System

Abstract

An object of a system according to an embodiment is to analyze a user's speech and automatically generate an appropriate prompt.SOLUTION: A system includes an analysis unit, a generation unit, and an instruction unit. The analysis unit analyzes an utterance of a user. The generation section generates a question based on a result of the analysis by the analysis section. The instructor sends an instruction to the specialized generation AI based on the question generated by the generator.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, it was difficult to set appropriate prompts to effectively utilize generative AI, which meant that users could not fully enjoy its benefits.

[0005] The system according to the embodiment aims to analyze user utterances and automatically generate appropriate prompts. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a generation unit, and an instruction unit. The analysis unit analyzes user utterances. The generation unit generates questions based on the results of the analysis by the analysis unit. The instruction unit sends instructions to the specialized generation AI based on the questions generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze the user's utterances and automatically generate appropriate prompts. [Brief explanation of the drawings]

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

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

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention solves the problem of difficulty in setting appropriate prompts (questions) when using generative AI. In this system, a generative AI converses with a user, discovers the user's potential challenges, and automatically generates appropriate "questions." This system works in conjunction with specialized generative AIs, such as text generation and image generation, to perform tasks. For example, a user initiates a conversation with a generative AI, which analyzes the user's utterances to identify potential challenges. The generative AI then automatically generates appropriate "questions" based on the identified challenges and sends instructions to the specialized generative AI. This system allows users to benefit from generative AI without setting appropriate prompts. The system analyzes the user's utterances, generates appropriate questions, and sends instructions to the specialized generative AI, allowing users to benefit from generative AI without setting appropriate prompts. For example, if a user says, "I want ideas for a new project," the generative AI analyzes the utterance and generates a question such as, "What are the specific steps to generate ideas for a new project?" and sends instructions to the text generation AI. This allows users to obtain specific ideas.

[0029] A generative AI assistance system according to an embodiment includes an analysis unit, a generation unit, and an instruction unit. The analysis unit analyzes a user's utterance. The user's utterance may be, for example, a voice input or a text input, but is not limited to these examples. The analysis unit analyzes the utterance using, for example, natural language processing technology. The analysis unit can also analyze the utterance using sentiment analysis technology. The analysis unit can also analyze the user's utterance in real time. For example, the analysis unit converts a voice input into text and analyzes the text. The generation unit uses a generative AI to generate a question based on the analysis result by the analysis unit. The question may be, for example, a question sentence or a multiple-choice format, but is not limited to these examples. For example, the generation unit uses a generative AI (for example, a text generation AI or a multimodal generation AI) to generate an appropriate question based on the user's utterance. The generation unit can also use the generative AI to understand the context of the user's utterance and generate an appropriate question. The instruction unit sends an instruction to a specialized generative AI based on the question generated by the generation unit. Examples of specialized generative AI include, but are not limited to, sentence generation AI and image generation AI. For example, the instruction unit may send the generated question to the sentence generation AI to cause it to perform a sentence generation task. The instruction unit may also send the generated question to the image generation AI to cause it to perform an image generation task. As a result, the generative AI support system according to the embodiment analyzes user utterances, generates appropriate questions, and sends instructions to the specialized generative AI, allowing the user to benefit from the generative AI without having to set appropriate prompts.

[0030] The analysis unit can analyze user utterances and identify potential issues. The analysis unit, for example, analyzes user utterances using natural language processing technology. For example, the analysis unit extracts frequently occurring issues from user utterances and identifies potential issues. The analysis unit can also analyze user utterances using sentiment analysis technology to identify user needs. For example, the analysis unit analyzes the emotional tone of the user utterances and identifies potential issues. The analysis unit can also analyze user utterances in real time and instantly identify potential issues. For example, the analysis unit converts voice input into text and analyzes the text to identify potential issues. In this way, by analyzing user utterances and identifying potential issues, more appropriate questions can be generated. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input user utterance data into a generation AI and have the generation AI identify potential issues.

[0031] The generation unit can generate an appropriate question based on the identified task. The generation unit generates an appropriate question based on the identified task, for example, using a generation AI. For example, the generation unit uses a generation AI (e.g., a text generation AI or a multimodal generation AI) to generate a question based on the identified task. The generation unit can also use the generation AI to generate multiple-choice questions based on the identified task. The generation unit can also use the generation AI to understand the context and generate an appropriate question based on the identified task. For example, the generation unit collects related information based on the identified task and generates a question based on that information. This allows the generation AI to generate an appropriate question based on the identified task, making the generation AI's instructions more effective. Some or all of the above-described processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input identified task data into the generation AI and cause the generation AI to generate an appropriate question.

[0032] The instruction unit can send instructions to the sentence generation AI based on the generated question. The instruction unit, for example, sends the generated question to the sentence generation AI and causes it to perform a sentence generation task. For example, the instruction unit can send the generated question to the sentence generation AI, causing the sentence generation AI to generate a sentence based on the question. The instruction unit can also send the generated question to the sentence generation AI, causing the sentence generation AI to generate a template-based sentence based on the question. The instruction unit can also send the generated question to the sentence generation AI, causing the sentence generation AI to generate a sentence using natural language generation technology based on the question. In this way, the sentence generation task is performed by sending instructions to the sentence generation AI based on the generated question. Some or all of the above-mentioned processing in the instruction unit may be performed using AI, for example, or may be performed without using AI. For example, the instruction unit can input generated question data to the generation AI and cause the generation AI to execute the instructions to the sentence generation AI.

[0033] The instruction unit can send instructions to the image generation AI based on the generated question. The instruction unit, for example, sends the generated question to the image generation AI and causes it to execute an image generation task. For example, the instruction unit can send the generated question to the image generation AI, causing the image generation AI to generate an image based on the question. The instruction unit can also send the generated question to the image generation AI, causing the image generation AI to generate an image using deep learning technology based on the question. The instruction unit can also send the generated question to the image generation AI, causing the image generation AI to generate an image using image synthesis technology based on the question. In this way, the image generation task is executed by sending instructions to the image generation AI based on the generated question. Some or all of the above-mentioned processing in the instruction unit may be performed using AI, for example, or may be performed without using AI. For example, the instruction unit can input generated question data to the generation AI and cause the generation AI to execute the instructions to the image generation AI.

[0034] The analysis unit can analyze a user's past comment history and select an analysis algorithm. For example, the analysis unit stores the user's past comment history as log data and analyzes it using text mining technology. For example, the analysis unit selects an optimal analysis algorithm based on keywords frequently used by the user in the past. The analysis unit can also analyze the user's past comment patterns and select an optimal analysis algorithm for a specific topic. The analysis unit can also customize the analysis algorithm based on the user's past feedback. For example, the analysis unit adjusts the analysis algorithm based on the user's past feedback. This allows the analysis of the past comment history to select an optimal analysis algorithm and improve analysis accuracy. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input past comment history data into a generation AI and have the generation AI select an analysis algorithm.

[0035] When analyzing comments, the analysis unit can filter based on the user's current situation and areas of interest. The analysis unit, for example, considers location information and time of day to identify the user's current situation. For example, the analysis unit prioritizes analyzing comments related to the user's current project. The analysis unit can also filter relevant comments based on the user's areas of interest. For example, the analysis unit identifies the user's areas of interest based on the user's past search history and social media activity. The analysis unit can also select appropriate comments based on the user's current situation (e.g., at work, on break). For example, if the user is at work, the analysis unit prioritizes analyzing work-related comments. This enables highly relevant analysis by filtering based on the user's current situation and areas of interest. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's current situation data and area of ​​interest data into the generation AI and have the generation AI perform filtering.

[0036] When analyzing a utterance, the analysis unit can select the optimal analysis means depending on the user's input method. For example, if the user uses voice input, the analysis unit analyzes the utterance using voice recognition technology. For example, the analysis unit converts the voice input into text and analyzes the text. Furthermore, if the user uses text input, the analysis unit can also analyze the utterance using natural language processing technology. For example, the analysis unit analyzes the text input and identifies the intention of the utterance. Furthermore, if the user uses images, the analysis unit can also analyze the utterance using image recognition technology. For example, the analysis unit analyzes the images and understands their contents. This improves analysis accuracy by selecting the optimal analysis means depending on the user's input method. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's input data into a generation AI and have the generation AI select the optimal analysis means.

[0037] When analyzing utterances, the analysis unit can prioritize analyzing highly relevant utterances by taking into account the user's geographical location information. The analysis unit, for example, collects the user's geographical location information using GPS data or an IP address. For example, if the user is in a specific area, the analysis unit prioritizes analyzing utterances related to that area. Furthermore, if the user is traveling, the analysis unit can prioritize analyzing utterances related to the user's travel destination. Furthermore, if the user is at home, the analysis unit can prioritize analyzing utterances related to information about the area around the user's home. For example, the analysis unit filters utterances related to the area based on the user's geographical location information. This allows for prioritized analysis of highly relevant utterances by taking the user's geographical location information into account. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's geographical location information data into the generation AI and cause the generation AI to perform prioritized analysis of highly relevant utterances.

[0038] When analyzing comments, the analysis unit can analyze the user's social media activity and analyze related comments. For example, the analysis unit saves the user's social media activity as log data and analyzes it using text mining technology. For example, the analysis unit analyzes comments based on keywords frequently used by the user on social media. The analysis unit can also analyze the content of the user's social media posts and analyze related comments. The analysis unit can also analyze related comments by referring to the activities of the user's friends on social media. For example, the analysis unit filters out highly relevant comments based on the user's social media activity. This makes it easier to analyze related comments by analyzing social media activity. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's social media activity data into a generation AI and have the generation AI analyze related comments.

[0039] When analyzing utterances, the analysis unit can customize the analysis method by reflecting the user's past feedback. The analysis unit, for example, collects and analyzes the user's past feedback as survey results or user reviews. For example, the analysis unit adjusts the analysis method based on the user's past feedback. The analysis unit can also prioritize the use of a specific analysis method based on the user's past feedback. The analysis unit can also optimize the analysis method by reflecting the user's feedback in real time. For example, the analysis unit customizes the analysis algorithm based on the user's feedback. By reflecting the past feedback, the analysis method is customized and accuracy is improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past feedback data into the generation AI and have the generation AI customize the analysis method.

[0040] When generating a question, the generation unit can adjust the level of detail of the question based on the importance of the identified issue. The generation unit, for example, evaluates the importance of the identified issue based on the scope of impact and the urgency of resolution. For example, the generation unit generates a detailed question for an issue of high importance. The generation unit can also generate a concise question for an issue of low importance. The generation unit can also generate a question with an appropriate level of detail for an issue of medium importance. In this way, by adjusting the level of detail of the question based on the importance of the issue, an appropriate question can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the identified issue data into a generation AI and cause the generation AI to adjust the level of detail of the question.

[0041] When generating a question, the generation unit can apply different generation algorithms depending on the category of the question. For example, the generation unit classifies question categories into technical questions, business questions, creative questions, etc. For example, the generation unit applies a technology-specialized generation algorithm to technical questions. The generation unit can also apply a creativity-oriented generation algorithm to creative questions. The generation unit can also apply a business-specialized generation algorithm to business-related questions. In this way, appropriate questions can be generated by applying different generation algorithms depending on the category of the question. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input question category data into the generation AI and cause the generation AI to apply different generation algorithms.

[0042] When generating a question, the generation unit can improve the accuracy of the generation by referring to the user's past question generation results. For example, the generation unit saves the user's past question generation results as log data and analyzes them using text mining technology. For example, the generation unit analyzes the results of questions generated by the user in the past to improve accuracy. The generation unit can also select an optimal generation algorithm from the user's past question generation results. The generation unit can also improve the question generation method based on user feedback. For example, the generation unit adjusts the generation algorithm based on user feedback. This improves the accuracy of generation by referring to the past question generation results. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input past question generation result data into the generation AI and cause the generation AI to improve the accuracy of generation.

[0043] When generating questions, the generation unit can determine the priority of the questions based on the time when the issues occurred. The generation unit identifies the time when the issues occurred, for example, using a timestamp or an event log. For example, the generation unit generates questions with priority for urgent issues. The generation unit can also generate questions for long-term issues later. The generation unit can also generate questions with an appropriate priority for medium-term issues. In this way, by determining the priority of questions based on the time when the issues occurred, appropriate questions can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the time when the issues occurred into the generation AI and have the generation AI determine the priority of the questions.

[0044] When generating questions, the generation unit can adjust the order of questions based on the relevance of the tasks. The generation unit evaluates the relevance of tasks based on, for example, a common theme or a scope of influence. For example, the generation unit generates questions first for tasks with high relevance. The generation unit can also generate questions later for tasks with low relevance. The generation unit can also generate questions in an appropriate order for tasks with medium relevance. In this way, appropriate questions can be generated by adjusting the order of questions based on the relevance of the tasks. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input task relevance data into the generation AI and have the generation AI adjust the order of questions.

[0045] When generating a question, the generation unit can adjust the use of technical terminology in the question according to the user's level of expertise. The generation unit, for example, evaluates the user's level of expertise based on qualification information and past comments. For example, the generation unit generates questions that use a lot of technical terminology for users with high levels of expertise. The generation unit can also generate questions in simple language for users with low levels of expertise. The generation unit can also generate questions that use appropriate technical terminology for users with medium levels of expertise. In this way, appropriate questions can be generated by adjusting the use of technical terminology according to the user's level of expertise. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0046] When giving instructions, the instruction unit can adjust the level of detail of the instructions based on the importance of the generated question. The instruction unit, for example, evaluates the importance of the generated question based on the scope of impact and the urgency of resolution. For example, the instruction unit provides detailed instructions for questions of high importance. The instruction unit can also provide concise instructions for questions of low importance. The instruction unit can also provide instructions with an appropriate level of detail for questions of medium importance. In this way, by adjusting the level of detail of the instructions based on the importance of the generated question, appropriate instructions can be provided. Some or all of the above-mentioned processing in the instruction unit may be performed, for example, using AI or without using AI. For example, the instruction unit can input the generated question data to the generation AI and cause the generation AI to adjust the level of detail of the instructions.

[0047] When giving instructions, the instruction unit can apply different instruction algorithms depending on the type of specialized generation AI. The instruction unit, for example, classifies the types of specialized generation AI into sentence generation AI, image generation AI, voice generation AI, etc. For example, the instruction unit applies an instruction algorithm specialized for sentence generation to a sentence generation AI. The instruction unit can also apply an instruction algorithm specialized for image generation to an image generation AI. The instruction unit can also apply an instruction algorithm specialized for voice generation to a voice generation AI. In this way, by applying different instruction algorithms depending on the type of specialized generation AI, appropriate instructions can be provided. Some or all of the above-mentioned processing in the instruction unit may be performed, for example, using AI or without AI. For example, the instruction unit can input type data of the specialized generation AI to the generation AI and cause the generation AI to apply different instruction algorithms.

[0048] When giving instructions, the instruction unit can improve the accuracy of the instructions by referring to the user's past instruction results. The instruction unit, for example, stores the user's past instruction results as log data and analyzes them using feedback analysis technology. For example, the instruction unit improves the accuracy of the instructions based on the instruction results provided by the user in the past. The instruction unit can also select an optimal instruction algorithm from the user's past instruction results. The instruction unit can also improve the instruction method based on user feedback. For example, the instruction unit adjusts the instruction algorithm based on user feedback. This improves the accuracy of the instructions by referring to the past instruction results. Some or all of the above-mentioned processing in the instruction unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction unit can input past instruction result data into the generation AI and cause the generation AI to improve the accuracy of the instructions.

[0049] When giving instructions, the instruction unit can adjust the order of instructions based on the time of occurrence of the generated questions. The instruction unit, for example, identifies the time of occurrence of the generated questions based on a timeline or dependencies. For example, the instruction unit provides instructions first for urgent questions. The instruction unit can also provide instructions later for long-term questions. The instruction unit can also provide instructions in an appropriate order for medium-term questions. In this way, by adjusting the order of instructions based on the time of occurrence of the generated questions, appropriate instructions can be provided. Some or all of the above-mentioned processing in the instruction unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction unit can input data on the time of occurrence of the generated questions to the generation AI and cause the generation AI to adjust the order of instructions.

[0050] When giving instructions, the instruction unit can adjust the content of the instructions based on the performance of the specialized generation AI. The instruction unit evaluates the performance of the specialized generation AI based on, for example, processing speed and generation quality. For example, the instruction unit provides detailed instructions to a high-performance generation AI. The instruction unit can also provide concise instructions to a low-performance generation AI. The instruction unit can also provide instructions with an appropriate level of detail to a generation AI with medium performance. In this way, appropriate instructions can be provided by adjusting the content of the instructions based on the performance of the specialized generation AI. Some or all of the above-mentioned processing in the instruction unit may be performed, for example, using AI or without using AI. For example, the instruction unit can input performance data of the specialized generation AI to the generation AI and cause the generation AI to adjust the content of the instructions.

[0051] The instruction unit can customize the instruction method by reflecting user feedback when giving instructions. The instruction unit, for example, collects and analyzes user feedback as survey results or user reviews. For example, the instruction unit adjusts the instruction method based on feedback previously provided by the user. The instruction unit can also preferentially use a specific instruction method based on the user feedback. The instruction unit can also optimize the instruction method by reflecting user feedback in real time. For example, the instruction unit customizes the instruction algorithm based on user feedback. By doing so, the instruction method is customized and accuracy is improved by reflecting user feedback. Some or all of the above-described processing in the instruction unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction unit can input user feedback data into a generation AI and cause the generation AI to customize the instruction method.

[0052] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0053] The analysis unit can take into account the user's past behavioral history when analyzing a user's comments. For example, the analysis unit can analyze what questions the user has asked in the past and what answers they have received to more accurately understand the intention of the current comment. The analysis unit can also take into account what topics the user has been interested in in the past and prioritize analysis of related information. Furthermore, the analysis unit can customize the method of analyzing comments based on the user's past behavioral patterns. This allows for more accurate analysis by taking into account the user's past behavioral history.

[0054] The analysis unit can take into account the user's current health condition when analyzing the user's comments. For example, the analysis unit can measure the user's heart rate and stress level using a sensor and adjust the analysis method for the comments based on that data. In addition, if the user is tired, the analysis unit can provide a concise and easy-to-understand analysis result. Furthermore, the analysis unit can change the priority of analysis depending on the user's health condition. This allows for more appropriate analysis by taking the user's health condition into consideration.

[0055] The generator can take the user's learning style into consideration when generating appropriate questions based on the identified task. For example, the generator can generate questions using diagrams and graphs for visual learners. The generator can also generate questions that are explained by voice for auditory learners. Furthermore, the generator can generate questions that require hands-on solutions for experiential learners. This allows for more effective learning support by generating questions that match the user's learning style.

[0056] The instruction unit can take the user's language settings into consideration when sending instructions to the sentence generation AI based on the generated question. For example, if the user's native language is English, the instruction unit can send instructions in English. Also, if the user uses multiple languages, the instruction unit can send instructions in an appropriate language according to the user's language settings. Furthermore, the instruction unit can take into consideration whether the user understands specific technical terms and send instructions in a language at an appropriate level. This enables more effective communication by sending instructions according to the user's language settings.

[0057] The instruction unit can take the user's visual preferences into consideration when sending instructions to the image generation AI based on the generated question. For example, the instruction unit can send instructions to the image generation AI based on the user's preferred colors or design style. Also, if the user likes a specific theme or motif, the instruction unit can send instructions to generate an image based on that. Furthermore, the instruction unit can send instructions to generate a more personalized image based on the user's past preference data. This allows for the generation of an image that meets the user's visual preferences, resulting in a more satisfying result.

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

[0059] Step 1: The analysis unit analyzes the user's utterances. The user's utterances include voice input and text input. The analysis unit analyzes the utterances using natural language processing technology and sentiment analysis technology, and can also perform analysis in real time. For example, the analysis unit converts the voice input into text and analyzes the text. Step 2: The generator generates questions based on the results of the analysis by the analyzer. Questions include question sentences and multiple-choice formats. The generator uses a generation AI (e.g., text generation AI or multimodal generation AI) to generate appropriate questions based on the user's utterances. The generator can also understand the context of the user's utterances and generate appropriate questions. Step 3: The instruction unit sends instructions to the specialized generative AI based on the question generated by the generation unit. Specialized generative AIs include text generation AI and image generation AI. For example, the instruction unit can send the generated question to the text generation AI and have it perform a text generation task. It can also send the generated question to the image generation AI and have it perform an image generation task.

[0060] (Example 2) A system according to an embodiment of the present invention solves the problem of difficulty in setting appropriate prompts (questions) when using generative AI. In this system, a generative AI converses with a user, discovers the user's potential challenges, and automatically generates appropriate "questions." This system works in conjunction with specialized generative AIs, such as text generation and image generation, to perform tasks. For example, a user initiates a conversation with a generative AI, which analyzes the user's utterances to identify potential challenges. The generative AI then automatically generates appropriate "questions" based on the identified challenges and sends instructions to the specialized generative AI. This system allows users to benefit from generative AI without setting appropriate prompts. The system analyzes the user's utterances, generates appropriate questions, and sends instructions to the specialized generative AI, allowing users to benefit from generative AI without setting appropriate prompts. For example, if a user says, "I want ideas for a new project," the generative AI analyzes the utterance and generates a question such as, "What are the specific steps to generate ideas for a new project?" and sends instructions to the text generation AI. This allows users to obtain specific ideas.

[0061] A generative AI assistance system according to an embodiment includes an analysis unit, a generation unit, and an instruction unit. The analysis unit analyzes a user's utterance. The user's utterance may be, for example, a voice input or a text input, but is not limited to these examples. The analysis unit analyzes the utterance using, for example, natural language processing technology. The analysis unit can also analyze the utterance using sentiment analysis technology. The analysis unit can also analyze the user's utterance in real time. For example, the analysis unit converts a voice input into text and analyzes the text. The generation unit uses a generative AI to generate a question based on the analysis result by the analysis unit. The question may be, for example, a question sentence or a multiple-choice format, but is not limited to these examples. For example, the generation unit uses a generative AI (for example, a text generation AI or a multimodal generation AI) to generate an appropriate question based on the user's utterance. The generation unit can also use the generative AI to understand the context of the user's utterance and generate an appropriate question. The instruction unit sends an instruction to a specialized generative AI based on the question generated by the generation unit. Examples of specialized generative AI include, but are not limited to, sentence generation AI and image generation AI. For example, the instruction unit may send the generated question to the sentence generation AI to cause it to perform a sentence generation task. The instruction unit may also send the generated question to the image generation AI to cause it to perform an image generation task. As a result, the generative AI support system according to the embodiment analyzes user utterances, generates appropriate questions, and sends instructions to the specialized generative AI, allowing the user to benefit from the generative AI without having to set appropriate prompts.

[0062] The analysis unit can analyze user utterances and identify potential issues. The analysis unit, for example, analyzes user utterances using natural language processing technology. For example, the analysis unit extracts frequently occurring issues from user utterances and identifies potential issues. The analysis unit can also analyze user utterances using sentiment analysis technology to identify user needs. For example, the analysis unit analyzes the emotional tone of the user utterances and identifies potential issues. The analysis unit can also analyze user utterances in real time and instantly identify potential issues. For example, the analysis unit converts voice input into text and analyzes the text to identify potential issues. In this way, by analyzing user utterances and identifying potential issues, more appropriate questions can be generated. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input user utterance data into a generation AI and have the generation AI identify potential issues.

[0063] The generation unit can generate an appropriate question based on the identified task. The generation unit generates an appropriate question based on the identified task, for example, using a generation AI. For example, the generation unit uses a generation AI (e.g., a text generation AI or a multimodal generation AI) to generate a question based on the identified task. The generation unit can also use the generation AI to generate multiple-choice questions based on the identified task. The generation unit can also use the generation AI to understand the context and generate an appropriate question based on the identified task. For example, the generation unit collects related information based on the identified task and generates a question based on that information. This allows the generation AI to generate an appropriate question based on the identified task, making the generation AI's instructions more effective. Some or all of the above-described processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input identified task data into the generation AI and cause the generation AI to generate an appropriate question.

[0064] The instruction unit can send instructions to the sentence generation AI based on the generated question. The instruction unit, for example, sends the generated question to the sentence generation AI and causes it to perform a sentence generation task. For example, the instruction unit can send the generated question to the sentence generation AI, causing the sentence generation AI to generate a sentence based on the question. The instruction unit can also send the generated question to the sentence generation AI, causing the sentence generation AI to generate a template-based sentence based on the question. The instruction unit can also send the generated question to the sentence generation AI, causing the sentence generation AI to generate a sentence using natural language generation technology based on the question. In this way, the sentence generation task is performed by sending instructions to the sentence generation AI based on the generated question. Some or all of the above-mentioned processing in the instruction unit may be performed using AI, for example, or may be performed without using AI. For example, the instruction unit can input generated question data to the generation AI and cause the generation AI to execute the instructions to the sentence generation AI.

[0065] The instruction unit can send instructions to the image generation AI based on the generated question. The instruction unit, for example, sends the generated question to the image generation AI and causes it to execute an image generation task. For example, the instruction unit can send the generated question to the image generation AI, causing the image generation AI to generate an image based on the question. The instruction unit can also send the generated question to the image generation AI, causing the image generation AI to generate an image using deep learning technology based on the question. The instruction unit can also send the generated question to the image generation AI, causing the image generation AI to generate an image using image synthesis technology based on the question. In this way, the image generation task is executed by sending instructions to the image generation AI based on the generated question. Some or all of the above-mentioned processing in the instruction unit may be performed using AI, for example, or may be performed without using AI. For example, the instruction unit can input generated question data to the generation AI and cause the generation AI to execute the instructions to the image generation AI.

[0066] The analysis unit can estimate the user's emotions and adjust the analysis method of the utterances based on the estimated user emotions. The analysis unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the analysis unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The analysis unit can also estimate the user's emotions using voice tone analysis technology. For example, the analysis unit records the user's voice and estimates the emotions using a voice tone analysis algorithm. The analysis unit can also adjust the analysis method of the utterances based on the estimated user emotions. For example, if the user is stressed, the analysis unit selects a simple and intuitive analysis method. If the user is relaxed, the analysis unit can select a detailed analysis method to provide deeper insights. If the user is excited, the analysis unit can perform a quick analysis and provide immediate feedback. This allows for more appropriate analysis by adjusting the analysis method of the utterances based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input user emotion data into the generation AI and cause the generation AI to adjust the method of analyzing utterances.

[0067] The analysis unit can analyze a user's past comment history and select an analysis algorithm. For example, the analysis unit stores the user's past comment history as log data and analyzes it using text mining technology. For example, the analysis unit selects an optimal analysis algorithm based on keywords frequently used by the user in the past. The analysis unit can also analyze the user's past comment patterns and select an optimal analysis algorithm for a specific topic. The analysis unit can also customize the analysis algorithm based on the user's past feedback. For example, the analysis unit adjusts the analysis algorithm based on the user's past feedback. This allows the analysis of the past comment history to select an optimal analysis algorithm and improve analysis accuracy. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input past comment history data into a generation AI and have the generation AI select an analysis algorithm.

[0068] When analyzing comments, the analysis unit can filter based on the user's current situation and areas of interest. The analysis unit, for example, considers location information and time of day to identify the user's current situation. For example, the analysis unit prioritizes analyzing comments related to the user's current project. The analysis unit can also filter relevant comments based on the user's areas of interest. For example, the analysis unit identifies the user's areas of interest based on the user's past search history and social media activity. The analysis unit can also select appropriate comments based on the user's current situation (e.g., at work, on break). For example, if the user is at work, the analysis unit prioritizes analyzing work-related comments. This enables highly relevant analysis by filtering based on the user's current situation and areas of interest. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's current situation data and area of ​​interest data into the generation AI and have the generation AI perform filtering.

[0069] When analyzing a utterance, the analysis unit can select the optimal analysis means depending on the user's input method. For example, if the user uses voice input, the analysis unit analyzes the utterance using voice recognition technology. For example, the analysis unit converts the voice input into text and analyzes the text. Furthermore, if the user uses text input, the analysis unit can also analyze the utterance using natural language processing technology. For example, the analysis unit analyzes the text input and identifies the intention of the utterance. Furthermore, if the user uses images, the analysis unit can also analyze the utterance using image recognition technology. For example, the analysis unit analyzes the images and understands their contents. This improves analysis accuracy by selecting the optimal analysis means depending on the user's input method. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's input data into a generation AI and have the generation AI select the optimal analysis means.

[0070] The analysis unit can estimate the user's emotions and prioritize utterances to be analyzed based on the estimated user emotions. The analysis unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the analysis unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The analysis unit can also estimate the user's emotions using voice tone analysis technology. For example, the analysis unit records the user's voice and estimates the emotions using a voice tone analysis algorithm. The analysis unit can also prioritize utterances to be analyzed based on the estimated user emotions. For example, if the user is feeling anxious, the analysis unit can prioritize utterances that give a sense of security. If the user is excited, the analysis unit can prioritize utterances that require a prompt response. If the user is relaxed, the analysis unit can prioritize utterances that require detailed analysis. This enables more accurate analysis by prioritizing utterances based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit may input user emotion data into the generation AI and have the generation AI determine the priority of utterances.

[0071] When analyzing utterances, the analysis unit can prioritize analyzing highly relevant utterances by taking into account the user's geographical location information. The analysis unit, for example, collects the user's geographical location information using GPS data or an IP address. For example, if the user is in a specific area, the analysis unit prioritizes analyzing utterances related to that area. Furthermore, if the user is traveling, the analysis unit can prioritize analyzing utterances related to the user's travel destination. Furthermore, if the user is at home, the analysis unit can prioritize analyzing utterances related to information about the area around the user's home. For example, the analysis unit filters utterances related to the area based on the user's geographical location information. This allows for prioritized analysis of highly relevant utterances by taking the user's geographical location information into account. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's geographical location information data into the generation AI and cause the generation AI to perform prioritized analysis of highly relevant utterances.

[0072] When analyzing comments, the analysis unit can analyze the user's social media activity and analyze related comments. For example, the analysis unit saves the user's social media activity as log data and analyzes it using text mining technology. For example, the analysis unit analyzes comments based on keywords frequently used by the user on social media. The analysis unit can also analyze the content of the user's social media posts and analyze related comments. The analysis unit can also analyze related comments by referring to the activities of the user's friends on social media. For example, the analysis unit filters out highly relevant comments based on the user's social media activity. This makes it easier to analyze related comments by analyzing social media activity. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's social media activity data into a generation AI and have the generation AI analyze related comments.

[0073] When analyzing utterances, the analysis unit can customize the analysis method by reflecting the user's past feedback. The analysis unit, for example, collects and analyzes the user's past feedback as survey results or user reviews. For example, the analysis unit adjusts the analysis method based on the user's past feedback. The analysis unit can also prioritize the use of a specific analysis method based on the user's past feedback. The analysis unit can also optimize the analysis method by reflecting the user's feedback in real time. For example, the analysis unit customizes the analysis algorithm based on the user's feedback. By reflecting the past feedback, the analysis method is customized and accuracy is improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past feedback data into the generation AI and have the generation AI customize the analysis method.

[0074] The generation unit can estimate the user's emotions and adjust the way questions are expressed based on the estimated user emotions. The generation unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the generation unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The generation unit can also estimate the user's emotions using voice tone analysis technology. For example, the generation unit records the user's voice and estimates the emotions using a voice tone analysis algorithm. The generation unit can also adjust the way questions are expressed based on the estimated user emotions. For example, if the user is stressed, the generation unit generates a concise and clear question. If the user is relaxed, the generation unit can generate a detailed and complex question. If the user is excited, the generation unit can generate a question that can be answered quickly. This allows for the generation of more appropriate questions by adjusting the way questions are expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit may input user emotion data into the generation AI and cause the generation AI to adjust the way the question is expressed.

[0075] When generating a question, the generation unit can adjust the level of detail of the question based on the importance of the identified issue. The generation unit, for example, evaluates the importance of the identified issue based on the scope of impact and the urgency of resolution. For example, the generation unit generates a detailed question for an issue of high importance. The generation unit can also generate a concise question for an issue of low importance. The generation unit can also generate a question with an appropriate level of detail for an issue of medium importance. In this way, by adjusting the level of detail of the question based on the importance of the issue, an appropriate question can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the identified issue data into a generation AI and cause the generation AI to adjust the level of detail of the question.

[0076] When generating a question, the generation unit can apply different generation algorithms depending on the category of the question. For example, the generation unit classifies question categories into technical questions, business questions, creative questions, etc. For example, the generation unit applies a technology-specialized generation algorithm to technical questions. The generation unit can also apply a creativity-oriented generation algorithm to creative questions. The generation unit can also apply a business-specialized generation algorithm to business-related questions. In this way, appropriate questions can be generated by applying different generation algorithms depending on the category of the question. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input question category data into the generation AI and cause the generation AI to apply different generation algorithms.

[0077] When generating a question, the generation unit can improve the accuracy of the generation by referring to the user's past question generation results. For example, the generation unit saves the user's past question generation results as log data and analyzes them using text mining technology. For example, the generation unit analyzes the results of questions generated by the user in the past to improve accuracy. The generation unit can also select an optimal generation algorithm from the user's past question generation results. The generation unit can also improve the question generation method based on user feedback. For example, the generation unit adjusts the generation algorithm based on user feedback. This improves the accuracy of generation by referring to the past question generation results. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input past question generation result data into the generation AI and cause the generation AI to improve the accuracy of generation.

[0078] The generation unit can estimate the user's emotions and adjust the length of the generated questions based on the estimated user emotions. The generation unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the generation unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The generation unit can also estimate the user's emotions using voice tone analysis technology. For example, the generation unit records the user's voice and estimates the emotions using a voice tone analysis algorithm. The generation unit can also adjust the length of the generated questions based on the estimated user emotions. For example, if the user is in a hurry, the generation unit can generate short, to-the-point questions. If the user is relaxed, the generation unit can generate longer questions with detailed explanations. If the user is excited, the generation unit can generate questions with visually stimulating effects. This allows appropriate questions to be generated by adjusting the length of the questions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit may input user emotion data into the generation AI and cause the generation AI to adjust the length of the question.

[0079] When generating questions, the generation unit can determine the priority of the questions based on the time when the issues occurred. The generation unit identifies the time when the issues occurred, for example, using a timestamp or an event log. For example, the generation unit generates questions with priority for urgent issues. The generation unit can also generate questions for long-term issues later. The generation unit can also generate questions with an appropriate priority for medium-term issues. In this way, by determining the priority of questions based on the time when the issues occurred, appropriate questions can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the time when the issues occurred into the generation AI and have the generation AI determine the priority of the questions.

[0080] When generating questions, the generation unit can adjust the order of questions based on the relevance of the tasks. The generation unit evaluates the relevance of tasks based on, for example, a common theme or a scope of influence. For example, the generation unit generates questions first for tasks with high relevance. The generation unit can also generate questions later for tasks with low relevance. The generation unit can also generate questions in an appropriate order for tasks with medium relevance. In this way, appropriate questions can be generated by adjusting the order of questions based on the relevance of the tasks. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input task relevance data into the generation AI and have the generation AI adjust the order of questions.

[0081] When generating a question, the generation unit can adjust the use of technical terminology in the question according to the user's level of expertise. The generation unit, for example, evaluates the user's level of expertise based on qualification information and past comments. For example, the generation unit generates questions that use a lot of technical terminology for users with high levels of expertise. The generation unit can also generate questions in simple language for users with low levels of expertise. The generation unit can also generate questions that use appropriate technical terminology for users with medium levels of expertise. In this way, appropriate questions can be generated by adjusting the use of technical terminology according to the user's level of expertise. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0082] The instruction unit can estimate the user's emotion and adjust the instruction method based on the estimated user's emotion. The instruction unit, for example, estimates the user's emotion using facial expression recognition technology. For example, the instruction unit captures the user's facial expression with a camera and estimates the emotion using a facial expression recognition algorithm. The instruction unit can also estimate the user's emotion using voice tone analysis technology. For example, the instruction unit records the user's voice and estimates the emotion using a voice tone analysis algorithm. The instruction unit can also adjust the instruction method based on the estimated user's emotion. For example, if the user is stressed, the instruction unit can provide concise and clear instructions. If the user is relaxed, the instruction unit can provide detailed instructions. If the user is excited, the instruction unit can provide instructions that require a quick response. In this way, appropriate instructions can be provided by adjusting the instruction method based on the user's emotion. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the instruction unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction unit may input user emotion data to the generation AI and cause the generation AI to adjust the instruction method.

[0083] When giving instructions, the instruction unit can adjust the level of detail of the instructions based on the importance of the generated question. The instruction unit, for example, evaluates the importance of the generated question based on the scope of impact and the urgency of resolution. For example, the instruction unit provides detailed instructions for questions of high importance. The instruction unit can also provide concise instructions for questions of low importance. The instruction unit can also provide instructions with an appropriate level of detail for questions of medium importance. In this way, by adjusting the level of detail of the instructions based on the importance of the generated question, appropriate instructions can be provided. Some or all of the above-mentioned processing in the instruction unit may be performed, for example, using AI or without using AI. For example, the instruction unit can input the generated question data to the generation AI and cause the generation AI to adjust the level of detail of the instructions.

[0084] When giving instructions, the instruction unit can apply different instruction algorithms depending on the type of specialized generation AI. The instruction unit, for example, classifies the types of specialized generation AI into sentence generation AI, image generation AI, voice generation AI, etc. For example, the instruction unit applies an instruction algorithm specialized for sentence generation to a sentence generation AI. The instruction unit can also apply an instruction algorithm specialized for image generation to an image generation AI. The instruction unit can also apply an instruction algorithm specialized for voice generation to a voice generation AI. In this way, by applying different instruction algorithms depending on the type of specialized generation AI, appropriate instructions can be provided. Some or all of the above-mentioned processing in the instruction unit may be performed, for example, using AI or without AI. For example, the instruction unit can input type data of the specialized generation AI to the generation AI and cause the generation AI to apply different instruction algorithms.

[0085] When giving instructions, the instruction unit can improve the accuracy of the instructions by referring to the user's past instruction results. The instruction unit, for example, stores the user's past instruction results as log data and analyzes them using feedback analysis technology. For example, the instruction unit improves the accuracy of the instructions based on the instruction results provided by the user in the past. The instruction unit can also select an optimal instruction algorithm from the user's past instruction results. The instruction unit can also improve the instruction method based on user feedback. For example, the instruction unit adjusts the instruction algorithm based on user feedback. This improves the accuracy of the instructions by referring to the past instruction results. Some or all of the above-mentioned processing in the instruction unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction unit can input past instruction result data into the generation AI and cause the generation AI to improve the accuracy of the instructions.

[0086] The instruction unit can estimate the user's emotions and prioritize instructions based on the estimated user's emotions. The instruction unit can estimate the user's emotions using, for example, facial expression recognition technology. For example, the instruction unit can capture the user's facial expressions with a camera and estimate the emotions using a facial expression recognition algorithm. The instruction unit can also estimate the user's emotions using voice tone analysis technology. For example, the instruction unit can record the user's voice and estimate the emotions using a voice tone analysis algorithm. The instruction unit can also prioritize instructions based on the estimated user's emotions. For example, if the user is feeling anxious, the instruction unit can prioritize providing instructions that provide a sense of security. If the user is excited, the instruction unit can prioritize providing instructions that require a quick response. If the user is relaxed, the instruction unit can prioritize detailed instructions. In this way, by prioritizing instructions based on the user's emotions, appropriate instructions can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the instruction unit may be performed using AI, or may be performed without using AI. For example, the instruction unit may input user emotion data into the generation AI and cause the generation AI to determine the priority of instructions.

[0087] When giving instructions, the instruction unit can adjust the order of instructions based on the time of occurrence of the generated questions. The instruction unit, for example, identifies the time of occurrence of the generated questions based on a timeline or dependencies. For example, the instruction unit provides instructions first for urgent questions. The instruction unit can also provide instructions later for long-term questions. The instruction unit can also provide instructions in an appropriate order for medium-term questions. In this way, by adjusting the order of instructions based on the time of occurrence of the generated questions, appropriate instructions can be provided. Some or all of the above-mentioned processing in the instruction unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction unit can input data on the time of occurrence of the generated questions to the generation AI and cause the generation AI to adjust the order of instructions.

[0088] When giving instructions, the instruction unit can adjust the content of the instructions based on the performance of the specialized generation AI. The instruction unit evaluates the performance of the specialized generation AI based on, for example, processing speed and generation quality. For example, the instruction unit provides detailed instructions to a high-performance generation AI. The instruction unit can also provide concise instructions to a low-performance generation AI. The instruction unit can also provide instructions with an appropriate level of detail to a generation AI with medium performance. In this way, appropriate instructions can be provided by adjusting the content of the instructions based on the performance of the specialized generation AI. Some or all of the above-mentioned processing in the instruction unit may be performed, for example, using AI or without using AI. For example, the instruction unit can input performance data of the specialized generation AI to the generation AI and cause the generation AI to adjust the content of the instructions.

[0089] The instruction unit can customize the instruction method by reflecting user feedback when giving instructions. The instruction unit, for example, collects and analyzes user feedback as survey results or user reviews. For example, the instruction unit adjusts the instruction method based on feedback previously provided by the user. The instruction unit can also preferentially use a specific instruction method based on the user feedback. The instruction unit can also optimize the instruction method by reflecting user feedback in real time. For example, the instruction unit customizes the instruction algorithm based on user feedback. By doing so, the instruction method is customized and accuracy is improved by reflecting user feedback. Some or all of the above-described processing in the instruction unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction unit can input user feedback data into a generation AI and cause the generation AI to customize the instruction method. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, generation unit, and instruction unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14 and analyzes voice input and text input. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates appropriate questions based on the analyzed results. The instruction unit is realized, for example, by the control unit 46A of the smart device 14 and transmits the generated questions to the specialized generation AI. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, generation unit, and instruction unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 and analyzes voice input and text input. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates appropriate questions based on the analyzed results. The instruction unit is realized, for example, by the control unit 46A of the smart glasses 214 and transmits the generated questions to the specialized generation AI. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, generation unit, and instruction unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset type terminal 314 and analyzes voice input and text input. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates appropriate questions based on the analysis results. The instruction unit is realized, for example, by the control unit 46A of the headset type terminal 314 and transmits the generated questions to the specialized generation AI. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, generation unit, and instruction unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 and analyzes voice input and text input. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates appropriate questions based on the analysis results. The instruction unit is realized, for example, by the control unit 46A of the robot 414 and transmits the generated questions to the specialized generation AI.

[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 analysis unit can take into account the user's past behavioral history when analyzing a user's comments. For example, the analysis unit can analyze what questions the user has asked in the past and what answers they have received to more accurately understand the intention of the current comment. The analysis unit can also take into account what topics the user has been interested in in the past and prioritize analysis of related information. Furthermore, the analysis unit can customize the method of analyzing comments based on the user's past behavioral patterns. This allows for more accurate analysis by taking into account the user's past behavioral history.

[0092] The analysis unit can take into account the user's current health condition when analyzing the user's comments. For example, the analysis unit can measure the user's heart rate and stress level using a sensor and adjust the analysis method for the comments based on that data. In addition, if the user is tired, the analysis unit can provide a concise and easy-to-understand analysis result. Furthermore, the analysis unit can change the priority of analysis depending on the user's health condition. This allows for more appropriate analysis by taking the user's health condition into consideration.

[0093] The generator can take the user's learning style into consideration when generating appropriate questions based on the identified task. For example, the generator can generate questions using diagrams and graphs for visual learners. The generator can also generate questions that are explained by voice for auditory learners. Furthermore, the generator can generate questions that require hands-on solutions for experiential learners. This allows for more effective learning support by generating questions that match the user's learning style.

[0094] The instruction unit can take the user's language settings into consideration when sending instructions to the sentence generation AI based on the generated question. For example, if the user's native language is English, the instruction unit can send instructions in English. Also, if the user uses multiple languages, the instruction unit can send instructions in an appropriate language according to the user's language settings. Furthermore, the instruction unit can take into consideration whether the user understands specific technical terms and send instructions in a language at an appropriate level. This enables more effective communication by sending instructions according to the user's language settings.

[0095] The instruction unit can take the user's visual preferences into consideration when sending instructions to the image generation AI based on the generated question. For example, the instruction unit can send instructions to the image generation AI based on the user's preferred colors or design style. Also, if the user likes a specific theme or motif, the instruction unit can send instructions to generate an image based on that. Furthermore, the instruction unit can send instructions to generate a more personalized image based on the user's past preference data. This allows for the generation of an image that meets the user's visual preferences, resulting in a more satisfying result.

[0096] The analysis unit can estimate the user's emotions and adjust the analysis method of the utterances based on the estimated user emotions. For example, the analysis unit can estimate the user's emotions using facial expression recognition technology. For example, the analysis unit can capture the user's facial expressions with a camera and estimate the emotions using a facial expression recognition algorithm. The analysis unit can also estimate the user's emotions using voice tone analysis technology. For example, the analysis unit can record the user's voice and estimate the emotions using a voice tone analysis algorithm. The analysis unit can also adjust the analysis method of the utterances based on the estimated user emotions. For example, if the user is stressed, the analysis unit can select a simple and intuitive analysis method. If the user is relaxed, the analysis unit can select a detailed analysis method to provide deeper insights. If the user is excited, the analysis unit can perform a quick analysis and provide immediate feedback. This allows for more appropriate analysis by adjusting the analysis method of the utterances based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input user emotion data into the generation AI and cause the generation AI to adjust the method of analyzing utterances.

[0097] The generation unit can estimate the user's emotions and adjust the way questions are expressed based on the estimated user emotions. For example, the generation unit estimates the user's emotions using facial expression recognition technology. For example, the generation unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The generation unit can also estimate the user's emotions using voice tone analysis technology. For example, the generation unit records the user's voice and estimates the emotions using a voice tone analysis algorithm. The generation unit can also adjust the way questions are expressed based on the estimated user emotions. For example, if the user is stressed, the generation unit generates a concise and clear question. If the user is relaxed, the generation unit can generate a detailed and complex question. If the user is excited, the generation unit can generate a question that can be answered quickly. This allows for the generation of more appropriate questions by adjusting the way questions are expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit may input user emotion data into the generation AI and cause the generation AI to adjust the way the question is expressed.

[0098] The generation unit can estimate the user's emotions and adjust the length of the generated questions based on the estimated user emotions. For example, the generation unit can estimate the user's emotions using facial expression recognition technology. For example, the generation unit can capture the user's facial expressions with a camera and estimate the emotions using a facial expression recognition algorithm. The generation unit can also estimate the user's emotions using voice tone analysis technology. For example, the generation unit can record the user's voice and estimate the emotions using a voice tone analysis algorithm. The generation unit can also adjust the length of the generated questions based on the estimated user emotions. For example, if the user is in a hurry, the generation unit can generate short, to-the-point questions. If the user is relaxed, the generation unit can generate longer questions with detailed explanations. If the user is excited, the generation unit can generate questions with visually stimulating effects. This allows appropriate questions to be generated by adjusting the length of the questions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit may input user emotion data into the generation AI and cause the generation AI to adjust the length of the question.

[0099] The instruction unit can estimate the user's emotion and adjust the instruction method based on the estimated user's emotion. For example, the instruction unit estimates the user's emotion using facial expression recognition technology. For example, the instruction unit captures the user's facial expression with a camera and estimates the emotion using a facial expression recognition algorithm. The instruction unit can also estimate the user's emotion using voice tone analysis technology. For example, the instruction unit records the user's voice and estimates the emotion using a voice tone analysis algorithm. The instruction unit can also adjust the instruction method based on the estimated user's emotion. For example, if the user is stressed, the instruction unit can provide concise and clear instructions. If the user is relaxed, the instruction unit can provide detailed instructions. If the user is excited, the instruction unit can provide instructions that require a quick response. In this way, appropriate instructions can be provided by adjusting the instruction method based on the user's emotion. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the instruction unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction unit may input user emotion data to the generation AI and cause the generation AI to adjust the instruction method.

[0100] The instruction unit can estimate the user's emotions and prioritize instructions based on the estimated user's emotions. For example, the instruction unit estimates the user's emotions using facial expression recognition technology. For example, the instruction unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The instruction unit can also estimate the user's emotions using voice tone analysis technology. For example, the instruction unit records the user's voice and estimates the emotions using a voice tone analysis algorithm. The instruction unit can also prioritize instructions based on the estimated user's emotions. For example, if the user is feeling anxious, the instruction unit can prioritize instructions that provide a sense of security. If the user is excited, the instruction unit can prioritize instructions that require a quick response. If the user is relaxed, the instruction unit can prioritize detailed instructions. This allows appropriate instructions to be provided by prioritizing instructions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the instruction unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction unit may input user emotion data to the generation AI and have the generation AI determine the priority of instructions.

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

[0102] Step 1: The analysis unit analyzes the user's utterances. The user's utterances include voice input and text input. The analysis unit analyzes the utterances using natural language processing technology and sentiment analysis technology, and can also perform analysis in real time. For example, the analysis unit converts the voice input into text and analyzes the text. Step 2: The generator generates questions based on the results of the analysis by the analyzer. Questions include question sentences and multiple-choice formats. The generator uses a generation AI (e.g., text generation AI or multimodal generation AI) to generate appropriate questions based on the user's utterances. The generator can also understand the context of the user's utterances and generate appropriate questions. Step 3: The instruction unit sends instructions to the specialized generative AI based on the question generated by the generation unit. Specialized generative AIs include text generation AI and image generation AI. For example, the instruction unit can send the generated question to the text generation AI and have it perform a text generation task. It can also send the generated question to the image generation AI and have it perform an image generation task.

[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 (registered trademark) (Internet search engine).<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] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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."

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] [Explanation of symbols]

[0175] 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. an analysis unit that analyzes user comments; a generation unit that generates a question based on the result of the analysis by the analysis unit; An instruction unit that sends instructions to a specialized generation AI based on the question generated by the generation unit; Equipped with A system characterized by:

2. The analysis unit Analyze user comments and identify potential issues 2. The system of claim 1.

3. The generation unit Generate appropriate questions based on identified issues 2. The system of claim 1.

4. The instruction unit Send instructions to the sentence generation AI based on the generated question 2. The system of claim 1.

5. The instruction unit Send instructions to the image generation AI based on the generated question 2. The system of claim 1.

6. The analysis unit Estimate the user's emotions and adjust the analysis method of the speech based on the estimated user emotions.

2. The system of claim 1.

7. The analysis unit Analyze the user's past comment history and select an analysis algorithm 2. The system of claim 1.

8. The analysis unit When analyzing comments, filtering is performed based on the user's current situation and areas of interest.

2. The system of claim 1.

Images