to the user's related literature. As a result, the analysis accuracy is improved by referring to the user's related literature. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI.

[0086] The generation unit can estimate the user's emotion and adjust the way of expressing the response based on the estimated emotion of the user. For example, when the user is relaxed, the generation unit generates a response using a calm expression method. In addition, when the user is excited, the generation unit can also generate a response using a lively expression method. Furthermore, when the user is anxious, the generation unit can also generate a response using an expression method that gives a sense of security. In this way, by adjusting the way of expressing the response based on the emotion of the user, a more appropriate response can be generated. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI.

[0087] The generation unit can adjust the level of detail of the response based on the user's state and needs when generating the response. For example, when the user requests detailed information, the generation unit generates a detailed response. Also, when the user requests concise information, the generation unit can generate a concise response. Furthermore, the generation unit can generate a response with an appropriate level of detail according to the user's state. This makes it possible to generate an optimal response for the user by adjusting the level of detail of the response based on the user's state and needs. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0088] The generation unit can apply different response algorithms depending on the user category when generating a response. For example, the generation unit applies a response algorithm for elderly people to generate an easy-to-understand response. The generation unit can also apply a response algorithm that corresponds to a dialect or accent specific to a region. Furthermore, the generation unit can also apply a response algorithm according to the needs of the user to generate an appropriate response. This makes it possible to generate an optimal response according to the user category. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI.

[0089] The generation unit can estimate the user's emotion and adjust the length of the response based on the estimated user's emotion. For example, when the user is in a hurry, the generation unit generates a short and to the point response. Also, when the user is relaxed, the generation unit can generate a longer response including a detailed explanation. Furthermore, when the user is excited, the generation unit can generate a response with a visually stimulating effect. This allows a more appropriate response to be generated by adjusting the length of the response based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI.

[0090] The generation unit can determine the priority of the response based on the time of the user's speech when generating the response. The generation unit determines the priority of the response based on, for example, the time when the user frequently spoke in the past. The generation unit can also generate an appropriate response preferentially according to the time of the user's speech. Furthermore, the generation unit can also generate an optimal response by taking into account the time of the user's speech. As a result, a more appropriate response can be generated by determining the priority of the response based on the time of the user's speech. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI.

[0091] The generation unit can adjust the order of responses based on the relevance of the user when generating responses. The generation unit preferentially generates highly relevant responses based on, for example, the user's past dialogue history. The generation unit can also preferentially generate highly relevant responses based on the user's current situation. Furthermore, the generation unit can also preferentially generate highly relevant responses based on the user's field of interest. This allows the order of responses to be adjusted based on the relevance of the user, thereby generating more appropriate responses. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0092] The output unit can estimate the user's emotion and adjust the expression method of the voice output based on the estimated user's emotion. For example, when the user is relaxed, the output unit performs voice output in a calm voice. Furthermore, when the user is excited, the output unit can also perform voice output in a cheerful voice. Furthermore, when the user is anxious, the output unit can also perform voice output in a voice that gives a sense of security. In this way, by adjusting the expression method of the voice output based on the user's emotion, more appropriate voice output can be performed. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the output unit may be performed using, for example, an AI, or may be performed without using an AI.

[0093] The output unit can select the optimal output method by referring to the user's past dialogue history when outputting voice. For example, the output unit preferentially selects a voice output method that the user has used in the past. The output unit can also select a voice output method suitable for a specific time period from the user's past dialogue history. Furthermore, the output unit can also select the optimal voice output method based on the user's past dialogue history. In this way, the optimal voice output method can be selected by referring to the user's past dialogue history. A part or all of the above-mentioned processing in the output unit may be performed, for example, using AI or may be performed without using AI.

[0094] The output unit can customize the means of output based on the current situation of the user when outputting audio. For example, when the user is in a quiet environment, the output unit outputs audio at a low volume. Also, when the user is in a noisy environment, the output unit can also output audio at a high volume. Furthermore, the output unit can customize the optimal audio output means according to the current situation of the user. As a result, by customizing the means of output based on the current situation of the user, more appropriate audio output can be performed. A part or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI.

[0095] The output unit can estimate the user's emotion and determine the priority of the voice output based on the estimated user's emotion. For example, when the user is excited, the output unit prioritizes the voice output with high urgency. In addition, when the user is relaxed, the output unit can also prioritize normal voice output. Furthermore, when the user is anxious, the output unit can also prioritize voice output that gives a sense of security. In this way, by determining the priority of the voice output based on the user's emotion, it is possible to prioritize the voice output with high urgency. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the output unit may be performed using, for example, an AI, or may be performed without using an AI.

[0096] The output unit can select the optimal output method in consideration of the geographical location information of the user when outputting audio. For example, when the user is in a specific area, the output unit prioritizes audio output related to the area. In addition, when the user is traveling, the output unit can also prioritize audio output related to the travel destination. Furthermore, when the user is at home, the output unit can also prioritize audio output related to the home. In this way, the optimal audio output method can be selected by considering the geographical location information of the user. A part or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI.

[0097] The output unit can analyze the user's social media activity and suggest a means of output when outputting voice. The output unit prioritizes related voice output based on, for example, keywords frequently used by the user on social media. The output unit can also analyze the user's social media activity and suggest related topics as voice output. Furthermore, the output unit can also prioritize related voice output in consideration of the user's friendships on social media. In this way, by analyzing the user's social media activity, related voice output can be prioritized. A part or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] The analysis unit can analyze the tone and speed of the user's voice input to estimate the user's level of tension or relaxation. For example, if the user's voice is fast and has a high tone, the analysis unit can estimate that the user is tense and respond calmly. Also, if the user's voice is slow and has a low tone, the analysis unit can estimate that the user is relaxed and respond energetically. Furthermore, the analysis unit can monitor changes in the user's voice in real time and adjust responses at appropriate times. This makes it possible to provide a more appropriate dialogue based on the user's voice tone and speed.

[0100] The generation unit can refer to the user's past dialogue history and generate a response based on topics that the user likes or is interested in. For example, if the user liked topics related to sports in the past, the generation unit can provide the latest news and information about sports. Also, if the user enjoys gardening as a hobby, the generation unit can provide gardening advice according to the season. Furthermore, the generation unit can select a topic suitable for a specific time period from the user's past dialogue history and generate a response. This makes it possible to provide a more personalized dialogue based on the user's past dialogue history.

[0101] The generating unit can monitor the user's health condition and provide health advice and information. For example, if the user measures his / her blood pressure regularly, the generating unit can provide appropriate advice based on the fluctuations in blood pressure. In addition, if the user complains of lack of exercise, the generating unit can also suggest simple exercises and stretching exercises. Furthermore, the generating unit can provide advice on nutritional balance based on the user's diet. This makes it possible to provide appropriate advice and information according to the user's health condition.

[0102] The analysis unit can analyze background sounds and environmental sounds in response to the user's voice input and estimate the user's current environment. For example, if the user's voice input includes birds chirping, the analysis unit can estimate that the user is outdoors and adjust the response. If the user's voice input includes the sound of a car, the analysis unit can estimate that the user is moving and can simplify the response. Furthermore, if the user's voice input includes an echo, the analysis unit can estimate that the user is in a large space and adjust the volume of the response. This can provide a more appropriate dialogue based on the user's current environment.

[0103] The generation unit can estimate the user's emotions and adjust the tone and content of the dialogue based on the estimated emotions. For example, if the user is sad, the generation unit can provide words of encouragement or comfort. If the user is happy, the generation unit can also provide words of sympathy or congratulations. Furthermore, if the user is angry, the generation unit can conduct the dialogue in a calm tone to calm the user's feelings. This makes it possible to provide a more appropriate dialogue based on the user's emotions.

[0104] The analysis unit can analyze the strength and rhythm of the user's voice input and infer the user's emotions and intentions. For example, if the user's voice is strong and rhythmic, the analysis unit can infer that the user is excited and respond energetically. Also, if the user's voice is weak and slow, the analysis unit can infer that the user is tired and respond calmly. Furthermore, the analysis unit can monitor changes in the user's voice in real time and adjust responses at appropriate times. This makes it possible to provide a more appropriate dialogue based on the strength and rhythm of the user's voice.

[0105] The generator can analyze the user's past dialogue history and generate a response based on the user's preferred dialogue style. For example, if the user has preferred humor in the past, the generator can generate a humorous response. If the user has preferred serious dialogue in the past, the generator can generate a response in a serious tone. Furthermore, if the user has preferred short dialogues in the past, the generator can generate a concise response. This allows for a more personalized dialogue to be provided based on the user's past dialogue history.

[0106] The analysis unit can analyze the pitch and tempo of the user's voice input and infer the user's emotions and intentions. For example, if the user's voice has a high pitch and a fast tempo, the analysis unit can infer that the user is excited and respond energetically. Also, if the user's voice has a low pitch and a slow tempo, the analysis unit can infer that the user is relaxed and respond calmly. Furthermore, the analysis unit can monitor changes in the user's voice in real time and adjust responses at appropriate times. This makes it possible to provide a more appropriate dialogue based on the pitch and tempo of the user's voice.

[0107] The generator can generate a response based on the user's current activity. For example, if the user is cooking, the generator can provide cooking advice and recipes. If the user is exercising, the generator can provide encouraging words about the exercise and suggestions for stretching. If the user is reading, the generator can provide impressions about the book and recommended books. This makes it possible to provide a more appropriate dialogue based on the user's current activity.

[0108] The analysis unit can analyze the intonation and pauses of the user's voice input and infer the user's emotions and intentions. For example, if the user's voice has intonation and the pauses are short, the analysis unit can infer that the user is excited and respond energetically. Also, if the user's voice has no intonation and the pauses are long, the analysis unit can infer that the user is tired and respond calmly. Furthermore, the analysis unit can monitor changes in the user's voice in real time and adjust the response at an appropriate time. This makes it possible to provide a more appropriate dialogue based on the intonation and pauses of the user's voice.

[0109] The process flow of the second embodiment will be briefly described below.

[0110] Step 1: The reception unit receives a voice input from a user. The user's voice input may include, but is not limited to, a dialect or accent. The reception unit may collect the voice using, for example, a microphone and convert it into digital data. The reception unit may also convert the voice data into text data using voice recognition technology. For example, the reception unit may analyze the voice using voice recognition software and save it as text data. Step 2: The analysis unit uses the generation AI to analyze the voice received by the reception unit and understand the dialect or accent. The analysis is performed, for example, using a voice recognition algorithm or machine learning technology, but is not limited to such examples. For example, the analysis unit uses a voice database to learn the characteristics of the dialect or accent and improve the analysis accuracy. The analysis unit can also estimate the user's emotions and reflect them in the analysis results. For example, the analysis unit estimates the user's emotions using voice tone and facial expression analysis technology and reflects them in the analysis results. Step 3: The generation unit uses a generation AI to generate an appropriate response based on the content analyzed by the analysis unit. The response is generated in, for example, text format or voice format, but is not limited to such examples. For example, the generation unit generates a response using a text generation AI (for example, LLM). The generation unit can also generate a dialogue according to the user's condition and needs. For example, when the user complains of poor health, the generation unit generates an appropriate question. When the user feels lonely, the generation unit can also generate a dialogue to provide mental care. Step 4: The output unit outputs the response generated by the generation unit by voice. The voice output is performed, for example, using a speaker, but is not limited to such an example. For example, the output unit converts text data into voice data using a voice synthesis technology and outputs it through the speaker. The output unit can also estimate the user's emotions and adjust the expression method of the voice output. For example, when the user is relaxed, the output unit outputs the voice in a gentle voice.

[0111] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0113] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and output unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit collects voice using the microphone 38B of the smart device 14 and converts it into digital data by the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the voice using a generation AI to understand dialects and accents. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an appropriate response based on the analyzed content. The output unit performs voice output using, for example, the speaker 40B of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0121] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0122] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0123] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0125] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0126] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0127] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0128] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0129] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and output unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit collects voice using the microphone 238 of the smart glasses 214 and converts it into digital data by the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the voice using a generation AI to understand dialects and accents. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an appropriate response based on the analyzed content. The output unit performs voice output using, for example, the speaker 240 of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0133] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0138] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0141] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0142] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0144] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0145] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and output unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit collects voice using the microphone 238 of the headset type terminal 314 and converts it into digital data by the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the voice using a generation AI to understand dialects and accents. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an appropriate response based on the analyzed content. The output unit performs voice output using, for example, the speaker 240 of the headset type terminal 314. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0154] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0155] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0156] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0157] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0158] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0159] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0161] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0162] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and output unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit collects voice using the microphone 238 of the robot 414 and converts it into digital data by the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the voice using a generation AI to understand dialects and accents. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an appropriate response based on the analyzed content. The output unit performs voice output using, for example, the speaker 240 of the robot 414. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0164] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0165] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0167] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0168] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0169] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0172] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0173] In addition, 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 upon request from the data processing device 12.

[0174] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0175] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0176] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0177] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0178] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0180] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0181] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0182] (Appendix 1) A reception unit that receives voice input from a user; an analysis unit that analyzes the voice received by the reception unit and understands dialects or accents; a generation unit that generates a response based on the content analyzed by the analysis unit; an output unit that outputs the response generated by the generation unit by voice; A system characterized by: (Appendix 2) The analysis unit is Understanding dialects and accents through machine learning using a speech database 2. The system of claim 1, (Appendix 3) The generation unit is Generate interactions based on the user's state or needs 2. The system of claim 1, (Appendix 4) The generation unit is Generate questions when a user complains of feeling unwell 2. The system of claim 1, (Appendix 5) The generation unit is Generate a caring dialogue if the user feels lonely 2. The system of claim 1, (Appendix 6) The analysis unit is Understand the user's state by collecting data using facial expression recognition or sensors 2. The system of claim 1, (Appendix 7) The reception unit is To estimate a user's emotion and adjust the timing of accepting voice input based on the estimated user's emotion. 2. The system of claim 1, (Appendix 8) The reception unit is Analyze the user's past dialogue history and select the optimal voice input method 2. The system of claim 1, (Appendix 9) The reception unit is When you speak, it filters based on the user's current situation and interests. 2. The system of claim 1, (Appendix 10) The reception unit is Estimate the user's emotions and prioritize the voice inputs to be accepted based on the estimated user's emotions. 2. The system of claim 1, (Appendix 11) The reception unit is When inputting voice, the system takes into account the user's geographic location information and prioritizes relevant input. 2. The system of claim 1, (Appendix 12) The reception unit is Analyzes the user's social media activity and accepts relevant input when using voice input 2. The system of claim 1, (Appendix 13) The analysis unit is Infer user emotions and adjust dialect and accent analysis methods based on the estimated user emotions 2. The system of claim 1, (Appendix 14) The analysis unit is During analysis, the frequency of updates to the speech database is adjusted to reflect the latest dialects and accents. 2. The system of claim 1, (Appendix 15) The analysis unit is During analysis, the accuracy of the analysis is improved by referring to the user's past speech patterns. 2. The system of claim 1, (Appendix 16) The analysis unit is Infer user emotions and adjust the way analysis results are displayed based on the inferred user emotions 2. The system of claim 1, (Appendix 17) The analysis unit is Improve analysis accuracy by considering the user's geographical background during analysis 2. The system of claim 1, (Appendix 18) The analysis unit is During analysis, the accuracy of the analysis is improved by referring to the user's related literature. 2. The system of claim 1, (Appendix 19) The generation unit is Inferring a user's emotions and adjusting the way responses are expressed based on the inferred user emotions 2. The system of claim 1, (Appendix 20) The generation unit is When generating a response, adjust the level of detail in the response based on the user's state and needs 2. The system of claim 1, (Appendix 21) The generation unit is Apply different response algorithms depending on the user category when generating responses 2. The system of claim 1, (Appendix 22) The generation unit is Inferring a user's emotion and adjusting the length of a response based on the estimated user's emotion 2. The system of claim 1, (Appendix 23) The generation unit is When generating responses, prioritize responses based on when the user spoke 2. The system of claim 1, (Appendix 24) The generation unit is Adjusting the order of responses based on user relevance when generating responses 2. The system of claim 1, (Appendix 25) The output unit is Estimating a user's emotion and adjusting the manner in which speech output is expressed based on the estimated user's emotion 2. The system of claim 1, (Appendix 26) The output unit is When outputting voice, the optimal output method is selected by referring to the user's past dialogue history. 2. The system of claim 1, (Appendix 27) The output unit is When outputting speech, customize the output method based on the user's current situation 2. The system of claim 1, (Appendix 28) The output unit is To estimate a user's emotion and determine a priority of speech output based on the estimated user's emotion. 2. The system of claim 1, (Appendix 29) The output unit is When outputting voice, the optimal output method is selected taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 30) The output unit is When outputting voice, the system analyzes the user's social media activity and suggests output methods. 2. The system of claim 1, [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception unit that receives voice input from a user; an analysis unit that analyzes the voice received by the reception unit and understands dialects or accents; a generation unit that generates a response based on the content analyzed by the analysis unit; an output unit that outputs the response generated by the generation unit by voice; A system characterized by:

2. The analysis unit is Understanding dialects and accents through machine learning using a speech database 2. The system of claim 1 .

3. The generation unit is Generate interactions based on the user's state or needs 2. The system of claim 1 .

4. The generation unit is Generate questions when a user complains of feeling unwell 2. The system of claim 1 .

5. The generation unit is Generate a caring dialogue if the user feels lonely 2. The system of claim 1 .

6. The analysis unit is Understand the user's state by collecting data using facial expression recognition or sensors 2. The system of claim 1 .

7. The reception unit is To estimate a user's emotion and adjust the timing of accepting voice input based on the estimated user's emotion.

2. The system of claim 1 .

8. The reception unit is Analyze the user's past dialogue history and select the optimal voice input method 2. The system of claim 1 .

Images