System

Abstract

An object of the system according to the embodiment is to automatically generate a question of a questionnaire and to save cost and time.SOLUTION: A system according to an embodiment includes an analysis unit, a generation unit, and a presentation unit. The analysis unit analyzes the answer content or the emotion of the answerer. The generation unit generates a next question based on the content analyzed by the analysis unit. The presentation unit presents the question generated by the 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 an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

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

[0004] Conventional technology requires survey questions to be prepared in advance, which is costly and time-consuming.

[0005] The system according to the embodiment aims to automatically generate survey questions, thereby saving costs and time. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a generation unit, and a presentation unit. The analysis unit analyzes the content or sentiment of the respondent's answer. The generation unit generates the next question based on the content analyzed by the analysis unit. The presentation unit presents the question generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically generate survey questions, thereby saving costs and time. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A questionnaire system according to an embodiment of the present invention analyzes the respondent's responses and emotions, and a generation AI generates and presents the next question. When a respondent answers a questionnaire, the generation AI analyzes the responses and emotions and generates the next question. This process allows the respondent to understand their true feelings and identify needs that they themselves may not have been aware of. Companies do not need to plan the questionnaire questions in advance, saving time and money. For example, in a questionnaire system, the respondent answers the questionnaire. The respondent's responses and emotions are input into the generation AI. For example, if the respondent feels "this is bothersome," the generation AI analyzes their emotions and generates the next question. In this way, questions are generated based on the respondent's emotions. Next, the questionnaire system uses the generation AI to analyze the responses and emotions. The generation AI uses natural language processing and speech recognition technology to analyze the respondent's responses and emotions. For example, if the respondent answers "I like this product," the generation AI analyzes the responses and generates the next question. This process allows the respondent to understand their true feelings and identify needs that they themselves may not have been aware of. Furthermore, the survey system uses a generation AI to generate the next question. The generation AI generates the next question based on the respondent's response and emotions. For example, if a respondent answers, "I like this product," the generation AI generates a next question such as, "What do you particularly like about it?" In this way, the respondent's true feelings and needs can be uncovered. This eliminates the need for companies to plan survey questions in advance, saving time and money. For example, when a company collects feedback on a new product, the generation AI automatically generates questions, reducing the time and cost required to create them. Furthermore, because the generation AI uncovers the respondent's true feelings and needs, more accurate feedback can be obtained. This improves the survey response process, creating a system that benefits both companies and respondents. The survey system analyzes the respondent's response content and emotions and generates and presents the next question, improving the efficiency and accuracy of surveys.For example, when a company collects feedback on a new product, generative AI can automatically generate questions, reducing the time and cost required to create the questions. In addition, generative AI can uncover the true feelings and needs of respondents, resulting in more accurate feedback.

[0029] A questionnaire system according to an embodiment includes an analysis unit, a generation unit, and a presentation unit. The analysis unit analyzes the content of a respondent's answer or emotions. The analysis unit analyzes the content of the respondent's answer using, for example, natural language processing technology. The analysis unit can also analyze the respondent's emotions using voice recognition technology. The analysis unit can also classify the respondent's emotions using a sentiment analysis algorithm. For example, the analysis unit inputs the content of the respondent's answer as text data and analyzes it using natural language processing technology. The analysis unit can also input the respondent's voice data and analyze the emotions using voice recognition technology. The analysis unit can also classify the respondent's emotions using a sentiment analysis algorithm. The generation unit generates a next question based on the content analyzed by the analysis unit. The generation unit generates the next question based on, for example, the analyzed text data or emotion labels. The generation unit can also generate the next question based on the analyzed content using a generation AI. For example, the generation unit inputs the analyzed text data and generates the next question using a generation AI. The generation unit can also generate the next question based on the analyzed emotion labels. The presentation unit presents the question generated by the generation unit. The presentation unit presents the question using, for example, a text display or a voice output. The presentation unit can also present the question in an optimal manner depending on the type of interface. For example, the presentation unit presents the question using a text display. The presentation unit can also present the question using a voice output. The presentation unit can also present the question in an optimal manner depending on the type of interface. As a result, the questionnaire system according to the embodiment analyzes the content and emotions of the respondent's answers and generates and presents the next question, thereby improving the efficiency and accuracy of the questionnaire.

[0030] The analysis unit can analyze the content of the answerer's answer using natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, semantic analysis, etc., but is not limited to these examples. For example, the analysis unit analyzes the content of the answerer's answer using morphological analysis. The analysis unit can also analyze the content of the answerer's answer using grammatical analysis. Furthermore, the analysis unit can analyze the content of the answerer's answer using semantic analysis. For example, the analysis unit uses morphological analysis to divide words in the content of the answer and analyze their meaning. The analysis unit can also analyze the grammatical structure of the content of the answer using grammatical analysis. Furthermore, the analysis unit can analyze the meaning of the content of the answer using semantic analysis. As a result, the use of natural language processing technology improves the accuracy of analysis of the content of the answer.

[0031] The analysis unit can analyze the respondent's emotions using speech recognition technology. Speech recognition technology includes, for example, preprocessing of speech data, types of speech models, and the like, but is not limited to these examples. For example, the analysis unit performs preprocessing of speech data to analyze the respondent's emotions. The analysis unit can also analyze the respondent's emotions using a speech model. Furthermore, the analysis unit can analyze the respondent's emotions using speech recognition technology. For example, the analysis unit preprocesses the speech data, removes noise, and converts the speech data into a format that is easy to analyze. The analysis unit can also analyze the respondent's emotions using a speech model. Furthermore, the analysis unit can analyze the respondent's emotions using speech recognition technology. As a result, analysis of the respondent's emotions is possible using speech recognition technology.

[0032] The generation unit can generate a next question based on the analyzed content. The analyzed content includes, for example, text data, emotion labels, etc., but is not limited to these examples. The generation unit can generate a next question based on, for example, the analyzed text data. The generation unit can also generate a next question based on the analyzed emotion labels. Furthermore, the generation unit can use a generation AI to generate a next question based on the analyzed content. For example, the generation unit inputs the analyzed text data and generates a next question using the generation AI. The generation unit can also generate a next question based on the analyzed emotion labels. In this way, by generating a next question based on the analyzed content, it is possible to uncover the respondent's true feelings and needs.

[0033] The presentation unit can present the generated question to the respondent. The presentation unit presents the question using, for example, a text display or an audio output. The presentation unit presents the question using, for example, a text display. The presentation unit can also present the question using an audio output. Furthermore, the presentation unit can present the question in an optimal manner depending on the type of interface. For example, the presentation unit presents the question using a text display. The presentation unit can also present the question using an audio output. In this way, presenting the generated question to the respondent makes the flow of the survey smoother.

[0034] The analysis unit can classify the respondent's emotions using a sentiment analysis algorithm. Sentiment analysis algorithms include, but are not limited to, for example, machine learning models and rule-based approaches. For example, the analysis unit classifies the respondent's emotions using a machine learning model. The analysis unit can also classify the respondent's emotions using a rule-based approach. Furthermore, the analysis unit can classify the respondent's emotions using a sentiment analysis algorithm. For example, the analysis unit classifies the respondent's emotions using a machine learning model. The analysis unit can also classify the respondent's emotions using a rule-based approach. In this way, the use of a sentiment analysis algorithm can classify the respondent's emotions in detail.

[0035] The analysis unit can analyze the respondent's past response history and select the optimal analysis method. For example, if the respondent has given a detailed response in the past, the analysis unit causes the generation AI to select a detailed analysis method. Also, if the respondent has given a concise response in the past, the analysis unit can cause the generation AI to select a concise analysis method. Furthermore, the analysis unit can extract specific patterns from the respondent's past response history and select the optimal analysis method. For example, the analysis unit analyzes the respondent's past response history and selects the optimal analysis method. In this way, the optimal analysis method can be selected by analyzing the past response history.

[0036] When analyzing the content of the responses, the analysis unit can filter based on the respondent's current situation and areas of interest. For example, if the respondent answers that their current situation is "busy," the analysis unit can cause the generation AI to prioritize concise questions. Also, if the respondent answers that their area of ​​interest is "technology," the analysis unit can cause the generation AI to prioritize questions related to technology. Furthermore, the analysis unit can cause the generation AI to filter highly relevant information based on the respondent's current situation and areas of interest. For example, if the respondent answers that their current situation is "busy," the analysis unit can cause the generation AI to prioritize concise questions. Also, if the respondent answers that their area of ​​interest is "technology," the analysis unit can cause the generation AI to prioritize questions related to technology. In this way, highly relevant information can be extracted by filtering based on the respondent's situation and areas of interest.

[0037] When analyzing the response content, the analysis unit can select the optimal analysis method depending on the respondent's input method. For example, if the respondent responds by voice, the analysis unit has the generation AI analyze it using voice recognition technology. Also, if the respondent responds by text, the analysis unit can have the generation AI analyze it using natural language processing technology. Furthermore, if the respondent responds by image, the analysis unit can have the generation AI analyze it using image analysis technology. For example, if the respondent responds by voice, the analysis unit has the generation AI analyze it using voice recognition technology. Also, if the respondent responds by text, the analysis unit can have the generation AI analyze it using natural language processing technology. This improves the accuracy of the analysis by selecting the optimal analysis method depending on the respondent's input method.

[0038] When analyzing the content of the answers, the analysis unit can prioritize analyzing highly relevant content by taking into account the respondent's geographical location information. For example, if the respondent is in a specific region, the analysis unit causes the generation AI to prioritize analyzing questions related to that region. The analysis unit can also cause the generation AI to prioritize analyzing questions specific to the region based on the respondent's geographical location information. The analysis unit can also cause the generation AI to prioritize analyzing highly relevant information by taking into account the respondent's location information. For example, if the respondent is in a specific region, the analysis unit causes the generation AI to prioritize analyzing questions related to that region. The analysis unit can also cause the generation AI to prioritize analyzing questions specific to the region based on the respondent's geographical location information. In this way, by taking geographical location information into account, highly relevant information specific to the region can be prioritized in the analysis.

[0039] When analyzing the content of the answers, the analysis unit can analyze the respondent's social media activity and analyze related content. For example, the analysis unit analyzes the content posted on social media by the respondent, and the generation AI prioritizes analyzing related questions. The analysis unit can also analyze questions that are highly relevant to the generation AI based on the respondent's social media activity. The analysis unit can also analyze questions that are highly relevant to the generation AI based on the activity of the respondent's friends on social media. For example, the analysis unit analyzes the content posted on social media by the respondent, and analyzes questions that are highly relevant to the generation AI. The analysis unit can also analyze questions that are highly relevant to the generation AI based on the respondent's social media activity. In this way, highly relevant information can be extracted by analyzing social media activity.

[0040] When analyzing the response content, the analysis unit can customize the analysis method by reflecting the respondent's past feedback. For example, the analysis unit allows the generation AI to customize the analysis method based on feedback provided by the respondent in the past. The analysis unit can also allow the generation AI to select the optimal analysis method by reflecting the respondent's past feedback. Furthermore, the analysis unit can allow the generation AI to adjust the analysis accuracy and method based on the respondent's feedback. For example, the analysis unit allows the generation AI to customize the analysis method based on feedback provided by the respondent in the past. The analysis unit can also allow the generation AI to select the optimal analysis method by reflecting the respondent's past feedback. In this way, the analysis method can be optimized by reflecting past feedback.

[0041] When generating a question, the generation unit can adjust the level of detail of the question based on the importance of the answer content. For example, if the answer content is important, the generation AI generates a detailed question. Furthermore, if the answer content is general, the generation unit can also generate a concise question. Furthermore, the generation unit can adjust the level of detail of the question based on the importance of the answer content. For example, if the answer content is important, the generation AI generates a detailed question. Furthermore, if the answer content is general, the generation unit can also generate a concise question. In this way, by adjusting the level of detail of the question based on the importance of the answer content, it is possible to generate an appropriate question.

[0042] When generating a question, the generation unit can apply different generation algorithms depending on the category of the answer content. For example, if the answer content is related to technology, the generation AI can apply an algorithm specialized in technology. Furthermore, if the answer content is related to marketing, the generation unit can also have the generation AI apply an algorithm specialized in marketing. Furthermore, the generation unit can also have the generation AI select the optimal generation algorithm depending on the category of the answer content. For example, if the answer content is related to technology, the generation unit can have the generation AI apply an algorithm specialized in technology. Furthermore, if the answer content is related to marketing, the generation unit can have the generation AI apply an algorithm specialized in marketing. In this way, by applying the optimal generation algorithm depending on the category of the answer content, the accuracy of the question is improved.

[0043] When generating a question, the generation unit can improve the accuracy of the question by referring to the respondent's past answer results. For example, the generation unit causes the generation AI to improve the accuracy of the question based on the respondent's past answer results. The generation unit can also cause the generation AI to generate an optimal question by reflecting the respondent's past answer results. Furthermore, the generation unit can analyze the respondent's past answer results and cause the generation AI to adjust the accuracy of the question. For example, the generation unit causes the generation AI to improve the accuracy of the question based on the respondent's past answer results. The generation unit can also cause the generation AI to generate an optimal question by reflecting the respondent's past answer results. In this way, the accuracy of the question is improved by referring to the past answer results.

[0044] When generating questions, the generation unit can determine the priority of questions based on the time when the answer content was submitted. For example, if the answer content was recently submitted, the generation unit causes the generation AI to preferentially generate questions based on that content. Also, if the answer content is old, the generation unit can cause the generation AI to postpone generating questions based on that content. Furthermore, the generation unit can cause the generation AI to adjust the priority of questions based on the time of submission. For example, if the answer content was recently submitted, the generation unit causes the generation AI to preferentially generate questions based on that content. Also, if the answer content is old, the generation unit can cause the generation AI to postpone generating questions based on that content. In this way, by determining the priority of questions based on the time of submission, appropriate questions can be generated.

[0045] When generating questions, the generation unit can adjust the order of questions based on the relevance of the answer content. For example, if the answer content is highly relevant, the generation unit causes the generation AI to preferentially generate questions based on that content. Also, if the answer content is low relevance, the generation unit can cause the generation AI to postpone generating questions based on that content. Furthermore, the generation unit can cause the generation AI to adjust the order of questions based on the relevance. For example, if the answer content is highly relevant, the generation unit causes the generation AI to preferentially generate questions based on that content. Also, if the answer content is low relevance, the generation unit can cause the generation AI to postpone generating questions based on that content. In this way, by adjusting the order of questions based on the relevance of the answer content, appropriate questions can be generated.

[0046] When generating questions, the generation unit can adjust the use of technical terms in the questions according to the expertise level of the respondent. For example, if the respondent has specialized knowledge, the generation AI can generate questions that use a lot of technical terms. Furthermore, if the respondent does not have specialized knowledge, the generation unit can also generate questions that avoid technical terms. Furthermore, the generation unit can adjust the use of technical terms in the questions according to the expertise level of the respondent. For example, if the respondent has specialized knowledge, the generation AI can generate questions that use a lot of technical terms. Furthermore, if the respondent does not have specialized knowledge, the generation unit can also generate questions that avoid technical terms. In this way, appropriate questions can be generated by adjusting the use of technical terms in the questions according to the expertise level of the respondent.

[0047] When presenting a question, the presentation unit can select the optimal presentation method by referring to the respondent's past answer history. For example, the presentation unit allows the generation AI to select the optimal presentation method based on the respondent's past answer history. The presentation unit can also provide the optimal presentation method by reflecting the respondent's past answer history. Furthermore, the presentation unit can analyze the respondent's past answer history and select the optimal presentation method by the generation AI. For example, the presentation unit selects the optimal presentation method based on the respondent's past answer history. The presentation unit can also provide the optimal presentation method by reflecting the respondent's past answer history. In this way, the optimal presentation method can be selected by referring to the past answer history.

[0048] When presenting a question, the presentation unit can customize the content of the presentation according to the respondent's current task. For example, if the respondent answers that their current task is "busy," the generation AI can present a concise question. Furthermore, if the respondent answers that their current task is "relaxing," the presentation unit can also present a detailed question. Furthermore, the presentation unit can customize the optimal content of the presentation according to the respondent's current task. For example, if the respondent answers that their current task is "busy," the generation AI can present a concise question. Furthermore, if the respondent answers that their current task is "relaxing," the presentation unit can also present a detailed question. In this way, by customizing the content of the presentation according to the current task, appropriate questions can be presented.

[0049] The presentation unit can improve the presentation method by reflecting the respondent's feedback when presenting a question. For example, the presentation unit allows the generation AI to improve the presentation method based on feedback provided by the respondent. The presentation unit can also reflect the respondent's feedback and allow the generation AI to provide the optimal presentation method. The presentation unit can also analyze the respondent's feedback and allow the generation AI to improve the presentation method. For example, the presentation unit allows the generation AI to improve the presentation method based on feedback provided by the respondent. The presentation unit can also reflect the respondent's feedback and allow the generation AI to provide the optimal presentation method. In this way, the presentation method can be improved by reflecting feedback.

[0050] When presenting a question, the presentation unit can select the optimal presentation method by taking into account the respondent's device information. For example, if the respondent is using a smartphone, the generation AI can provide a presentation method that matches the screen size. Furthermore, if the respondent is using a tablet, the presentation unit can also provide a presentation method that is optimized for a large screen. Furthermore, if the respondent is using a desktop, the presentation unit can also provide a presentation method that includes detailed information. For example, if the respondent is using a smartphone, the presentation unit can provide a presentation method that matches the screen size. Furthermore, if the respondent is using a tablet, the presentation unit can also provide a presentation method that is optimized for a large screen. This makes it possible to select the optimal presentation method by taking into account device information.

[0051] When presenting a question, the presentation unit can make the presented content multilingual in accordance with the respondent's language setting. In the presentation unit, for example, the generation AI automatically translates the question and presents it based on the language setting of the respondent's device. In addition, the presentation unit can also provide a language switching function if the respondent uses multiple languages. In addition, the presentation unit can also provide the generation AI with a language switching function if the respondent selects a specific language, in which case the generation AI presents the question in that language. For example, the presentation unit can provide the generation AI automatically translates the question and presents it based on the language setting of the respondent's device. In addition, the presentation unit can provide a language switching function if the respondent uses multiple languages. This makes it possible to present appropriate questions by providing multilingual support according to the language setting.

[0052] When presenting a question, the presentation unit can customize the presentation method by reflecting the respondent's past feedback. In the presentation unit, for example, the generation AI customizes the presentation method based on feedback provided by the respondent in the past. The presentation unit can also provide the optimal presentation method by reflecting the respondent's past feedback. Furthermore, the presentation unit can also adjust the presentation order and content by the generation AI based on the respondent's feedback. For example, the presentation unit customizes the presentation method based on feedback provided by the respondent in the past. The presentation unit can also provide the optimal presentation method by reflecting the respondent's past feedback. In this way, the presentation method can be customized by reflecting past feedback.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The analysis unit can not only analyze the content and emotions of respondents, but also analyze their past purchasing history and website browsing history. For example, the analysis unit can analyze data on products and services purchased by respondents in the past to generate the next question. The analysis unit can also generate related questions based on information on websites frequently visited by respondents. Furthermore, the analysis unit can analyze respondents' social media activities to generate questions based on their interests and concerns. This makes it possible to generate more personalized questions by taking into account the respondents' behavioral history.

[0055] The analysis unit can take into account the respondent's health condition and fitness data when analyzing the respondent's answers. For example, the analysis unit can analyze the heart rate and exercise amount data obtained from the respondent's smartwatch to generate the next question. The analysis unit can also generate appropriate questions based on the respondent's sleep data. Furthermore, the analysis unit can analyze the respondent's food record to generate health-related questions. This allows the analysis unit to generate more appropriate questions by taking the respondent's health condition into consideration.

[0056] The analysis unit can not only analyze the content and emotions of the respondent's answers, but also take into account the respondent's cultural background and language habits. For example, the analysis unit can generate culturally appropriate questions based on the respondent's place of origin and native language. The analysis unit can also generate appropriate questions based on the respondent's religion or beliefs. Furthermore, the analysis unit can take into account the respondent's language habits and generate questions that are easy to understand. This makes it possible to generate more appropriate questions by taking into account the respondent's cultural background.

[0057] The generation unit can take into account the respondent's learning style and knowledge level when generating the next question based on the analyzed content. For example, if the respondent is a visual learner, the generation unit can generate a question using images or diagrams. Also, if the respondent is an auditory learner, the generation unit can generate a question using audio. Furthermore, the generation unit can generate specialized questions or general questions depending on the respondent's knowledge level. In this way, more effective questions can be generated by taking the respondent's learning style and knowledge level into consideration.

[0058] The presentation unit can take into account the respondent's device usage status and environment when presenting the generated questions to the respondent. For example, the presentation unit can present simple and short questions when the respondent is on the move. The presentation unit can also present detailed questions when the respondent is in a quiet environment. Furthermore, the presentation unit can present multiple questions at once when the respondent is using a desktop. This allows the presentation of more appropriate questions by taking into account the respondent's usage status and environment.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The analysis unit analyzes the content or emotions of the respondent. The analysis unit can analyze the content of the respondent's answers using natural language processing technology and can analyze the emotions of the respondent using voice recognition technology. Furthermore, the analysis unit can classify the emotions of the respondent using an emotion analysis algorithm. Step 2: The generator generates the next question based on the content analyzed by the analyzer. The generator can use a generative AI to generate the next question based on the analyzed text data and emotion labels. Step 3: The presenter presents the question generated by the generator. The presenter can present the question using text display or voice output, and can present the question in the most appropriate way depending on the type of interface.

[0061] (Example 2) A questionnaire system according to an embodiment of the present invention analyzes the respondent's responses and emotions, and a generation AI generates and presents the next question. When a respondent answers a questionnaire, the generation AI analyzes the responses and emotions and generates the next question. This process allows the respondent to understand their true feelings and identify needs that they themselves may not have been aware of. Companies do not need to plan the questionnaire questions in advance, saving time and money. For example, in a questionnaire system, the respondent answers the questionnaire. The respondent's responses and emotions are input into the generation AI. For example, if the respondent feels "this is bothersome," the generation AI analyzes their emotions and generates the next question. In this way, questions are generated based on the respondent's emotions. Next, the questionnaire system uses the generation AI to analyze the responses and emotions. The generation AI uses natural language processing and speech recognition technology to analyze the respondent's responses and emotions. For example, if the respondent answers "I like this product," the generation AI analyzes the responses and generates the next question. This process allows the respondent to understand their true feelings and identify needs that they themselves may not have been aware of. Furthermore, the survey system uses a generation AI to generate the next question. The generation AI generates the next question based on the respondent's response and emotions. For example, if a respondent answers, "I like this product," the generation AI generates a next question such as, "What do you particularly like about it?" In this way, the respondent's true feelings and needs can be uncovered. This eliminates the need for companies to plan survey questions in advance, saving time and money. For example, when a company collects feedback on a new product, the generation AI automatically generates questions, reducing the time and cost required to create them. Furthermore, because the generation AI uncovers the respondent's true feelings and needs, more accurate feedback can be obtained. This improves the survey response process, creating a system that benefits both companies and respondents. The survey system analyzes the respondent's response content and emotions and generates and presents the next question, improving the efficiency and accuracy of surveys.For example, when a company collects feedback on a new product, generative AI can automatically generate questions, reducing the time and cost required to create the questions. In addition, generative AI can uncover the true feelings and needs of respondents, resulting in more accurate feedback.

[0062] A questionnaire system according to an embodiment includes an analysis unit, a generation unit, and a presentation unit. The analysis unit analyzes the content of a respondent's answer or emotions. The analysis unit analyzes the content of the respondent's answer using, for example, natural language processing technology. The analysis unit can also analyze the respondent's emotions using voice recognition technology. The analysis unit can also classify the respondent's emotions using a sentiment analysis algorithm. For example, the analysis unit inputs the content of the respondent's answer as text data and analyzes it using natural language processing technology. The analysis unit can also input the respondent's voice data and analyze the emotions using voice recognition technology. The analysis unit can also classify the respondent's emotions using a sentiment analysis algorithm. The generation unit generates a next question based on the content analyzed by the analysis unit. The generation unit generates the next question based on, for example, the analyzed text data or emotion labels. The generation unit can also generate the next question based on the analyzed content using a generation AI. For example, the generation unit inputs the analyzed text data and generates the next question using a generation AI. The generation unit can also generate the next question based on the analyzed emotion labels. The presentation unit presents the question generated by the generation unit. The presentation unit presents the question using, for example, a text display or a voice output. The presentation unit can also present the question in an optimal manner depending on the type of interface. For example, the presentation unit presents the question using a text display. The presentation unit can also present the question using a voice output. The presentation unit can also present the question in an optimal manner depending on the type of interface. As a result, the questionnaire system according to the embodiment analyzes the content and emotions of the respondent's answers and generates and presents the next question, thereby improving the efficiency and accuracy of the questionnaire.

[0063] The analysis unit can analyze the content of the answerer's answer using natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, semantic analysis, etc., but is not limited to these examples. For example, the analysis unit analyzes the content of the answerer's answer using morphological analysis. The analysis unit can also analyze the content of the answerer's answer using grammatical analysis. Furthermore, the analysis unit can analyze the content of the answerer's answer using semantic analysis. For example, the analysis unit uses morphological analysis to divide words in the content of the answer and analyze their meaning. The analysis unit can also analyze the grammatical structure of the content of the answer using grammatical analysis. Furthermore, the analysis unit can analyze the meaning of the content of the answer using semantic analysis. As a result, the use of natural language processing technology improves the accuracy of analysis of the content of the answer.

[0064] The analysis unit can analyze the respondent's emotions using speech recognition technology. Speech recognition technology includes, for example, preprocessing of speech data, types of speech models, and the like, but is not limited to these examples. For example, the analysis unit performs preprocessing of speech data to analyze the respondent's emotions. The analysis unit can also analyze the respondent's emotions using a speech model. Furthermore, the analysis unit can analyze the respondent's emotions using speech recognition technology. For example, the analysis unit preprocesses the speech data, removes noise, and converts the speech data into a format that is easy to analyze. The analysis unit can also analyze the respondent's emotions using a speech model. Furthermore, the analysis unit can analyze the respondent's emotions using speech recognition technology. As a result, analysis of the respondent's emotions is possible using speech recognition technology.

[0065] The generation unit can generate a next question based on the analyzed content. The analyzed content includes, for example, text data, emotion labels, etc., but is not limited to these examples. The generation unit can generate a next question based on, for example, the analyzed text data. The generation unit can also generate a next question based on the analyzed emotion labels. Furthermore, the generation unit can use a generation AI to generate a next question based on the analyzed content. For example, the generation unit inputs the analyzed text data and generates a next question using the generation AI. The generation unit can also generate a next question based on the analyzed emotion labels. In this way, by generating a next question based on the analyzed content, it is possible to uncover the respondent's true feelings and needs.

[0066] The presentation unit can present the generated question to the respondent. The presentation unit presents the question using, for example, a text display or an audio output. The presentation unit presents the question using, for example, a text display. The presentation unit can also present the question using an audio output. Furthermore, the presentation unit can present the question in an optimal manner depending on the type of interface. For example, the presentation unit presents the question using a text display. The presentation unit can also present the question using an audio output. In this way, presenting the generated question to the respondent makes the flow of the survey smoother.

[0067] The analysis unit can classify the respondent's emotions using a sentiment analysis algorithm. Sentiment analysis algorithms include, but are not limited to, for example, machine learning models and rule-based approaches. For example, the analysis unit classifies the respondent's emotions using a machine learning model. The analysis unit can also classify the respondent's emotions using a rule-based approach. Furthermore, the analysis unit can classify the respondent's emotions using a sentiment analysis algorithm. For example, the analysis unit classifies the respondent's emotions using a machine learning model. The analysis unit can also classify the respondent's emotions using a rule-based approach. In this way, the use of a sentiment analysis algorithm can classify the respondent's emotions in detail.

[0068] The analysis unit can estimate the respondent's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the respondent is feeling stressed, the analysis unit causes the generation AI to relax the analysis accuracy, thereby reducing the respondent's burden. Furthermore, if the respondent is relaxed, the analysis unit can cause the generation AI to increase the analysis accuracy and extract more detailed information. Furthermore, if the respondent is excited, the analysis unit can cause the generation AI to adjust the analysis accuracy to minimize the influence of emotions. For example, the analysis unit can estimate the respondent's emotions and adjust the analysis accuracy based on the estimated emotions. This allows for more appropriate analysis by adjusting the analysis accuracy according to the respondent's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0069] The analysis unit can analyze the respondent's past response history and select the optimal analysis method. For example, if the respondent has given a detailed response in the past, the analysis unit causes the generation AI to select a detailed analysis method. Also, if the respondent has given a concise response in the past, the analysis unit can cause the generation AI to select a concise analysis method. Furthermore, the analysis unit can extract specific patterns from the respondent's past response history and select the optimal analysis method. For example, the analysis unit analyzes the respondent's past response history and selects the optimal analysis method. In this way, the optimal analysis method can be selected by analyzing the past response history.

[0070] When analyzing the content of the responses, the analysis unit can filter based on the respondent's current situation and areas of interest. For example, if the respondent answers that their current situation is "busy," the analysis unit can cause the generation AI to prioritize concise questions. Also, if the respondent answers that their area of ​​interest is "technology," the analysis unit can cause the generation AI to prioritize questions related to technology. Furthermore, the analysis unit can cause the generation AI to filter highly relevant information based on the respondent's current situation and areas of interest. For example, if the respondent answers that their current situation is "busy," the analysis unit can cause the generation AI to prioritize concise questions. Also, if the respondent answers that their area of ​​interest is "technology," the analysis unit can cause the generation AI to prioritize questions related to technology. In this way, highly relevant information can be extracted by filtering based on the respondent's situation and areas of interest.

[0071] When analyzing the response content, the analysis unit can select the optimal analysis method depending on the respondent's input method. For example, if the respondent responds by voice, the analysis unit has the generation AI analyze it using voice recognition technology. Also, if the respondent responds by text, the analysis unit can have the generation AI analyze it using natural language processing technology. Furthermore, if the respondent responds by image, the analysis unit can have the generation AI analyze it using image analysis technology. For example, if the respondent responds by voice, the analysis unit has the generation AI analyze it using voice recognition technology. Also, if the respondent responds by text, the analysis unit can have the generation AI analyze it using natural language processing technology. This improves the accuracy of the analysis by selecting the optimal analysis method depending on the respondent's input method.

[0072] The analysis unit can estimate the respondent's emotions and determine the priority of the answer content to be analyzed based on the estimated emotions. For example, if the respondent is feeling stressed, the analysis unit can cause the generation AI to prioritize important questions in the analysis. Furthermore, if the respondent is relaxed, the analysis unit can cause the generation AI to prioritize detailed questions in the analysis. Furthermore, if the respondent is excited, the analysis unit can cause the generation AI to determine the analysis priority taking into account the influence of emotions. For example, the analysis unit can estimate the respondent's emotions and determine the priority of the answer content to be analyzed based on the estimated emotions. In this way, by determining the analysis priority based on the respondent's emotions, important information can be analyzed preferentially. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0073] When analyzing the content of the answers, the analysis unit can prioritize analyzing highly relevant content by taking into account the respondent's geographical location information. For example, if the respondent is in a specific region, the analysis unit causes the generation AI to prioritize analyzing questions related to that region. The analysis unit can also cause the generation AI to prioritize analyzing questions specific to the region based on the respondent's geographical location information. The analysis unit can also cause the generation AI to prioritize analyzing highly relevant information by taking into account the respondent's location information. For example, if the respondent is in a specific region, the analysis unit causes the generation AI to prioritize analyzing questions related to that region. The analysis unit can also cause the generation AI to prioritize analyzing questions specific to the region based on the respondent's geographical location information. In this way, by taking geographical location information into account, highly relevant information specific to the region can be prioritized in the analysis.

[0074] When analyzing the content of the answers, the analysis unit can analyze the respondent's social media activity and analyze related content. For example, the analysis unit analyzes the content posted on social media by the respondent, and the generation AI prioritizes analyzing related questions. The analysis unit can also analyze questions that are highly relevant to the generation AI based on the respondent's social media activity. The analysis unit can also analyze questions that are highly relevant to the generation AI based on the activity of the respondent's friends on social media. For example, the analysis unit analyzes the content posted on social media by the respondent, and analyzes questions that are highly relevant to the generation AI. The analysis unit can also analyze questions that are highly relevant to the generation AI based on the respondent's social media activity. In this way, highly relevant information can be extracted by analyzing social media activity.

[0075] When analyzing the response content, the analysis unit can customize the analysis method by reflecting the respondent's past feedback. For example, the analysis unit allows the generation AI to customize the analysis method based on feedback provided by the respondent in the past. The analysis unit can also allow the generation AI to select the optimal analysis method by reflecting the respondent's past feedback. Furthermore, the analysis unit can allow the generation AI to adjust the analysis accuracy and method based on the respondent's feedback. For example, the analysis unit allows the generation AI to customize the analysis method based on feedback provided by the respondent in the past. The analysis unit can also allow the generation AI to select the optimal analysis method by reflecting the respondent's past feedback. In this way, the analysis method can be optimized by reflecting past feedback.

[0076] The generation unit can estimate the respondent's emotions and adjust the way the questions are phrased based on the estimated emotions. For example, if the respondent is feeling stressed, the generation AI can generate simple and intuitive questions. Furthermore, if the respondent is relaxed, the generation unit can generate detailed and polite questions. Furthermore, if the respondent is excited, the generation unit can generate questions that calm the respondent. For example, the generation unit can estimate the respondent's emotions and adjust the way the questions are phrased based on the estimated emotions. This allows for the generation of more appropriate questions by adjusting the way the questions are phrased according to the respondent's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0077] When generating a question, the generation unit can adjust the level of detail of the question based on the importance of the answer content. For example, if the answer content is important, the generation AI generates a detailed question. Furthermore, if the answer content is general, the generation unit can also generate a concise question. Furthermore, the generation unit can adjust the level of detail of the question based on the importance of the answer content. For example, if the answer content is important, the generation AI generates a detailed question. Furthermore, if the answer content is general, the generation unit can also generate a concise question. In this way, by adjusting the level of detail of the question based on the importance of the answer content, it is possible to generate an appropriate question.

[0078] When generating a question, the generation unit can apply different generation algorithms depending on the category of the answer content. For example, if the answer content is related to technology, the generation AI can apply an algorithm specialized in technology. Furthermore, if the answer content is related to marketing, the generation unit can also have the generation AI apply an algorithm specialized in marketing. Furthermore, the generation unit can also have the generation AI select the optimal generation algorithm depending on the category of the answer content. For example, if the answer content is related to technology, the generation unit can have the generation AI apply an algorithm specialized in technology. Furthermore, if the answer content is related to marketing, the generation unit can have the generation AI apply an algorithm specialized in marketing. In this way, by applying the optimal generation algorithm depending on the category of the answer content, the accuracy of the question is improved.

[0079] When generating a question, the generation unit can improve the accuracy of the question by referring to the respondent's past answer results. For example, the generation unit causes the generation AI to improve the accuracy of the question based on the respondent's past answer results. The generation unit can also cause the generation AI to generate an optimal question by reflecting the respondent's past answer results. Furthermore, the generation unit can analyze the respondent's past answer results and cause the generation AI to adjust the accuracy of the question. For example, the generation unit causes the generation AI to improve the accuracy of the question based on the respondent's past answer results. The generation unit can also cause the generation AI to generate an optimal question by reflecting the respondent's past answer results. In this way, the accuracy of the question is improved by referring to the past answer results.

[0080] The generation unit can estimate the respondent's emotions and adjust the length of the questions to be generated based on the estimated emotions. For example, if the respondent is stressed, the generation AI can generate short and concise questions. Furthermore, if the respondent is relaxed, the generation unit can generate long and detailed questions. Furthermore, if the respondent is excited, the generation unit can generate short questions to calm the respondent. For example, the generation unit can estimate the respondent's emotions and adjust the length of the questions to be generated based on the estimated emotions. In this way, appropriate questions can be generated by adjusting the length of the questions according to the respondent's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0081] When generating questions, the generation unit can determine the priority of questions based on the time when the answer content was submitted. For example, if the answer content was recently submitted, the generation unit causes the generation AI to preferentially generate questions based on that content. Also, if the answer content is old, the generation unit can cause the generation AI to postpone generating questions based on that content. Furthermore, the generation unit can cause the generation AI to adjust the priority of questions based on the time of submission. For example, if the answer content was recently submitted, the generation unit causes the generation AI to preferentially generate questions based on that content. Also, if the answer content is old, the generation unit can cause the generation AI to postpone generating questions based on that content. In this way, by determining the priority of questions based on the time of submission, appropriate questions can be generated.

[0082] When generating questions, the generation unit can adjust the order of questions based on the relevance of the answer content. For example, if the answer content is highly relevant, the generation unit causes the generation AI to preferentially generate questions based on that content. Also, if the answer content is low relevance, the generation unit can cause the generation AI to postpone generating questions based on that content. Furthermore, the generation unit can cause the generation AI to adjust the order of questions based on the relevance. For example, if the answer content is highly relevant, the generation unit causes the generation AI to preferentially generate questions based on that content. Also, if the answer content is low relevance, the generation unit can cause the generation AI to postpone generating questions based on that content. In this way, by adjusting the order of questions based on the relevance of the answer content, appropriate questions can be generated.

[0083] When generating questions, the generation unit can adjust the use of technical terms in the questions according to the expertise level of the respondent. For example, if the respondent has specialized knowledge, the generation AI can generate questions that use a lot of technical terms. Furthermore, if the respondent does not have specialized knowledge, the generation unit can also generate questions that avoid technical terms. Furthermore, the generation unit can adjust the use of technical terms in the questions according to the expertise level of the respondent. For example, if the respondent has specialized knowledge, the generation AI can generate questions that use a lot of technical terms. Furthermore, if the respondent does not have specialized knowledge, the generation unit can also generate questions that avoid technical terms. In this way, appropriate questions can be generated by adjusting the use of technical terms in the questions according to the expertise level of the respondent.

[0084] The presentation unit can estimate the respondent's emotions and adjust the way questions are presented based on the estimated emotions. For example, if the respondent is feeling stressed, the generation AI can provide a simple and intuitive presentation method. Furthermore, if the respondent is relaxed, the presentation unit can provide a detailed and polite presentation method. Furthermore, if the respondent is excited, the presentation unit can provide a presentation method that calms the respondent. For example, the presentation unit can estimate the respondent's emotions and adjust the way questions are presented based on the estimated emotions. This allows appropriate questions to be presented by adjusting the way questions are presented according to the respondent's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0085] When presenting a question, the presentation unit can select the optimal presentation method by referring to the respondent's past answer history. For example, the presentation unit allows the generation AI to select the optimal presentation method based on the respondent's past answer history. The presentation unit can also provide the optimal presentation method by reflecting the respondent's past answer history. Furthermore, the presentation unit can analyze the respondent's past answer history and select the optimal presentation method by the generation AI. For example, the presentation unit selects the optimal presentation method based on the respondent's past answer history. The presentation unit can also provide the optimal presentation method by reflecting the respondent's past answer history. In this way, the optimal presentation method can be selected by referring to the past answer history.

[0086] When presenting a question, the presentation unit can customize the content of the presentation according to the respondent's current task. For example, if the respondent answers that their current task is "busy," the generation AI can present a concise question. Furthermore, if the respondent answers that their current task is "relaxing," the presentation unit can also present a detailed question. Furthermore, the presentation unit can customize the optimal content of the presentation according to the respondent's current task. For example, if the respondent answers that their current task is "busy," the generation AI can present a concise question. Furthermore, if the respondent answers that their current task is "relaxing," the presentation unit can also present a detailed question. In this way, by customizing the content of the presentation according to the current task, appropriate questions can be presented.

[0087] The presentation unit can improve the presentation method by reflecting the respondent's feedback when presenting a question. For example, the presentation unit allows the generation AI to improve the presentation method based on feedback provided by the respondent. The presentation unit can also reflect the respondent's feedback and allow the generation AI to provide the optimal presentation method. The presentation unit can also analyze the respondent's feedback and allow the generation AI to improve the presentation method. For example, the presentation unit allows the generation AI to improve the presentation method based on feedback provided by the respondent. The presentation unit can also reflect the respondent's feedback and allow the generation AI to provide the optimal presentation method. In this way, the presentation method can be improved by reflecting feedback.

[0088] The presentation unit can estimate the respondent's emotions and adjust the order in which questions are presented based on the estimated emotions. For example, if the respondent is feeling stressed, the presentation unit causes the generation AI to present important questions first. Furthermore, if the respondent is relaxed, the presentation unit can cause the generation AI to present detailed questions later. Furthermore, if the respondent is excited, the presentation unit can cause the generation AI to present questions that will calm the respondent first. For example, the presentation unit can estimate the respondent's emotions and adjust the order in which questions are presented based on the estimated emotions. In this way, appropriate questions can be presented by adjusting the presentation order based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0089] When presenting a question, the presentation unit can select the optimal presentation method by taking into account the respondent's device information. For example, if the respondent is using a smartphone, the generation AI can provide a presentation method that matches the screen size. Furthermore, if the respondent is using a tablet, the presentation unit can also provide a presentation method that is optimized for a large screen. Furthermore, if the respondent is using a desktop, the presentation unit can also provide a presentation method that includes detailed information. For example, if the respondent is using a smartphone, the presentation unit can provide a presentation method that matches the screen size. Furthermore, if the respondent is using a tablet, the presentation unit can also provide a presentation method that is optimized for a large screen. This makes it possible to select the optimal presentation method by taking into account device information.

[0090] When presenting a question, the presentation unit can make the presented content multilingual in accordance with the respondent's language setting. In the presentation unit, for example, the generation AI automatically translates the question and presents it based on the language setting of the respondent's device. In addition, the presentation unit can also provide a language switching function if the respondent uses multiple languages. In addition, the presentation unit can also provide the generation AI with a language switching function if the respondent selects a specific language, in which case the generation AI presents the question in that language. For example, the presentation unit can provide the generation AI automatically translates the question and presents it based on the language setting of the respondent's device. In addition, the presentation unit can provide a language switching function if the respondent uses multiple languages. This makes it possible to present appropriate questions by providing multilingual support according to the language setting.

[0091] When presenting a question, the presentation unit can customize the presentation method by reflecting the respondent's past feedback. In the presentation unit, for example, the generation AI customizes the presentation method based on feedback provided by the respondent in the past. The presentation unit can also provide the optimal presentation method by reflecting the respondent's past feedback. Furthermore, the presentation unit can also adjust the presentation order and content by the generation AI based on the respondent's feedback. For example, the presentation unit customizes the presentation method based on feedback provided by the respondent in the past. The presentation unit can also provide the optimal presentation method by reflecting the respondent's past feedback. In this way, the presentation method can be customized by reflecting past feedback. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, generation unit, and presentation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart device 14 and analyzes the content and emotions of the respondent's answer. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates the next question based on the analyzed content. The presentation unit is realized, for example, by the output device 40 of the smart device 14 and presents the generated question by text display or audio output. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, generation unit, and presentation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart glasses 214 and analyzes the content and emotions of the respondent's answer. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates the next question based on the analyzed content. The presentation unit is realized, for example, by the speaker 240 of the smart glasses 214 and presents the generated question by audio output. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, generation unit, and presentation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the headset type terminal 314 and analyzes the content and emotions of the respondent's answer. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates the next question based on the analyzed content. The presentation unit is realized, for example, by the display 343 of the headset type terminal 314 and presents the generated question in text format. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, generation unit, and presentation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the robot 414 and analyzes the content and emotions of the respondent's answer. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates the next question based on the analyzed content. The presentation unit is realized, for example, by the speaker 240 of the robot 414 and presents the generated question by audio output.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The analysis unit can not only analyze the content and emotions of respondents, but also analyze their past purchasing history and website browsing history. For example, the analysis unit can analyze data on products and services purchased by respondents in the past to generate the next question. The analysis unit can also generate related questions based on information on websites frequently visited by respondents. Furthermore, the analysis unit can analyze respondents' social media activities to generate questions based on their interests and concerns. This makes it possible to generate more personalized questions by taking into account the respondents' behavioral history.

[0094] The analysis unit can take into account the respondent's health condition and fitness data when analyzing the respondent's answers. For example, the analysis unit can analyze the heart rate and exercise amount data obtained from the respondent's smartwatch to generate the next question. The analysis unit can also generate appropriate questions based on the respondent's sleep data. Furthermore, the analysis unit can analyze the respondent's food record to generate health-related questions. This allows the analysis unit to generate more appropriate questions by taking the respondent's health condition into consideration.

[0095] The analysis unit can not only analyze the content and emotions of the respondent's answers, but also take into account the respondent's cultural background and language habits. For example, the analysis unit can generate culturally appropriate questions based on the respondent's place of origin and native language. The analysis unit can also generate appropriate questions based on the respondent's religion or beliefs. Furthermore, the analysis unit can take into account the respondent's language habits and generate questions that are easy to understand. This makes it possible to generate more appropriate questions by taking into account the respondent's cultural background.

[0096] The generation unit can take into account the respondent's learning style and knowledge level when generating the next question based on the analyzed content. For example, if the respondent is a visual learner, the generation unit can generate a question using images or diagrams. Also, if the respondent is an auditory learner, the generation unit can generate a question using audio. Furthermore, the generation unit can generate specialized questions or general questions depending on the respondent's knowledge level. In this way, more effective questions can be generated by taking the respondent's learning style and knowledge level into consideration.

[0097] The presentation unit can take into account the respondent's device usage status and environment when presenting the generated questions to the respondent. For example, the presentation unit can present simple and short questions when the respondent is on the move. The presentation unit can also present detailed questions when the respondent is in a quiet environment. Furthermore, the presentation unit can present multiple questions at once when the respondent is using a desktop. This allows the presentation of more appropriate questions by taking into account the respondent's usage status and environment.

[0098] The analysis unit can estimate the respondent's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the respondent is feeling stressed, the generation AI will relax the accuracy of the analysis, reducing the burden on the respondent. Also, if the respondent is relaxed, the analysis unit can increase the accuracy of the analysis and extract more detailed information. Furthermore, if the respondent is excited, the generation AI can adjust the accuracy of the analysis to minimize the influence of emotions. This allows for more appropriate analysis by adjusting the accuracy of the analysis according to the respondent's emotions.

[0099] The generation unit can estimate the respondent's emotions and adjust the way questions are phrased based on the estimated emotions. For example, if the respondent is feeling stressed, the generation AI can generate simple and intuitive questions. If the respondent is relaxed, the generation AI can also generate detailed and polite questions. Furthermore, if the respondent is excited, the generation AI can generate questions that calm the respondent. This makes it possible to generate more appropriate questions by adjusting the way questions are phrased according to the respondent's emotions.

[0100] The presentation unit can estimate the respondent's emotions and adjust the way questions are presented based on the estimated emotions. For example, if the respondent is feeling stressed, the generation AI can provide a simple and intuitive way of presenting questions. If the respondent is relaxed, the generation AI can also provide a detailed and polite way of presenting questions. Furthermore, if the respondent is excited, the generation AI can also provide a way of presenting questions that calms the respondent. This makes it possible to present appropriate questions by adjusting the way questions are presented according to the respondent's emotions.

[0101] The analysis unit can estimate the respondent's emotions and determine the priority of the answers to be analyzed based on the estimated emotions. For example, if the respondent is feeling stressed, the generation AI will prioritize analyzing important questions. Also, if the respondent is relaxed, the generation AI can prioritize analyzing detailed questions. Furthermore, if the respondent is excited, the generation AI can determine the analysis priority taking into account the influence of emotions. In this way, by determining the analysis priority based on the respondent's emotions, important information can be analyzed preferentially.

[0102] The generation unit can estimate the respondent's emotions and adjust the length of the questions it generates based on the estimated emotions. For example, if the respondent is feeling stressed, the generation AI can generate short, concise questions. Alternatively, if the respondent is relaxed, the generation AI can generate long, detailed questions. Furthermore, if the respondent is excited, the generation AI can generate short questions that calm the respondent. This allows the system to generate appropriate questions by adjusting the length of the questions according to the respondent's emotions.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The analysis unit analyzes the content or emotions of the respondent. The analysis unit can analyze the content of the respondent's answers using natural language processing technology and can analyze the emotions of the respondent using voice recognition technology. Furthermore, the analysis unit can classify the emotions of the respondent using an emotion analysis algorithm. Step 2: The generator generates the next question based on the content analyzed by the analyzer. The generator can use a generative AI to generate the next question based on the analyzed text data and emotion labels. Step 3: The presenter presents the question generated by the generator. The presenter can present the question using text display or voice output, and can present the question in the most appropriate way depending on the type of interface.

[0105] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0106] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0107] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0108] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0109] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0110] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0111] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0112] 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.

[0113] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0114] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0115] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0116] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0117] 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.

[0118] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0119] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0120] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0121] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0122] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0123] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0124] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0125] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0126] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0127] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0128] 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.

[0129] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0130] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0131] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0132] 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.

[0133] 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.

[0134] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0135] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0136] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0137] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0138] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0139] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] 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.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0148] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0149] 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.

[0150] 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.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0153] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0156] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0159] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0160] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0161] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0162] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0163] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0164] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0165] 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.

[0166] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0167] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0168] 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.

[0169] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0170] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0171] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0172] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0173] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0174] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0175] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0176] [Explanation of symbols]

[0177] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes the content or emotions of the respondents; a generation unit that generates a next question based on the content analyzed by the analysis unit; a presentation unit that presents the question generated by the generation unit. A system characterized by:

2. The analysis unit Analyze the content of respondents' responses using natural language processing technology 2. The system of claim 1.

3. The analysis unit Describe the specific method for analyzing respondent emotions using voice recognition technology 2. The system of claim 1.

4. The generation unit Generate the next question based on the parsed content 2. The system of claim 1.

5. The presentation unit Present the generated questions to the respondent 2. The system of claim 1.

6. The analysis unit Classifying respondent sentiment using a sentiment analysis algorithm 2. The system of claim 1.

7. The analysis unit Describe the specific method for estimating the respondent's emotions and adjusting the accuracy of the analysis based on the estimated emotions.

2. The system of claim 1.

8. The analysis unit Analyze the respondent's past response history and select the appropriate analysis method 2. The system of claim 1.

Images