system

Abstract

The system according to the embodiment aims to support the prevention of dementia through conversations with elderly people. [Solution] A system according to an embodiment includes a receiving unit, a generating unit, and a providing unit. The receiving unit receives an input for starting a conversation. The generating unit analyzes the input received by the receiving unit and generates an appropriate response. The providing unit provides the response generated by the generating unit to a user.

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not adequately prevent dementia through conversation with the elderly, and there is room for improvement.

[0005] The system according to the embodiment aims to support the prevention of dementia through conversations with elderly people. [Means for solving the problem]

[0006] A system according to an embodiment includes a receiving unit, a generating unit, and a providing unit. The receiving unit receives an input for starting a conversation. The generating unit analyzes the input received by the receiving unit and generates an appropriate response. The providing unit provides the response generated by the generating unit to a user. [Effects of the Invention]

[0007] The system according to the embodiment can support the prevention of dementia through conversations with elderly people. [Brief explanation 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. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

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

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and 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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[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, RAM 30, and 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 (for example, 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., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with 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 CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

[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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 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 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. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A conversational bot system according to an embodiment of the present invention is a conversational bot system specifically designed for elderly people, aimed at preventing dementia in a super-aging society. This conversational bot system allows users to input information to initiate a conversation. The AI ​​analyzes the input, generates an appropriate response, and provides the generated response to the user, thereby continuing the conversation. For example, when a user inputs a question such as "What's the weather like today?", the question is input to the AI. The AI ​​analyzes the input question and generates an appropriate response. The AI ​​generates an interesting response for the user based on past conversation data and general knowledge. For example, it generates a response such as "It's sunny today. How about going for a walk?" The generated response is provided to the user, continuing the conversation. For example, if a user responds, "Going for a walk is a good idea," the AI ​​then replies with a question such as "Where do you want to go?" In this way, the conversation continues naturally. This mechanism allows elderly people to enjoy conversations at all times, contributing to the prevention of dementia. Through conversations with the AI, users can stimulate their thinking. Furthermore, the generation AI generates responses based on the user's interests and concerns, making conversations more enjoyable. For example, if a user says, "I want to talk about my old memories," the generation AI will ask, "What memories do you have?" to help the user talk. This allows the user to reminisce about past events and enjoy the conversation. Furthermore, the generation AI can collect information about the user's health and daily life and provide appropriate advice. For example, if a user says, "I haven't had much of an appetite lately," the generation AI will provide advice such as, "Try to eat a balanced diet." This also contributes to the user's health management. In this way, a conversation bot system specialized for the elderly is not only useful for dementia prevention and health management, but also allows users to enjoy fun conversations. This allows the elderly to always enjoy conversations and contributes to dementia prevention.

[0029] A conversational bot system according to an embodiment includes a reception unit, a generation unit, and a provision unit. The reception unit receives input from a user to start a conversation. Examples of input from a user to start a conversation include, but are not limited to, voice input, text input, and gesture input. The reception unit receives voice input via a microphone and converts it into text data using voice recognition technology. The reception unit can also receive text input via a keyboard or touch screen. The reception unit can also detect gesture input using a camera and analyze it using gesture recognition technology. The generation unit uses a generation AI to analyze the input received by the reception unit and generate an appropriate response. The generation unit can analyze the input using, for example, natural language processing technology to understand the user's intention. The generation unit can also estimate the user's emotions using sentiment analysis technology. The generation unit generates an interesting response for the user based on past conversation data and general knowledge. For example, the generation AI can use a text generation AI (e.g., LLM) to generate an accurate answer to a user's question. The generation unit can also use a multimodal generation AI to generate a response that takes into consideration the user's emotions. The provision unit provides the response generated by the generation unit to the user. The provision unit, for example, converts text data into audio data using speech synthesis technology and plays the audio on a speaker. The provision unit can also display the text data on a display. The provision unit can also provide a response using gestures or facial expressions. For example, the provision unit converts the generated response into audio data using speech synthesis technology and plays the audio on a speaker. The provision unit can also display the generated response as text data on a display. In this way, the conversation bot system according to the embodiment can analyze a user's input, generate an appropriate response, and provide it, thereby continuing the conversation.

[0030] The conversational bot system includes a collection unit that collects information about the user's health condition or daily life. The collection unit collects information about the user's health condition or daily life. The health condition information includes, but is not limited to, heart rate, blood pressure, and body temperature. For example, the collection unit measures the heart rate using a wearable device and collects data. The collection unit can also measure blood pressure using a blood pressure monitor and collect data. The collection unit can also measure body temperature using a thermometer and collect data. The information about the daily life includes, but is not limited to, dietary content, exercise amount, and sleep duration. For example, the collection unit provides an interface for the user to input dietary content and collects data. The collection unit can also provide an interface for the user to input exercise amount and collect data. The collection unit can also provide an interface for the user to input sleep duration and collect data. In this way, the collection unit can provide appropriate advice by collecting information about the user's health condition or daily life.

[0031] The conversational bot system includes an advice unit that provides appropriate advice based on the information collected by the collection unit. The advice unit provides appropriate advice based on the information collected by the collection unit. Examples of appropriate advice include, but are not limited to, specific guidelines for health management, dietary and exercise advice, etc. For example, the advice unit may recommend deep breathing to relax if the user's heart rate is high. Furthermore, the advice unit may also advise the user to limit salt intake if the user's blood pressure is high. Furthermore, the advice unit may also recommend hydration if the user's body temperature is high. The advice unit may advise the user to maintain a balanced diet based on the user's dietary habits. For example, the advice unit may recommend the user to eat more vegetables. Furthermore, the advice unit may also advise the user to engage in moderate exercise. For example, the advice unit may recommend the user to walk 30 minutes daily. Furthermore, the advice unit may advise the user to get enough sleep based on the user's sleep duration. For example, the advice unit may recommend the user to get at least seven hours of sleep each night. This allows the advice unit to provide appropriate advice based on the collected information, thereby contributing to the user's health management.

[0032] The generation unit can generate a response based on past conversation data or general knowledge. The generation unit generates a response based on past conversation data or general knowledge. Past conversation data includes, for example, a past dialogue history with the user and a conversation context, but is not limited to these examples. For example, the generation unit analyzes a past dialogue history with the user to understand the user's interests and concerns. The generation unit can also understand the conversation context and generate an appropriate response. General knowledge includes, for example, encyclopedic knowledge, specialized knowledge, etc., but is not limited to these examples. For example, the generation unit generates an accurate answer to a user's question based on encyclopedic knowledge. The generation unit can also generate a detailed answer to a user's question based on specialized knowledge. In this way, the generation unit can provide a more appropriate response by generating a response based on past conversation data or general knowledge.

[0033] The providing unit provides the generated response to the user, allowing the conversation to continue. The providing unit provides the generated response to the user, allowing the conversation to continue. The providing unit, for example, converts text data into audio data using speech synthesis technology and plays the audio data on a speaker. The providing unit can also display the text data on a display. The providing unit can also provide a response using gestures or facial expressions. For example, the providing unit converts the generated response into audio data using speech synthesis technology and plays the audio data on a speaker. The providing unit can also display the generated response as text data on a display. In this way, the providing unit provides the generated response to the user, allowing the conversation to continue, allowing the user to always enjoy the conversation.

[0034] The advice unit can provide appropriate advice based on the user's health condition. The advice unit provides appropriate advice based on the user's health condition. Health conditions include, but are not limited to, heart rate, blood pressure, body temperature, and the like. For example, if the user's heart rate is high, the advice unit can recommend taking deep breaths to relax. Furthermore, if the user's blood pressure is high, the advice unit can also advise the user to limit their salt intake. Furthermore, if the user's body temperature is high, the advice unit can also recommend hydration. In this way, the advice unit can contribute to the user's health management by providing appropriate advice based on the user's health condition.

[0035] In the conversation bot system, a reception unit analyzes a user's past conversation history and selects an optimal conversation initiation method. The reception unit analyzes a user's past conversation history and selects an optimal conversation initiation method. The past conversation history includes, for example, past dialogue content with the user and the context of the conversation, but is not limited to these examples. The reception unit analyzes, for example, past dialogue content with the user to understand the user's preferred topics. The reception unit can also understand the context of the conversation and identify topics the user avoided. The optimal conversation initiation method includes, for example, selecting a topic based on the user's interests and concerns, but is not limited to these examples. The reception unit can start a conversation from, for example, a topic that the user previously preferred. The reception unit can also start a conversation while avoiding topics that the user previously avoided. Furthermore, if the user previously preferred conversations during a specific time period, the reception unit can start a conversation during that time period. In this way, the reception unit can select an optimal conversation initiation method by analyzing the user's past conversation history.

[0036] In the conversation bot system, the reception unit can filter the user's current interests and concerns when starting a conversation. The reception unit filters the user's current interests and concerns when starting a conversation. Current interests and concerns include, but are not limited to, recent search history and social media activity. The reception unit can start a conversation based on keywords recently searched by the user. The reception unit can also start a conversation based on news recently viewed by the user. The reception unit can also start a conversation based on events the user recently participated in. Specific filtering methods include, but are not limited to, prioritizing topics of interest. For example, the reception unit can prioritize topics that interest the user. The reception unit can also exclude topics that the user is less interested in. This allows the reception unit to start a conversation based on the user's current interests and concerns, thereby providing a more interesting conversation.

[0037] In the conversation bot system, the reception unit can prioritize providing highly relevant topics by taking into account the user's geographical location information when starting a conversation. The reception unit prioritizes providing highly relevant topics by taking into account the user's geographical location information when starting a conversation. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, if the user is in a park, the reception unit can provide topics related to the park. Furthermore, if the user is in a hospital, the reception unit can provide topics related to health. Furthermore, if the user is at home, the reception unit can provide topics related to the home. Examples of highly relevant topics include, but are not limited to, news and events related to the user's current location. For example, the reception unit can provide news related to the user's current location. Furthermore, the reception unit can provide event information related to the user's current location. In this way, the reception unit can provide highly relevant topics by taking into account the user's geographical location information.

[0038] In the conversation bot system, the reception unit analyzes the user's social media activity at the start of a conversation and provides related topics. The reception unit analyzes the user's social media activity at the start of a conversation and provides related topics. Social media activity includes, for example, but is not limited to, posted content, likes, and comment history. The reception unit, for example, starts a conversation based on posts that the user recently "liked." The reception unit can also start a conversation based on posts that the user recently commented on. The reception unit can also start a conversation based on posts that the user recently shared. Related topics include, for example, topics or themes that the user is interested in, but are not limited to, examples. The reception unit provides topics based on topics that the user is interested in. The reception unit can also provide topics based on themes that the user is interested in. In this way, the reception unit can provide related topics by analyzing the user's social media activity.

[0039] In the conversation bot system, the generation unit can adjust the level of detail of a response based on the importance of the conversation when generating a response. The generation unit adjusts the level of detail of a response based on the importance of the conversation when generating a response. The importance of the conversation includes, but is not limited to, the user's level of interest and the urgency of the conversation. The generation unit can also adjust the level of detail of a response based on, for example, the user's level of interest. The generation unit can also adjust the level of detail of a response based on the urgency of the conversation. Specific methods for adjusting the level of detail of a response include, but are not limited to, whether to add a detailed explanation or to summarize briefly. For example, the generation unit can generate a detailed response for an important topic. The generation unit can also generate a concise response for a general topic. Furthermore, the generation unit can generate a response including additional information for a topic in which the user is particularly interested. In this way, the generation unit can provide a more appropriate response by adjusting the level of detail of a response based on the importance of the conversation.

[0040] In the conversational bot system, the generation unit can apply different response algorithms depending on the conversation category when generating a response. The generation unit applies different response algorithms depending on the conversation category when generating a response. Conversation categories include, but are not limited to, business, personal, and technical topics. For example, in the case of a business topic, the generation unit generates a response based on business knowledge. Furthermore, in the case of a personal topic, the generation unit can generate a response including related information. Furthermore, in the case of a technical topic, the generation unit can generate a response based on specialized knowledge. The response algorithm can include, but is not limited to, rule-based and machine learning-based algorithms. For example, the generation unit can use a rule-based algorithm to generate a response according to specific rules. Furthermore, the generation unit can use a machine learning-based algorithm to generate a response based on past data. In this way, the generation unit can provide a more appropriate response by applying different response algorithms depending on the conversation category.

[0041] In the conversation bot system, when generating a response, the generation unit can determine the priority of the response based on the time of submission of the conversation. When generating a response, the generation unit determines the priority of the response based on the time of submission of the conversation. The time of submission of the conversation includes, but is not limited to, for example, the start time of the conversation and the user's activity time. The generation unit can also determine the priority of the response based on, for example, the start time of the conversation. The generation unit can also determine the priority of the response based on the user's activity time. A specific method for determining the priority of the response includes, but is not limited to, for example, setting the priority based on the time of submission. For example, the generation unit can prioritize generating a response to the most recent conversation. The generation unit can also postpone responses to past conversations. Furthermore, the generation unit can prioritize generating responses to conversations that took place during a specific time period. In this way, the generation unit can provide more appropriate responses by determining the priority of the responses based on the time of submission of the conversation.

[0042] In the conversational bot system, the generation unit can adjust the order of responses based on the relevance of the conversation when generating responses. The generation unit adjusts the order of responses based on the relevance of the conversation when generating responses. Conversational relevance includes, but is not limited to, for example, the degree of similarity of the topic and the user's interest. The generation unit can also adjust the order of responses based on the user's interest. Specific methods for adjusting the order of responses include, but are not limited to, for example, setting the order of responses based on relevance. For example, the generation unit prioritizes generating responses related to the most recent conversation. The generation unit can also postpone responses to conversations with low relevance. Furthermore, the generation unit can prioritize generating responses to topics in which the user has shown particular interest. In this way, the generation unit can provide more appropriate responses by adjusting the order of responses based on the relevance of the conversation.

[0043] In the conversation bot system, the providing unit can select the optimal delivery method by referring to the user's past conversation history when providing a response. The providing unit selects the optimal delivery method by referring to the user's past conversation history when providing a response. The past conversation history includes, for example, past dialogue content with the user and the context of the conversation, but is not limited to these examples. For example, the providing unit analyzes past dialogue content with the user to understand the delivery method preferred by the user. The providing unit can also understand the context of the conversation and identify delivery methods avoided by the user. The optimal delivery method includes, for example, selection of a delivery method based on the user's past responses, but is not limited to these examples. For example, the providing unit prioritizes the use of delivery methods that the user has previously preferred. The providing unit can also avoid delivery methods that the user has previously avoided. Furthermore, the providing unit can use delivery methods that the user has previously preferred during a specific time period. In this way, the providing unit can select the optimal delivery method by referring to the user's past conversation history.

[0044] In the conversational bot system, the providing unit can customize the means of providing a response based on the user's current living situation when providing a response. The providing unit customizes the means of providing a response based on the user's current living situation when providing a response. The current living situation includes, but is not limited to, the user's current activity, lifestyle, etc. For example, if the user is out, the providing unit can provide a response by voice. Also, if the user is at home, the providing unit can provide a response by text. Furthermore, if the user is in a meeting, the providing unit can provide a response by silent notification. Specific methods for customizing the means of providing a response include, but are not limited to, selecting a means of providing a response based on the user's living situation. For example, the providing unit selects a means of providing a response based on the user's current activity. Also, the providing unit can select a means of providing a response based on the user's lifestyle. In this way, the providing unit can provide a more appropriate response by customizing the means of providing a response based on the user's current living situation.

[0045] In the conversation bot system, the providing unit can select the optimal delivery method by taking into account the user's geographical location information when providing a response. The providing unit selects the optimal delivery method by taking into account the user's geographical location information when providing a response. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, if the user is in a park, the providing unit can provide topics related to the park. Furthermore, if the user is in a hospital, the providing unit can provide topics related to health. Furthermore, if the user is at home, the providing unit can provide topics related to the home. Examples of the optimal delivery method include, but are not limited to, selecting a delivery method based on the geographical location information. For example, the providing unit can provide news related to the user's current location. Furthermore, the providing unit can provide event information related to the user's current location. In this way, the providing unit can select the optimal delivery method by taking into account the user's geographical location information.

[0046] In the conversation bot system, when providing a response, the providing unit can analyze the user's social media activity and suggest a means of delivery. When providing a response, the providing unit analyzes the user's social media activity and suggest a means of delivery. Social media activity includes, for example, but is not limited to, post content, likes, and comment history. For example, the providing unit can start a conversation based on posts that the user recently "liked." The providing unit can also start a conversation based on posts that the user recently commented on. The providing unit can also start a conversation based on posts that the user recently shared. Specific methods for suggesting a means of delivery include, for example, but are not limited to, selecting a means of delivery based on social media activity. For example, the providing unit can select a means of delivery based on topics that the user is interested in. The providing unit can also select a means of delivery based on themes that the user is interested in. In this way, the providing unit can suggest the optimal means of delivery by analyzing the user's social media activity.

[0047] In the conversational bot system, the collection unit can select an optimal collection method by analyzing the user's past health data when collecting health information. The collection unit can select an optimal collection method by analyzing the user's past health data when collecting health information. Past health data includes, but is not limited to, past diagnosis results and health checkup data. For example, the collection unit can analyze the user's past diagnosis results to determine the user's preferred collection method. The collection unit can also analyze health checkup data to identify collection methods the user avoided. The optimal collection method can include, but is not limited to, selection of a collection method based on the past health data. For example, the collection unit can prioritize the use of collection methods that the user previously preferred. The collection unit can also avoid collection methods that the user previously avoided. Furthermore, the collection unit can use collection methods that the user previously preferred during specific time periods. In this way, the collection unit can select an optimal collection method by analyzing the user's past health data.

[0048] In the conversational bot system, when collecting health information, the collection unit can prioritize collecting highly relevant information by taking into account the user's geographical location information. When collecting health information, the collection unit prioritizes collecting highly relevant information by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, if the user is in a park, the collection unit can collect health information related to the park. Furthermore, if the user is in a hospital, the collection unit can also collect health information related to the hospital. Furthermore, if the user is at home, the collection unit can also collect health information related to the home. Examples of highly relevant information include, but are not limited to, selection of health information based on geographical location information. For example, the collection unit prioritizes collecting health information related to the user's current location. Furthermore, the collection unit can prioritize collecting event information related to the user's current location. In this way, the collection unit can prioritize collecting highly relevant information by taking into account the user's geographical location information.

[0049] In the conversational bot system, the advice unit can provide optimal advice by referring to the user's past health data when providing advice. The advice unit can provide optimal advice by referring to the user's past health data when providing advice. Past health data includes, but is not limited to, past diagnosis results and health checkup data. For example, the advice unit can analyze the user's past diagnosis results to determine the advice method the user preferred. The advice unit can also analyze health checkup data to identify advice methods the user avoided. Optimal advice can include, but is not limited to, selection of advice based on past health data. For example, the advice unit can prioritize advice methods that the user preferred in the past. The advice unit can also avoid advice methods that the user avoided in the past. Furthermore, the advice unit can use advice methods that the user preferred in a specific time period in the past. In this way, the advice unit can provide optimal advice by referring to the user's past health data.

[0050] In the conversational bot system, the advice unit can provide optimal advice by taking into account the user's geographical location information when providing advice. The advice unit can provide optimal advice by taking into account the user's geographical location information when providing advice. Examples of geographical location information include, but are not limited to, GPS data, location information services, etc. For example, if the user is in a park, the advice unit can provide advice related to the park. Furthermore, if the user is in a hospital, the advice unit can provide advice related to the hospital. Furthermore, if the user is at home, the advice unit can provide advice related to the home. Examples of optimal advice include, but are not limited to, selection of advice based on geographical location information. For example, the advice unit can provide health advice related to the user's current location. Furthermore, the advice unit can provide lifestyle advice related to the user's current location. In this way, the advice unit can provide optimal advice by taking into account the user's geographical location information.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The conversation bot system may have a function for recording the user's dietary content with photos when the collection unit collects the user's health status. For example, if the user takes photos of their meals and sends them to the collection unit, the collection unit can analyze the dietary content and evaluate the nutritional balance. The collection unit can also record when the user takes photos of their meals and analyze the frequency and time of day they eat. Furthermore, by allowing users to share photos of their meals, the collection unit can promote interaction with other users and support healthy eating habits. This allows the collection unit to more accurately understand the user's dietary content and provide appropriate advice.

[0053] The conversational bot system can take the user's lifestyle into consideration when the advice unit provides advice based on the user's health condition. For example, if the user is a nocturnal person, the advice unit can provide health advice suitable for the nighttime. If the user is a morning person, the advice unit can also provide health advice suitable for the morning hours. Furthermore, if the user has an irregular lifestyle, the advice unit can provide specific advice for adjusting the user's lifestyle. This allows the advice unit to provide more effective health advice based on the user's lifestyle.

[0054] When providing the generated response to the user, the providing unit can customize the display method based on the user's visual preferences. For example, if the user prefers large letters, the providing unit can display the response in a large font size. Also, if the user prefers a specific color, the providing unit can display the response using that color. Furthermore, if the user prefers visual animation, the providing unit can display the response using animation. In this way, the providing unit can provide a more comfortable conversation experience by providing a response based on the user's visual preferences.

[0055] When providing advice based on the user's health condition, the advice unit can improve the accuracy of the advice by referring to the user's past health data. For example, if the user has been diagnosed with high blood pressure in the past, the advice unit can advise the user to limit their salt intake. Furthermore, if the user has been told in the past that they do not get enough exercise, the advice unit can recommend moderate exercise. Furthermore, if the user has complained of insufficient sleep in the past, the advice unit can provide specific advice for improving the quality of sleep. This allows the advice unit to provide more appropriate advice based on the user's past health data.

[0056] In the conversation bot system, the reception unit can analyze the user's past conversation history and select the optimal conversation start method. For example, the system can start a conversation from a topic that the user liked in the past. It can also start a conversation by avoiding topics that the user avoided in the past. Furthermore, if the user liked conversation during a specific time period in the past, the system can start a conversation during that time period. This allows the reception unit to select the optimal conversation start method by analyzing the user's past conversation history.

[0057] In the conversation bot system, the reception unit can filter based on the user's current interests and concerns when starting a conversation. For example, a conversation can be started based on keywords recently searched by the user. A conversation can also be started based on news recently viewed by the user. A conversation can also be started based on events recently attended by the user. This allows the reception unit to provide more interesting conversations by starting a conversation based on the user's current interests and concerns.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The reception unit receives input from the user to start a conversation. User input includes voice input, text input, and gesture input. For example, voice input is received through a microphone and converted into text data using voice recognition technology. Text input is received through a keyboard or touch screen, and gesture input is detected by a camera and analyzed using gesture recognition technology. Step 2: The generation unit analyzes the input received by the reception unit and generates an appropriate response. The generation unit uses generation AI to utilize natural language processing and sentiment analysis technologies to understand the user's intentions and emotions. Furthermore, it generates responses that are interesting to the user based on past conversation data and general knowledge. For example, it uses text generation AI (LLM) to generate accurate answers and multimodal generation AI to generate responses that take emotions into consideration. Step 3: The providing unit provides the response generated by the generating unit to the user. The providing unit converts the text data into voice data using speech synthesis technology and plays it back through a speaker. The providing unit can also display the text data on a display. It can also provide a response using gestures and facial expressions.

[0060] (Example 2) A conversational bot system according to an embodiment of the present invention is a conversational bot system specifically designed for elderly people, aimed at preventing dementia in a super-aging society. This conversational bot system allows users to input information to initiate a conversation. The AI ​​analyzes the input, generates an appropriate response, and provides the generated response to the user, thereby continuing the conversation. For example, when a user inputs a question such as "What's the weather like today?", the question is input to the AI. The AI ​​analyzes the input question and generates an appropriate response. The AI ​​generates an interesting response for the user based on past conversation data and general knowledge. For example, it generates a response such as "It's sunny today. How about going for a walk?" The generated response is provided to the user, continuing the conversation. For example, if a user responds, "Going for a walk is a good idea," the AI ​​then replies with a question such as "Where do you want to go?" In this way, the conversation continues naturally. This mechanism allows elderly people to enjoy conversations at all times, contributing to the prevention of dementia. Through conversations with the AI, users can stimulate their thinking. Furthermore, the generation AI generates responses based on the user's interests and concerns, making conversations more enjoyable. For example, if a user says, "I want to talk about my old memories," the generation AI will ask, "What memories do you have?" to help the user talk. This allows the user to reminisce about past events and enjoy the conversation. Furthermore, the generation AI can collect information about the user's health and daily life and provide appropriate advice. For example, if a user says, "I haven't had much of an appetite lately," the generation AI will provide advice such as, "Try to eat a balanced diet." This also contributes to the user's health management. In this way, a conversation bot system specialized for the elderly is not only useful for dementia prevention and health management, but also allows users to enjoy fun conversations. This allows the elderly to always enjoy conversations and contributes to dementia prevention.

[0061] A conversational bot system according to an embodiment includes a reception unit, a generation unit, and a provision unit. The reception unit receives input from a user to start a conversation. Examples of input from a user to start a conversation include, but are not limited to, voice input, text input, and gesture input. The reception unit receives voice input via a microphone and converts it into text data using voice recognition technology. The reception unit can also receive text input via a keyboard or touch screen. The reception unit can also detect gesture input using a camera and analyze it using gesture recognition technology. The generation unit uses a generation AI to analyze the input received by the reception unit and generate an appropriate response. The generation unit can analyze the input using, for example, natural language processing technology to understand the user's intention. The generation unit can also estimate the user's emotions using sentiment analysis technology. The generation unit generates an interesting response for the user based on past conversation data and general knowledge. For example, the generation AI can use a text generation AI (e.g., LLM) to generate an accurate answer to a user's question. The generation unit can also use a multimodal generation AI to generate a response that takes into consideration the user's emotions. The provision unit provides the response generated by the generation unit to the user. The provision unit, for example, converts text data into audio data using speech synthesis technology and plays the audio on a speaker. The provision unit can also display the text data on a display. The provision unit can also provide a response using gestures or facial expressions. For example, the provision unit converts the generated response into audio data using speech synthesis technology and plays the audio on a speaker. The provision unit can also display the generated response as text data on a display. In this way, the conversation bot system according to the embodiment can analyze a user's input, generate an appropriate response, and provide it, thereby continuing the conversation.

[0062] The conversational bot system includes a collection unit that collects information about the user's health condition or daily life. The collection unit collects information about the user's health condition or daily life. The health condition information includes, but is not limited to, heart rate, blood pressure, and body temperature. For example, the collection unit measures the heart rate using a wearable device and collects data. The collection unit can also measure blood pressure using a blood pressure monitor and collect data. The collection unit can also measure body temperature using a thermometer and collect data. The information about the daily life includes, but is not limited to, dietary content, exercise amount, and sleep duration. For example, the collection unit provides an interface for the user to input dietary content and collects data. The collection unit can also provide an interface for the user to input exercise amount and collect data. The collection unit can also provide an interface for the user to input sleep duration and collect data. In this way, the collection unit can provide appropriate advice by collecting information about the user's health condition or daily life.

[0063] The conversational bot system includes an advice unit that provides appropriate advice based on the information collected by the collection unit. The advice unit provides appropriate advice based on the information collected by the collection unit. Examples of appropriate advice include, but are not limited to, specific guidelines for health management, dietary and exercise advice, etc. For example, the advice unit may recommend deep breathing to relax if the user's heart rate is high. Furthermore, the advice unit may also advise the user to limit salt intake if the user's blood pressure is high. Furthermore, the advice unit may also recommend hydration if the user's body temperature is high. The advice unit may advise the user to maintain a balanced diet based on the user's dietary habits. For example, the advice unit may recommend the user to eat more vegetables. Furthermore, the advice unit may also advise the user to engage in moderate exercise. For example, the advice unit may recommend the user to walk 30 minutes daily. Furthermore, the advice unit may advise the user to get enough sleep based on the user's sleep duration. For example, the advice unit may recommend the user to get at least seven hours of sleep each night. This allows the advice unit to provide appropriate advice based on the collected information, thereby contributing to the user's health management.

[0064] The generation unit can generate a response based on past conversation data or general knowledge. The generation unit generates a response based on past conversation data or general knowledge. Past conversation data includes, for example, a past dialogue history with the user and a conversation context, but is not limited to these examples. For example, the generation unit analyzes a past dialogue history with the user to understand the user's interests and concerns. The generation unit can also understand the conversation context and generate an appropriate response. General knowledge includes, for example, encyclopedic knowledge, specialized knowledge, etc., but is not limited to these examples. For example, the generation unit generates an accurate answer to a user's question based on encyclopedic knowledge. The generation unit can also generate a detailed answer to a user's question based on specialized knowledge. In this way, the generation unit can provide a more appropriate response by generating a response based on past conversation data or general knowledge.

[0065] The providing unit provides the generated response to the user, allowing the conversation to continue. The providing unit provides the generated response to the user, allowing the conversation to continue. The providing unit, for example, converts text data into audio data using speech synthesis technology and plays the audio data on a speaker. The providing unit can also display the text data on a display. The providing unit can also provide a response using gestures or facial expressions. For example, the providing unit converts the generated response into audio data using speech synthesis technology and plays the audio data on a speaker. The providing unit can also display the generated response as text data on a display. In this way, the providing unit provides the generated response to the user, allowing the conversation to continue, allowing the user to always enjoy the conversation.

[0066] The advice unit can provide appropriate advice based on the user's health condition. The advice unit provides appropriate advice based on the user's health condition. Health conditions include, but are not limited to, heart rate, blood pressure, body temperature, and the like. For example, if the user's heart rate is high, the advice unit can recommend taking deep breaths to relax. Furthermore, if the user's blood pressure is high, the advice unit can also advise the user to limit their salt intake. Furthermore, if the user's body temperature is high, the advice unit can also recommend hydration. In this way, the advice unit can contribute to the user's health management by providing appropriate advice based on the user's health condition.

[0067] In the conversation bot system, a reception unit estimates a user's emotions and adjusts the timing of starting a conversation based on the estimated user emotions. The reception unit estimates a user's emotions and adjusts the timing of starting a conversation based on the estimated user emotions. Specific methods for estimating emotions include, but are not limited to, voice tone analysis, facial expression recognition, and text analysis. For example, the reception unit estimates a user's emotions using voice tone analysis. The reception unit can also estimate a user's emotions using facial expression recognition technology. The reception unit can also estimate a user's emotions using text analysis technology. Specific methods for adjusting the timing of starting a conversation include, but are not limited to, selecting a timing based on the user's emotional state. For example, the reception unit can start a conversation immediately if the user is relaxed. Furthermore, the reception unit can start a conversation after a short delay if the user is nervous. Furthermore, the reception unit can start a conversation after sending a short message to calm the user if the user is excited. In this way, the reception unit can start a conversation at a more appropriate time by adjusting the timing of starting a conversation based on the user's emotions.

[0068] In the conversation bot system, a reception unit analyzes a user's past conversation history and selects an optimal conversation initiation method. The reception unit analyzes a user's past conversation history and selects an optimal conversation initiation method. The past conversation history includes, for example, past dialogue content with the user and the context of the conversation, but is not limited to these examples. The reception unit analyzes, for example, past dialogue content with the user to understand the user's preferred topics. The reception unit can also understand the context of the conversation and identify topics the user avoided. The optimal conversation initiation method includes, for example, selecting a topic based on the user's interests and concerns, but is not limited to these examples. The reception unit can start a conversation from, for example, a topic that the user previously preferred. The reception unit can also start a conversation while avoiding topics that the user previously avoided. Furthermore, if the user previously preferred conversations during a specific time period, the reception unit can start a conversation during that time period. In this way, the reception unit can select an optimal conversation initiation method by analyzing the user's past conversation history.

[0069] In the conversation bot system, the reception unit can filter the user's current interests and concerns when starting a conversation. The reception unit filters the user's current interests and concerns when starting a conversation. Current interests and concerns include, but are not limited to, recent search history and social media activity. The reception unit can start a conversation based on keywords recently searched by the user. The reception unit can also start a conversation based on news recently viewed by the user. The reception unit can also start a conversation based on events the user recently participated in. Specific filtering methods include, but are not limited to, prioritizing topics of interest. For example, the reception unit can prioritize topics that interest the user. The reception unit can also exclude topics that the user is less interested in. This allows the reception unit to start a conversation based on the user's current interests and concerns, thereby providing a more interesting conversation.

[0070] In the conversation bot system, a reception unit can estimate a user's emotions and determine conversation priorities based on the estimated user emotions. The reception unit estimates a user's emotions and determines conversation priorities based on the estimated user emotions. Specific methods for estimating emotions include, but are not limited to, voice tone analysis, facial expression recognition, and text analysis. For example, the reception unit estimates a user's emotions using voice tone analysis. The reception unit can also estimate a user's emotions using facial expression recognition technology. The reception unit can also estimate a user's emotions using text analysis technology. Specific methods for determining conversation priorities include, but are not limited to, setting priorities based on the user's emotional state. For example, if the user is sad, the reception unit can prioritize providing encouraging words. If the user is happy, the reception unit can prioritize providing empathetic words. If the user is angry, the reception unit can prioritize providing advice to stay calm. This allows the reception unit to provide more appropriate conversations by determining conversation priorities based on the user's emotions.

[0071] In the conversation bot system, the reception unit can prioritize providing highly relevant topics by taking into account the user's geographical location information when starting a conversation. The reception unit prioritizes providing highly relevant topics by taking into account the user's geographical location information when starting a conversation. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, if the user is in a park, the reception unit can provide topics related to the park. Furthermore, if the user is in a hospital, the reception unit can provide topics related to health. Furthermore, if the user is at home, the reception unit can provide topics related to the home. Examples of highly relevant topics include, but are not limited to, news and events related to the user's current location. For example, the reception unit can provide news related to the user's current location. Furthermore, the reception unit can provide event information related to the user's current location. In this way, the reception unit can provide highly relevant topics by taking into account the user's geographical location information.

[0072] In the conversation bot system, the reception unit analyzes the user's social media activity at the start of a conversation and provides related topics. The reception unit analyzes the user's social media activity at the start of a conversation and provides related topics. Social media activity includes, for example, but is not limited to, posted content, likes, and comment history. The reception unit, for example, starts a conversation based on posts that the user recently "liked." The reception unit can also start a conversation based on posts that the user recently commented on. The reception unit can also start a conversation based on posts that the user recently shared. Related topics include, for example, topics or themes that the user is interested in, but are not limited to, examples. The reception unit provides topics based on topics that the user is interested in. The reception unit can also provide topics based on themes that the user is interested in. In this way, the reception unit can provide related topics by analyzing the user's social media activity.

[0073] In the conversational bot system, a generation unit can estimate a user's emotions and adjust the way a response is expressed based on the estimated user's emotions. The generation unit estimates the user's emotions and adjusts the way a response is expressed based on the estimated user's emotions. Specific methods for estimating emotions include, but are not limited to, voice tone analysis, facial expression recognition, and text analysis. For example, the generation unit estimates the user's emotions using voice tone analysis. The generation unit can also estimate the user's emotions using facial expression recognition technology. The generation unit can also estimate the user's emotions using text analysis technology. Specific methods for adjusting the way a response is expressed include, but are not limited to, emotion-sensitive language and tone adjustment. For example, if the user is sad, the generation unit can respond with kind words. If the user is happy, the generation unit can respond with cheerful words. If the user is angry, the generation unit can respond with calm words. This allows the generation unit to provide a more appropriate response by adjusting the way a response is expressed based on the user's emotions.

[0074] In the conversation bot system, the generation unit can adjust the level of detail of a response based on the importance of the conversation when generating a response. The generation unit adjusts the level of detail of a response based on the importance of the conversation when generating a response. The importance of the conversation includes, but is not limited to, the user's level of interest and the urgency of the conversation. The generation unit can also adjust the level of detail of a response based on, for example, the user's level of interest. The generation unit can also adjust the level of detail of a response based on the urgency of the conversation. Specific methods for adjusting the level of detail of a response include, but are not limited to, whether to add a detailed explanation or to summarize briefly. For example, the generation unit can generate a detailed response for an important topic. The generation unit can also generate a concise response for a general topic. Furthermore, the generation unit can generate a response including additional information for a topic in which the user is particularly interested. In this way, the generation unit can provide a more appropriate response by adjusting the level of detail of a response based on the importance of the conversation.

[0075] In the conversational bot system, the generation unit can apply different response algorithms depending on the conversation category when generating a response. The generation unit applies different response algorithms depending on the conversation category when generating a response. Conversation categories include, but are not limited to, business, personal, and technical topics. For example, in the case of a business topic, the generation unit generates a response based on business knowledge. Furthermore, in the case of a personal topic, the generation unit can generate a response including related information. Furthermore, in the case of a technical topic, the generation unit can generate a response based on specialized knowledge. The response algorithm can include, but is not limited to, rule-based and machine learning-based algorithms. For example, the generation unit can use a rule-based algorithm to generate a response according to specific rules. Furthermore, the generation unit can use a machine learning-based algorithm to generate a response based on past data. In this way, the generation unit can provide a more appropriate response by applying different response algorithms depending on the conversation category.

[0076] In the conversational bot system, a generation unit can estimate a user's emotion and adjust the length of a response based on the estimated user's emotion. The generation unit estimates the user's emotion and adjusts the length of a response based on the estimated user's emotion. Specific methods for estimating emotion include, but are not limited to, voice tone analysis, facial expression recognition, and text analysis. For example, the generation unit estimates the user's emotion using voice tone analysis. The generation unit can also estimate the user's emotion using facial expression recognition technology. The generation unit can also estimate the user's emotion using text analysis technology. Specific methods for adjusting the length of a response include, but are not limited to, setting the length of a response based on the user's emotional state. For example, the generation unit can generate a short response if the user is in a hurry. The generation unit can also generate a longer response if the user is relaxed. The generation unit can also generate a response of appropriate length if the user is excited. This allows the generation unit to provide a more appropriate response by adjusting the length of the response based on the user's emotion.

[0077] In the conversation bot system, when generating a response, the generation unit can determine the priority of the response based on the time of submission of the conversation. When generating a response, the generation unit determines the priority of the response based on the time of submission of the conversation. The time of submission of the conversation includes, but is not limited to, for example, the start time of the conversation and the user's activity time. The generation unit can also determine the priority of the response based on, for example, the start time of the conversation. The generation unit can also determine the priority of the response based on the user's activity time. A specific method for determining the priority of the response includes, but is not limited to, for example, setting the priority based on the time of submission. For example, the generation unit can prioritize generating a response to the most recent conversation. The generation unit can also postpone responses to past conversations. Furthermore, the generation unit can prioritize generating responses to conversations that took place during a specific time period. In this way, the generation unit can provide more appropriate responses by determining the priority of the responses based on the time of submission of the conversation.

[0078] In the conversational bot system, the generation unit can adjust the order of responses based on the relevance of the conversation when generating responses. The generation unit adjusts the order of responses based on the relevance of the conversation when generating responses. Conversational relevance includes, but is not limited to, for example, the degree of similarity of the topic and the user's interest. The generation unit can also adjust the order of responses based on the user's interest. Specific methods for adjusting the order of responses include, but are not limited to, for example, setting the order of responses based on relevance. For example, the generation unit prioritizes generating responses related to the most recent conversation. The generation unit can also postpone responses to conversations with low relevance. Furthermore, the generation unit can prioritize generating responses to topics in which the user has shown particular interest. In this way, the generation unit can provide more appropriate responses by adjusting the order of responses based on the relevance of the conversation.

[0079] In the conversational bot system, the providing unit can estimate a user's emotion and adjust the response providing method based on the estimated user's emotion. The providing unit estimates the user's emotion and adjusts the response providing method based on the estimated user's emotion. Specific methods for estimating emotion include, but are not limited to, voice tone analysis, facial expression recognition, and text analysis. For example, the providing unit estimates the user's emotion using voice tone analysis. The providing unit can also estimate the user's emotion using facial expression recognition technology. The providing unit can also estimate the user's emotion using text analysis technology. Specific methods for adjusting the response providing method include, but are not limited to, selecting a response providing method that takes emotion into consideration. For example, the providing unit can provide a response in a gentle voice if the user is sad. The providing unit can also provide a response in a cheerful voice if the user is happy. The providing unit can also provide a response in a calm voice if the user is angry. This allows the providing unit to provide a more appropriate response by adjusting the response providing method based on the user's emotion.

[0080] In the conversation bot system, the providing unit can select the optimal delivery method by referring to the user's past conversation history when providing a response. The providing unit selects the optimal delivery method by referring to the user's past conversation history when providing a response. The past conversation history includes, for example, past dialogue content with the user and the context of the conversation, but is not limited to these examples. For example, the providing unit analyzes past dialogue content with the user to understand the delivery method preferred by the user. The providing unit can also understand the context of the conversation and identify delivery methods avoided by the user. The optimal delivery method includes, for example, selection of a delivery method based on the user's past responses, but is not limited to these examples. For example, the providing unit prioritizes the use of delivery methods that the user has previously preferred. The providing unit can also avoid delivery methods that the user has previously avoided. Furthermore, the providing unit can use delivery methods that the user has previously preferred during a specific time period. In this way, the providing unit can select the optimal delivery method by referring to the user's past conversation history.

[0081] In the conversational bot system, the providing unit can customize the means of providing a response based on the user's current living situation when providing a response. The providing unit customizes the means of providing a response based on the user's current living situation when providing a response. The current living situation includes, but is not limited to, the user's current activity, lifestyle, etc. For example, if the user is out, the providing unit can provide a response by voice. Also, if the user is at home, the providing unit can provide a response by text. Furthermore, if the user is in a meeting, the providing unit can provide a response by silent notification. Specific methods for customizing the means of providing a response include, but are not limited to, selecting a means of providing a response based on the user's living situation. For example, the providing unit selects a means of providing a response based on the user's current activity. Also, the providing unit can select a means of providing a response based on the user's lifestyle. In this way, the providing unit can provide a more appropriate response by customizing the means of providing a response based on the user's current living situation.

[0082] In the conversational bot system, the providing unit can estimate a user's emotions and determine the priority of responses based on the estimated user emotions. The providing unit estimates a user's emotions and determines the priority of responses based on the estimated user emotions. Specific methods for estimating emotions include, but are not limited to, voice tone analysis, facial expression recognition, and text analysis. For example, the providing unit can estimate a user's emotions using voice tone analysis. The providing unit can also estimate a user's emotions using facial expression recognition technology. The providing unit can also estimate a user's emotions using text analysis technology. Specific methods for determining the priority of responses include, but are not limited to, emotion-based prioritization. For example, if the user is sad, the providing unit can prioritize providing encouraging words. If the user is happy, the providing unit can prioritize providing empathetic words. If the user is angry, the providing unit can prioritize providing advice to stay calm. This allows the providing unit to provide more appropriate responses by prioritizing responses based on the user's emotions.

[0083] In the conversation bot system, the providing unit can select the optimal delivery method by taking into account the user's geographical location information when providing a response. The providing unit selects the optimal delivery method by taking into account the user's geographical location information when providing a response. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, if the user is in a park, the providing unit can provide topics related to the park. Furthermore, if the user is in a hospital, the providing unit can provide topics related to health. Furthermore, if the user is at home, the providing unit can provide topics related to the home. Examples of the optimal delivery method include, but are not limited to, selecting a delivery method based on the geographical location information. For example, the providing unit can provide news related to the user's current location. Furthermore, the providing unit can provide event information related to the user's current location. In this way, the providing unit can select the optimal delivery method by taking into account the user's geographical location information.

[0084] In the conversation bot system, when providing a response, the providing unit can analyze the user's social media activity and suggest a means of delivery. When providing a response, the providing unit analyzes the user's social media activity and suggest a means of delivery. Social media activity includes, for example, but is not limited to, post content, likes, and comment history. For example, the providing unit can start a conversation based on posts that the user recently "liked." The providing unit can also start a conversation based on posts that the user recently commented on. The providing unit can also start a conversation based on posts that the user recently shared. Specific methods for suggesting a means of delivery include, for example, but are not limited to, selecting a means of delivery based on social media activity. For example, the providing unit can select a means of delivery based on topics that the user is interested in. The providing unit can also select a means of delivery based on themes that the user is interested in. In this way, the providing unit can suggest the optimal means of delivery by analyzing the user's social media activity.

[0085] In the conversational bot system, the collection unit estimates a user's emotions and adjusts the timing of collecting health information based on the estimated user emotions. The collection unit estimates a user's emotions and adjusts the timing of collecting health information based on the estimated user emotions. Specific methods for estimating emotions include, but are not limited to, voice tone analysis, facial expression recognition, and text analysis. For example, the collection unit estimates a user's emotions using voice tone analysis. The collection unit can also estimate a user's emotions using facial expression recognition technology. The collection unit can also estimate a user's emotions using text analysis technology. Specific methods for adjusting the timing of collecting health information include, but are not limited to, setting the collection timing based on emotions. For example, the collection unit collects health information immediately if the user is relaxed. Furthermore, the collection unit can wait a short time before collecting health information if the user is nervous. Furthermore, the collection unit can collect health information after sending a short message to calm the user if the user is excited. In this way, the collection unit adjusts the timing of collecting health information based on the user's emotions, allowing information to be collected at a more appropriate time.

[0086] In the conversational bot system, the collection unit can select an optimal collection method by analyzing the user's past health data when collecting health information. The collection unit can select an optimal collection method by analyzing the user's past health data when collecting health information. Past health data includes, but is not limited to, past diagnosis results and health checkup data. For example, the collection unit can analyze the user's past diagnosis results to determine the user's preferred collection method. The collection unit can also analyze health checkup data to identify collection methods the user avoided. The optimal collection method can include, but is not limited to, selection of a collection method based on the past health data. For example, the collection unit can prioritize the use of collection methods that the user previously preferred. The collection unit can also avoid collection methods that the user previously avoided. Furthermore, the collection unit can use collection methods that the user previously preferred during specific time periods. In this way, the collection unit can select an optimal collection method by analyzing the user's past health data.

[0087] In the conversational bot system, the collection unit can estimate a user's emotions and determine the priority of the health information to be collected based on the estimated user's emotions. The collection unit can estimate a user's emotions and determine the priority of the health information to be collected based on the estimated user's emotions. Specific methods for estimating emotions include, but are not limited to, voice tone analysis, facial expression recognition, and text analysis. For example, the collection unit can estimate a user's emotions using voice tone analysis. The collection unit can also estimate a user's emotions using facial expression recognition technology. The collection unit can also estimate a user's emotions using text analysis technology. Specific methods for determining the priority of health information include, but are not limited to, emotion-based prioritization. For example, if the user is sad, the collection unit can prioritize collecting mental health information. If the user is happy, the collection unit can prioritize collecting physical health information. If the user is angry, the collection unit can prioritize collecting stress-related health information. This allows the collection unit to collect more appropriate information by prioritizing health information based on the user's emotions.

[0088] In the conversational bot system, when collecting health information, the collection unit can prioritize collecting highly relevant information by taking into account the user's geographical location information. When collecting health information, the collection unit prioritizes collecting highly relevant information by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, if the user is in a park, the collection unit can collect health information related to the park. Furthermore, if the user is in a hospital, the collection unit can also collect health information related to the hospital. Furthermore, if the user is at home, the collection unit can also collect health information related to the home. Examples of highly relevant information include, but are not limited to, selection of health information based on geographical location information. For example, the collection unit prioritizes collecting health information related to the user's current location. Furthermore, the collection unit can prioritize collecting event information related to the user's current location. In this way, the collection unit can prioritize collecting highly relevant information by taking into account the user's geographical location information.

[0089] In the conversational bot system, the advice unit can estimate a user's emotions and adjust the way the advice is expressed based on the estimated user's emotions. The advice unit estimates a user's emotions and adjusts the way the advice is expressed based on the estimated user's emotions. Specific methods for estimating emotions include, but are not limited to, voice tone analysis, facial expression recognition, and text analysis. For example, the advice unit estimates a user's emotions using voice tone analysis. The advice unit can also estimate a user's emotions using facial expression recognition technology. The advice unit can also estimate a user's emotions using text analysis technology. Specific methods for adjusting the way the advice is expressed include, but are not limited to, emotion-sensitive language and tone adjustment. For example, if the user is sad, the advice unit can provide advice in gentle language. If the user is happy, the advice unit can provide advice in cheerful language. If the user is angry, the advice unit can provide advice in calm language. This allows the advice unit to provide more appropriate advice by adjusting the way the advice is expressed based on the user's emotions.

[0090] In the conversational bot system, the advice unit can provide optimal advice by referring to the user's past health data when providing advice. The advice unit can provide optimal advice by referring to the user's past health data when providing advice. Past health data includes, but is not limited to, past diagnosis results and health checkup data. For example, the advice unit can analyze the user's past diagnosis results to determine the advice method the user preferred. The advice unit can also analyze health checkup data to identify advice methods the user avoided. Optimal advice can include, but is not limited to, selection of advice based on past health data. For example, the advice unit can prioritize advice methods that the user preferred in the past. The advice unit can also avoid advice methods that the user avoided in the past. Furthermore, the advice unit can use advice methods that the user preferred in a specific time period in the past. In this way, the advice unit can provide optimal advice by referring to the user's past health data.

[0091] In the conversational bot system, the advice unit can estimate a user's emotions and determine the priority of advice based on the estimated user emotions. The advice unit estimates a user's emotions and determines the priority of advice based on the estimated user emotions. Specific methods for estimating emotions include, but are not limited to, voice tone analysis, facial expression recognition, and text analysis. For example, the advice unit estimates a user's emotions using voice tone analysis. The advice unit can also estimate a user's emotions using facial expression recognition technology. The advice unit can also estimate a user's emotions using text analysis technology. Specific methods for determining the priority of advice include, but are not limited to, setting priorities based on emotions. For example, if the user is sad, the advice unit can prioritize providing words of encouragement. If the user is happy, the advice unit can prioritize providing words of sympathy. If the user is angry, the advice unit can prioritize providing advice to calm down. This allows the advice unit to provide more appropriate advice by determining the priority of advice based on the user's emotions.

[0092] In the conversational bot system, the advice unit can provide optimal advice by taking into account the user's geographical location information when providing advice. The advice unit can provide optimal advice by taking into account the user's geographical location information when providing advice. Examples of geographical location information include, but are not limited to, GPS data, location information services, etc. For example, if the user is in a park, the advice unit can provide advice related to the park. Furthermore, if the user is in a hospital, the advice unit can provide advice related to the hospital. Furthermore, if the user is at home, the advice unit can provide advice related to the home. Examples of optimal advice include, but are not limited to, selection of advice based on geographical location information. For example, the advice unit can provide health advice related to the user's current location. Furthermore, the advice unit can provide lifestyle advice related to the user's current location. In this way, the advice unit can provide optimal advice by taking into account the user's geographical location information. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, generation unit, provision unit, collection unit, and advice 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 receives user input using the microphone 38B or touch panel 38A of the smart device 14. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the input using a generation AI to generate an appropriate response. The provision unit provides the generated response to the user using the speaker 40B or display 40A of the smart device 14. The collection unit collects information on the user's health condition and daily life using the camera 42 and sensors of the smart device 14. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and provides appropriate advice based on the collected information. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, generation unit, provision unit, collection unit, and advice 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 receives user input using the microphone 238 or camera 42 of the smart glasses 214. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the input using a generation AI to generate an appropriate response. The provision unit provides the generated response to the user using the speaker 240 or display of the smart glasses 214. The collection unit collects information on the user's health condition and daily life using the camera 42 or sensor of the smart glasses 214. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and provides appropriate advice based on the collected information. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, generation unit, provision unit, collection unit, and advice 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 receives user input using the microphone 238 or camera 42 of the headset type terminal 314. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the input using a generation AI to generate an appropriate response. The provision unit provides the generated response to the user using the speaker 240 or display 343 of the headset type terminal 314. The collection unit collects information on the user's health condition and daily life using the camera 42 or sensor of the headset type terminal 314. The advice unit is realized by the specific processing unit 290 of the data processing device 12, and provides appropriate advice based on the collected information. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, generation unit, provision unit, collection unit, and advice unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit receives user input using the microphone 238 or camera 42 of the robot 414. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the input using a generation AI to generate an appropriate response. The provision unit provides the generated response to the user using the speaker 240 or display of the robot 414. The collection unit collects information on the user's health condition and daily life using the camera 42 or sensor of the robot 414. The advice unit is realized by the specific processing unit 290 of the data processing device 12, and provides appropriate advice based on the collected information.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] When the reception unit receives user input, the conversation bot system analyzes the user's tone of voice and speaking patterns to estimate the user's stress level. For example, if the user speaks hurriedly, the reception unit can infer that the user is feeling stressed and provide advice to relax. If the user speaks slowly, the reception unit can infer that the user is relaxed and provide appropriate topics to continue the conversation. Furthermore, if the user is emotional, the reception unit can generate an appropriate response to calm the user's emotions. This allows the reception unit to take appropriate action based on the user's stress level.

[0095] The conversation bot system may have a function for recording the user's dietary content with photos when the collection unit collects the user's health status. For example, if the user takes photos of their meals and sends them to the collection unit, the collection unit can analyze the dietary content and evaluate the nutritional balance. The collection unit can also record when the user takes photos of their meals and analyze the frequency and time of day they eat. Furthermore, by allowing users to share photos of their meals, the collection unit can promote interaction with other users and support healthy eating habits. This allows the collection unit to more accurately understand the user's dietary content and provide appropriate advice.

[0096] The conversational bot system can take the user's lifestyle into consideration when the advice unit provides advice based on the user's health condition. For example, if the user is a nocturnal person, the advice unit can provide health advice suitable for the nighttime. If the user is a morning person, the advice unit can also provide health advice suitable for the morning hours. Furthermore, if the user has an irregular lifestyle, the advice unit can provide specific advice for adjusting the user's lifestyle. This allows the advice unit to provide more effective health advice based on the user's lifestyle.

[0097] The generator can generate a response based on the user's current mood and physical condition, in addition to past conversation data and general knowledge. For example, if the user is tired, the generator can provide relaxing topics. If the user is in good health, the generator can provide lively topics. Furthermore, if the user complains of poor health, the generator can provide health advice. This allows the generator to generate an appropriate response according to the user's current condition.

[0098] When providing the generated response to the user, the providing unit can customize the display method based on the user's visual preferences. For example, if the user prefers large letters, the providing unit can display the response in a large font size. Also, if the user prefers a specific color, the providing unit can display the response using that color. Furthermore, if the user prefers visual animation, the providing unit can display the response using animation. In this way, the providing unit can provide a more comfortable conversation experience by providing a response based on the user's visual preferences.

[0099] When providing advice based on the user's health condition, the advice unit can improve the accuracy of the advice by referring to the user's past health data. For example, if the user has been diagnosed with high blood pressure in the past, the advice unit can advise the user to limit their salt intake. Furthermore, if the user has been told in the past that they do not get enough exercise, the advice unit can recommend moderate exercise. Furthermore, if the user has complained of insufficient sleep in the past, the advice unit can provide specific advice for improving the quality of sleep. This allows the advice unit to provide more appropriate advice based on the user's past health data.

[0100] In the conversation bot system, the reception unit estimates the user's emotions and can adjust the timing of starting a conversation based on the estimated user emotions. For example, if the user is relaxed, the reception unit can start the conversation immediately. If the user is nervous, the reception unit can wait a short time before starting the conversation. Furthermore, if the user is excited, the reception unit can start the conversation after sending a short message to calm the user. In this way, the reception unit can start the conversation at a more appropriate time by adjusting the timing of starting the conversation based on the user's emotions.

[0101] In the conversation bot system, the reception unit can analyze the user's past conversation history and select the optimal conversation start method. For example, the system can start a conversation from a topic that the user liked in the past. It can also start a conversation by avoiding topics that the user avoided in the past. Furthermore, if the user liked conversation during a specific time period in the past, the system can start a conversation during that time period. This allows the reception unit to select the optimal conversation start method by analyzing the user's past conversation history.

[0102] In the conversation bot system, the reception unit can filter based on the user's current interests and concerns when starting a conversation. For example, a conversation can be started based on keywords recently searched by the user. A conversation can also be started based on news recently viewed by the user. A conversation can also be started based on events recently attended by the user. This allows the reception unit to provide more interesting conversations by starting a conversation based on the user's current interests and concerns.

[0103] In the conversation bot system, the reception unit can estimate the user's emotions and determine the priority of the conversation based on the estimated user emotions. For example, if the user is sad, it can prioritize providing words of encouragement. If the user is happy, it can prioritize providing words of sympathy. Furthermore, if the user is angry, it can prioritize providing advice to help the user stay calm. In this way, the reception unit can provide more appropriate conversation by prioritizing the conversation based on the user's emotions.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The reception unit receives input from the user to start a conversation. User input includes voice input, text input, and gesture input. For example, voice input is received through a microphone and converted into text data using voice recognition technology. Text input is received through a keyboard or touch screen, and gesture input is detected by a camera and analyzed using gesture recognition technology. Step 2: The generation unit analyzes the input received by the reception unit and generates an appropriate response. The generation unit uses generation AI to utilize natural language processing and sentiment analysis technologies to understand the user's intentions and emotions. Furthermore, it generates responses that are interesting to the user based on past conversation data and general knowledge. For example, it uses text generation AI (LLM) to generate accurate answers and multimodal generation AI to generate responses that take emotions into consideration. Step 3: The providing unit provides the response generated by the generating unit to the user. The providing unit converts the text data into voice data using speech synthesis technology and plays it back through a speaker. The providing unit can also display the text data on a display. It can also provide a response using gestures and facial expressions.

[0106] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0108] Furthermore, the processing by the data processing system 10 described above 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 necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 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.

[0112] 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, RAM 30, and 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.

[0113] 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.

[0114] 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 audio according to instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0116] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0117] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0118] 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.

[0119] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0120] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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. The smart glasses 214 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0121] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] 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. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0124] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, 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, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] 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, RAM 30, and 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.

[0129] 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.

[0130] 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 audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0134] 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.

[0135] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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.

[0137] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] 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. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0140] 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 also 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. Furthermore, 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, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 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.

[0144] 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, RAM 30, and 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.

[0145] 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.

[0146] 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 audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0150] 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.

[0151] 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.

[0152] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0154] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0156] 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. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0157] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, 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.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0160] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0161] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0162] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0163] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0164] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0165] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0166] 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.

[0167] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0168] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0169] 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.

[0170] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0171] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0172] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0173] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0174] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0175] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0176] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0177] [Explanation of symbols]

[0178] 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 an input for starting a conversation; a generation unit that analyzes the input received by the reception unit and generates an appropriate response; a providing unit that provides the response generated by the generating unit to a user; Equipped with A system characterized by:

2. A collection unit is provided to collect information about the user's health condition or daily life.

2. The system of claim 1.

3. An advice unit that provides appropriate advice based on the information collected by the collection unit 3. The system of claim 2.

4. The generation unit Generate responses based on past conversation data or general knowledge 2. The system of claim 1.

5. The providing unit Providing the generated response to the user and continuing the conversation 2. The system of claim 1.

6. The advice unit Providing appropriate advice based on the user's health status 4. The system of claim 3.

7. The reception unit Estimates the user's emotions and adjusts the timing of conversation start based on the estimated user emotions.

2. The system of claim 1.

8. The reception unit Analyze the user's past conversation history and choose the best way to start a conversation 2. The system of claim 1.

9. The reception unit Filtering based on the user's current interests at the start of a conversation 2. The system of claim 1.

Images