System

Abstract

An object of the system according to the embodiment is to generate an answer that is easy for anyone to understand regardless of the age and living environment of the user and the presence or absence of expert knowledge.SOLUTION: A system includes an age optimization part, a living environment optimization part, a technical term optimization part, a dialect optimization part, and an easy-to-understand answer generation part. The age appropriateness section uses the generated AI to select an appropriate language or word in accordance with the age of the user. The living environment optimizing section selects an appropriate language or word in accordance with the living environment of the user. The technical term adjustment unit generates an answer in easy-to-understand words while avoiding technical terms and difficult expressions. A dialect optimization part generates an answer by adopting the dialect of an area where the user lives. The easy-to-understand answer generation unit generates an answer that is easy for anyone to understand regardless of the age and living environment of the user and the presence or absence of expert knowledge.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, the answers given by generative AI could be technical or contain expressions that are not suitable for certain age groups or regions, meaning that not everyone could understand them instantly.

[0005] The system according to the embodiment aims to generate answers that are easy to understand for anyone, regardless of the user's age, living environment, or whether or not they have specialized knowledge. [Means for solving the problem]

[0006] The system according to the embodiment includes an age optimization unit, a living environment optimization unit, a technical term optimization unit, a dialect optimization unit, and an easy-to-understand answer generation unit. The age optimization unit uses a generation AI to select appropriate language and words according to the user's age. The living environment optimization unit selects appropriate language and words according to the user's living environment. The technical term optimization unit generates answers in easy-to-understand language, avoiding technical terminology and difficult expressions. The dialect optimization unit generates answers by incorporating the dialect of the area in which the user lives. The easy-to-understand answer generation unit generates answers that are easy to understand for anyone, regardless of the user's age, living environment, or whether or not they have specialized knowledge. [Effects of the Invention]

[0007] The system according to the embodiment can generate answers that are easy to understand for anyone, regardless of the user's age, living environment, or whether or not they have specialized knowledge. [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) The answer optimization system according to the embodiment of the present invention uses a generation AI to generate answers in language and vocabulary that is easy to understand depending on the user's age and living environment. This allows anyone, regardless of age, gender, or region, to comfortably use the generation AI and enjoy its benefits.

[0029] An answer optimization system according to an embodiment includes an age optimization unit, a living environment optimization unit, a technical term optimization unit, a dialect optimization unit, and an easy-to-understand answer generation unit. The age optimization unit selects appropriate language and words according to the user's age. For example, the age optimization unit uses simple words and short sentences for children. The age optimization unit uses a slower pace and easier-to-understand words for elderly people. The age optimization unit generates answers based on prompts including information about the user's age and level of understanding. The living environment optimization unit selects appropriate language and words according to the user's living environment. For example, the living environment optimization unit uses standard Japanese for users living in urban areas. The living environment optimization unit incorporates the local dialect for users living in rural areas. The living environment optimization unit generates answers based on prompts including information about the user's living environment. The technical term optimization unit generates answers in easy-to-understand language, avoiding technical terminology and difficult expressions. For example, the technical term optimization unit provides explanations in general terms, avoiding technical terminology, for questions about medical care. Furthermore, the technical terminology optimization unit generates an answer based on a prompt including an instruction to avoid technical terminology. The dialect optimization unit generates an answer by incorporating the dialect of the region in which the user lives. For example, the dialect optimization unit generates an answer using Kansai dialect for a user living in the Kansai region. Furthermore, the dialect optimization unit generates an answer based on a prompt including an instruction to incorporate the dialect. The easy-to-understand answer generation unit generates an answer that is easy to understand for anyone, regardless of the user's age, living environment, or whether or not they have specialized knowledge. For example, the easy-to-understand answer generation unit explains even complex technical questions in simple terms. Furthermore, the easy-to-understand answer generation unit generates an answer based on a prompt including an instruction to generate an easy-to-understand answer. In this way, the answer optimization system according to the embodiment can generate answers that are easy to understand for anyone, regardless of the user's age, living environment, or whether or not they have specialized knowledge.

[0030] The age optimization unit can optimize language based on the user's educational level and interests. For example, the generation AI analyzes the user's educational level from the prompt and selects appropriate language. For example, it uses simple language for elementary school students and more complex language for high school students. The age optimization unit also extracts the user's interests from the prompt and generates answers based on them. For example, it uses scientific examples to explain things to children who are interested in science. The age optimization unit also combines the user's age and educational level to select the optimal language. For example, it provides easy-to-understand explanations that include technical terms for university students. This allows appropriate language to be selected based on the user's educational level and interests.

[0031] The age optimization unit can analyze the user's past dialogue history and select words that correspond to each individual's level of comprehension. For example, the generation AI in the age optimization unit analyzes the user's past dialogue history and evaluates the level of comprehension. For example, it prioritizes the use of words that were easy to understand in the past. The age optimization unit also extracts frequently used words and phrases from the user's dialogue history and generates answers based on them. For example, it repeatedly uses specific terms. The age optimization unit also learns language patterns that are easy for users to understand based on the past dialogue history and reflects these in the answers. For example, it frequently uses simple words. This makes it possible to select words that correspond to the user's level of comprehension based on the user's past dialogue history.

[0032] The age optimization unit can provide visual aids appropriate for the user's age. For example, the generation AI provides explanations using illustrations and animations for children. For example, it uses illustrations of animals to explain living things. The age optimization unit also provides videos with large, easy-to-read text for the elderly. For example, it explains health information using videos. The age optimization unit also selects visual aids appropriate for the user's age. For example, it uses colorful illustrations for younger people and simple diagrams for the elderly. This makes it possible to provide visual aids appropriate for the user's age.

[0033] The age optimization unit can add age-appropriate voice assistant functions and provide voice answers. For example, the generation AI provides voice answers in a gentle voice using simple words for children. For example, it may explain things in a fairy tale-like style. The age optimization unit also provides easy-to-understand voice answers at a slower pace for elderly people. For example, it may carefully explain health advice. The age optimization unit also adjusts the tone and speed of the voice assistant's voice according to the user's age. For example, it may use a lively voice for younger people and a calm voice for elderly people. This makes it possible to provide voice assistant functions appropriate for each age.

[0034] The living environment optimization unit can optimize language based on the user's cultural background and lifestyle habits. For example, the generation AI analyzes the user's cultural background from the prompt and selects appropriate language. For example, it uses words rooted in a specific culture. The living environment optimization unit also extracts the user's lifestyle habits from the prompt and generates answers based on them. For example, it uses examples related to agriculture for users in rural areas. The living environment optimization unit also combines the user's living environment and cultural background to select the optimal language. For example, it uses business terms for users in urban areas and regional terms for users in rural areas. This allows the appropriate language to be selected based on the user's cultural background and lifestyle habits.

[0035] The living environment optimization unit can generate answers that incorporate local news and trends. For example, the generation AI in the living environment optimization unit collects the latest news in the user's area from prompts and generates answers based on that. For example, it may include information about local events. The living environment optimization unit also analyzes trends in the user's area from prompts and generates answers based on that. For example, it may incorporate food and fashion that are popular in the area. The living environment optimization unit also collects local news and trends in real time and reflects them in answers. For example, it may include local weather and traffic information. This makes it possible to generate answers that incorporate local news and trends.

[0036] The living environment optimization unit can provide local event and service information tailored to the user's living environment. For example, the generation AI in the living environment optimization unit collects local event information in the area where the user lives from prompts and generates an answer based on that information. For example, it includes information on local festivals and events. The living environment optimization unit also analyzes service information in the area where the user lives from prompts and generates an answer based on that information. For example, it provides information on local restaurants and medical institutions. The living environment optimization unit also collects local event and service information in real time and reflects it in the answer. For example, it includes information on new stores and services in the area. This makes it possible to provide local event and service information tailored to the user's living environment.

[0037] The living environment optimization unit can provide visual assistance according to the living environment. For example, the generation AI collects maps of the area where the user lives from the prompt and generates an answer based on that. For example, it provides a map of local tourist spots and famous places. The living environment optimization unit also analyzes photos of the area where the user lives from the prompt and generates an answer based on that. For example, it provides photos of local scenery and buildings. The living environment optimization unit also collects maps and photos of the area in real time and reflects them in the answer. For example, it provides the latest photos and maps of the area. This makes it possible to provide visual assistance according to the living environment.

[0038] The terminology optimization unit can automatically evaluate the user's level of expertise and optimize the terminology accordingly. For example, the generation AI analyzes the user's level of expertise from the prompt and selects appropriate terminology. For example, it uses simple words for beginners and technical terms for experts. The terminology optimization unit also extracts the user's level of expertise from the prompt and generates answers based on that. For example, it uses technical terms for medical professionals for medical questions. The terminology optimization unit also evaluates the user's level of expertise in real time and selects appropriate terminology. For example, it uses technical terms for engineers for technical questions. This makes it possible to optimize the terminology according to the user's level of expertise.

[0039] The terminology optimization unit can automatically insert brief explanations of technical terms to aid comprehension. For example, the generation AI analyzes technical terms from the prompt and automatically inserts their brief explanations. For example, an explanation of medical terms is included in the answer. The terminology optimization unit also extracts brief explanations of technical terms from the prompt and incorporates them into the answer. For example, an explanation of technical terms is included in the answer. The terminology optimization unit also generates brief explanations of technical terms in real time and reflects them in the answer. For example, an explanation of legal terms is included in the answer. This allows brief explanations of technical terms to be automatically inserted to aid comprehension.

[0040] In addition to optimizing the terminology, the terminology optimization unit can provide related visual materials. For example, the generation AI collects diagrams related to the explanation of the terminology from the prompt and incorporates them into the answer. For example, an anatomical diagram is used to explain medical terminology. The terminology optimization unit also analyzes videos related to the explanation of the terminology from the prompt and incorporates them into the answer. For example, an operation video is used to explain technical terminology. The terminology optimization unit also collects visual materials related to the explanation of the terminology in real time and reflects them in the answer. For example, a flowchart is used to explain legal terminology. This makes it possible to provide related visual materials in addition to optimizing the terminology.

[0041] The terminology optimization unit can provide audio explanations in addition to optimizing the terminology. For example, the terminology optimization unit builds a system in which a generation AI provides audio explanations of terminology. For example, it provides audio explanations of medical terms. The terminology optimization unit also provides audio explanations of terminology to make it easier for users to understand. For example, it provides audio explanations of technical terms. The terminology optimization unit also converts the explanations of terminology into audio in real time and reflects this in the answer. For example, it provides audio explanations of legal terms. This makes it possible to provide audio explanations in addition to optimizing the terminology.

[0042] The dialect optimization unit can incorporate not only the user's dialect, but also regional expressions and slang. For example, the dialect optimization unit uses Kansai dialect slang to analyze the user's dialect from the prompt and incorporate regional expressions and slang into the answer. For example, Kansai dialect slang is used. The dialect optimization unit also extracts regional expressions from the prompt and generates an answer based on that. For example, Tohoku dialect expressions are used. The dialect optimization unit also collects regional expressions and slang in real time and reflects them in the answer. For example, Kyushu dialect slang is used. This makes it possible to incorporate not only the user's dialect, but also regional expressions and slang.

[0043] The dialect optimization unit can use a language model that accurately reflects dialect nuances and emotions. For example, the dialect optimization unit uses a language model that enables the generation AI to accurately reflect dialect nuances and emotions to generate an answer. For example, it accurately reflects emotional expressions in the Kansai dialect. The dialect optimization unit also analyzes a language model that accurately reflects dialect nuances and emotions from a prompt and generates an answer based on that. For example, it accurately reflects emotional expressions in the Tohoku dialect. The dialect optimization unit also collects dialect nuances and emotions in real time and uses a language model that reflects them. For example, it accurately reflects emotional expressions in the Kyushu dialect. This makes it possible to use a language model that accurately reflects dialect nuances and emotions.

[0044] The dialect optimization unit can provide information based on the culture and history of the region in addition to the dialect. For example, the generation AI collects information based on the culture and history of the region where the user lives from the prompt and generates an answer based on that information. For example, it includes traditional events and historical background of the region. The dialect optimization unit also analyzes the culture and history of the region where the user lives from the prompt and generates an answer based on that information. For example, it introduces traditional crafts and famous places of the region. The dialect optimization unit also collects information based on the culture and history of the region in real time and reflects that information in the answer. For example, it introduces historical events and cultural assets of the region. This makes it possible to provide information based on the culture and history of the region in addition to the dialect.

[0045] The dialect optimization unit can provide information about local music and art in addition to dialects. For example, the generation AI collects information about music and art in the user's area from prompts and generates answers based on that information. For example, it introduces traditional music and art works in the area. The dialect optimization unit also analyzes music and art in the user's area from prompts and generates answers based on that information. For example, it introduces local music festivals and art events. The dialect optimization unit also collects information about local music and art in real time and reflects that information in answers. For example, it introduces local artists and music groups. This makes it possible to provide information about local music and art in addition to dialects.

[0046] The easy-to-understand answer generation unit can evaluate the user's level of understanding in real time and adjust the answer accordingly. For example, the easy-to-understand answer generation unit uses a generation AI to evaluate the user's level of understanding in real time from prompts and select appropriate words. For example, if the level of understanding is low, simple words are used. The easy-to-understand answer generation unit also analyzes the user's level of understanding in real time and generates answers based on that. For example, if the level of understanding is high, detailed explanations are provided. The easy-to-understand answer generation unit also builds a system that evaluates the level of understanding in real time and adjusts the answer accordingly. For example, if the level of understanding is low, specific examples are used frequently. This makes it possible to evaluate the user's level of understanding in real time and adjust the answer accordingly.

[0047] The easy-to-understand answer generation unit can use multiple explanation methods to aid understanding. For example, the generation AI collects multiple explanation methods from a prompt and generates an answer based on them. For example, it uses analogies and metaphors. The easy-to-understand answer generation unit also analyzes multiple explanation methods from a prompt and generates an answer based on them. For example, it uses specific examples and metaphors. The easy-to-understand answer generation unit also collects multiple explanation methods in real time and reflects them in the answer. For example, it uses analogies and metaphors. This makes it possible to use multiple explanation methods to aid understanding.

[0048] The easy-to-understand answer generation unit can provide visual aids to aid understanding. For example, the generation AI collects visual aids from prompts and generates answers based on them. For example, it uses diagrams and animations. The easy-to-understand answer generation unit also analyzes visual aids from prompts and generates answers based on them. For example, it uses specific diagrams and animations. The easy-to-understand answer generation unit also collects visual aids in real time and reflects them in answers. For example, it uses diagrams and animations. This makes it possible to provide visual aids and aid understanding.

[0049] The easy-to-understand answer generation unit can provide audio explanations to aid understanding from both a visual and an auditory perspective. For example, the easy-to-understand answer generation unit uses audio explanations in which the generation AI collects audio explanations from prompts and generates answers based on the collected explanations. For example, it uses audio explanations. The easy-to-understand answer generation unit also analyzes audio explanations from prompts and generates answers based on the analyzed explanations. For example, it uses specific audio explanations. The easy-to-understand answer generation unit also collects audio explanations in real time and reflects them in the answer. For example, it uses audio explanations. This allows the provision of audio explanations to aid understanding from both a visual and an auditory perspective.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The answer optimization system may further include a health optimization unit that adjusts the answer based on the user's health condition. For example, if the user has high blood pressure, the health optimization unit provides advice on a low-salt diet. If the user has diabetes, the health optimization unit provides information on diet and exercise to manage blood sugar levels. The health optimization unit also analyzes information on the user's health condition from the prompt and generates an optimal answer based on that information. This makes it possible to provide appropriate advice according to the user's health condition.

[0052] The answer optimization system may further include an interest optimization unit that customizes answers based on the user's interests and preferences. For example, if the user likes music, the interest optimization unit may provide explanations using music-related examples. If the user likes sports, the interest optimization unit may provide explanations using sports-related examples. The interest optimization unit may also analyze information about the user's interests and preferences from the prompt and generate an optimal answer based on that information. This allows the system to provide answers customized to the user's interests and preferences.

[0053] The answer optimization system may further include a learning optimization unit that adjusts answers based on the user's learning style. For example, if the user is a visual learner, the learning optimization unit may provide explanations that make extensive use of diagrams and illustrations. If the user is an auditory learner, the learning optimization unit may provide explanations that use audio or music. The learning optimization unit may also analyze information about the user's learning style from the prompt and generate optimal answers based on that information. This allows for the provision of effective answers that match the user's learning style.

[0054] The answer optimization system may further include an occupation optimization unit that customizes answers based on the user's occupation. For example, if the user is a medical professional, the occupation optimization unit provides specialized information related to medicine. If the user is an engineer, the occupation optimization unit provides technical information. The occupation optimization unit may also analyze information about the user's occupation from the prompt and generate an optimal answer based on the information. This allows the system to provide specialized information according to the user's occupation.

[0055] The answer optimization system may further include a time optimization unit that adjusts the answer based on the user's time zone. For example, if the user asks a question at night, the time optimization unit provides an answer using words that will help the user relax. Alternatively, if the user asks a question in the morning, the time optimization unit provides an answer using words that will cheer the user up. The time optimization unit may also analyze information about the time zone in which the user asked the question from the prompt and generate an optimal answer based on that information. This allows the system to provide an appropriate answer according to the user's time zone.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The age-appropriateness module selects appropriate language and words depending on the user's age. For example, it uses simple words and short sentences for children, and slower paced and easier-to-understand words for seniors. It also generates answers based on prompts that include information about the user's age and level of comprehension. Step 2: The living environment optimization unit selects the appropriate language and words based on the user's living environment. For example, it uses standard Japanese for users living in urban areas and adopts the local dialect for users living in rural areas. It also generates answers based on prompts that include information about the user's living environment. Step 3: The terminology optimization unit generates answers in easy-to-understand language, avoiding technical jargon and difficult expressions. For example, it generates answers in general terms to answer medical questions, avoiding technical jargon. It also generates answers based on prompts that include instructions to avoid technical jargon. Step 4: The dialect optimization unit generates answers incorporating the dialect of the region where the user lives. For example, answers in Kansai dialect are generated for users living in the Kansai region. Answers are also generated based on prompts that include instructions to incorporate the dialect. Step 5: The easy-to-understand answer generator generates answers that are easy to understand for anyone, regardless of the user's age, living environment, or level of specialized knowledge. For example, it provides simple explanations for complex technical questions. It also generates answers based on prompts that include instructions for generating easy-to-understand answers.

[0058] (Example 2) The answer optimization system according to the embodiment of the present invention uses a generation AI to generate answers in language and vocabulary that is easy to understand depending on the user's age and living environment. This allows anyone, regardless of age, gender, or region, to comfortably use the generation AI and enjoy its benefits.

[0059] An answer optimization system according to an embodiment includes an age optimization unit, a living environment optimization unit, a technical term optimization unit, a dialect optimization unit, and an easy-to-understand answer generation unit. The age optimization unit selects appropriate language and words according to the user's age. For example, the age optimization unit uses simple words and short sentences for children. The age optimization unit uses a slower pace and easier-to-understand words for elderly people. The age optimization unit generates answers based on prompts including information about the user's age and level of understanding. The living environment optimization unit selects appropriate language and words according to the user's living environment. For example, the living environment optimization unit uses standard Japanese for users living in urban areas. The living environment optimization unit incorporates the local dialect for users living in rural areas. The living environment optimization unit generates answers based on prompts including information about the user's living environment. The technical term optimization unit generates answers in easy-to-understand language, avoiding technical terminology and difficult expressions. For example, the technical term optimization unit provides explanations in general terms, avoiding technical terminology, for questions about medical care. Furthermore, the technical terminology optimization unit generates an answer based on a prompt including an instruction to avoid technical terminology. The dialect optimization unit generates an answer by incorporating the dialect of the region in which the user lives. For example, the dialect optimization unit generates an answer using Kansai dialect for a user living in the Kansai region. Furthermore, the dialect optimization unit generates an answer based on a prompt including an instruction to incorporate the dialect. The easy-to-understand answer generation unit generates an answer that is easy to understand for anyone, regardless of the user's age, living environment, or whether or not they have specialized knowledge. For example, the easy-to-understand answer generation unit explains even complex technical questions in simple terms. Furthermore, the easy-to-understand answer generation unit generates an answer based on a prompt including an instruction to generate an easy-to-understand answer. In this way, the answer optimization system according to the embodiment can generate answers that are easy to understand for anyone, regardless of the user's age, living environment, or whether or not they have specialized knowledge.

[0060] The age optimization unit can optimize language based on the user's educational level and interests. For example, the generation AI analyzes the user's educational level from the prompt and selects appropriate language. For example, it uses simple language for elementary school students and more complex language for high school students. The age optimization unit also extracts the user's interests from the prompt and generates answers based on them. For example, it uses scientific examples to explain things to children who are interested in science. The age optimization unit also combines the user's age and educational level to select the optimal language. For example, it provides easy-to-understand explanations that include technical terms for university students. This allows appropriate language to be selected based on the user's educational level and interests.

[0061] The age optimization unit can analyze the user's past dialogue history and select words that correspond to each individual's level of comprehension. For example, the generation AI in the age optimization unit analyzes the user's past dialogue history and evaluates the level of comprehension. For example, it prioritizes the use of words that were easy to understand in the past. The age optimization unit also extracts frequently used words and phrases from the user's dialogue history and generates answers based on them. For example, it repeatedly uses specific terms. The age optimization unit also learns language patterns that are easy for users to understand based on the past dialogue history and reflects these in the answers. For example, it frequently uses simple words. This makes it possible to select words that correspond to the user's level of comprehension based on the user's past dialogue history.

[0062] The age optimization unit uses the emotion estimation function to adjust the choice of words according to the user's emotional state, thereby reducing stress. For example, the age optimization unit uses the emotion estimation function to select kind words when the user is feeling stressed. For example, encouraging words are used frequently. The age optimization unit also analyzes the user's emotional state in real time and selects words that elicit positive emotions. For example, compliments are used frequently. The age optimization unit also uses the emotion estimation function to provide more detailed explanations when the user is relaxed. For example, specific examples are used frequently. This allows the choice of words to be adjusted according to the user's emotional state, thereby reducing stress.

[0063] The age optimization unit can provide visual aids appropriate for the user's age. For example, the generation AI provides explanations using illustrations and animations for children. For example, it uses illustrations of animals to explain living things. The age optimization unit also provides videos with large, easy-to-read text for the elderly. For example, it explains health information using videos. The age optimization unit also selects visual aids appropriate for the user's age. For example, it uses colorful illustrations for younger people and simple diagrams for the elderly. This makes it possible to provide visual aids appropriate for the user's age.

[0064] The age optimization unit can add age-appropriate voice assistant functions and provide voice answers. For example, the generation AI provides voice answers in a gentle voice using simple words for children. For example, it may explain things in a fairy tale-like style. The age optimization unit also provides easy-to-understand voice answers at a slower pace for elderly people. For example, it may carefully explain health advice. The age optimization unit also adjusts the tone and speed of the voice assistant's voice according to the user's age. For example, it may use a lively voice for younger people and a calm voice for elderly people. This makes it possible to provide voice assistant functions appropriate for each age.

[0065] The age optimization unit can incorporate entertainment elements appropriate for the user's age into the answer using the emotion estimation function. For example, the age optimization unit can use the emotion estimation function to incorporate fun jokes and stories for children into the answer. For example, stories featuring animal characters can be used. The age optimization unit can also incorporate nostalgic stories and folk tales into the answer for elderly people. For example, episodes from the Showa era can be used. The age optimization unit can also select entertainment elements appropriate for the user's age. For example, the latest trends can be used for younger people, and old classics can be used for elderly people. This makes it possible to incorporate entertainment elements appropriate for the user's age into the answer.

[0066] The living environment optimization unit can optimize language based on the user's cultural background and lifestyle habits. For example, the generation AI analyzes the user's cultural background from the prompt and selects appropriate language. For example, it uses words rooted in a specific culture. The living environment optimization unit also extracts the user's lifestyle habits from the prompt and generates answers based on them. For example, it uses examples related to agriculture for users in rural areas. The living environment optimization unit also combines the user's living environment and cultural background to select the optimal language. For example, it uses business terms for users in urban areas and regional terms for users in rural areas. This allows the appropriate language to be selected based on the user's cultural background and lifestyle habits.

[0067] The living environment optimization unit can generate answers that incorporate local news and trends. For example, the generation AI in the living environment optimization unit collects the latest news in the user's area from prompts and generates answers based on that. For example, it may include information about local events. The living environment optimization unit also analyzes trends in the user's area from prompts and generates answers based on that. For example, it may incorporate food and fashion that are popular in the area. The living environment optimization unit also collects local news and trends in real time and reflects them in answers. For example, it may include local weather and traffic information. This makes it possible to generate answers that incorporate local news and trends.

[0068] The living environment optimization unit can use the emotion estimation function to generate answers that incorporate region-specific emotional expressions. The living environment optimization unit, for example, uses the emotion estimation function to incorporate region-specific emotional expressions into answers. For example, for a user in the Kansai region, emotional expressions in the Kansai dialect are used. The living environment optimization unit also analyzes emotional expressions in the region where the user lives from the prompt and generates answers based on the analysis. For example, for a user in the Tohoku region, emotional expressions in the Tohoku dialect are used. The living environment optimization unit also collects region-specific emotional expressions in real time and reflects them in answers. For example, regional dialects and slang are used. This makes it possible to generate answers that incorporate region-specific emotional expressions.

[0069] The living environment optimization unit can provide local event and service information tailored to the user's living environment. For example, the generation AI in the living environment optimization unit collects local event information in the area where the user lives from prompts and generates an answer based on that information. For example, it includes information on local festivals and events. The living environment optimization unit also analyzes service information in the area where the user lives from prompts and generates an answer based on that information. For example, it provides information on local restaurants and medical institutions. The living environment optimization unit also collects local event and service information in real time and reflects it in the answer. For example, it includes information on new stores and services in the area. This makes it possible to provide local event and service information tailored to the user's living environment.

[0070] The living environment optimization unit can provide visual assistance according to the living environment. For example, the generation AI collects maps of the area where the user lives from the prompt and generates an answer based on that. For example, it provides a map of local tourist spots and famous places. The living environment optimization unit also analyzes photos of the area where the user lives from the prompt and generates an answer based on that. For example, it provides photos of local scenery and buildings. The living environment optimization unit also collects maps and photos of the area in real time and reflects them in the answer. For example, it provides the latest photos and maps of the area. This makes it possible to provide visual assistance according to the living environment.

[0071] The living environment optimization unit can incorporate entertainment elements based on local culture and customs into answers using the emotion estimation function. The living environment optimization unit, for example, uses the emotion estimation function to incorporate entertainment elements based on local culture and customs into answers. For example, it may introduce traditional local festivals and events. The living environment optimization unit also analyzes the culture and customs of the area where the user lives from the prompt and generates answers based on that. For example, it may introduce traditional local cuisine and crafts. The living environment optimization unit also collects entertainment elements based on local culture and customs in real time and reflects them in answers. For example, it may introduce traditional local music and dance. This makes it possible to incorporate entertainment elements based on local culture and customs into answers.

[0072] The terminology optimization unit can automatically evaluate the user's level of expertise and optimize the terminology accordingly. For example, the generation AI analyzes the user's level of expertise from the prompt and selects appropriate terminology. For example, it uses simple words for beginners and technical terms for experts. The terminology optimization unit also extracts the user's level of expertise from the prompt and generates answers based on that. For example, it uses technical terms for medical professionals for medical questions. The terminology optimization unit also evaluates the user's level of expertise in real time and selects appropriate terminology. For example, it uses technical terms for engineers for technical questions. This makes it possible to optimize the terminology according to the user's level of expertise.

[0073] The terminology optimization unit can automatically insert brief explanations of technical terms to aid comprehension. For example, the generation AI analyzes technical terms from the prompt and automatically inserts their brief explanations. For example, an explanation of medical terms is included in the answer. The terminology optimization unit also extracts brief explanations of technical terms from the prompt and incorporates them into the answer. For example, an explanation of technical terms is included in the answer. The terminology optimization unit also generates brief explanations of technical terms in real time and reflects them in the answer. For example, an explanation of legal terms is included in the answer. This allows brief explanations of technical terms to be automatically inserted to aid comprehension.

[0074] The technical term optimization unit can use the emotion estimation function to select words that reduce the stress that technical terms cause to the user. The technical term optimization unit, for example, uses the emotion estimation function to select words that reduce the stress that technical terms cause to the user. For example, it avoids technical terms and uses simple words. The technical term optimization unit also analyzes the emotional state of the user in real time and selects words that reduce stress. For example, it carefully explains technical terms. The technical term optimization unit also uses the emotion estimation function to avoid technical terms and select gentler words when the user is feeling stressed. For example, it uses general words instead of technical terms. In this way, it is possible to select words that reduce the stress that technical terms cause to the user.

[0075] In addition to optimizing the terminology, the terminology optimization unit can provide related visual materials. For example, the generation AI collects diagrams related to the explanation of the terminology from the prompt and incorporates them into the answer. For example, an anatomical diagram is used to explain medical terminology. The terminology optimization unit also analyzes videos related to the explanation of the terminology from the prompt and incorporates them into the answer. For example, an operation video is used to explain technical terminology. The terminology optimization unit also collects visual materials related to the explanation of the terminology in real time and reflects them in the answer. For example, a flowchart is used to explain legal terminology. This makes it possible to provide related visual materials in addition to optimizing the terminology.

[0076] The terminology optimization unit can provide audio explanations in addition to optimizing the terminology. For example, the terminology optimization unit builds a system in which a generation AI provides audio explanations of terminology. For example, it provides audio explanations of medical terms. The terminology optimization unit also provides audio explanations of terminology to make it easier for users to understand. For example, it provides audio explanations of technical terms. The terminology optimization unit also converts the explanations of terminology into audio in real time and reflects this in the answer. For example, it provides audio explanations of legal terms. This makes it possible to provide audio explanations in addition to optimizing the terminology.

[0077] The terminology optimization unit can use the emotion estimation function to incorporate entertainment elements that attract the user's interest in addition to optimizing the terminology. The terminology optimization unit, for example, uses the emotion estimation function to incorporate entertainment elements into explanations of terminology. For example, it uses funny anecdotes related to explanations of medical terms. The terminology optimization unit also attracts the user's interest by incorporating entertainment elements into explanations of terminology. For example, it uses jokes related to explanations of technical terms. The terminology optimization unit also uses the emotion estimation function to collect entertainment elements that attract the user's interest in real time and reflect them in answers. For example, it uses stories related to explanations of legal terms. This makes it possible to incorporate entertainment elements that attract the user's interest in addition to optimizing the terminology.

[0078] The dialect optimization unit can incorporate not only the user's dialect, but also regional expressions and slang. For example, the dialect optimization unit uses Kansai dialect slang to analyze the user's dialect from the prompt and incorporate regional expressions and slang into the answer. For example, Kansai dialect slang is used. The dialect optimization unit also extracts regional expressions from the prompt and generates an answer based on that. For example, Tohoku dialect expressions are used. The dialect optimization unit also collects regional expressions and slang in real time and reflects them in the answer. For example, Kyushu dialect slang is used. This makes it possible to incorporate not only the user's dialect, but also regional expressions and slang.

[0079] The dialect optimization unit can use a language model that accurately reflects dialect nuances and emotions. For example, the dialect optimization unit uses a language model that enables the generation AI to accurately reflect dialect nuances and emotions to generate an answer. For example, it accurately reflects emotional expressions in the Kansai dialect. The dialect optimization unit also analyzes a language model that accurately reflects dialect nuances and emotions from a prompt and generates an answer based on that. For example, it accurately reflects emotional expressions in the Tohoku dialect. The dialect optimization unit also collects dialect nuances and emotions in real time and uses a language model that reflects them. For example, it accurately reflects emotional expressions in the Kyushu dialect. This makes it possible to use a language model that accurately reflects dialect nuances and emotions.

[0080] The dialect optimization unit can use the emotion estimation function to generate an answer that takes into account the emotional impact of a dialect on a user. The dialect optimization unit, for example, uses the emotion estimation function to generate an answer that takes into account the emotional impact of a dialect on a user. For example, the dialect optimization unit takes into account the familiarity that Kansai dialect gives to a user. The dialect optimization unit also analyzes the emotional state of a user in real time to generate an answer that takes into account the emotional impact of a dialect. For example, the dialect optimization unit takes into account the sense of security that Tohoku dialect gives to a user. The dialect optimization unit also uses the emotion estimation function to collect the emotional impact that dialects give to a user in real time and reflects it in an answer. For example, the dialect optimization unit takes into account the familiarity that Kyushu dialect gives to a user. This makes it possible to generate an answer that takes into account the emotional impact of a dialect on a user.

[0081] The dialect optimization unit can provide information based on the culture and history of the region in addition to the dialect. For example, the generation AI collects information based on the culture and history of the region where the user lives from the prompt and generates an answer based on that information. For example, it includes traditional events and historical background of the region. The dialect optimization unit also analyzes the culture and history of the region where the user lives from the prompt and generates an answer based on that information. For example, it introduces traditional crafts and famous places of the region. The dialect optimization unit also collects information based on the culture and history of the region in real time and reflects that information in the answer. For example, it introduces historical events and cultural assets of the region. This makes it possible to provide information based on the culture and history of the region in addition to the dialect.

[0082] The dialect optimization unit can provide information about local music and art in addition to dialects. For example, the generation AI collects information about music and art in the user's area from prompts and generates answers based on that information. For example, it introduces traditional music and art works in the area. The dialect optimization unit also analyzes music and art in the user's area from prompts and generates answers based on that information. For example, it introduces local music festivals and art events. The dialect optimization unit also collects information about local music and art in real time and reflects that information in answers. For example, it introduces local artists and music groups. This makes it possible to provide information about local music and art in addition to dialects.

[0083] The dialect optimization unit can incorporate regional humor and jokes into answers in addition to dialects using the emotion estimation function. The dialect optimization unit, for example, uses the emotion estimation function to incorporate regional humor and jokes into answers. For example, jokes in Kansai dialect are used for users in the Kansai region. The dialect optimization unit also analyzes humor and jokes from the region where the user lives from the prompt and generates answers based on that. For example, jokes in Tohoku dialect are used for users in the Tohoku region. The dialect optimization unit also collects regional humor and jokes in real time and reflects them in answers. For example, jokes in Kyushu dialect are used for users in the Kyushu region. This makes it possible to incorporate regional humor and jokes into answers in addition to dialects.

[0084] The easy-to-understand answer generation unit can evaluate the user's level of understanding in real time and adjust the answer accordingly. For example, the easy-to-understand answer generation unit uses a generation AI to evaluate the user's level of understanding in real time from prompts and select appropriate words. For example, if the level of understanding is low, simple words are used. The easy-to-understand answer generation unit also analyzes the user's level of understanding in real time and generates answers based on that. For example, if the level of understanding is high, detailed explanations are provided. The easy-to-understand answer generation unit also builds a system that evaluates the level of understanding in real time and adjusts the answer accordingly. For example, if the level of understanding is low, specific examples are used frequently. This makes it possible to evaluate the user's level of understanding in real time and adjust the answer accordingly.

[0085] The easy-to-understand answer generation unit can use multiple explanation methods to aid understanding. For example, the generation AI collects multiple explanation methods from a prompt and generates an answer based on them. For example, it uses analogies and metaphors. The easy-to-understand answer generation unit also analyzes multiple explanation methods from a prompt and generates an answer based on them. For example, it uses specific examples and metaphors. The easy-to-understand answer generation unit also collects multiple explanation methods in real time and reflects them in the answer. For example, it uses analogies and metaphors. This makes it possible to use multiple explanation methods to aid understanding.

[0086] The easy-to-understand answer generation unit can use the emotion estimation function to generate an answer that is easy to emotionally empathize with according to the user's level of understanding. The easy-to-understand answer generation unit, for example, uses the emotion estimation function to generate an answer that is easy to emotionally empathize with according to the user's level of understanding. For example, if the level of understanding is low, encouraging words are used. The easy-to-understand answer generation unit also analyzes the user's level of understanding in real time to generate an answer that is easy to emotionally empathize with. For example, if the level of understanding is high, compliments are used. The easy-to-understand answer generation unit also uses the emotion estimation function to generate an answer that is easy to emotionally empathize with according to the user's level of understanding in real time. For example, if the level of understanding is low, kind words are used. This makes it possible to generate an answer that is easy to emotionally empathize with according to the user's level of understanding.

[0087] The easy-to-understand answer generation unit can provide visual aids to aid understanding. For example, the generation AI collects visual aids from prompts and generates answers based on them. For example, it uses diagrams and animations. The easy-to-understand answer generation unit also analyzes visual aids from prompts and generates answers based on them. For example, it uses specific diagrams and animations. The easy-to-understand answer generation unit also collects visual aids in real time and reflects them in answers. For example, it uses diagrams and animations. This makes it possible to provide visual aids and aid understanding.

[0088] The easy-to-understand answer generation unit can provide audio explanations to aid understanding from both a visual and an auditory perspective. For example, the easy-to-understand answer generation unit uses audio explanations in which the generation AI collects audio explanations from prompts and generates answers based on the collected explanations. For example, it uses audio explanations. The easy-to-understand answer generation unit also analyzes audio explanations from prompts and generates answers based on the analyzed explanations. For example, it uses specific audio explanations. The easy-to-understand answer generation unit also collects audio explanations in real time and reflects them in the answer. For example, it uses audio explanations. This allows the provision of audio explanations to aid understanding from both a visual and an auditory perspective.

[0089] The easy-to-understand answer generation unit can use the emotion estimation function to incorporate entertainment elements that will interest the user into the answer. The easy-to-understand answer generation unit, for example, uses the emotion estimation function to incorporate entertainment elements that will interest the user into the answer. For example, it uses funny anecdotes and jokes. The easy-to-understand answer generation unit also analyzes the emotional state of the user in real time and incorporates entertainment elements that will interest the user into the answer. For example, it uses stories that are easy to emotionally empathize with. The easy-to-understand answer generation unit also uses the emotion estimation function to collect entertainment elements that will interest the user in real time and reflect them in the answer. For example, it uses the latest trends and topics. This makes it possible to incorporate entertainment elements that will interest the user into the answer.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The answer optimization system may further include a health optimization unit that adjusts the answer based on the user's health condition. For example, if the user has high blood pressure, the health optimization unit provides advice on a low-salt diet. If the user has diabetes, the health optimization unit provides information on diet and exercise to manage blood sugar levels. The health optimization unit also analyzes information on the user's health condition from the prompt and generates an optimal answer based on that information. This makes it possible to provide appropriate advice according to the user's health condition.

[0092] The answer optimization system may further include an interest optimization unit that customizes answers based on the user's interests and preferences. For example, if the user likes music, the interest optimization unit may provide explanations using music-related examples. If the user likes sports, the interest optimization unit may provide explanations using sports-related examples. The interest optimization unit may also analyze information about the user's interests and preferences from the prompt and generate an optimal answer based on that information. This allows the system to provide answers customized to the user's interests and preferences.

[0093] The answer optimization system may further include a learning optimization unit that adjusts answers based on the user's learning style. For example, if the user is a visual learner, the learning optimization unit may provide explanations that make extensive use of diagrams and illustrations. If the user is an auditory learner, the learning optimization unit may provide explanations that use audio or music. The learning optimization unit may also analyze information about the user's learning style from the prompt and generate optimal answers based on that information. This allows for the provision of effective answers that match the user's learning style.

[0094] The answer optimization system may further include an occupation optimization unit that customizes answers based on the user's occupation. For example, if the user is a medical professional, the occupation optimization unit provides specialized information related to medicine. If the user is an engineer, the occupation optimization unit provides technical information. The occupation optimization unit may also analyze information about the user's occupation from the prompt and generate an optimal answer based on the information. This allows the system to provide specialized information according to the user's occupation.

[0095] The answer optimization system may further include a time optimization unit that adjusts the answer based on the user's time zone. For example, if the user asks a question at night, the time optimization unit provides an answer using words that will help the user relax. Alternatively, if the user asks a question in the morning, the time optimization unit provides an answer using words that will cheer the user up. The time optimization unit may also analyze information about the time zone in which the user asked the question from the prompt and generate an optimal answer based on that information. This allows the system to provide an appropriate answer according to the user's time zone.

[0096] The answer optimization system may further include an emotion optimization unit that adjusts the answer based on the user's emotional state. For example, if the user is sad, the emotion optimization unit provides an answer using comforting words. If the user is angry, the emotion optimization unit provides advice on how to stay calm. The emotion optimization unit also analyzes information about the user's emotional state from the prompt and generates an optimal answer based on that information. This allows the system to provide an appropriate answer according to the user's emotional state.

[0097] The answer optimization system may further include a stress optimization unit that adjusts the answer based on the user's stress level. For example, if the user is in a high stress state, the stress optimization unit provides an answer using words that will help the user relax. Alternatively, if the user is in a low stress state, the stress optimization unit provides more detailed information. The stress optimization unit may also analyze information related to the user's stress level from the prompt and generate an optimal answer based on that information. This allows the system to provide an appropriate answer according to the user's stress level.

[0098] The answer optimization system may further include a motivation optimization unit that adjusts the answer based on the user's motivation level. For example, if the user is in a low motivation state, the motivation optimization unit provides an answer using encouraging words. Alternatively, if the user is in a high motivation state, the motivation optimization unit provides a challenging task. Furthermore, the motivation optimization unit analyzes information about the user's motivation level from the prompt and generates an optimal answer based on that information. This allows the system to provide an appropriate answer according to the user's motivation level.

[0099] The answer optimization system can further incorporate entertainment elements based on the user's emotional state. For example, using the emotion estimation function, if the user is sad, it can incorporate fun jokes or stories into the answer. On the other hand, if the user is angry, it can provide entertainment elements that will help the user relax. In addition, using the emotion estimation function, it can collect entertainment elements according to the user's emotional state in real time and reflect them in the answer. This allows entertainment elements according to the user's emotional state to be incorporated into the answer.

[0100] The answer optimization system can further provide visual assistance based on the user's emotional state. For example, by using the emotion estimation function, if the user is feeling stressed, it can provide images or videos that help the user relax. If the user is relaxed, it can provide more detailed visual assistance. Furthermore, by using the emotion estimation function, it can collect visual assistance according to the user's emotional state in real time and reflect it in the answer. This makes it possible to provide visual assistance according to the user's emotional state.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The age-appropriateness module selects appropriate language and words depending on the user's age. For example, it uses simple words and short sentences for children, and slower paced and easier-to-understand words for seniors. It also generates answers based on prompts that include information about the user's age and level of comprehension. Step 2: The living environment optimization unit selects the appropriate language and words based on the user's living environment. For example, it uses standard Japanese for users living in urban areas and adopts the local dialect for users living in rural areas. It also generates answers based on prompts that include information about the user's living environment. Step 3: The terminology optimization unit generates answers in easy-to-understand language, avoiding technical jargon and difficult expressions. For example, it generates answers in general terms to answer medical questions, avoiding technical jargon. It also generates answers based on prompts that include instructions to avoid technical jargon. Step 4: The dialect optimization unit generates answers incorporating the dialect of the region where the user lives. For example, answers in Kansai dialect are generated for users living in the Kansai region. Answers are also generated based on prompts that include instructions to incorporate the dialect. Step 5: The easy-to-understand answer generator generates answers that are easy to understand for anyone, regardless of the user's age, living environment, or level of specialized knowledge. For example, it provides simple explanations for complex technical questions. It also generates answers based on prompts that include instructions for generating easy-to-understand answers.

[0103] 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.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] 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.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] 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.

[0130] 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.

[0131] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0132] 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.

[0133] 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.

[0134] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] In the robot 414, 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 robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0148] 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.

[0149] 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.

[0150] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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. [Explanation of symbols]

[0170] 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. Using generative AI, an age-appropriateness unit that selects appropriate language and words according to the user's age; a living environment optimization unit that selects an appropriate language or words according to the user's living environment; a terminology optimization unit that generates answers in easy-to-understand language, avoiding technical terms and difficult expressions; a dialect optimization unit that generates answers by incorporating the dialect of the area where the user lives; and an easy-to-understand answer generation unit that generates answers that are easy to understand for anyone, regardless of the user's age, living environment, or whether or not they have specialized knowledge. A system characterized by:

2. The age optimization unit Adapting language based on the user's education level and interests 2. The system of claim 1.

3. The age optimization unit Analyze the user's past dialogue history and select words that correspond to the individual's level of understanding 2. The system of claim 1.

4. The age optimization unit Adjusting the user's choice of words depending on their emotional state to reduce stress 2. The system of claim 1.

5. The age optimization unit Providing visual aids appropriate to the user's age 2. The system of claim 1.

6. The age optimization unit Adding age-appropriate voice assistant functionality to provide spoken answers 2. The system of claim 1.

Images