System

Abstract

To provide a system that allows users to obtain high-level output using only simple prompt input.SOLUTION: A system according to an embodiment comprises a reception unit, a generation unit, a response generation unit, and a selection unit. The reception unit accepts a prompt input from a user. The generation unit produces a plurality of different prompts based on the prompt received by the reception unit. The response generation unit generates responses corresponding to the prompts produced by the generation unit. The selection unit selects the most suitable response from among the responses generated by the response generation unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] Conventional techniques have the drawback that it is costly for users to learn prompting techniques and that a great deal of trial and error is required to obtain appropriate answers.

[0005] The system according to the embodiment aims to enable a user to elicit advanced output even with simple prompt input. [Means for solving the problem]

[0006] A system according to an embodiment includes a reception unit, a generation unit, an answer generation unit, and a selection unit. The reception unit receives a prompt from a user. The generation unit generates a plurality of different prompts based on the prompt received by the reception unit. The answer generation unit generates an answer based on the prompt generated by the generation unit. The selection unit selects an appropriate answer from the plurality of answers generated by the answer generation unit. Effect of the Invention

[0007] The system according to the embodiment can enable users to elicit sophisticated output from simple prompt inputs. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The generation AI system according to the embodiment of the present invention is a system that draws out a high-level output even when the user inputs a simple prompt. In this generation AI system, the user inputs a simple prompt, and the generation AI automatically generates multiple different prompts based on the prompt, so that the user can obtain answers from multiple different perspectives at once. Furthermore, the generation AI integrates these multiple answers and provides the most appropriate answer to the user. For example, if the user inputs "tell me a new recipe," the generation AI automatically generates different prompts such as "easy recipes," "healthy recipes," and "time-saving recipes," and generates answers for each of them. Next, the generation AI integrates these answers and provides the most appropriate recipe to the user. This mechanism allows the user to obtain a high-level output with a simple input without having to learn prompt techniques. In addition, the prompts automatically generated by the generation AI more accurately reflect the user's intentions, so that a more appropriate answer can be obtained. Furthermore, by adding a mechanism for accepting feedback from the user, the generation AI can learn and generate more appropriate prompts. By also adding a mechanism for collecting information from different data sources, the generation AI can generate a more diverse range of prompts. This allows the generation AI system to obtain a high-level output even when the user inputs a simple prompt.

[0029] The generation AI system according to the embodiment includes a reception unit, a generation unit, an answer generation unit, and a selection unit. The reception unit receives a prompt from a user. The prompt may be in a text format, a voice format, an image format, or the like, but is not limited to such examples. The reception unit receives, for example, a text prompt input by the user. The reception unit may also receive a voice prompt from the user using a voice input. Furthermore, the reception unit may also receive an image prompt. For example, the user uploads an image and generates a prompt based on the image. The generation unit uses a generation AI to generate multiple different prompts based on the prompt received by the reception unit. The generation AI may use, for example, a text generation AI (e.g., LLM) to generate prompts from different perspectives or contexts. The generation unit may also use a multimodal generation AI to generate prompts in different formats. For example, the generation AI generates prompts from different perspectives based on a text prompt input by the user. The answer generation unit uses a generation AI to generate an answer based on the prompt generated by the generation unit. The answer generation unit uses, for example, a generation AI to generate an answer to the generated prompt. The answer generation unit can also integrate answers to multiple prompts using the generation AI. For example, the generation AI generates answers to multiple prompts and integrates them to generate an optimal answer. The selection unit selects an optimal answer from multiple answers generated by the answer generation unit. The selection unit selects an optimal answer from multiple answers using, for example, the generation AI. The selection unit can also select an optimal answer based on the user's intention or feedback. For example, the selection unit selects an answer that reflects the user's intention. As a result, the generation AI system according to the embodiment can obtain an advanced output even when the user inputs a simple prompt. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can select an optimal answer using an AI model that inputs multiple answers generated by the generation AI and outputs an optimal answer.

[0030] The reception unit receives a prompt from the user. The prompt may be in a text format, a voice format, an image format, or the like, but is not limited to such examples. The reception unit receives, for example, a text prompt input by the user. The reception unit may also receive a voice prompt from the user using voice input. The reception unit may also receive an image prompt. For example, the user uploads an image and generates a prompt based on the image. The reception unit has an input interface specialized for each format in order to accommodate these various input formats. For example, in the case of text input, an intuitive user interface is provided so that the user can easily input text. In the case of voice input, a voice recognition technology is used to convert the user's voice into text with high accuracy. In the case of image input, an image analysis technology is used to extract features from the uploaded image and generate an appropriate prompt. This allows the reception unit to quickly and accurately accept the prompt regardless of the format in which the user inputs it. The reception unit also temporarily stores the input prompt and provides information necessary for subsequent processing. For example, depending on the content and format of the prompt, an appropriate generation AI is selected and passed to the generation unit. Furthermore, the reception unit can support the generation of more appropriate prompts and answers by managing the user's input history and referring to past prompts and answers, thereby enabling the reception unit to respond to the diverse needs of users and improve the efficiency and accuracy of the entire system.

[0031] The generation unit uses a generation AI to generate multiple different prompts based on the prompts received by the reception unit. The generation AI generates prompts from different perspectives and contexts using, for example, a text generation AI (e.g., LLM). The generation unit can also generate prompts in different formats using a multimodal generation AI. For example, the generation AI generates prompts from different perspectives based on a text prompt entered by a user. The generation unit appropriately selects a model of the generation AI and performs optimal generation according to the content and format of the prompt. For example, in the case of a text prompt, natural language processing technology is used to analyze the context and intention, and prompts from different perspectives and contexts are generated. In the case of a voice prompt, voice recognition technology and natural language processing technology are combined to convert voice data into text, and a prompt is generated based on the text. In the case of an image prompt, image analysis technology is used to extract image features, and a text prompt is generated based on the extracted features. In order to perform these generation processes efficiently, the generation unit utilizes high-performance computing resources to generate prompts in real time. In addition, the generation unit evaluates the quality of the generated prompt, and corrects or regenerates it as necessary. For example, if the generated prompt does not match the user's intention, the generation AI is used again to generate a new prompt. This enables the generation unit to respond to the diverse needs of users and provide high-quality prompts.

[0032] The answer generation unit uses the generation AI to generate an answer based on the prompt generated by the generation unit. The answer generation unit uses, for example, the generation AI to generate an answer to the generated prompt. The answer generation unit can also use the generation AI to integrate answers to multiple prompts. For example, the generation AI generates answers to multiple prompts and integrates them to generate an optimal answer. The answer generation unit appropriately selects a model of the generation AI and generates an optimal answer according to the content and format of the prompt. For example, in the case of a text prompt, natural language processing technology is used to analyze the intention and context of the prompt and generate an appropriate answer. In the case of a voice prompt, voice recognition technology and natural language processing technology are combined to convert voice data into text, and an answer is generated based on the text. In the case of an image prompt, image analysis technology is used to extract features of the image and generate a text answer based on the extracted features. In order to efficiently perform these generation processes, the answer generation unit utilizes high-performance computing resources to generate answers in real time. In addition, the answer generation unit evaluates the quality of the generated answer and corrects or regenerates it as necessary. For example, if the generated answer does not match the user's intention, the generation AI is used again to generate a new answer. Furthermore, the answer generator integrates answers to a plurality of prompts to generate an optimal answer, thereby enabling the answer generator to provide high-quality answers that meet the diverse needs of users.

[0033] The selection unit selects the optimal answer from the multiple answers generated by the answer generation unit. The selection unit, for example, uses a generation AI to select the optimal answer from the multiple answers. The selection unit can also select the optimal answer based on the user's intention and feedback. For example, the selection unit selects an answer that reflects the user's intention. The selection unit appropriately selects a model of the generation AI and selects the optimal answer according to the content and format of the answer. For example, in the case of a text answer, natural language processing technology is used to analyze the intention and context of the answer and select the optimal answer. In the case of a voice answer, voice recognition technology and natural language processing technology are combined to convert voice data into text, and the optimal answer is selected based on the text. In the case of an image answer, image analysis technology is used to extract the features of the image and select the optimal answer based on that. In order to perform these selection processes efficiently, the selection unit utilizes high-performance computing resources to select the optimal answer in real time. In addition, the selection unit evaluates the quality of the selected answer and corrects or reselects it as necessary. For example, if the selected answer does not match the user's intent, the generation AI is used again to select a new answer. Furthermore, the selection unit can collect user feedback and continuously improve the accuracy and effectiveness of the selection process. This allows the selection unit to respond to the diverse needs of users and provide high-quality answers.

[0034] The generation AI system includes a feedback receiving unit that receives feedback from a user. The feedback receiving unit receives feedback from the user. The feedback includes, for example, a text format, an evaluation score, a comment, and the like, but is not limited to such examples. The feedback receiving unit receives, for example, text feedback input by the user. The feedback receiving unit can also receive the user's feedback using the evaluation score. Furthermore, the feedback receiving unit can also receive feedback in the form of a comment. For example, the user inputs a comment, and the feedback is received based on the comment. In this way, the generation AI can learn by receiving the user's feedback and generate a more appropriate prompt. A part or all of the above-mentioned processing in the feedback receiving unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the feedback receiving unit can input the user's feedback data to the generation AI and cause the generation AI to analyze the feedback.

[0035] The generation AI system includes a collection unit that collects information from different data sources. The collection unit collects information from different data sources. The data sources include, but are not limited to, for example, websites, databases, and APIs. The collection unit collects information, for example, from websites. The collection unit can also collect information from databases. Furthermore, the collection unit can collect information using APIs. For example, the collection unit collects information by scraping from a specific website. Information collection from a database involves obtaining data using a specific query. Information collection using an API involves sending a request to a specific endpoint and obtaining data as a response. This allows the generation AI to generate more diverse prompts by collecting information from different data sources. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit may input data obtained from a website into the generation AI and cause the generation AI to perform analysis of the data.

[0036] The generation AI system includes an evaluation unit that evaluates the quality of the generated prompt. The evaluation unit evaluates the quality of the generated prompt. The quality includes, for example, accuracy, reliability, user satisfaction, and the like, but is not limited to such examples. The evaluation unit evaluates, for example, the accuracy of the generated prompt. The evaluation unit can also evaluate the reliability of the generated prompt. Furthermore, the evaluation unit can evaluate the generated prompt based on the user satisfaction. For example, the evaluation unit evaluates whether the content of the generated prompt is accurate. The reliability evaluation checks whether the generated prompt is based on a reliable information source. The user satisfaction evaluation is performed based on user feedback. In this way, by evaluating the quality of the generated prompt, a more appropriate prompt can be generated. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input quality data of the generated prompt to the generation AI and cause the generation AI to execute the quality evaluation.

[0037] The generation unit can generate a plurality of different prompts using the generation AI. The generation unit generates a plurality of different prompts using the generation AI. The generation AI generates a plurality of different prompts from different perspectives and contexts, for example, using a text generation AI (for example, LLM). The generation unit can also generate a different format of prompt using a multimodal generation AI. For example, the generation AI generates a prompt from a different perspective based on a text prompt input by the user. For example, the generation AI generates different prompts such as "easy recipes," "healthy recipes," and "time-saving recipes" in response to a prompt such as "tell me a new recipe." In this way, by generating a plurality of different prompts using the generation AI, the user can obtain answers from a plurality of different perspectives at once. A part or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input a prompt input by the user to the generation AI and cause the generation AI to generate different prompts.

[0038] The answer generation unit can generate an answer based on the prompt generated by the generation AI. The answer generation unit generates an answer based on the generated prompt using the generation AI. The generation AI generates an answer to the generated prompt using, for example, a text generation AI (for example, LLM). The answer generation unit can also integrate answers to multiple prompts using the generation AI. For example, the generation AI generates answers to multiple prompts and integrates them to generate an optimal answer. The generation AI generates answers to prompts such as "easy recipes," "healthy recipes," and "time-saving recipes," and integrates them to provide an optimal recipe. As a result, a more appropriate answer can be obtained by generating an answer based on the prompt generated by the generation AI. A part or all of the above-mentioned processing in the answer generation unit is performed using the generation AI. For example, the answer generation unit can input the generated prompt to the generation AI and cause the generation AI to generate an answer.

[0039] The reception unit can analyze the user's past prompt input history and select an appropriate reception method. For example, the reception unit preferentially accepts a prompt format that the user has frequently used in the past. The reception unit can also suggest a prompt reception method suitable for a specific time period from the user's past input history. Furthermore, the reception unit can analyze the contents of prompts that the user has input in the past and automatically accept similar prompts. In this way, the optimal reception method can be selected by analyzing the user's past prompt input history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's past prompt input data to the generation AI and cause the generation AI to select the optimal reception method.

[0040] The reception unit can perform filtering based on the user's current field of interest when receiving a prompt. For example, the reception unit preferentially receives prompts related to topics in which the user is currently interested. The reception unit can also filter and receive related prompts based on the user's recent search history. Furthermore, the reception unit can automatically select an appropriate prompt based on the field in which the user has shown interest. As a result, by filtering based on the user's current field of interest, it is possible to receive more relevant prompts. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's field of interest data to the generation AI and cause the generation AI to perform filtering of the prompt.

[0041] The reception unit can preferentially accept a highly relevant prompt in consideration of the geographical location information of the user when accepting a prompt. For example, when the user is in a specific area, the reception unit preferentially accepts a prompt related to the area. The reception unit can also preferentially accept a prompt related to local information based on the user's current location. Furthermore, when the user is traveling, the reception unit can also preferentially accept a prompt related to the travel destination. In this way, by considering the geographical location information of the user, a highly relevant prompt can be preferentially accepted. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the geographical location information of the user to the generation AI and cause the generation AI to select a highly relevant prompt.

[0042] The reception unit can analyze the user's social media activity and receive a related prompt when receiving a prompt. For example, the reception unit preferentially receives a prompt related to a topic in which the user has shown interest on social media. The reception unit can also analyze the content of the user's social media posts and automatically receive a related prompt. Furthermore, the reception unit can also receive an appropriate prompt based on the activity of an account the user follows. In this way, the user's social media activity can be analyzed to receive a related prompt. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's social media activity data to the generation AI and cause the generation AI to select a prompt.

[0043] The generation unit can incorporate feedback to more accurately reflect the user's intention when generating a prompt. The generation unit adjusts the expression method of the prompt based on, for example, feedback provided by the user. The generation unit can also incorporate feedback in real time to reflect the user's intention. Furthermore, the generation unit can analyze the user's feedback and reflect it in the next prompt generation. As a result, a more appropriate prompt can be generated by incorporating feedback to more accurately reflect the user's intention. 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 feedback data to the generation AI and cause the generation AI to generate a prompt.

[0044] The generation unit can apply different generation algorithms according to different categories when generating a prompt. For example, in the case of a prompt related to a recipe, the generation unit applies a generation algorithm specialized for cooking. In addition, in the case of a prompt related to travel, the generation unit can also apply a generation algorithm specialized for tourist information. In addition, in the case of a prompt related to health, the generation unit can also apply a generation algorithm specialized for medical information. In this way, by applying different generation algorithms according to different categories, a more appropriate prompt can be generated. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input category data of the prompt to the generation AI and cause the generation AI to apply the generation algorithm.

[0045] The generation unit can determine the priority of generation based on the user's past input history when generating a prompt. For example, the generation unit preferentially generates a prompt format that the user has frequently used in the past. The generation unit can also preferentially generate a prompt suitable for a specific time period from the user's past input history. Furthermore, the generation unit can analyze the contents of a prompt that the user has input in the past and preferentially generate a similar prompt. In this way, a more appropriate prompt can be generated by determining the priority of generation based on the user's past input history. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or may be performed without using AI. For example, the generation unit can input the user's past input history data to the generation AI and cause the generation AI to determine the priority of generation.

[0046] The generation unit can adjust the order of generation by referring to information highly relevant to the user when generating a prompt. For example, the generation unit preferentially generates a prompt related to a topic in which the user is currently interested. The generation unit can also preferentially generate a related prompt based on the user's recent search history. Furthermore, the generation unit can also preferentially generate an appropriate prompt based on a field in which the user has shown interest. This makes it possible to generate a more appropriate prompt by referring to information highly relevant to the user. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or may be performed without using AI. For example, the generation unit can input information data highly relevant to the user to the generation AI and cause the generation AI to adjust the order of generation.

[0047] The answer generation unit can adjust the level of detail of the answer based on the importance of the prompt when generating an answer. For example, the answer generation unit generates a detailed answer for an important prompt. The answer generation unit can also generate a concise answer for a general prompt. Furthermore, the answer generation unit can also quickly generate an answer for a prompt with high urgency. In this way, by adjusting the level of detail of the answer based on the importance of the prompt, a more appropriate answer can be generated. A part or all of the above-mentioned processing in the answer generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the answer generation unit can input the importance data of the prompt to the generation AI and cause the generation AI to adjust the level of detail of the answer.

[0048] The answer generation unit can apply different answer algorithms depending on the category of the prompt when generating an answer. For example, in the case of a prompt regarding a recipe, the answer generation unit applies an answer algorithm specialized for cooking. In addition, in the case of a prompt regarding travel, the answer generation unit can also apply an answer algorithm specialized for tourist information. In addition, in the case of a prompt regarding health, the answer generation unit can also apply an answer algorithm specialized for medical information. In this way, by applying different answer algorithms depending on the category of the prompt, a more appropriate answer can be generated. Part or all of the above-mentioned processing in the answer generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the answer generation unit can input category data of the prompt to the generation AI and cause the generation AI to apply the answer algorithm.

[0049] The answer generation unit can determine the priority of answers based on the submission time of the prompt when generating an answer. For example, the answer generation unit quickly generates an answer for a prompt with high urgency. The answer generation unit can also generate an answer preferentially for a prompt submitted earlier. Furthermore, the answer generation unit can generate an answer based on the latest information for a prompt submitted recently. In this way, by determining the priority of answers based on the submission time of the prompt, a more appropriate answer can be generated. A part or all of the above-mentioned processing in the answer generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the answer generation unit can input prompt submission time data to the generation AI and cause the generation AI to determine the priority of answers.

[0050] The answer generation unit can adjust the order of answers based on the relevance of the prompt when generating an answer. For example, the answer generation unit generates answers preferentially for a highly relevant prompt. Also, the answer generation unit can generate answers later for a less relevant prompt. Furthermore, the answer generation unit can analyze the relevance of the prompt and generate answers in an optimal order. In this way, a more appropriate answer can be generated by adjusting the order of answers based on the relevance of the prompt. A part or all of the above-mentioned processing in the answer generation unit may be performed, for example, using AI or may be performed without using AI. For example, the answer generation unit can input relevance data of the prompt to the generation AI and cause the generation AI to adjust the order of the answers.

[0051] The selection unit can improve the accuracy of the selection by considering the interrelationships between multiple answers at the time of selection. For example, the selection unit compares the contents of multiple answers and selects the most relevant answer. The selection unit can also analyze the interrelationships between multiple answers and select the optimal answer. Furthermore, the selection unit can check the consistency of multiple answers and select a highly reliable answer. In this way, a more appropriate answer can be selected by considering the interrelationships between multiple answers. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI or may be performed without using AI. For example, the selection unit can input multiple answer data to the generation AI and cause the generation AI to analyze the interrelationships and perform the selection.

[0052] The selection unit can select an appropriate answer by considering the attribute information of the user at the time of selection. The selection unit selects an appropriate answer based on, for example, the age and gender of the user. The selection unit can also select a highly relevant answer based on the occupation and interests of the user. Furthermore, the selection unit can select an optimal answer by referring to the user's past behavior history. In this way, a more appropriate answer can be selected by considering the attribute information of the user. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the attribute information data of the user to the generation AI and cause the generation AI to select an appropriate answer.

[0053] The selection unit can make a selection taking into consideration the geographic distribution of the answers. For example, the selection unit preferentially selects answers including local information based on the user's current location. In addition, when the user is traveling, the selection unit can also preferentially select answers related to the travel destination. Furthermore, the selection unit can select an appropriate answer based on the user's geographical interests. In this way, a more appropriate answer can be selected by taking into consideration the geographic distribution of the answers. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the geographic distribution data of the answers to the generation AI and cause the generation AI to execute the selection.

[0054] The selection unit can improve the accuracy of the selection by referring to the related literature of the answer at the time of selection. For example, the selection unit refers to the related literature to confirm the reliability of the answer. The selection unit can also refer to the related literature to complement the content of the answer. Furthermore, the selection unit can also refer to the related literature to confirm the consistency of the answer. In this way, by referring to the related literature of the answer, a more appropriate answer can be selected. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the related literature data to the generation AI and cause the generation AI to perform the improvement of the accuracy of the selection.

[0055] The feedback receiving unit can select the optimal receiving method by referring to the user's past feedback history when receiving feedback. For example, the feedback receiving unit preferentially receives the form of feedback provided by the user in the past. The feedback receiving unit can also suggest a feedback receiving method suitable for a specific time period from the user's past feedback history. Furthermore, the feedback receiving unit can analyze the content of feedback provided by the user in the past and preferentially accept similar feedback. In this way, the optimal feedback receiving method can be selected by referring to the user's past feedback history. A part or all of the above-mentioned processing in the feedback receiving unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback receiving unit can input the user's past feedback history data to the generation AI and cause the generation AI to select the optimal receiving method.

[0056] The feedback reception unit can select the optimal reception method in consideration of the device information of the user when receiving feedback. For example, when the user is using a smartphone, the feedback reception unit provides a feedback reception method that matches the screen size. In addition, when the user is using a tablet, the feedback reception unit can also provide a feedback reception method optimized for a large screen. Furthermore, when the user is using a smartwatch, the feedback reception unit can also provide a feedback reception method that is simple and highly visible. This makes it possible to select the optimal feedback reception method by considering the device information of the user. A part or all of the above-mentioned processing in the feedback reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback reception unit can input the device information data of the user to the generation AI and cause the generation AI to select the optimal reception method.

[0057] The collection unit can improve the accuracy of collection by evaluating the reliability of different data sources at the time of collection. For example, the collection unit evaluates the reliability of the data source and preferentially collects highly reliable information. The collection unit can also analyze the reliability of the data source and exclude less reliable information. Furthermore, the collection unit can collect optimal information based on the reliability of the data source. This allows more reliable information to be collected by evaluating the reliability of different data sources. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input reliability data of the data source to the generation AI and cause the generation AI to evaluate the reliability and collect the information.

[0058] The collection unit can collect data while taking into account the geographical distribution of the data sources. For example, the collection unit preferentially collects local information based on the user's current location. In addition, when the user is traveling, the collection unit can also preferentially collect information related to the travel destination. Furthermore, the collection unit can collect appropriate information based on the user's geographical interests. In this way, more appropriate information can be collected by taking into account the geographical distribution of the data sources. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input geographical distribution data of the data sources to the generation AI and cause the generation AI to collect information.

[0059] The evaluation unit can improve the accuracy of the evaluation by referring to the past evaluation history of the generated prompt at the time of evaluation. The evaluation unit adjusts the evaluation criteria based on the past evaluation history of the generated prompt, for example. The evaluation unit can also analyze the past evaluation history and improve the accuracy of the evaluation. Furthermore, the evaluation unit can also apply optimal evaluation criteria by referring to the evaluation history of the generated prompt. As a result, a more accurate evaluation can be performed by referring to the past evaluation history of the generated prompt. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input past evaluation history data to the generation AI and cause the generation AI to improve the accuracy of the evaluation.

[0060] The evaluation unit can improve the accuracy of the evaluation by referring to the related literature of the prompt during the evaluation. The evaluation unit, for example, refers to the related literature to confirm the reliability of the evaluation. The evaluation unit can also refer to the related literature to complement the content of the evaluation. Furthermore, the evaluation unit can also refer to the related literature to confirm the consistency of the evaluation. As a result, by referring to the related literature of the prompt, a more accurate evaluation can be performed. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input related literature data to the generation AI and cause the generation AI to perform the improvement of the accuracy of the evaluation.

[0061] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0062] The generation AI system may further include an environmental sound analysis unit that analyzes environmental sounds at the time of inputting a prompt by the user. For example, the environmental sound analysis unit generates a detailed prompt when the user is in a quiet environment. The environmental sound analysis unit may also generate a concise and clear prompt when the user is in a noisy environment. Furthermore, the environmental sound analysis unit may generate a prompt with a relaxing tone when the user is in nature. This allows the content of the prompt to be adjusted based on the user's environmental sounds, thereby providing a more appropriate prompt.

[0063] The generation AI system may further include a posture detection unit that detects the posture of the user when inputting the prompt. For example, the posture detection unit may generate a relaxed prompt when the user is sitting. The posture detection unit may also generate a prompt that can be quickly processed when the user is standing. Furthermore, the posture detection unit may also generate a concise and intuitive prompt when the user is walking. This allows the content of the prompt to be adjusted based on the user's posture, thereby providing a more appropriate prompt.

[0064] The generation AI system may further include an eye-tracking unit that tracks the user's gaze when inputting a prompt. For example, when the user focuses his / her gaze on a particular part, the eye-tracking unit generates a prompt related to that part. In addition, when the user frequently moves his / her gaze, the eye-tracking unit may generate a concise and to-the-point prompt. In addition, when the user fixates his / her gaze, the eye-tracking unit may generate a detailed prompt. This allows the prompt content to be adjusted based on the user's gaze, thereby providing a more appropriate prompt.

[0065] The generation AI system may further include a heart rate measurement unit that measures the user's heart rate when the user inputs the prompt. For example, the heart rate measurement unit generates a prompt to relax the user when the user's heart rate is high. The heart rate measurement unit may also generate a stimulating prompt when the user's heart rate is low. Furthermore, the heart rate measurement unit may also generate a detailed prompt when the user's heart rate is stable. This allows the content of the prompt to be adjusted based on the user's heart rate, thereby providing a more appropriate prompt.

[0066] The generation AI system may further include a breathing analysis unit that analyzes the breathing pattern of the user when the user inputs a prompt. For example, the breathing analysis unit generates a prompt to relax the user when the user's breathing is fast. The breathing analysis unit may also generate a detailed prompt when the user's breathing is slow. Furthermore, the breathing analysis unit may also generate a standard prompt when the user's breathing is stable. This allows the content of the prompt to be adjusted based on the user's breathing pattern, thereby providing a more appropriate prompt.

[0067] The process flow of the first embodiment will be briefly described below.

[0068] Step 1: The reception unit receives a prompt from a user. The prompt may be in a text format, a voice format, an image format, etc. For example, a text prompt, a voice prompt, or an image prompt input by the user is received. Step 2: The generator uses a generation AI to generate multiple different prompts based on the prompts received by the receiver. For example, the generator uses a text generation AI (LLM) or a multimodal generation AI to generate prompts from different perspectives and contexts. Step 3: The answer generator uses the generation AI to generate answers based on the prompts generated by the generator. For example, the generation AI can be used to generate answers to the generated prompts and can also aggregate answers to multiple prompts. Step 4: The selection unit selects the optimal answer from the multiple answers generated by the answer generation unit. For example, a generation AI can be used to select the optimal answer from the multiple answers, and the optimal answer can be selected based on the user's intentions and feedback.

[0069] (Example 2) The generation AI system according to the embodiment of the present invention is a system that draws out a high-level output even when the user inputs a simple prompt. In this generation AI system, the user inputs a simple prompt, and the generation AI automatically generates multiple different prompts based on the prompt, so that the user can obtain answers from multiple different perspectives at once. Furthermore, the generation AI integrates these multiple answers and provides the most appropriate answer to the user. For example, if the user inputs "tell me a new recipe," the generation AI automatically generates different prompts such as "easy recipes," "healthy recipes," and "time-saving recipes," and generates answers for each of them. Next, the generation AI integrates these answers and provides the most appropriate recipe to the user. This mechanism allows the user to obtain a high-level output with a simple input without having to learn prompt techniques. In addition, the prompts automatically generated by the generation AI more accurately reflect the user's intentions, so that a more appropriate answer can be obtained. Furthermore, by adding a mechanism for accepting feedback from the user, the generation AI can learn and generate more appropriate prompts. By also adding a mechanism for collecting information from different data sources, the generation AI can generate a more diverse range of prompts. This allows the generation AI system to obtain a high-level output even when the user inputs a simple prompt.

[0070] The generation AI system according to the embodiment includes a reception unit, a generation unit, an answer generation unit, and a selection unit. The reception unit receives a prompt from a user. The prompt may be in a text format, a voice format, an image format, or the like, but is not limited to such examples. The reception unit receives, for example, a text prompt input by the user. The reception unit may also receive a voice prompt from the user using a voice input. Furthermore, the reception unit may also receive an image prompt. For example, the user uploads an image and generates a prompt based on the image. The generation unit uses a generation AI to generate multiple different prompts based on the prompt received by the reception unit. The generation AI may use, for example, a text generation AI (e.g., LLM) to generate prompts from different perspectives or contexts. The generation unit may also use a multimodal generation AI to generate prompts in different formats. For example, the generation AI generates prompts from different perspectives based on a text prompt input by the user. The answer generation unit uses a generation AI to generate an answer based on the prompt generated by the generation unit. The answer generation unit uses, for example, a generation AI to generate an answer to the generated prompt. The answer generation unit can also integrate answers to multiple prompts using the generation AI. For example, the generation AI generates answers to multiple prompts and integrates them to generate an optimal answer. The selection unit selects an optimal answer from multiple answers generated by the answer generation unit. The selection unit selects an optimal answer from multiple answers using, for example, the generation AI. The selection unit can also select an optimal answer based on the user's intention or feedback. For example, the selection unit selects an answer that reflects the user's intention. As a result, the generation AI system according to the embodiment can obtain an advanced output even when the user inputs a simple prompt. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can select an optimal answer using an AI model that inputs multiple answers generated by the generation AI and outputs an optimal answer.

[0071] The reception unit receives a prompt from the user. The prompt may be in a text format, a voice format, an image format, or the like, but is not limited to such examples. The reception unit receives, for example, a text prompt input by the user. The reception unit may also receive a voice prompt from the user using voice input. The reception unit may also receive an image prompt. For example, the user uploads an image and generates a prompt based on the image. The reception unit has an input interface specialized for each format in order to accommodate these various input formats. For example, in the case of text input, an intuitive user interface is provided so that the user can easily input text. In the case of voice input, a voice recognition technology is used to convert the user's voice into text with high accuracy. In the case of image input, an image analysis technology is used to extract features from the uploaded image and generate an appropriate prompt. This allows the reception unit to quickly and accurately accept the prompt regardless of the format in which the user inputs it. The reception unit also temporarily stores the input prompt and provides information necessary for subsequent processing. For example, depending on the content and format of the prompt, an appropriate generation AI is selected and passed to the generation unit. Furthermore, the reception unit can support the generation of more appropriate prompts and answers by managing the user's input history and referring to past prompts and answers, thereby enabling the reception unit to respond to the diverse needs of users and improve the efficiency and accuracy of the entire system.

[0072] The generation unit uses a generation AI to generate multiple different prompts based on the prompts received by the reception unit. The generation AI generates prompts from different perspectives and contexts using, for example, a text generation AI (e.g., LLM). The generation unit can also generate prompts in different formats using a multimodal generation AI. For example, the generation AI generates prompts from different perspectives based on a text prompt entered by a user. The generation unit appropriately selects a model of the generation AI and performs optimal generation according to the content and format of the prompt. For example, in the case of a text prompt, natural language processing technology is used to analyze the context and intention, and prompts from different perspectives and contexts are generated. In the case of a voice prompt, voice recognition technology and natural language processing technology are combined to convert voice data into text, and a prompt is generated based on the text. In the case of an image prompt, image analysis technology is used to extract image features, and a text prompt is generated based on the extracted features. In order to perform these generation processes efficiently, the generation unit utilizes high-performance computing resources to generate prompts in real time. In addition, the generation unit evaluates the quality of the generated prompt, and corrects or regenerates it as necessary. For example, if the generated prompt does not match the user's intention, the generation AI is used again to generate a new prompt. This enables the generation unit to respond to the diverse needs of users and provide high-quality prompts.

[0073] The answer generation unit uses the generation AI to generate an answer based on the prompt generated by the generation unit. The answer generation unit uses, for example, the generation AI to generate an answer to the generated prompt. The answer generation unit can also use the generation AI to integrate answers to multiple prompts. For example, the generation AI generates answers to multiple prompts and integrates them to generate an optimal answer. The answer generation unit appropriately selects a model of the generation AI and generates an optimal answer according to the content and format of the prompt. For example, in the case of a text prompt, natural language processing technology is used to analyze the intention and context of the prompt and generate an appropriate answer. In the case of a voice prompt, voice recognition technology and natural language processing technology are combined to convert voice data into text, and an answer is generated based on the text. In the case of an image prompt, image analysis technology is used to extract features of the image and generate a text answer based on the extracted features. In order to efficiently perform these generation processes, the answer generation unit utilizes high-performance computing resources to generate answers in real time. In addition, the answer generation unit evaluates the quality of the generated answer and corrects or regenerates it as necessary. For example, if the generated answer does not match the user's intention, the generation AI is used again to generate a new answer. Furthermore, the answer generator integrates answers to a plurality of prompts to generate an optimal answer, thereby enabling the answer generator to provide high-quality answers that meet the diverse needs of users.

[0074] The selection unit selects the optimal answer from the multiple answers generated by the answer generation unit. The selection unit, for example, uses a generation AI to select the optimal answer from the multiple answers. The selection unit can also select the optimal answer based on the user's intention and feedback. For example, the selection unit selects an answer that reflects the user's intention. The selection unit appropriately selects a model of the generation AI and selects the optimal answer according to the content and format of the answer. For example, in the case of a text answer, natural language processing technology is used to analyze the intention and context of the answer and select the optimal answer. In the case of a voice answer, voice recognition technology and natural language processing technology are combined to convert voice data into text, and the optimal answer is selected based on the text. In the case of an image answer, image analysis technology is used to extract the features of the image and select the optimal answer based on that. In order to perform these selection processes efficiently, the selection unit utilizes high-performance computing resources to select the optimal answer in real time. In addition, the selection unit evaluates the quality of the selected answer and corrects or reselects it as necessary. For example, if the selected answer does not match the user's intent, the generation AI is used again to select a new answer. Furthermore, the selection unit can collect user feedback and continuously improve the accuracy and effectiveness of the selection process. This allows the selection unit to respond to the diverse needs of users and provide high-quality answers.

[0075] The generation AI system includes a feedback receiving unit that receives feedback from a user. The feedback receiving unit receives feedback from the user. The feedback includes, for example, a text format, an evaluation score, a comment, and the like, but is not limited to such examples. The feedback receiving unit receives, for example, text feedback input by the user. The feedback receiving unit can also receive the user's feedback using the evaluation score. Furthermore, the feedback receiving unit can also receive feedback in the form of a comment. For example, the user inputs a comment, and the feedback is received based on the comment. In this way, the generation AI can learn by receiving the user's feedback and generate a more appropriate prompt. A part or all of the above-mentioned processing in the feedback receiving unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the feedback receiving unit can input the user's feedback data to the generation AI and cause the generation AI to analyze the feedback.

[0076] The generation AI system includes a collection unit that collects information from different data sources. The collection unit collects information from different data sources. The data sources include, but are not limited to, for example, websites, databases, and APIs. The collection unit collects information, for example, from websites. The collection unit can also collect information from databases. Furthermore, the collection unit can collect information using APIs. For example, the collection unit collects information by scraping from a specific website. Information collection from a database involves obtaining data using a specific query. Information collection using an API involves sending a request to a specific endpoint and obtaining data as a response. This allows the generation AI to generate more diverse prompts by collecting information from different data sources. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit may input data obtained from a website into the generation AI and cause the generation AI to perform analysis of the data.

[0077] The generation AI system includes an evaluation unit that evaluates the quality of the generated prompt. The evaluation unit evaluates the quality of the generated prompt. The quality includes, for example, accuracy, reliability, user satisfaction, and the like, but is not limited to such examples. The evaluation unit evaluates, for example, the accuracy of the generated prompt. The evaluation unit can also evaluate the reliability of the generated prompt. Furthermore, the evaluation unit can evaluate the generated prompt based on the user satisfaction. For example, the evaluation unit evaluates whether the content of the generated prompt is accurate. The reliability evaluation checks whether the generated prompt is based on a reliable information source. The user satisfaction evaluation is performed based on user feedback. In this way, by evaluating the quality of the generated prompt, a more appropriate prompt can be generated. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input quality data of the generated prompt to the generation AI and cause the generation AI to execute the quality evaluation.

[0078] The generation unit can generate a plurality of different prompts using the generation AI. The generation unit generates a plurality of different prompts using the generation AI. The generation AI generates a plurality of different prompts from different perspectives and contexts, for example, using a text generation AI (for example, LLM). The generation unit can also generate a different format of prompt using a multimodal generation AI. For example, the generation AI generates a prompt from a different perspective based on a text prompt input by the user. For example, the generation AI generates different prompts such as "easy recipes," "healthy recipes," and "time-saving recipes" in response to a prompt such as "tell me a new recipe." In this way, by generating a plurality of different prompts using the generation AI, the user can obtain answers from a plurality of different perspectives at once. A part or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input a prompt input by the user to the generation AI and cause the generation AI to generate different prompts.

[0079] The answer generation unit can generate an answer based on the prompt generated by the generation AI. The answer generation unit generates an answer based on the generated prompt using the generation AI. The generation AI generates an answer to the generated prompt using, for example, a text generation AI (for example, LLM). The answer generation unit can also integrate answers to multiple prompts using the generation AI. For example, the generation AI generates answers to multiple prompts and integrates them to generate an optimal answer. The generation AI generates answers to prompts such as "easy recipes," "healthy recipes," and "time-saving recipes," and integrates them to provide an optimal recipe. As a result, a more appropriate answer can be obtained by generating an answer based on the prompt generated by the generation AI. A part or all of the above-mentioned processing in the answer generation unit is performed using the generation AI. For example, the answer generation unit can input the generated prompt to the generation AI and cause the generation AI to generate an answer.

[0080] The reception unit can estimate the user's emotion and adjust the timing of receiving the prompt based on the estimated user's emotion. For example, when the user is feeling stressed, the reception unit can delay the reception of the prompt to provide time for the user to relax. Also, when the user is relaxed, the reception unit can immediately receive the prompt to promote smooth operation. Furthermore, when the user is in a hurry, the reception unit can quickly receive the prompt and immediately start processing. In this way, the prompt can be received at a more appropriate timing by adjusting the timing of receiving the prompt according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0081] The reception unit can analyze the user's past prompt input history and select an appropriate reception method. For example, the reception unit preferentially accepts a prompt format that the user has frequently used in the past. The reception unit can also suggest a prompt reception method suitable for a specific time period from the user's past input history. Furthermore, the reception unit can analyze the contents of prompts that the user has input in the past and automatically accept similar prompts. In this way, the optimal reception method can be selected by analyzing the user's past prompt input history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's past prompt input data to the generation AI and cause the generation AI to select the optimal reception method.

[0082] The reception unit can perform filtering based on the user's current field of interest when receiving a prompt. For example, the reception unit preferentially receives prompts related to topics in which the user is currently interested. The reception unit can also filter and receive related prompts based on the user's recent search history. Furthermore, the reception unit can automatically select an appropriate prompt based on the field in which the user has shown interest. As a result, by filtering based on the user's current field of interest, it is possible to receive more relevant prompts. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's field of interest data to the generation AI and cause the generation AI to perform filtering of the prompt.

[0083] The reception unit can estimate the user's emotion and determine the priority of the prompts to be received based on the estimated user's emotion. For example, when the user is stressed, the reception unit preferentially receives a simple and intuitive prompt. Furthermore, when the user is relaxed, the reception unit can also preferentially receive a detailed prompt. Furthermore, when the user is in a hurry, the reception unit can also preferentially receive a prompt that can be processed quickly. In this way, by determining the priority of the prompts according to the user's emotion, it is possible to preferentially receive a more appropriate prompt. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of the prompts.

[0084] The reception unit can preferentially accept a highly relevant prompt in consideration of the geographical location information of the user when accepting a prompt. For example, when the user is in a specific area, the reception unit preferentially accepts a prompt related to the area. The reception unit can also preferentially accept a prompt related to local information based on the user's current location. Furthermore, when the user is traveling, the reception unit can also preferentially accept a prompt related to the travel destination. In this way, by considering the geographical location information of the user, a highly relevant prompt can be preferentially accepted. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the geographical location information of the user to the generation AI and cause the generation AI to select a highly relevant prompt.

[0085] The reception unit can analyze the user's social media activity and receive a related prompt when receiving a prompt. For example, the reception unit preferentially receives a prompt related to a topic in which the user has shown interest on social media. The reception unit can also analyze the content of the user's social media posts and automatically receive a related prompt. Furthermore, the reception unit can also receive an appropriate prompt based on the activity of an account the user follows. In this way, the user's social media activity can be analyzed to receive a related prompt. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's social media activity data to the generation AI and cause the generation AI to select a prompt.

[0086] The generation unit can estimate the user's emotion and adjust the expression method of the generated prompt based on the estimated user's emotion. For example, when the user is relaxed, the generation unit generates a prompt with a soft expression. In addition, when the user is in a hurry, the generation unit can also generate a concise and clear prompt. Furthermore, when the user is excited, the generation unit can also generate a visually stimulating prompt. This allows a more appropriate prompt to be generated by adjusting the expression method of the prompt according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the expression method of the prompt.

[0087] The generation unit can incorporate feedback to more accurately reflect the user's intention when generating a prompt. The generation unit adjusts the expression method of the prompt based on, for example, feedback provided by the user. The generation unit can also incorporate feedback in real time to reflect the user's intention. Furthermore, the generation unit can analyze the user's feedback and reflect it in the next prompt generation. As a result, a more appropriate prompt can be generated by incorporating feedback to more accurately reflect the user's intention. 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 feedback data to the generation AI and cause the generation AI to generate a prompt.

[0088] The generation unit can apply different generation algorithms according to different categories when generating a prompt. For example, in the case of a prompt related to a recipe, the generation unit applies a generation algorithm specialized for cooking. In addition, in the case of a prompt related to travel, the generation unit can also apply a generation algorithm specialized for tourist information. In addition, in the case of a prompt related to health, the generation unit can also apply a generation algorithm specialized for medical information. In this way, by applying different generation algorithms according to different categories, a more appropriate prompt can be generated. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input category data of the prompt to the generation AI and cause the generation AI to apply the generation algorithm.

[0089] The generation unit can estimate the user's emotion and adjust the length of the prompt to be generated based on the estimated user's emotion. For example, when the user is in a hurry, the generation unit generates a short prompt that is to the point. In addition, when the user is relaxed, the generation unit can also generate a longer prompt that includes a detailed explanation. Furthermore, when the user is excited, the generation unit can also generate a prompt with a visually stimulating effect. In this way, a more appropriate prompt can be generated by adjusting the length of the prompt according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the prompt.

[0090] The generation unit can determine the priority of generation based on the user's past input history when generating a prompt. For example, the generation unit preferentially generates a prompt format that the user has frequently used in the past. The generation unit can also preferentially generate a prompt suitable for a specific time period from the user's past input history. Furthermore, the generation unit can analyze the contents of a prompt that the user has input in the past and preferentially generate a similar prompt. In this way, a more appropriate prompt can be generated by determining the priority of generation based on the user's past input history. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or may be performed without using AI. For example, the generation unit can input the user's past input history data to the generation AI and cause the generation AI to determine the priority of generation.

[0091] The generation unit can adjust the order of generation by referring to information highly relevant to the user when generating a prompt. For example, the generation unit preferentially generates a prompt related to a topic in which the user is currently interested. The generation unit can also preferentially generate a related prompt based on the user's recent search history. Furthermore, the generation unit can also preferentially generate an appropriate prompt based on a field in which the user has shown interest. This makes it possible to generate a more appropriate prompt by referring to information highly relevant to the user. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or may be performed without using AI. For example, the generation unit can input information data highly relevant to the user to the generation AI and cause the generation AI to adjust the order of generation.

[0092] The answer generation unit can estimate the user's emotion and adjust the way of expressing the answer based on the estimated emotion of the user. For example, when the user is relaxed, the answer generation unit generates an answer with a soft expression. In addition, when the user is in a hurry, the answer generation unit can also generate a concise and clear answer. Furthermore, when the user is excited, the answer generation unit can also generate a visually stimulating answer. This allows a more appropriate answer to be generated by adjusting the way of expressing the answer according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the answer generation unit is performed using the generation AI. For example, the answer generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the way of expressing the answer.

[0093] The answer generation unit can adjust the level of detail of the answer based on the importance of the prompt when generating an answer. For example, the answer generation unit generates a detailed answer for an important prompt. The answer generation unit can also generate a concise answer for a general prompt. Furthermore, the answer generation unit can also quickly generate an answer for a prompt with high urgency. In this way, by adjusting the level of detail of the answer based on the importance of the prompt, a more appropriate answer can be generated. A part or all of the above-mentioned processing in the answer generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the answer generation unit can input the importance data of the prompt to the generation AI and cause the generation AI to adjust the level of detail of the answer.

[0094] The answer generation unit can apply different answer algorithms depending on the category of the prompt when generating an answer. For example, in the case of a prompt regarding a recipe, the answer generation unit applies an answer algorithm specialized for cooking. In addition, in the case of a prompt regarding travel, the answer generation unit can also apply an answer algorithm specialized for tourist information. In addition, in the case of a prompt regarding health, the answer generation unit can also apply an answer algorithm specialized for medical information. In this way, by applying different answer algorithms depending on the category of the prompt, a more appropriate answer can be generated. Part or all of the above-mentioned processing in the answer generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the answer generation unit can input category data of the prompt to the generation AI and cause the generation AI to apply the answer algorithm.

[0095] The answer generation unit can estimate the user's emotion and adjust the length of the answer based on the estimated user's emotion. For example, when the user is in a hurry, the answer generation unit generates a short answer that is to the point. In addition, when the user is relaxed, the answer generation unit can also generate a longer answer that includes a detailed explanation. Furthermore, when the user is excited, the answer generation unit can also generate an answer with a visually stimulating effect. This allows a more appropriate answer to be generated by adjusting the length of the answer according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the answer generation unit is performed using the generation AI. For example, the answer generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the answer.

[0096] The answer generation unit can determine the priority of answers based on the submission time of the prompt when generating an answer. For example, the answer generation unit quickly generates an answer for a prompt with high urgency. The answer generation unit can also generate an answer preferentially for a prompt submitted earlier. Furthermore, the answer generation unit can generate an answer based on the latest information for a prompt submitted recently. In this way, by determining the priority of answers based on the submission time of the prompt, a more appropriate answer can be generated. A part or all of the above-mentioned processing in the answer generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the answer generation unit can input prompt submission time data to the generation AI and cause the generation AI to determine the priority of answers.

[0097] The answer generation unit can adjust the order of answers based on the relevance of the prompt when generating an answer. For example, the answer generation unit generates answers preferentially for a highly relevant prompt. Also, the answer generation unit can generate answers later for a less relevant prompt. Furthermore, the answer generation unit can analyze the relevance of the prompt and generate answers in an optimal order. In this way, a more appropriate answer can be generated by adjusting the order of answers based on the relevance of the prompt. A part or all of the above-mentioned processing in the answer generation unit may be performed, for example, using AI or may be performed without using AI. For example, the answer generation unit can input relevance data of the prompt to the generation AI and cause the generation AI to adjust the order of the answers.

[0098] The selection unit can estimate the user's emotion and adjust the selection criteria based on the estimated user's emotion. For example, when the user is relaxed, the selection unit preferentially selects an answer that includes detailed information. In addition, when the user is in a hurry, the selection unit can also preferentially select a concise and clear answer. Furthermore, when the user is excited, the selection unit can also preferentially select a visually stimulating answer. In this way, by adjusting the selection criteria according to the user's emotion, a more appropriate answer can be selected. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the selection unit is performed using the generation AI. For example, the selection unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the selection criteria.

[0099] The selection unit can improve the accuracy of the selection by considering the interrelationships between multiple answers at the time of selection. For example, the selection unit compares the contents of multiple answers and selects the most relevant answer. The selection unit can also analyze the interrelationships between multiple answers and select the optimal answer. Furthermore, the selection unit can check the consistency of multiple answers and select a highly reliable answer. In this way, a more appropriate answer can be selected by considering the interrelationships between multiple answers. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI or may be performed without using AI. For example, the selection unit can input multiple answer data to the generation AI and cause the generation AI to analyze the interrelationships and perform the selection.

[0100] The selection unit can select an appropriate answer by considering the attribute information of the user at the time of selection. The selection unit selects an appropriate answer based on, for example, the age and gender of the user. The selection unit can also select a highly relevant answer based on the occupation and interests of the user. Furthermore, the selection unit can select an optimal answer by referring to the user's past behavior history. In this way, a more appropriate answer can be selected by considering the attribute information of the user. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the attribute information data of the user to the generation AI and cause the generation AI to select an appropriate answer.

[0101] The selection unit can estimate the user's emotion and adjust the display order of the selection results based on the estimated user's emotion. For example, when the user is relaxed, the selection unit preferentially displays answers including detailed information. In addition, when the user is in a hurry, the selection unit can also preferentially display concise and clear answers. Furthermore, when the user is excited, the selection unit can also preferentially display visually stimulating answers. In this way, by adjusting the display order of the selection results according to the user's emotion, more appropriate answers can be displayed. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the selection unit is performed using the generation AI. For example, the selection unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display order.

[0102] The selection unit can make a selection taking into consideration the geographic distribution of the answers. For example, the selection unit preferentially selects answers including local information based on the user's current location. In addition, when the user is traveling, the selection unit can also preferentially select answers related to the travel destination. Furthermore, the selection unit can select an appropriate answer based on the user's geographical interests. In this way, a more appropriate answer can be selected by taking into consideration the geographic distribution of the answers. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the geographic distribution data of the answers to the generation AI and cause the generation AI to execute the selection.

[0103] The selection unit can improve the accuracy of the selection by referring to the related literature of the answer at the time of selection. For example, the selection unit refers to the related literature to confirm the reliability of the answer. The selection unit can also refer to the related literature to complement the content of the answer. Furthermore, the selection unit can also refer to the related literature to confirm the consistency of the answer. In this way, by referring to the related literature of the answer, a more appropriate answer can be selected. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the related literature data to the generation AI and cause the generation AI to perform the improvement of the accuracy of the selection.

[0104] The feedback receiving unit can estimate the user's emotion and adjust the feedback receiving method based on the estimated user's emotion. For example, when the user is relaxed, the feedback receiving unit can receive detailed feedback. Also, when the user is in a hurry, the feedback receiving unit can receive brief feedback. Furthermore, when the user is excited, the feedback receiving unit can receive visually stimulating feedback. This allows more appropriate feedback to be received by adjusting the feedback receiving method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the feedback receiving unit is performed using the generation AI. For example, the feedback receiving unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the feedback receiving method.

[0105] The feedback receiving unit can select the optimal receiving method by referring to the user's past feedback history when receiving feedback. For example, the feedback receiving unit preferentially receives the form of feedback provided by the user in the past. The feedback receiving unit can also suggest a feedback receiving method suitable for a specific time period from the user's past feedback history. Furthermore, the feedback receiving unit can analyze the content of feedback provided by the user in the past and preferentially accept similar feedback. In this way, the optimal feedback receiving method can be selected by referring to the user's past feedback history. A part or all of the above-mentioned processing in the feedback receiving unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback receiving unit can input the user's past feedback history data to the generation AI and cause the generation AI to select the optimal receiving method.

[0106] The feedback receiving unit can estimate the user's emotion and determine the priority of the feedback based on the estimated user's emotion. For example, when the user is relaxed, the feedback receiving unit preferentially receives detailed feedback. Also, when the user is in a hurry, the feedback receiving unit can preferentially receive brief feedback. Furthermore, when the user is excited, the feedback receiving unit can preferentially receive visually stimulating feedback. In this way, by determining the priority of the feedback according to the user's emotion, it is possible to preferentially receive more appropriate feedback. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the feedback receiving unit is performed using the generation AI. For example, the feedback receiving unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of the feedback.

[0107] The feedback reception unit can select the optimal reception method in consideration of the device information of the user when receiving feedback. For example, when the user is using a smartphone, the feedback reception unit provides a feedback reception method that matches the screen size. In addition, when the user is using a tablet, the feedback reception unit can also provide a feedback reception method optimized for a large screen. Furthermore, when the user is using a smartwatch, the feedback reception unit can also provide a feedback reception method that is simple and highly visible. This makes it possible to select the optimal feedback reception method by considering the device information of the user. A part or all of the above-mentioned processing in the feedback reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback reception unit can input the device information data of the user to the generation AI and cause the generation AI to select the optimal reception method.

[0108] The collection unit can estimate the user's emotion and adjust the type of information to be collected based on the estimated user's emotion. For example, when the user is relaxed, the collection unit collects detailed information. In addition, when the user is in a hurry, the collection unit can also collect brief information. Furthermore, when the user is excited, the collection unit can also collect visually stimulating information. This allows more appropriate information to be collected by adjusting the type of information to be collected according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit is performed using the generation AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the type of information to be collected.

[0109] The collection unit can improve the accuracy of collection by evaluating the reliability of different data sources at the time of collection. For example, the collection unit evaluates the reliability of the data source and preferentially collects highly reliable information. The collection unit can also analyze the reliability of the data source and exclude less reliable information. Furthermore, the collection unit can collect optimal information based on the reliability of the data source. This allows more reliable information to be collected by evaluating the reliability of different data sources. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input reliability data of the data source to the generation AI and cause the generation AI to evaluate the reliability and collect the information.

[0110] The collection unit can estimate the user's emotion and determine the priority of information to be collected based on the estimated user's emotion. For example, when the user is relaxed, the collection unit preferentially collects detailed information. In addition, when the user is in a hurry, the collection unit can also preferentially collect brief information. Furthermore, when the user is excited, the collection unit can also preferentially collect visually stimulating information. In this way, by determining the priority of information to be collected according to the user's emotion, more appropriate information can be preferentially collected. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit is performed using the generation AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of information.

[0111] The collection unit can collect data while taking into account the geographical distribution of the data sources. For example, the collection unit preferentially collects local information based on the user's current location. In addition, when the user is traveling, the collection unit can also preferentially collect information related to the travel destination. Furthermore, the collection unit can collect appropriate information based on the user's geographical interests. In this way, more appropriate information can be collected by taking into account the geographical distribution of the data sources. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input geographical distribution data of the data sources to the generation AI and cause the generation AI to collect information.

[0112] The evaluation unit can estimate the user's emotion and adjust the evaluation criteria based on the estimated user's emotion. For example, the evaluation unit applies detailed evaluation criteria when the user is relaxed. In addition, the evaluation unit can also apply concise evaluation criteria when the user is in a hurry. Furthermore, the evaluation unit can apply visually stimulating evaluation criteria when the user is excited. This allows for more appropriate evaluation by adjusting the evaluation criteria according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit is performed using the generation AI. For example, the evaluation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the evaluation criteria.

[0113] The evaluation unit can improve the accuracy of the evaluation by referring to the past evaluation history of the generated prompt at the time of evaluation. The evaluation unit adjusts the evaluation criteria based on the past evaluation history of the generated prompt, for example. The evaluation unit can also analyze the past evaluation history and improve the accuracy of the evaluation. Furthermore, the evaluation unit can also apply optimal evaluation criteria by referring to the evaluation history of the generated prompt. As a result, a more accurate evaluation can be performed by referring to the past evaluation history of the generated prompt. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input past evaluation history data to the generation AI and cause the generation AI to improve the accuracy of the evaluation.

[0114] The evaluation unit can estimate the user's emotion and adjust the display order of the evaluation results based on the estimated user's emotion. For example, when the user is relaxed, the evaluation unit can preferentially display detailed evaluation results. Furthermore, when the user is in a hurry, the evaluation unit can also preferentially display brief evaluation results. Furthermore, when the user is excited, the evaluation unit can also preferentially display visually stimulating evaluation results. In this way, by adjusting the display order of the evaluation results according to the user's emotion, more appropriate evaluation results can be displayed. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit is performed using the generation AI. For example, the evaluation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display order.

[0115] The evaluation unit can improve the accuracy of the evaluation by referring to the related literature of the prompt during the evaluation. The evaluation unit, for example, refers to the related literature to confirm the reliability of the evaluation. The evaluation unit can also refer to the related literature to complement the content of the evaluation. Furthermore, the evaluation unit can also refer to the related literature to confirm the consistency of the evaluation. As a result, by referring to the related literature of the prompt, a more accurate evaluation can be performed. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input related literature data to the generation AI and cause the generation AI to perform the improvement of the accuracy of the evaluation.

[0116] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0117] The generation AI system may further include an environmental sound analysis unit that analyzes environmental sounds at the time of inputting a prompt by the user. For example, the environmental sound analysis unit generates a detailed prompt when the user is in a quiet environment. The environmental sound analysis unit may also generate a concise and clear prompt when the user is in a noisy environment. Furthermore, the environmental sound analysis unit may generate a prompt with a relaxing tone when the user is in nature. This allows the content of the prompt to be adjusted based on the user's environmental sounds, thereby providing a more appropriate prompt.

[0118] The generation AI system may further include a posture detection unit that detects the posture of the user when inputting the prompt. For example, the posture detection unit may generate a relaxed prompt when the user is sitting. The posture detection unit may also generate a prompt that can be quickly processed when the user is standing. Furthermore, the posture detection unit may also generate a concise and intuitive prompt when the user is walking. This allows the content of the prompt to be adjusted based on the user's posture, thereby providing a more appropriate prompt.

[0119] The generation AI system may further include an eye-tracking unit that tracks the user's gaze when inputting a prompt. For example, when the user focuses his / her gaze on a particular part, the eye-tracking unit generates a prompt related to that part. In addition, when the user frequently moves his / her gaze, the eye-tracking unit may generate a concise and to-the-point prompt. In addition, when the user fixates his / her gaze, the eye-tracking unit may generate a detailed prompt. This allows the prompt content to be adjusted based on the user's gaze, thereby providing a more appropriate prompt.

[0120] The generation AI system may further include a heart rate measurement unit that measures the user's heart rate when the user inputs the prompt. For example, the heart rate measurement unit generates a prompt to relax the user when the user's heart rate is high. The heart rate measurement unit may also generate a stimulating prompt when the user's heart rate is low. Furthermore, the heart rate measurement unit may also generate a detailed prompt when the user's heart rate is stable. This allows the content of the prompt to be adjusted based on the user's heart rate, thereby providing a more appropriate prompt.

[0121] The generation AI system may further include a breathing analysis unit that analyzes the breathing pattern of the user when the user inputs a prompt. For example, the breathing analysis unit generates a prompt to relax the user when the user's breathing is fast. The breathing analysis unit may also generate a detailed prompt when the user's breathing is slow. Furthermore, the breathing analysis unit may also generate a standard prompt when the user's breathing is stable. This allows the content of the prompt to be adjusted based on the user's breathing pattern, thereby providing a more appropriate prompt.

[0122] The generative AI system can further estimate the user's emotions and adjust the tone of the prompt based on the estimated user's emotions. For example, if the user is sad, a prompt with an encouraging tone can be generated. Also, if the user is happy, a prompt with an empathetic tone can be generated. Furthermore, if the user is angry, a prompt with a calm tone can be generated. This allows the system to provide more appropriate prompts by adjusting the tone of the prompt according to the user's emotions.

[0123] The generation AI system can further estimate the user's emotions and customize the content of the prompt based on the estimated user's emotions. For example, if the user is feeling stressed, a prompt containing content to relax the user can be generated. If the user is excited, a prompt containing content to attract interest can be generated. Furthermore, if the user is tired, a prompt containing concise and easy-to-understand content can be generated. This allows the system to provide more appropriate prompts by customizing the content of the prompt according to the user's emotions.

[0124] The generation AI system can further estimate the user's emotions and adjust the difficulty of the prompt based on the estimated user's emotions. For example, if the user is relaxed, a high level of difficulty prompt can be generated. Also, if the user is stressed, an easy prompt can be generated. Furthermore, if the user is concentrating, a moderate level of difficulty prompt can be generated. This allows for more appropriate prompts to be provided by adjusting the difficulty of the prompt according to the user's emotions.

[0125] The generative AI system can further estimate the user's emotions and adjust the format of the prompt based on the estimated user's emotions. For example, if the user is relaxed, a detailed text prompt can be generated. If the user is in a hurry, a concise bullet-point prompt can be generated. If the user is excited, a visually stimulating image prompt can be generated. This allows the system to provide more appropriate prompts by adjusting the prompt format according to the user's emotions.

[0126] The generative AI system can further estimate the user's emotions and adjust the timing of the prompts based on the estimated user's emotions. For example, if the user is relaxed, the prompts can be delayed. If the user is in a hurry, the prompts can be presented immediately. Furthermore, if the user is excited, the prompts can be presented at an appropriate time. This allows the system to provide more appropriate prompts by adjusting the timing of the prompts according to the user's emotions.

[0127] The process flow of the second embodiment will be briefly described below.

[0128] Step 1: The reception unit receives a prompt from a user. The prompt may be in a text format, a voice format, an image format, etc. For example, a text prompt, a voice prompt, or an image prompt input by the user is received. Step 2: The generator uses a generation AI to generate multiple different prompts based on the prompts received by the receiver. For example, the generator uses a text generation AI (LLM) or a multimodal generation AI to generate prompts from different perspectives and contexts. Step 3: The answer generator uses the generation AI to generate answers based on the prompts generated by the generator. For example, the generation AI can be used to generate answers to the generated prompts and can also aggregate answers to multiple prompts. Step 4: The selection unit selects the optimal answer from the multiple answers generated by the answer generation unit. For example, a generation AI can be used to select the optimal answer from the multiple answers, and the optimal answer can be selected based on the user's intentions and feedback.

[0129] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0130] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0131] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements including the above-mentioned reception unit, generation unit, answer generation unit, selection unit, feedback reception unit, collection unit, and evaluation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives a prompt from a user. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates multiple different prompts based on the received prompt. The answer generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates an answer based on the generated prompt. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects an optimal answer from the multiple generated answers. The feedback reception unit is realized, for example, by the control unit 46A of the smart device 14 and receives feedback from a user. The collection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and collects information from different data sources. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the quality of the generated prompt. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0133] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0134] 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.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] 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.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0140] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] 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.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0143] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0147] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0148] Each of the multiple elements including the above-mentioned reception unit, generation unit, answer generation unit, selection unit, feedback reception unit, collection unit, and evaluation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives a prompt from a user. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates multiple different prompts based on the received prompt. The answer generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates an answer based on the generated prompt. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects an optimal answer from the multiple generated answers. The feedback reception unit is realized, for example, by the control unit 46A of the smart glasses 214 and receives feedback from a user. The collection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and collects information from different data sources. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the quality of the generated prompt. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0149] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0150] 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.

[0151] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0152] 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.

[0153] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0155] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0156] 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.

[0157] 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.

[0158] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0159] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0160] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0161] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0162] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0163] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0164] Each of the multiple elements including the above-mentioned reception unit, generation unit, answer generation unit, selection unit, feedback reception unit, collection unit, and evaluation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives a prompt from a user. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates multiple different prompts based on the received prompt. The answer generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates an answer based on the generated prompt. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects an optimal answer from multiple generated answers. The feedback reception unit is realized, for example, by the control unit 46A of the headset type terminal 314 and receives feedback from a user. The collection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and collects information from different data sources. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the quality of the generated prompt. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0165] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0166] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0167] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0168] 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.

[0169] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0170] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0171] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0172] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0173] 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.

[0174] 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.

[0175] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0176] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0177] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0178] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0179] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0180] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0181] Each of the multiple elements including the above-mentioned reception unit, generation unit, answer generation unit, selection unit, feedback reception unit, collection unit, and evaluation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives a prompt from a user. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates multiple different prompts based on the received prompt. The answer generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates an answer based on the generated prompt. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects an optimal answer from the multiple generated answers. The feedback reception unit is realized, for example, by the control unit 46A of the robot 414 and receives feedback from a user. The collection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and collects information from different data sources. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the quality of the generated prompt. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0182] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0183] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0184] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0185] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0186] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0187] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0188] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0189] 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.

[0190] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0191] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0192] 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.

[0193] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0194] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0195] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0196] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0197] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0198] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0199] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0200] (Appendix 1) a reception unit for receiving a prompt from a user; a generating unit that generates a plurality of different prompts based on the prompts received by the receiving unit; an answer generator for generating an answer based on the prompt generated by the generator; A selection unit that selects an appropriate answer from the multiple answers generated by the answer generation unit. A system characterized by: (Appendix 2) A feedback receiving unit is provided to receive feedback from the user. 2. The system of claim 1, (Appendix 3) Equipped with a collection unit that collects information from different data sources 2. The system of claim 1, (Appendix 4) An evaluator is provided for evaluating the quality of the generated prompts. 2. The system of claim 1, (Appendix 5) The generation unit is Generate multiple different prompts with generative AI 2. The system of claim 1, (Appendix 6) The answer generation unit: Generate answers based on prompts generated by generative AI 2. The system of claim 1, (Appendix 7) The reception unit is To estimate a user's emotion and adjust a timing of receiving a prompt based on the estimated user's emotion. 2. The system of claim 1, (Appendix 8) The reception unit is Analyze the user's past prompt input history and select the appropriate reception method. 2. The system of claim 1, (Appendix 9) The reception unit is When a prompt is received, it is filtered based on the user's current interests. 2. The system of claim 1, (Appendix 10) The reception unit is Estimate the user's emotions and prioritize prompts based on the estimated user's emotions. 2. The system of claim 1, (Appendix 11) The reception unit is When accepting prompts, the system takes into account the user's geographic location to prioritize more relevant prompts. 2. The system of claim 1, (Appendix 12) The reception unit is When a prompt is received, analyze the user's social media activity and receive relevant prompts. 2. The system of claim 1, (Appendix 13) The generation unit is Inferring a user's emotion and adjusting the expression of the generated prompt based on the estimated user's emotion 2. The system of claim 1, (Appendix 14) The generation unit is Incorporating feedback into prompt generation to more accurately reflect user intent 2. The system of claim 1, (Appendix 15) The generation unit is When generating prompts, apply different generation algorithms for different categories 2. The system of claim 1, (Appendix 16) The generation unit is Inferring a user's emotion and adjusting the length of the generated prompt based on the estimated user emotion 2. The system of claim 1, (Appendix 17) The generation unit is When generating prompts, determine the priority of generation based on the user's past input history. 2. The system of claim 1, (Appendix 18) The generation unit is When generating prompts, adjust the order of generation based on the user's most relevant information 2. The system of claim 1, (Appendix 19) The answer generation unit: Infer user sentiment and adjust answer expression based on the inferred sentiment 2. The system of claim 1, (Appendix 20) The answer generation unit: When generating an answer, adjust the detail of the answer based on the importance of the prompt 2. The system of claim 1, (Appendix 21) The answer generation unit: Apply different answer algorithms depending on the prompt category when generating answers 2. The system of claim 1, (Appendix 22) The answer generation unit: Infer user sentiment and adjust the length of answers based on the estimated user sentiment 2. The system of claim 1, (Appendix 23) The answer generation unit: During answer generation, prioritize answers based on when the prompt was submitted 2. The system of claim 1, (Appendix 24) The answer generation unit: During answer generation, adjust the order of answers based on prompt relevance 2. The system of claim 1, (Appendix 25) The selection unit is Inferring user sentiment and adjusting selection criteria based on the estimated user sentiment 2. The system of claim 1, (Appendix 26) The selection unit is When selecting, the accuracy of the selection is improved by considering the correlation between multiple responses. 2. The system of claim 1, (Appendix 27) The selection unit is When selecting an answer, the appropriate answer is selected taking into account the user's attribute information. 2. The system of claim 1, (Appendix 28) The selection unit is Inferring user emotions and adjusting the display order of selection results based on the estimated user emotions 2. The system of claim 1, (Appendix 29) The selection unit is At the time of selection, the geographical distribution of responses will be taken into consideration. 2. The system of claim 1, (Appendix 30) The selection unit is When selecting, refer to the relevant literature of the answers to improve the accuracy of the selection. 2. The system of claim 1, (Appendix 31) The feedback receiving unit, Infer user emotions and adjust the way feedback is received based on the estimated user emotions 3. The system of claim 2, (Appendix 32) The feedback receiving unit, When receiving feedback, select the optimal method of receiving feedback by referring to the user's past feedback history. 3. The system of claim 2, (Appendix 33) The feedback receiving unit, Estimate user emotions and prioritize feedback based on the estimated user emotions 3. The system of claim 2, (Appendix 34) The feedback receiving unit, When receiving feedback, select the optimal reception method taking into account the user's device information 3. The system of claim 2, (Appendix 35) The collecting unit includes: Inferring a user's emotions and adjusting the type of information to be collected based on the inferred user's emotions 4. The system of claim 3. (Appendix 36) The collecting unit includes: Assess the reliability of different data sources at the time of collection to improve accuracy of collection 4. The system of claim 3. (Appendix 37) The collecting unit includes: Estimate user emotions and prioritize information to be collected based on the estimated user emotions. 4. The system of claim 3. (Appendix 38) The collecting unit includes: When collecting data, the geographical distribution of the data sources should be taken into consideration. 4. The system of claim 3. (Appendix 39) The evaluation unit is Inferring a user's emotion and adjusting the evaluation criteria based on the estimated user's emotion 5. The system of claim 4. (Appendix 40) The evaluation unit is During evaluation, you can refer to the past evaluation history of generated prompts to improve the accuracy of your evaluation 5. The system of claim 4. (Appendix 41) The evaluation unit is Inferring user emotions and adjusting the display order of rating results based on the estimated user emotions 5. The system of claim 4. (Appendix 42) The evaluation unit is During evaluation, refer to the relevant literature for the prompt to improve the accuracy of the evaluation. 5. The system of claim 4. [Explanation of symbols]

[0201] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit for receiving a prompt from a user; a generating unit that generates a plurality of different prompts based on the prompts received by the receiving unit; an answer generator for generating an answer based on the prompt generated by the generator; A selection unit that selects an appropriate answer from the multiple answers generated by the answer generation unit. A system characterized by:

2. A feedback receiving unit is provided to receive feedback from the user.

2. The system of claim 1 .

3. Equipped with a collection unit that collects information from different data sources 2. The system of claim 1 .

4. An evaluator is provided for evaluating the quality of the generated prompts.

2. The system of claim 1 .

5. The generation unit is Generate multiple different prompts with generative AI 2. The system of claim 1 .

6. The answer generation unit: Generate answers based on prompts generated by generative AI 2. The system of claim 1 .

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

2. The system of claim 1 .

8. The reception unit is Analyze the user's past prompt input history and select the appropriate reception method.

2. The system of claim 1 .

Images