system

Abstract

The system according to the embodiment aims to gain a deeper understanding of the customer's true intentions and propose improvement measures. [Solution] A system according to an embodiment includes a questioning unit, an analysis unit, and a proposal unit. The questioning unit asks survey questions. The analysis unit analyzes the survey data collected by the questioning unit. The proposal unit proposes improvement measures based on the analysis results obtained by the analysis unit.

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 techniques have had the problem that the burden of answering questionnaires is heavy, making it difficult to fully grasp the customer's true intentions.

[0005] The system according to the embodiment aims to gain a deeper understanding of the customer's true intentions and propose improvement measures. [Means for solving the problem]

[0006] The system according to the embodiment includes a questioning unit, an analysis unit, and a proposal unit. The questioning unit asks questionnaire questions. The analysis unit analyzes the questionnaire data collected by the questioning unit. The proposal unit proposes improvement measures based on the analysis results obtained by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can gain a deeper understanding of the customer's true intentions and propose improvements. [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 is an interactive questionnaire system that conducts a post-game questionnaire with attendees and uses a generation AI to explore customer emotions. When attendees respond to the questionnaire after a baseball game, the generation AI asks them questions in an interactive format to elicit their emotions and opinions. Next, the generation AI analyzes the collected questionnaire data to explore their emotions and opinions. Finally, the generation AI generates the analysis results and improvement measures, making proposals to improve customer satisfaction (CS). For example, in a questionnaire system, attendees fill out a questionnaire after a game. The generation AI asks questions such as, "Which part of the game was most memorable for you?" and "Were there any aspects of the game that you found frustrating?" This allows attendees to express their emotions and opinions naturally. Next, the generation AI analyzes the collected questionnaire data. The generation AI analyzes the attendees' responses and explores their emotions and opinions. For example, if an attendee responds with, "I'm dissatisfied with the progress of the game," the generation AI asks an additional question such as, "Which aspect of the game were you particularly dissatisfied with?" to identify specific problems. Finally, the generation AI generates analysis results and improvement measures. Based on the collected data, the generation AI comprehensively analyzes the emotions and opinions of spectators and proposes improvement measures. For example, it makes specific suggestions such as "shorten the interval time to ensure smooth game progress." This reduces the burden on spectators to respond and allows the survey system to collect more accurate emotions and opinions. In addition, because the generation AI automatically performs analysis and proposals, improvement measures can be implemented quickly and efficiently. For example, it is possible to analyze the survey results immediately after a game and quickly implement improvement measures for the next game. This allows the survey system to delve deeper into spectators' emotions and opinions and propose specific improvement measures to improve CS. For example, it reduces the burden on spectators to respond and allows more accurate emotions and opinions to be collected. In addition, because the generation AI automatically performs analysis and proposals, improvement measures can be implemented quickly and efficiently.

[0029] A questionnaire system according to an embodiment includes a questioning unit, an analysis unit, and a proposal unit. The questioning unit asks questions in the questionnaire. The questioning unit can ask, for example, multiple-choice or open-ended questions. The questioning unit can also ask questions in an interactive format to elicit the emotions and opinions of attendees. For example, the questioning unit asks questions such as, "Which part of the game impressed you the most?" or "Were there any aspects of the game that dissatisfied you?" The analysis unit analyzes the questionnaire data collected by the questioning unit. The analysis unit can analyze the questionnaire data using, for example, statistical analysis or text mining. The analysis unit can also analyze the attendees' responses to delve deeper into their emotions and opinions. For example, if an attendee answers, "I'm dissatisfied with the progress of the game," the analysis unit asks a follow-up question such as, "Which aspect of the game did you find particularly dissatisfying?" to identify specific problems. The proposal unit proposes improvement measures based on the analysis results obtained by the analysis unit. The proposal unit can propose, for example, a specific action plan or recommendations. The suggestion unit can also comprehensively analyze the emotions and opinions of spectators based on the collected data and propose improvement measures. For example, the suggestion unit makes a specific suggestion such as "shorten the interval time to ensure smooth progress of the match." This allows the questionnaire system according to the embodiment to efficiently ask questions in the questionnaire, perform analysis, and propose improvement measures.

[0030] The questionnaire system includes an additional questioning unit that asks additional questions to investigate the emotions of attendees in more detail. The additional questioning unit asks additional questions to investigate the emotions of attendees in more detail. The additional questioning unit can, for example, use an emotion analysis algorithm to analyze the emotions of attendees and ask additional questions. The additional questioning unit can also ask multiple-choice or free-form additional questions. For example, the additional questioning unit asks an additional question such as, "Which part of the game did you feel particularly dissatisfied with?" to an attendee who answered, "I'm dissatisfied with the progress of the game." This allows for a deeper understanding of the emotions of attendees. Some or all of the above-described processing in the additional questioning unit may be performed using, or without, a generation AI. For example, the additional questioning unit can input the attendee's response data into the generation AI and cause the generation AI to generate additional questions.

[0031] The survey system includes a display unit that displays survey results in real time. The display unit displays the survey results in real time. The display unit can, for example, set the data update frequency and display format. The display unit can also update the data in real time and display the latest survey results. For example, the display unit displays the survey results as graphs or charts, providing them in a visually easy-to-understand format. This allows the survey results to be checked in real time. Some or all of the above-described processing in the display unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the display unit can input survey data into the generation AI and cause the generation AI to generate a real-time display.

[0032] The questioning unit can ask questions in a dialogue format to collect the emotions and opinions of visitors. The questioning unit can ask questions in a dialogue format to collect the emotions and opinions of visitors. The dialogue format questions can be asked, for example, using a chatbot or in the form of an interview. For example, the questioning unit can ask questions such as, "Which part of the game impressed you the most?" or "Was there anything during the game that you were dissatisfied with?" This allows visitors to naturally express their emotions and opinions. Some or all of the above-mentioned processing in the questioning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the questioning unit can input dialogue format questions to the generation AI, which then asks the questions in a dialogue format.

[0033] The analysis unit can analyze the attendees' responses and investigate their emotions and opinions in detail. The analysis unit can analyze the attendees' responses and investigate their emotions and opinions in detail. The detailed investigation of emotions and opinions can be performed using, for example, text analysis or sentiment analysis. For example, if the attendee answers "dissatisfied with the progress of the game," the analysis unit can ask an additional question such as "Which part did you feel particularly dissatisfied with?" to identify the specific problem. This makes it possible to delve deeper into the attendees' emotions and opinions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the attendees' response data into the generation AI and have the generation AI perform a detailed investigation of emotions and opinions.

[0034] The suggestion unit can perform a detailed analysis of the emotions and opinions of spectators based on the collected data and propose improvement measures. The suggestion unit can perform a detailed analysis of the emotions and opinions of spectators based on the collected data and propose improvement measures. The detailed analysis of emotions and opinions can be performed using, for example, data mining or statistical analysis. For example, the suggestion unit can make a specific suggestion such as "shorten the interval time to ensure smooth progress of the match." This makes it possible to comprehensively analyze the emotions and opinions of spectators and propose specific improvement measures. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input the collected data into a generation AI and have the generation AI execute the proposed improvement measures.

[0035] When asking a question, the questioning unit can select the most appropriate question by referring to the visitor's past survey response history. When asking a question, the questioning unit can select the most appropriate question by referring to the visitor's past survey response history. The selection of the most appropriate question can be performed, for example, based on past response data and the relevance of the question. For example, the questioning unit can reconfirm points that the visitor was dissatisfied with in the past and ask whether they have been improved. The questioning unit can also request more detailed opinions on points that the visitor previously gave high ratings to. The questioning unit can also prioritize questions related to specific topics based on the visitor's past response history. This allows more appropriate questions to be asked by referring to the past survey response history. Some or all of the above-mentioned processing in the questioning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the questioning unit can input past response data into the generation AI and have the generation AI select the most appropriate question.

[0036] When asking a question, the questioning unit can customize the question content based on attribute information such as the visitor's age, gender, and occupation. When asking a question, the questioning unit customizes the question content based on attribute information such as the visitor's age, gender, and occupation. Customization based on attribute information can be performed based on information such as age, gender, and occupation. For example, the questioning unit may prioritize questions about the entertainment value of the game for younger people. The questioning unit may also prioritize questions about venue access and seat comfort for older people. The questioning unit may also customize questions about topics that are likely to interest people based on gender. This allows for more appropriate questions to be asked by taking the visitor's attribute information into consideration. Some or all of the above-described processing by the questioning unit may be performed using, or without, a generation AI. For example, the questioning unit may input attribute information into the generation AI and cause the generation AI to customize the question content.

[0037] The questioning unit can adjust the difficulty of the question depending on the visitor's answering speed when asking a question. The questioning unit can adjust the difficulty of the question depending on the visitor's answering speed when asking a question. Adjustment depending on the answering speed can be made based on, for example, measuring the answering time or setting a difficulty level. For example, if the visitor answers quickly, the questioning unit can add more detailed and in-depth questions. Also, if the visitor answers slowly, the questioning unit can prioritize simpler and shorter questions. The questioning unit can also adjust the order and content of the questions in real time depending on the visitor's answering speed. This allows for a more effective survey by adjusting the difficulty of the questions depending on the visitor's answering speed. Some or all of the above-mentioned processing in the questioning unit may be performed using, or without, a generation AI. For example, the questioning unit can input answering speed data into the generation AI and have the generation AI adjust the difficulty of the questions.

[0038] When asking a question, the questioning unit can prioritize relevant questions by taking into account the visitor's geographical location information. When asking a question, the questioning unit can prioritize relevant questions by taking into account the visitor's geographical location information. Selection of questions based on geographical location information can be based on, for example, issues specific to the region or geographical relevance. For example, if a visitor is coming from a distant location, the questioning unit can prioritize questions about access to the venue. Also, if the visitor is a local resident, the questioning unit can prioritize questions about local events and services. Also, the questioning unit can ask questions related to a specific region based on the visitor's location information. This allows for more appropriate questions to be asked by taking into account the visitor's geographical location information. Some or all of the above-described processing in the questioning unit may be performed using, or without, a generation AI. For example, the questioning unit can input geographical location information to the generation AI and cause the generation AI to select relevant questions.

[0039] The questioning unit can analyze the visitor's social media activity and ask a related question when asking a question. The questioning unit can analyze the visitor's social media activity and ask a related question when asking a question. Analysis of social media activity can be performed, for example, based on the content of posts and the reactions of followers. For example, if a visitor posts about a game on social media, the questioning unit can ask a question based on the content of the posts. The questioning unit can also analyze the visitor's interests and concerns on social media and ask a related question. The questioning unit can also ask a related question based on the activities of the visitor's friends on social media. In this way, by analyzing the visitor's social media activity, more appropriate questions can be asked. Some or all of the above-mentioned processing in the questioning unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the questioning unit can input social media data into the generation AI and cause the generation AI to generate related questions.

[0040] The questioning unit can customize the question content by reflecting the visitor's past feedback when asking a question. The questioning unit customizes the question content by reflecting the visitor's past feedback when asking a question. Customization based on past feedback can be performed, for example, based on past answer data or the content of the feedback. For example, the questioning unit can ask a question to confirm whether improvements have been made to areas where the visitor was dissatisfied in the past. The questioning unit can also ask a question seeking more detailed opinions on areas where the visitor previously gave a high rating. The questioning unit can also customize questions related to specific topics based on the visitor's past feedback. This allows for more appropriate questions to be asked by reflecting the visitor's past feedback. Some or all of the above-described processing in the questioning unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the questioning unit can input past feedback data into the generation AI and have the generation AI customize the question content.

[0041] During analysis, the analysis unit can investigate emotions and opinions in detail based on the context of the attendee's responses. During analysis, the analysis unit investigates emotions and opinions in detail based on the context of the attendee's responses. Context-based investigations can be performed, for example, based on the context before and after the response or related topics. For example, if an attendee answers, "I'm dissatisfied with the progress of the game," the analysis unit can dig deeper into the specific reasons for this. Similarly, if an attendee answers, "The atmosphere at the venue was good," the analysis unit can dig deeper into the specific factors. The analysis unit can also analyze the context of the attendee's responses and ask related additional questions. By taking the context of the attendee's responses into consideration, more specific problems can be identified. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input response data into a generation AI and have the generation AI execute a context-based investigation.

[0042] The analysis unit can customize the analysis results based on the visitor's attribute information during analysis. The analysis unit customizes the analysis results based on the visitor's attribute information during analysis. Customization based on attribute information can be performed based on information such as age, gender, and occupation. For example, the analysis unit analyzes the responses of younger visitors to extract opinions unique to a particular age group. The analysis unit can also analyze the responses of older visitors to extract opinions unique to a particular age group. The analysis unit can also customize the analysis results based on attribute information such as gender and age. This makes it possible to obtain more appropriate analysis results by taking the visitor's attribute information into consideration. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input attribute information into the generation AI and have the generation AI customize the analysis results.

[0043] During analysis, the analysis unit can check the consistency of the visitor's answers and identify inconsistencies. During analysis, the analysis unit can check the consistency of the visitor's answers and identify inconsistencies. The consistency check can be performed, for example, based on a method for checking inconsistencies and consistency in the answers. For example, if a visitor gives contradictory answers to different questions, the analysis unit can identify the inconsistencies. The analysis unit can also analyze the consistency of the visitor's answers and extract reliable data. The analysis unit can also identify inconsistencies in the visitor's answers and ask additional questions. In this way, by checking the consistency of the visitor's answers, reliable data can be obtained. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input the answer data into the generation AI and have the generation AI perform a consistency check.

[0044] The analysis unit can customize the analysis results based on the geographical location information of the visitors during the analysis. The analysis unit can customize the analysis results based on the geographical location information of the visitors during the analysis. Customization based on geographical location information can be performed, for example, based on regional issues or geographical relevance. For example, the analysis unit can analyze the responses of visitors from far away and extract opinions that are specific to a particular region. The analysis unit can also analyze the responses of local visitors and extract opinions that are specific to a particular region. The analysis unit can also customize the analysis results based on the geographical location information of the visitors. In this way, more appropriate analysis results can be obtained by taking the geographical location information of the visitors into consideration. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input geographical location information into the generation AI and have the generation AI customize the analysis results.

[0045] The analysis unit can improve the accuracy of the analysis by referring to the visitor's social media activity during analysis. The analysis unit can improve the accuracy of the analysis by referring to the visitor's social media activity during analysis. Referencing social media activity can be performed, for example, based on the content of posts and the reactions of followers. For example, the analysis unit can refer to the content of the visitor's social media posts to confirm the reliability of the answers. The analysis unit can also analyze the visitor's interests and concerns on social media to understand the background of the answers. The analysis unit can also refer to the activities of the visitor's friends on social media to confirm the reliability of the answers. In this way, by referring to the visitor's social media activity, more accurate analysis can be performed. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input social media data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0046] The analysis unit can customize the analysis results based on the market value of the visitor. The analysis unit customizes the analysis results based on the market value of the visitor. Customization based on market value can be performed, for example, based on economic value or market trends. For example, the analysis unit prioritizes analysis of responses from visitors with high market value. The analysis unit can also customize the analysis results by placing emphasis on the opinions of visitors with high market value. The analysis unit can also adjust the display method of the analysis results based on the market value of the visitor. In this way, more appropriate analysis results can be obtained by taking the market value of the visitor into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input market value data into the generation AI and have the generation AI customize the analysis results.

[0047] When making a proposal, the suggestion unit can make an optimal proposal by referring to the visitor's past feedback. When making a proposal, the suggestion unit can make an optimal proposal by referring to the visitor's past feedback. Suggestions based on past feedback can be made based on, for example, past response data or the content of the feedback. For example, the suggestion unit can suggest improvements for points that the visitor was dissatisfied with in the past. The suggestion unit can also make suggestions to further strengthen points that the visitor gave high ratings to in the past. The suggestion unit can also make suggestions regarding a specific theme based on the visitor's past feedback. In this way, more appropriate suggestions can be made by referring to the visitor's past feedback. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input past feedback data into the generation AI and cause the generation AI to generate an optimal proposal.

[0048] The suggestion unit can customize the proposal content by taking into account the visitor's attribute information when making a proposal. The suggestion unit customizes the proposal content by taking into account the visitor's attribute information when making a proposal. Customization based on attribute information can be performed based on information such as age, gender, and occupation. For example, the suggestion unit can make suggestions to improve entertainment value for younger visitors. The suggestion unit can also make suggestions to improve venue access and seat comfort for elderly visitors. The suggestion unit can also customize the proposal content based on attribute information such as gender and age. This allows for more appropriate suggestions to be made by taking into account the visitor's attribute information. Some or all of the above-described processing in the suggestion unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the suggestion unit can input attribute information into the generation AI and cause the generation AI to customize the proposal content.

[0049] When making a proposal, the suggestion unit can check the consistency of the visitor's answers, identify inconsistencies, and make a proposal. When making a proposal, the suggestion unit can check the consistency of the visitor's answers, identify inconsistencies, and make a proposal. The consistency check can be performed, for example, based on a method for checking inconsistencies and consistency in answers. For example, if a visitor gives contradictory answers to different questions, the suggestion unit can identify the inconsistencies and make a proposal. The suggestion unit can also analyze the consistency of the visitor's answers and make a proposal based on highly reliable data. The suggestion unit can also identify inconsistencies in the visitor's answers and ask additional questions before making a proposal. In this way, by checking the consistency of the visitor's answers, a highly reliable proposal can be made. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input answer data to the generation AI and have the generation AI check the consistency.

[0050] When making a proposal, the suggestion unit can make an optimal proposal taking into account the geographical location information of the visitor. When making a proposal, the suggestion unit can make an optimal proposal taking into account the geographical location information of the visitor. Suggestions based on geographical location information can be made based on, for example, problems specific to the region or geographical relevance. For example, the suggestion unit can suggest access improvement measures to visitors coming from far away. The suggestion unit can also suggest providing information about local events to local visitors. The suggestion unit can also make suggestions related to a specific region based on the geographical location information of the visitor. In this way, more appropriate suggestions can be made by taking into account the geographical location information of the visitor. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input geographical location information to the generation AI and cause the generation AI to generate an optimal proposal.

[0051] When making a suggestion, the suggestion unit can analyze the visitor's social media activity and make a related suggestion. When making a suggestion, the suggestion unit can analyze the visitor's social media activity and make a related suggestion. The analysis of social media activity can be performed, for example, based on the content of posts and the reactions of followers. For example, if a visitor posts about a game on social media, the suggestion unit can make a suggestion based on the content of the posts. The suggestion unit can also analyze the visitor's interests and concerns on social media and make a related suggestion. The suggestion unit can also make a related suggestion based on the activities of the visitor's friends on social media. In this way, more appropriate suggestions can be made by analyzing the visitor's social media activity. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input social media data into the generation AI and cause the generation AI to generate related suggestions.

[0052] The suggestion unit can customize the proposal content by reflecting the visitor's past feedback when making a proposal. The suggestion unit customizes the proposal content by reflecting the visitor's past feedback when making a proposal. Customization based on past feedback can be performed, for example, based on past response data or the content of the feedback. For example, the suggestion unit can suggest improvements for areas where the visitor was dissatisfied in the past. The suggestion unit can also make suggestions to further strengthen areas where the visitor gave high ratings in the past. The suggestion unit can also make suggestions regarding specific themes based on the visitor's past feedback. In this way, more appropriate suggestions can be made by reflecting the visitor's past feedback. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input past feedback data into the generation AI and cause the generation AI to customize the proposal content.

[0053] When asking an additional question, the additional question unit can select the most appropriate question by referring to the visitor's past answer history. When asking an additional question, the additional question unit can select the most appropriate question by referring to the visitor's past answer history. The selection of the most appropriate question can be performed, for example, based on past answer data and the relevance of the question. For example, the additional question unit can reconfirm points that the visitor was dissatisfied with in the past and ask whether they have been improved. The additional question unit can also preferentially suggest answering methods (text, voice, etc.) that the visitor has used in the past. The additional question unit can also ask an additional question on a specific topic based on the visitor's past answer history. This allows for more appropriate follow-up questions to be asked by referring to the visitor's past answer history. Some or all of the above-described processing in the additional question unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the additional question unit can input past answer data into the generation AI and have the generation AI select the most appropriate question.

[0054] The additional question unit can customize the question content by taking into account the visitor's attribute information when asking an additional question. The additional question unit customizes the question content by taking into account the visitor's attribute information when asking an additional question. Customization based on attribute information can be performed based on information such as age, gender, and occupation. For example, the additional question unit may prioritize additional questions about the entertainment value of the game for younger people. The additional question unit may also prioritize additional questions about venue access and seat comfort for older people. The additional question unit can also customize additional questions about topics that are likely to interest people based on gender. This allows for more appropriate additional questions to be asked by taking into account the visitor's attribute information. Some or all of the above-described processing in the additional question unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the additional question unit may input attribute information into the generation AI and have the generation AI customize the question content.

[0055] When asking an additional question, the additional question unit can prioritize relevant questions by taking into account the visitor's geographical location information. When asking an additional question, the additional question unit can prioritize relevant questions by taking into account the visitor's geographical location information. Selection of questions based on geographical location information can be based on, for example, issues specific to the region or geographical relevance. For example, if a visitor is coming from a distant location, the additional question unit can prioritize additional questions about access to the venue. Furthermore, if the visitor is a local resident, the additional question unit can prioritize additional questions about local events and services. Furthermore, the additional question unit can ask additional questions related to a specific region based on the visitor's location information. In this way, more appropriate additional questions can be asked by taking into account the visitor's geographical location information. Some or all of the above-described processing in the additional question unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the additional question unit can input geographical location information to the generation AI and cause the generation AI to select relevant questions.

[0056] The additional question unit can analyze the visitor's social media activity and ask related questions when asking an additional question. The additional question unit can analyze the visitor's social media activity and ask related questions when asking an additional question. Analysis of social media activity can be performed, for example, based on the content of posts and the reactions of followers. For example, if a visitor posts about a game on social media, the additional question unit can ask an additional question based on the content of the posts. The additional question unit can also analyze the visitor's interests and concerns on social media and ask related additional questions. The additional question unit can also ask related additional questions based on the activities of the visitor's friends on social media. In this way, by analyzing the visitor's social media activity, more appropriate additional questions can be asked. Some or all of the above-mentioned processing in the additional question unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the additional question unit can input social media data into the generation AI and cause the generation AI to generate related questions.

[0057] The display unit can select the optimal display method by referring to the visitor's past response history when displaying the content. The display unit can select the optimal display method by referring to the visitor's past response history when displaying the content. The optimal display method can be selected based on, for example, past response data and display relevance. For example, the display unit displays a message to confirm whether improvements have been made to the points that the visitor was dissatisfied with in the past. The display unit can also display more detailed information about points that the visitor previously gave high ratings to. The display unit can also display information related to a specific theme based on the visitor's past response history. This allows for more appropriate display by referring to the visitor's past response history. Some or all of the above-described processing in the display unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the display unit can input past response data into the generation AI and have the generation AI select the optimal display method.

[0058] The display unit can customize the display content taking into account the visitor's attribute information when displaying the content. The display unit customizes the display content taking into account the visitor's attribute information when displaying the content. Customization based on attribute information can be performed based on information such as age, gender, and occupation. For example, the display unit can provide a display that enhances entertainment value for younger visitors. The display unit can also provide a display regarding venue access and seat comfort for elderly visitors. The display unit can also customize the display content based on attribute information such as gender and age. This allows for more appropriate display by taking into account the visitor's attribute information. Some or all of the above-described processing in the display unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the display unit can input attribute information into the generation AI and have the generation AI customize the display content.

[0059] The display unit can check the consistency of the visitor's answers when displaying the answers, identify and display inconsistencies. The display unit can check the consistency of the visitor's answers when displaying the answers, identify and display inconsistencies. The consistency check can be performed, for example, based on a method for checking inconsistencies and consistency in the answers. For example, if a visitor gives contradictory answers to different questions, the display unit can identify and display the inconsistencies. The display unit can also analyze the consistency of the visitor's answers and display the answers based on reliable data. The display unit can also identify inconsistencies in the visitor's answers and ask additional questions before displaying the answers. In this way, by checking the consistency of the visitor's answers, a reliable display can be performed. Some or all of the above-mentioned processing in the display unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the display unit can input answer data to the generation AI and have the generation AI perform a consistency check.

[0060] The display unit can select the optimal display method taking into account the visitor's geographical location information when displaying. The display unit selects the optimal display method taking into account the visitor's geographical location information when displaying. The selection of the display method based on the geographical location information can be based on, for example, regional issues or geographical relevance. For example, the display unit can display access improvement measures for visitors coming from far away. The display unit can also display information about local events for local visitors. The display unit can also display information related to a specific region based on the visitor's geographical location information. This allows for more appropriate display by taking into account the visitor's geographical location information. Some or all of the above-described processing in the display unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the display unit can input geographical location information to the generation AI and have the generation AI select the optimal display method.

[0061] The display unit can analyze the visitor's social media activity and provide related display content when displaying the content. The display unit can analyze the visitor's social media activity and provide related display content when displaying the content. Analysis of social media activity can be performed, for example, based on the content of posts and the reactions of followers. For example, if a visitor posts about a game on social media, the display unit displays the content based on the content. The display unit can also analyze the visitor's social media interests and provide related display. The display unit can also provide related display based on the activity of the visitor's friends on social media. In this way, by analyzing the visitor's social media activity, more appropriate display can be provided. Some or all of the above-described processing in the display unit can be performed using, for example, a generation AI. For example, the display unit can input social media data into the generation AI and cause the generation AI to generate related display content.

[0062] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0063] The questionnaire system can refer to the visitor's past questionnaire response history and customize the questions based on the past responses. For example, if a visitor previously gave a high rating to a particular game, the questioning department can ask detailed questions related to that game. It can also ask questions to check whether improvements have been made to areas that the visitor was dissatisfied with in the past. Furthermore, questions related to specific themes can be prioritized based on the visitor's past response history. This allows more appropriate questions to be asked by referring to the visitor's past questionnaire response history.

[0064] The questionnaire system can customize the questions based on visitor demographic information such as age, gender, and occupation. For example, questions about the entertainment value of the game can be prioritized for younger people, while questions about venue access and seat comfort can be prioritized for older people. Questions can also be customized to focus on topics that are likely to interest different genders. This allows for more appropriate questions to be asked by taking visitor demographic information into consideration.

[0065] The survey system can adjust the difficulty of questions according to the visitor's response speed. For example, if a visitor responds quickly, more detailed and probing questions can be added. On the other hand, if a visitor responds slowly, simpler and shorter questions can be prioritized. Furthermore, the order and content of questions can be adjusted in real time according to the visitor's response speed. This allows for more effective surveys by adjusting the difficulty of questions according to the visitor's response speed.

[0066] The survey system can prioritize relevant questions by taking into account the visitor's geographic location information. For example, if a visitor is coming from afar, questions about access to the venue can be prioritized. Also, if the visitor is a local, questions about local events and services can be prioritized. Furthermore, questions related to specific areas can be asked based on the visitor's location information. This allows for more appropriate questions to be asked by taking into account the visitor's geographic location information.

[0067] The survey system can analyze visitors' social media activity and ask relevant questions. For example, if a visitor posts about a match on social media, questions can be asked based on the content of that post. It can also analyze visitors' social media interests and ask questions related to those. It can also ask relevant questions based on the activities of the visitor's friends on social media. In this way, by analyzing visitors' social media activity, it is possible to ask more appropriate questions.

[0068] The processing flow of the first embodiment will be briefly explained below.

[0069] Step 1: The questioning section asks survey questions. The questioning section can ask multiple choice or open-ended questions, and can also ask questions in a dialogue format to elicit the emotions and opinions of the audience. For example, they might ask questions such as, "Which part of the game impressed you the most?" or "Was there anything during the game that made you feel dissatisfied?" Step 2: The analysis department analyzes the survey data collected by the questioning department. The analysis department uses statistical analysis and text mining to analyze the survey data and dig deeper into the emotions and opinions of visitors by analyzing their responses. For example, if a visitor answers "I was dissatisfied with the progress of the game," the analysis department asks additional questions such as "Which part of the game did you find particularly dissatisfying?" to identify specific problems. Step 3: The Proposal Department proposes improvement measures based on the analysis results obtained by the Analysis Department. The Proposal Department proposes specific action plans and recommendations, and proposes improvement measures based on a comprehensive analysis of the emotions and opinions of spectators based on the collected data. For example, they make specific suggestions such as "shortening the interval time to ensure smooth progress in the match."

[0070] (Example 2) A questionnaire system according to an embodiment of the present invention is an interactive questionnaire system that conducts a post-game questionnaire with attendees and uses a generation AI to explore customer emotions. When attendees respond to the questionnaire after a baseball game, the generation AI asks them questions in an interactive format to elicit their emotions and opinions. Next, the generation AI analyzes the collected questionnaire data to explore their emotions and opinions. Finally, the generation AI generates the analysis results and improvement measures, making proposals to improve customer satisfaction (CS). For example, in a questionnaire system, attendees fill out a questionnaire after a game. The generation AI asks questions such as, "Which part of the game was most memorable for you?" and "Were there any aspects of the game that you found frustrating?" This allows attendees to express their emotions and opinions naturally. Next, the generation AI analyzes the collected questionnaire data. The generation AI analyzes the attendees' responses and explores their emotions and opinions. For example, if an attendee responds with, "I'm dissatisfied with the progress of the game," the generation AI asks an additional question such as, "Which aspect of the game were you particularly dissatisfied with?" to identify specific problems. Finally, the generation AI generates analysis results and improvement measures. Based on the collected data, the generation AI comprehensively analyzes the emotions and opinions of spectators and proposes improvement measures. For example, it makes specific suggestions such as "shorten the interval time to ensure smooth game progress." This reduces the burden on spectators to respond and allows the survey system to collect more accurate emotions and opinions. In addition, because the generation AI automatically performs analysis and proposals, improvement measures can be implemented quickly and efficiently. For example, it is possible to analyze the survey results immediately after a game and quickly implement improvement measures for the next game. This allows the survey system to delve deeper into spectators' emotions and opinions and propose specific improvement measures to improve CS. For example, it reduces the burden on spectators to respond and allows more accurate emotions and opinions to be collected. In addition, because the generation AI automatically performs analysis and proposals, improvement measures can be implemented quickly and efficiently.

[0071] A questionnaire system according to an embodiment includes a questioning unit, an analysis unit, and a proposal unit. The questioning unit asks questions in the questionnaire. The questioning unit can ask, for example, multiple-choice or open-ended questions. The questioning unit can also ask questions in an interactive format to elicit the emotions and opinions of attendees. For example, the questioning unit asks questions such as, "Which part of the game impressed you the most?" or "Were there any aspects of the game that dissatisfied you?" The analysis unit analyzes the questionnaire data collected by the questioning unit. The analysis unit can analyze the questionnaire data using, for example, statistical analysis or text mining. The analysis unit can also analyze the attendees' responses to delve deeper into their emotions and opinions. For example, if an attendee answers, "I'm dissatisfied with the progress of the game," the analysis unit asks a follow-up question such as, "Which aspect of the game did you find particularly dissatisfying?" to identify specific problems. The proposal unit proposes improvement measures based on the analysis results obtained by the analysis unit. The proposal unit can propose, for example, a specific action plan or recommendations. The suggestion unit can also comprehensively analyze the emotions and opinions of spectators based on the collected data and propose improvement measures. For example, the suggestion unit makes a specific suggestion such as "shorten the interval time to ensure smooth progress of the match." This allows the questionnaire system according to the embodiment to efficiently ask questions in the questionnaire, perform analysis, and propose improvement measures.

[0072] The questionnaire system includes an additional questioning unit that asks additional questions to investigate the emotions of attendees in more detail. The additional questioning unit asks additional questions to investigate the emotions of attendees in more detail. The additional questioning unit can, for example, use an emotion analysis algorithm to analyze the emotions of attendees and ask additional questions. The additional questioning unit can also ask multiple-choice or free-form additional questions. For example, the additional questioning unit asks an additional question such as, "Which part of the game did you feel particularly dissatisfied with?" to an attendee who answered, "I'm dissatisfied with the progress of the game." This allows for a deeper understanding of the emotions of attendees. Some or all of the above-described processing in the additional questioning unit may be performed using, or without, a generation AI. For example, the additional questioning unit can input the attendee's response data into the generation AI and cause the generation AI to generate additional questions.

[0073] The survey system includes a display unit that displays survey results in real time. The display unit displays the survey results in real time. The display unit can, for example, set the data update frequency and display format. The display unit can also update the data in real time and display the latest survey results. For example, the display unit displays the survey results as graphs or charts, providing them in a visually easy-to-understand format. This allows the survey results to be checked in real time. Some or all of the above-described processing in the display unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the display unit can input survey data into the generation AI and cause the generation AI to generate a real-time display.

[0074] The questioning unit can ask questions in a dialogue format to collect the emotions and opinions of visitors. The questioning unit can ask questions in a dialogue format to collect the emotions and opinions of visitors. The dialogue format questions can be asked, for example, using a chatbot or in the form of an interview. For example, the questioning unit can ask questions such as, "Which part of the game impressed you the most?" or "Was there anything during the game that you were dissatisfied with?" This allows visitors to naturally express their emotions and opinions. Some or all of the above-mentioned processing in the questioning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the questioning unit can input dialogue format questions to the generation AI, which then asks the questions in a dialogue format.

[0075] The analysis unit can analyze the attendees' responses and investigate their emotions and opinions in detail. The analysis unit can analyze the attendees' responses and investigate their emotions and opinions in detail. The detailed investigation of emotions and opinions can be performed using, for example, text analysis or sentiment analysis. For example, if the attendee answers "dissatisfied with the progress of the game," the analysis unit can ask an additional question such as "Which part did you feel particularly dissatisfied with?" to identify the specific problem. This makes it possible to delve deeper into the attendees' emotions and opinions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the attendees' response data into the generation AI and have the generation AI perform a detailed investigation of emotions and opinions.

[0076] The suggestion unit can perform a detailed analysis of the emotions and opinions of spectators based on the collected data and propose improvement measures. The suggestion unit can perform a detailed analysis of the emotions and opinions of spectators based on the collected data and propose improvement measures. The detailed analysis of emotions and opinions can be performed using, for example, data mining or statistical analysis. For example, the suggestion unit can make a specific suggestion such as "shorten the interval time to ensure smooth progress of the match." This makes it possible to comprehensively analyze the emotions and opinions of spectators and propose specific improvement measures. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input the collected data into a generation AI and have the generation AI execute the proposed improvement measures.

[0077] The questioning unit can estimate the visitor's emotions and adjust the order of questions based on the estimated visitor's emotions. The questioning unit can estimate the visitor's emotions and adjust the order of questions based on the estimated visitor's emotions. Emotion estimation can be performed using, for example, an emotion recognition algorithm or facial expression analysis. For example, if the visitor is excited, the questioning unit can start with positive questions and gradually move on to more detailed questions. Also, if the visitor is tired, the questioning unit can start with simple questions and gradually move on to more in-depth questions. Also, if the visitor is dissatisfied, the questioning unit can first ask about their dissatisfaction and then ask about areas for improvement. This allows for a more effective survey by adjusting the order of questions according to the visitor's emotions. Some or all of the above-described processing in the questioning unit may be performed using, for example, a generation AI. For example, the questioning unit can input visitor emotion data into the generation AI and have the generation AI adjust the order of questions.

[0078] When asking a question, the questioning unit can select the most appropriate question by referring to the visitor's past survey response history. When asking a question, the questioning unit can select the most appropriate question by referring to the visitor's past survey response history. The selection of the most appropriate question can be performed, for example, based on past response data and the relevance of the question. For example, the questioning unit can reconfirm points that the visitor was dissatisfied with in the past and ask whether they have been improved. The questioning unit can also request more detailed opinions on points that the visitor previously gave high ratings to. The questioning unit can also prioritize questions related to specific topics based on the visitor's past response history. This allows more appropriate questions to be asked by referring to the past survey response history. Some or all of the above-mentioned processing in the questioning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the questioning unit can input past response data into the generation AI and have the generation AI select the most appropriate question.

[0079] When asking a question, the questioning unit can customize the question content based on attribute information such as the visitor's age, gender, and occupation. When asking a question, the questioning unit customizes the question content based on attribute information such as the visitor's age, gender, and occupation. Customization based on attribute information can be performed based on information such as age, gender, and occupation. For example, the questioning unit may prioritize questions about the entertainment value of the game for younger people. The questioning unit may also prioritize questions about venue access and seat comfort for older people. The questioning unit may also customize questions about topics that are likely to interest people based on gender. This allows for more appropriate questions to be asked by taking the visitor's attribute information into consideration. Some or all of the above-described processing by the questioning unit may be performed using, or without, a generation AI. For example, the questioning unit may input attribute information into the generation AI and cause the generation AI to customize the question content.

[0080] The questioning unit can adjust the difficulty of the question depending on the visitor's answering speed when asking a question. The questioning unit can adjust the difficulty of the question depending on the visitor's answering speed when asking a question. Adjustment depending on the answering speed can be made based on, for example, measuring the answering time or setting a difficulty level. For example, if the visitor answers quickly, the questioning unit can add more detailed and in-depth questions. Also, if the visitor answers slowly, the questioning unit can prioritize simpler and shorter questions. The questioning unit can also adjust the order and content of the questions in real time depending on the visitor's answering speed. This allows for a more effective survey by adjusting the difficulty of the questions depending on the visitor's answering speed. Some or all of the above-mentioned processing in the questioning unit may be performed using, or without, a generation AI. For example, the questioning unit can input answering speed data into the generation AI and have the generation AI adjust the difficulty of the questions.

[0081] The questioning unit can estimate the visitor's emotions and adjust the way questions are phrased based on the estimated visitor's emotions. The questioning unit can estimate the visitor's emotions and adjust the way questions are phrased based on the estimated visitor's emotions. Emotion estimation can be performed using, for example, an emotion recognition algorithm or facial expression analysis. For example, if a visitor is nervous, the questioning unit can ask questions using gentle language. If a visitor is relaxed, the questioning unit can ask questions using casual language. If a visitor is dissatisfied, the questioning unit can ask questions using polite language. This allows for a more effective survey by adjusting the way questions are phrased according to the visitor's emotions. Some or all of the above-described processing in the questioning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the questioning unit can input emotion data into the generation AI and cause the generation AI to adjust the way questions are phrased.

[0082] When asking a question, the questioning unit can prioritize relevant questions by taking into account the visitor's geographical location information. When asking a question, the questioning unit can prioritize relevant questions by taking into account the visitor's geographical location information. Selection of questions based on geographical location information can be based on, for example, issues specific to the region or geographical relevance. For example, if a visitor is coming from a distant location, the questioning unit can prioritize questions about access to the venue. Also, if the visitor is a local resident, the questioning unit can prioritize questions about local events and services. Also, the questioning unit can ask questions related to a specific region based on the visitor's location information. This allows for more appropriate questions to be asked by taking into account the visitor's geographical location information. Some or all of the above-described processing in the questioning unit may be performed using, or without, a generation AI. For example, the questioning unit can input geographical location information to the generation AI and cause the generation AI to select relevant questions.

[0083] The questioning unit can analyze the visitor's social media activity and ask a related question when asking a question. The questioning unit can analyze the visitor's social media activity and ask a related question when asking a question. Analysis of social media activity can be performed, for example, based on the content of posts and the reactions of followers. For example, if a visitor posts about a game on social media, the questioning unit can ask a question based on the content of the posts. The questioning unit can also analyze the visitor's interests and concerns on social media and ask a related question. The questioning unit can also ask a related question based on the activities of the visitor's friends on social media. In this way, by analyzing the visitor's social media activity, more appropriate questions can be asked. Some or all of the above-mentioned processing in the questioning unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the questioning unit can input social media data into the generation AI and cause the generation AI to generate related questions.

[0084] The questioning unit can customize the question content by reflecting the visitor's past feedback when asking a question. The questioning unit customizes the question content by reflecting the visitor's past feedback when asking a question. Customization based on past feedback can be performed, for example, based on past answer data or the content of the feedback. For example, the questioning unit can ask a question to confirm whether improvements have been made to areas where the visitor was dissatisfied in the past. The questioning unit can also ask a question seeking more detailed opinions on areas where the visitor previously gave a high rating. The questioning unit can also customize questions related to specific topics based on the visitor's past feedback. This allows for more appropriate questions to be asked by reflecting the visitor's past feedback. Some or all of the above-described processing in the questioning unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the questioning unit can input past feedback data into the generation AI and have the generation AI customize the question content.

[0085] The analysis unit can estimate the visitor's emotions and determine the analysis priorities based on the estimated visitor's emotions. The analysis unit can estimate the visitor's emotions and determine the analysis priorities based on the estimated visitor's emotions. Emotion estimation can be performed using, for example, an emotion recognition algorithm or facial expression analysis. For example, if a visitor expresses strong dissatisfaction, the analysis unit can prioritize analyzing the dissatisfaction points. Alternatively, if a visitor is very satisfied, the analysis unit can prioritize analyzing the satisfaction points. The analysis unit can also adjust the analysis priorities in real time according to the strength of the visitor's emotions. This allows for more effective analysis by determining the analysis priorities according to the visitor's emotions. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input emotion data into a generation AI and have the generation AI determine the analysis priorities.

[0086] During analysis, the analysis unit can investigate emotions and opinions in detail based on the context of the attendee's responses. During analysis, the analysis unit investigates emotions and opinions in detail based on the context of the attendee's responses. Context-based investigations can be performed, for example, based on the context before and after the response or related topics. For example, if an attendee answers, "I'm dissatisfied with the progress of the game," the analysis unit can dig deeper into the specific reasons for this. Similarly, if an attendee answers, "The atmosphere at the venue was good," the analysis unit can dig deeper into the specific factors. The analysis unit can also analyze the context of the attendee's responses and ask related additional questions. By taking the context of the attendee's responses into consideration, more specific problems can be identified. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input response data into a generation AI and have the generation AI execute a context-based investigation.

[0087] The analysis unit can customize the analysis results based on the visitor's attribute information during analysis. The analysis unit customizes the analysis results based on the visitor's attribute information during analysis. Customization based on attribute information can be performed based on information such as age, gender, and occupation. For example, the analysis unit analyzes the responses of younger visitors to extract opinions unique to a particular age group. The analysis unit can also analyze the responses of older visitors to extract opinions unique to a particular age group. The analysis unit can also customize the analysis results based on attribute information such as gender and age. This makes it possible to obtain more appropriate analysis results by taking the visitor's attribute information into consideration. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input attribute information into the generation AI and have the generation AI customize the analysis results.

[0088] During analysis, the analysis unit can check the consistency of the visitor's answers and identify inconsistencies. During analysis, the analysis unit can check the consistency of the visitor's answers and identify inconsistencies. The consistency check can be performed, for example, based on a method for checking inconsistencies and consistency in the answers. For example, if a visitor gives contradictory answers to different questions, the analysis unit can identify the inconsistencies. The analysis unit can also analyze the consistency of the visitor's answers and extract reliable data. The analysis unit can also identify inconsistencies in the visitor's answers and ask additional questions. In this way, by checking the consistency of the visitor's answers, reliable data can be obtained. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input the answer data into the generation AI and have the generation AI perform a consistency check.

[0089] The analysis unit can estimate the visitor's emotions and adjust the display method of the analysis results based on the estimated visitor's emotions. The analysis unit can estimate the visitor's emotions and adjust the display method of the analysis results based on the estimated visitor's emotions. Emotion estimation can be performed using, for example, an emotion recognition algorithm or facial expression analysis. For example, if a visitor expresses dissatisfaction, the analysis unit can highlight the problems. Alternatively, if a visitor is satisfied, the analysis unit can highlight the positive aspects. The analysis unit can also adjust the display method of the analysis results in real time according to the visitor's emotions. This allows for more effective display by adjusting the display method of the analysis results according to the visitor's emotions. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input emotion data into the generation AI and have the generation AI adjust the display method.

[0090] The analysis unit can customize the analysis results based on the geographical location information of the visitors during the analysis. The analysis unit can customize the analysis results based on the geographical location information of the visitors during the analysis. Customization based on geographical location information can be performed, for example, based on regional issues or geographical relevance. For example, the analysis unit can analyze the responses of visitors from far away and extract opinions that are specific to a particular region. The analysis unit can also analyze the responses of local visitors and extract opinions that are specific to a particular region. The analysis unit can also customize the analysis results based on the geographical location information of the visitors. In this way, more appropriate analysis results can be obtained by taking the geographical location information of the visitors into consideration. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input geographical location information into the generation AI and have the generation AI customize the analysis results.

[0091] The analysis unit can improve the accuracy of the analysis by referring to the visitor's social media activity during analysis. The analysis unit can improve the accuracy of the analysis by referring to the visitor's social media activity during analysis. Referencing social media activity can be performed, for example, based on the content of posts and the reactions of followers. For example, the analysis unit can refer to the content of the visitor's social media posts to confirm the reliability of the answers. The analysis unit can also analyze the visitor's interests and concerns on social media to understand the background of the answers. The analysis unit can also refer to the activities of the visitor's friends on social media to confirm the reliability of the answers. In this way, by referring to the visitor's social media activity, more accurate analysis can be performed. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input social media data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0092] The analysis unit can customize the analysis results based on the market value of the visitor. The analysis unit customizes the analysis results based on the market value of the visitor. Customization based on market value can be performed, for example, based on economic value or market trends. For example, the analysis unit prioritizes analysis of responses from visitors with high market value. The analysis unit can also customize the analysis results by placing emphasis on the opinions of visitors with high market value. The analysis unit can also adjust the display method of the analysis results based on the market value of the visitor. In this way, more appropriate analysis results can be obtained by taking the market value of the visitor into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input market value data into the generation AI and have the generation AI customize the analysis results.

[0093] The suggestion unit can estimate the visitor's emotions and prioritize proposals based on the estimated visitor's emotions. The suggestion unit can estimate the visitor's emotions and prioritize proposals based on the estimated visitor's emotions. Emotion estimation can be performed using, for example, an emotion recognition algorithm or facial expression analysis. For example, if a visitor expresses strong dissatisfaction, the suggestion unit can prioritize proposals to address the dissatisfaction. Furthermore, if a visitor is very satisfied, the suggestion unit can prioritize proposals to maintain the visitor's satisfaction. The suggestion unit can also adjust the priority of proposals in real time according to the strength of the visitor's emotions. Thus, by prioritizing proposals according to the visitor's emotions, more effective proposals can be made. Some or all of the above-described processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input emotion data into the generation AI and have the generation AI determine the priority of proposals.

[0094] When making a proposal, the suggestion unit can make an optimal proposal by referring to the visitor's past feedback. When making a proposal, the suggestion unit can make an optimal proposal by referring to the visitor's past feedback. Suggestions based on past feedback can be made based on, for example, past response data or the content of the feedback. For example, the suggestion unit can suggest improvements for points that the visitor was dissatisfied with in the past. The suggestion unit can also make suggestions to further strengthen points that the visitor gave high ratings to in the past. The suggestion unit can also make suggestions regarding a specific theme based on the visitor's past feedback. In this way, more appropriate suggestions can be made by referring to the visitor's past feedback. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input past feedback data into the generation AI and cause the generation AI to generate an optimal proposal.

[0095] The suggestion unit can customize the proposal content by taking into account the visitor's attribute information when making a proposal. The suggestion unit customizes the proposal content by taking into account the visitor's attribute information when making a proposal. Customization based on attribute information can be performed based on information such as age, gender, and occupation. For example, the suggestion unit can make suggestions to improve entertainment value for younger visitors. The suggestion unit can also make suggestions to improve venue access and seat comfort for elderly visitors. The suggestion unit can also customize the proposal content based on attribute information such as gender and age. This allows for more appropriate suggestions to be made by taking into account the visitor's attribute information. Some or all of the above-described processing in the suggestion unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the suggestion unit can input attribute information into the generation AI and cause the generation AI to customize the proposal content.

[0096] When making a proposal, the suggestion unit can check the consistency of the visitor's answers, identify inconsistencies, and make a proposal. When making a proposal, the suggestion unit can check the consistency of the visitor's answers, identify inconsistencies, and make a proposal. The consistency check can be performed, for example, based on a method for checking inconsistencies and consistency in answers. For example, if a visitor gives contradictory answers to different questions, the suggestion unit can identify the inconsistencies and make a proposal. The suggestion unit can also analyze the consistency of the visitor's answers and make a proposal based on highly reliable data. The suggestion unit can also identify inconsistencies in the visitor's answers and ask additional questions before making a proposal. In this way, by checking the consistency of the visitor's answers, a highly reliable proposal can be made. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input answer data to the generation AI and have the generation AI check the consistency.

[0097] The suggestion unit can estimate the visitor's emotions and adjust the way the suggestion is expressed based on the estimated visitor's emotions. The suggestion unit can estimate the visitor's emotions and adjust the way the suggestion is expressed based on the estimated visitor's emotions. Emotion estimation can be performed using, for example, an emotion recognition algorithm or facial expression analysis. For example, if the visitor is nervous, the suggestion unit can make the suggestion using gentle language. If the visitor is relaxed, the suggestion unit can make the suggestion using casual language. If the visitor is dissatisfied, the suggestion unit can make the suggestion using polite language. In this way, by adjusting the way the suggestion is expressed based on the visitor's emotions, more effective suggestions can be made. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input emotion data into the generation AI and cause the generation AI to adjust the way the suggestion is expressed.

[0098] When making a proposal, the suggestion unit can make an optimal proposal taking into account the geographical location information of the visitor. When making a proposal, the suggestion unit can make an optimal proposal taking into account the geographical location information of the visitor. Suggestions based on geographical location information can be made based on, for example, problems specific to the region or geographical relevance. For example, the suggestion unit can suggest access improvement measures to visitors coming from far away. The suggestion unit can also suggest providing information about local events to local visitors. The suggestion unit can also make suggestions related to a specific region based on the geographical location information of the visitor. In this way, more appropriate suggestions can be made by taking into account the geographical location information of the visitor. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input geographical location information to the generation AI and cause the generation AI to generate an optimal proposal.

[0099] When making a suggestion, the suggestion unit can analyze the visitor's social media activity and make a related suggestion. When making a suggestion, the suggestion unit can analyze the visitor's social media activity and make a related suggestion. The analysis of social media activity can be performed, for example, based on the content of posts and the reactions of followers. For example, if a visitor posts about a game on social media, the suggestion unit can make a suggestion based on the content of the posts. The suggestion unit can also analyze the visitor's interests and concerns on social media and make a related suggestion. The suggestion unit can also make a related suggestion based on the activities of the visitor's friends on social media. In this way, more appropriate suggestions can be made by analyzing the visitor's social media activity. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input social media data into the generation AI and cause the generation AI to generate related suggestions.

[0100] The suggestion unit can customize the proposal content by reflecting the visitor's past feedback when making a proposal. The suggestion unit customizes the proposal content by reflecting the visitor's past feedback when making a proposal. Customization based on past feedback can be performed, for example, based on past response data or the content of the feedback. For example, the suggestion unit can suggest improvements for areas where the visitor was dissatisfied in the past. The suggestion unit can also make suggestions to further strengthen areas where the visitor gave high ratings in the past. The suggestion unit can also make suggestions regarding specific themes based on the visitor's past feedback. In this way, more appropriate suggestions can be made by reflecting the visitor's past feedback. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input past feedback data into the generation AI and cause the generation AI to customize the proposal content.

[0101] The additional questioning unit can estimate the visitor's emotions and adjust the timing of the additional questions based on the estimated visitor's emotions. The additional questioning unit can estimate the visitor's emotions and adjust the timing of the additional questions based on the estimated visitor's emotions. Emotion estimation can be performed using, for example, an emotion recognition algorithm or facial expression analysis. For example, if a visitor is excited, the additional questioning unit can immediately ask an additional question. If a visitor is tired, the additional questioning unit can also wait a short time before asking an additional question. If a visitor is dissatisfied, the additional questioning unit can first find out what the dissatisfaction is and then ask an additional question. This allows for a more effective survey by adjusting the timing of the additional questions according to the visitor's emotions. Some or all of the above-described processing in the additional questioning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the additional questioning unit can input emotion data into the generation AI and have the generation AI adjust the timing of the additional questions.

[0102] When asking an additional question, the additional question unit can select the most appropriate question by referring to the visitor's past answer history. When asking an additional question, the additional question unit can select the most appropriate question by referring to the visitor's past answer history. The selection of the most appropriate question can be performed, for example, based on past answer data and the relevance of the question. For example, the additional question unit can reconfirm points that the visitor was dissatisfied with in the past and ask whether they have been improved. The additional question unit can also preferentially suggest answering methods (text, voice, etc.) that the visitor has used in the past. The additional question unit can also ask an additional question on a specific topic based on the visitor's past answer history. This allows for more appropriate follow-up questions to be asked by referring to the visitor's past answer history. Some or all of the above-described processing in the additional question unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the additional question unit can input past answer data into the generation AI and have the generation AI select the most appropriate question.

[0103] The additional question unit can customize the question content by taking into account the visitor's attribute information when asking an additional question. The additional question unit customizes the question content by taking into account the visitor's attribute information when asking an additional question. Customization based on attribute information can be performed based on information such as age, gender, and occupation. For example, the additional question unit may prioritize additional questions about the entertainment value of the game for younger people. The additional question unit may also prioritize additional questions about venue access and seat comfort for older people. The additional question unit can also customize additional questions about topics that are likely to interest people based on gender. This allows for more appropriate additional questions to be asked by taking into account the visitor's attribute information. Some or all of the above-described processing in the additional question unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the additional question unit may input attribute information into the generation AI and have the generation AI customize the question content.

[0104] The additional question unit can estimate the visitor's emotions and adjust the way the additional question is phrased based on the estimated visitor's emotions. The additional question unit can estimate the visitor's emotions and adjust the way the additional question is phrased based on the estimated visitor's emotions. Emotion estimation can be performed using, for example, an emotion recognition algorithm or facial expression analysis. For example, if the visitor is nervous, the additional question unit can ask the additional question using gentle language. If the visitor is relaxed, the additional question unit can ask the additional question using casual language. If the visitor is dissatisfied, the additional question unit can ask the additional question using polite language. This allows for a more effective survey by adjusting the way the additional question is phrased based on the visitor's emotions. Some or all of the above-described processing in the additional question unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the additional question unit can input emotion data into the generation AI and cause the generation AI to adjust the way the additional question is phrased.

[0105] When asking an additional question, the additional question unit can prioritize relevant questions by taking into account the visitor's geographical location information. When asking an additional question, the additional question unit can prioritize relevant questions by taking into account the visitor's geographical location information. Selection of questions based on geographical location information can be based on, for example, issues specific to the region or geographical relevance. For example, if a visitor is coming from a distant location, the additional question unit can prioritize additional questions about access to the venue. Furthermore, if the visitor is a local resident, the additional question unit can prioritize additional questions about local events and services. Furthermore, the additional question unit can ask additional questions related to a specific region based on the visitor's location information. In this way, more appropriate additional questions can be asked by taking into account the visitor's geographical location information. Some or all of the above-described processing in the additional question unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the additional question unit can input geographical location information to the generation AI and cause the generation AI to select relevant questions.

[0106] The additional question unit can analyze the visitor's social media activity and ask related questions when asking an additional question. The additional question unit can analyze the visitor's social media activity and ask related questions when asking an additional question. Analysis of social media activity can be performed, for example, based on the content of posts and the reactions of followers. For example, if a visitor posts about a game on social media, the additional question unit can ask an additional question based on the content of the posts. The additional question unit can also analyze the visitor's interests and concerns on social media and ask related additional questions. The additional question unit can also ask related additional questions based on the activities of the visitor's friends on social media. In this way, by analyzing the visitor's social media activity, more appropriate additional questions can be asked. Some or all of the above-mentioned processing in the additional question unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the additional question unit can input social media data into the generation AI and cause the generation AI to generate related questions.

[0107] The display unit can estimate the visitor's emotions and adjust the display content based on the estimated visitor's emotions. The display unit can estimate the visitor's emotions and adjust the display content based on the estimated visitor's emotions. Emotion estimation can be performed using, for example, an emotion recognition algorithm or facial expression analysis. For example, if a visitor expresses dissatisfaction, the display unit can highlight the problems. Also, if a visitor is satisfied, the display unit can highlight the positive aspects. The display unit can also adjust the display content in real time according to the visitor's emotions. This allows for more effective display by adjusting the display content according to the visitor's emotions. Some or all of the above-described processing in the display unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the display unit can input emotion data to the generation AI and have the generation AI adjust the display content.

[0108] The display unit can select the optimal display method by referring to the visitor's past response history when displaying the content. The display unit can select the optimal display method by referring to the visitor's past response history when displaying the content. The optimal display method can be selected based on, for example, past response data and display relevance. For example, the display unit displays a message to confirm whether improvements have been made to the points that the visitor was dissatisfied with in the past. The display unit can also display more detailed information about points that the visitor previously gave high ratings to. The display unit can also display information related to a specific theme based on the visitor's past response history. This allows for more appropriate display by referring to the visitor's past response history. Some or all of the above-described processing in the display unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the display unit can input past response data into the generation AI and have the generation AI select the optimal display method.

[0109] The display unit can customize the display content taking into account the visitor's attribute information when displaying the content. The display unit customizes the display content taking into account the visitor's attribute information when displaying the content. Customization based on attribute information can be performed based on information such as age, gender, and occupation. For example, the display unit can provide a display that enhances entertainment value for younger visitors. The display unit can also provide a display regarding venue access and seat comfort for elderly visitors. The display unit can also customize the display content based on attribute information such as gender and age. This allows for more appropriate display by taking into account the visitor's attribute information. Some or all of the above-described processing in the display unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the display unit can input attribute information into the generation AI and have the generation AI customize the display content.

[0110] The display unit can check the consistency of the visitor's answers when displaying the answers, identify and display inconsistencies. The display unit can check the consistency of the visitor's answers when displaying the answers, identify and display inconsistencies. The consistency check can be performed, for example, based on a method for checking inconsistencies and consistency in the answers. For example, if a visitor gives contradictory answers to different questions, the display unit can identify and display the inconsistencies. The display unit can also analyze the consistency of the visitor's answers and display the answers based on reliable data. The display unit can also identify inconsistencies in the visitor's answers and ask additional questions before displaying the answers. In this way, by checking the consistency of the visitor's answers, a reliable display can be performed. Some or all of the above-mentioned processing in the display unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the display unit can input answer data to the generation AI and have the generation AI perform a consistency check.

[0111] The display unit can estimate the visitor's emotions and determine display priorities based on the estimated visitor's emotions. The display unit can estimate the visitor's emotions and determine display priorities based on the estimated visitor's emotions. Emotion estimation can be performed using, for example, an emotion recognition algorithm or facial expression analysis. For example, if a visitor is highly dissatisfied, the display unit can prioritize displaying the dissatisfaction points. Also, if a visitor is highly satisfied, the display unit can prioritize displaying the satisfaction points. The display unit can also adjust the display priorities in real time according to the intensity of the visitor's emotions. This allows for more effective display by determining display priorities according to the visitor's emotions. Some or all of the above-described processing in the display unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the display unit can input emotion data to the generation AI and have the generation AI determine the display priorities.

[0112] The display unit can select the optimal display method taking into account the visitor's geographical location information when displaying. The display unit selects the optimal display method taking into account the visitor's geographical location information when displaying. The selection of the display method based on the geographical location information can be based on, for example, regional issues or geographical relevance. For example, the display unit can display access improvement measures for visitors coming from far away. The display unit can also display information about local events for local visitors. The display unit can also display information related to a specific region based on the visitor's geographical location information. This allows for more appropriate display by taking into account the visitor's geographical location information. Some or all of the above-described processing in the display unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the display unit can input geographical location information to the generation AI and have the generation AI select the optimal display method.

[0113] The display unit can analyze the visitor's social media activity and provide related display content when displaying the content. The display unit can analyze the visitor's social media activity and provide related display content when displaying the content. Analysis of social media activity can be performed, for example, based on the content of posts and the reactions of followers. For example, if a visitor posts about a game on social media, the display unit displays the content based on the content. The display unit can also analyze the visitor's social media interests and provide related display. The display unit can also provide related display based on the activity of the visitor's friends on social media. In this way, by analyzing the visitor's social media activity, more appropriate display can be provided. Some or all of the above-described processing in the display unit can be performed using, for example, a generation AI. For example, the display unit can input social media data into the generation AI and cause the generation AI to generate related display content. === Hard Collateral 1-1 === Each of the multiple elements, including the questioning unit, analysis unit, suggestion unit, additional questioning unit, and display unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the questioning unit is realized by the control unit 46A of the smart device 14 and asks questions to visitors in an interactive format. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes collected questionnaire data. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suggests improvement measures based on the analysis results. The additional questioning unit is realized, for example, by the control unit 46A of the smart device 14 and asks additional questions to investigate visitors' emotions in detail. The display unit is realized, for example, by the output device 40 of the smart device 14 and displays the questionnaire results in real time. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned questioning unit, analysis unit, suggestion unit, additional questioning unit, and display unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the questioning unit is realized by the control unit 46A of the smart glasses 214 and asks questions to visitors in an interactive format. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes collected questionnaire data. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suggests improvement measures based on the analysis results. The additional questioning unit is realized, for example, by the control unit 46A of the smart glasses 214 and asks additional questions to investigate visitors' emotions in detail. The display unit is realized, for example, by the output device 40 of the smart glasses 214 and displays the questionnaire results in real time. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned questioning unit, analysis unit, suggestion unit, additional questioning unit, and display unit, is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the questioning unit is realized by the control unit 46A of the headset type terminal 314 and asks questions to visitors in an interactive format. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes collected questionnaire data. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suggests improvement measures based on the analysis results. The additional questioning unit is realized, for example, by the control unit 46A of the headset type terminal 314 and asks additional questions to investigate visitors' emotions in detail. The display unit is realized, for example, by the output device 40 of the headset type terminal 314 and displays the questionnaire results in real time. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned questioning unit, analysis unit, suggestion unit, additional questioning unit, and display unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the questioning unit is realized by the control unit 46A of the robot 414 and asks questions to visitors in an interactive format. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes collected questionnaire data. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suggests improvement measures based on the analysis results. The additional questioning unit is realized, for example, by the control unit 46A of the robot 414 and asks additional questions to investigate visitors' emotions in detail. The display unit is realized, for example, by the output device 40 of the robot 414 and displays the questionnaire results in real time.

[0114] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0115] The survey system can estimate the emotions of spectators and dynamically change the content of the survey questions based on the estimated emotions. For example, if spectators are excited after a game, the questioning department can prioritize positive questions to maintain their excitement. If spectators are tired, the questioning department can start with simple questions and gradually move on to more detailed questions. Furthermore, if spectators are dissatisfied, the questioning department can first find out what they are dissatisfied with and then ask about areas for improvement. This makes it possible to adjust the content of the questions according to spectators' emotions, resulting in more effective surveys.

[0116] The questionnaire system can refer to the visitor's past questionnaire response history and customize the questions based on the past responses. For example, if a visitor previously gave a high rating to a particular game, the questioning department can ask detailed questions related to that game. It can also ask questions to check whether improvements have been made to areas that the visitor was dissatisfied with in the past. Furthermore, questions related to specific themes can be prioritized based on the visitor's past response history. This allows more appropriate questions to be asked by referring to the visitor's past questionnaire response history.

[0117] The questionnaire system can customize the questions based on visitor demographic information such as age, gender, and occupation. For example, questions about the entertainment value of the game can be prioritized for younger people, while questions about venue access and seat comfort can be prioritized for older people. Questions can also be customized to focus on topics that are likely to interest different genders. This allows for more appropriate questions to be asked by taking visitor demographic information into consideration.

[0118] The survey system can adjust the difficulty of questions according to the visitor's response speed. For example, if a visitor responds quickly, more detailed and probing questions can be added. On the other hand, if a visitor responds slowly, simpler and shorter questions can be prioritized. Furthermore, the order and content of questions can be adjusted in real time according to the visitor's response speed. This allows for more effective surveys by adjusting the difficulty of questions according to the visitor's response speed.

[0119] The survey system can prioritize relevant questions by taking into account the visitor's geographic location information. For example, if a visitor is coming from afar, questions about access to the venue can be prioritized. Also, if the visitor is a local, questions about local events and services can be prioritized. Furthermore, questions related to specific areas can be asked based on the visitor's location information. This allows for more appropriate questions to be asked by taking into account the visitor's geographic location information.

[0120] The survey system can estimate the emotions of visitors and adjust the order of questions in the survey based on the estimated emotions. For example, if a visitor is excited, it can start with positive questions and gradually move on to more detailed questions. If a visitor is tired, it can start with simple questions and gradually move on to more in-depth questions. Furthermore, if a visitor is dissatisfied, it can first ask about their dissatisfaction and then ask about areas for improvement. This allows for more effective surveys by adjusting the order of questions according to the visitor's emotions.

[0121] The survey system can analyze visitors' social media activity and ask relevant questions. For example, if a visitor posts about a match on social media, questions can be asked based on the content of that post. It can also analyze visitors' social media interests and ask questions related to those. It can also ask relevant questions based on the activities of the visitor's friends on social media. In this way, by analyzing visitors' social media activity, it is possible to ask more appropriate questions.

[0122] The questionnaire system can estimate the emotions of visitors and adjust the way questions are phrased based on the estimated emotions. For example, if a visitor is nervous, the questions can be asked in gentle language. If a visitor is relaxed, the questions can be asked in casual language. Furthermore, if a visitor is dissatisfied, the questions can be asked in polite language. This allows for more effective questionnaires by adjusting the way questions are phrased according to the visitor's emotions.

[0123] The questionnaire system can estimate the emotions of visitors and determine the priorities of analysis based on the estimated emotions. For example, if a visitor expresses strong dissatisfaction, the system can prioritize analysis of those points of dissatisfaction. Conversely, if a visitor is very satisfied, the system can prioritize analysis of those points of satisfaction. Furthermore, the system can adjust the priorities of analysis in real time according to the strength of the visitor's emotions. This allows for more effective analysis by determining the priorities of analysis according to the visitor's emotions.

[0124] The survey system can estimate the emotions of visitors and adjust the way the analysis results are displayed based on the estimated emotions. For example, if a visitor expresses dissatisfaction, the system can highlight the problems. Alternatively, if a visitor is satisfied, the system can highlight the positive aspects. Furthermore, the system can adjust the way the analysis results are displayed in real time according to the visitor's emotions. This allows for more effective display by adjusting the way the analysis results are displayed according to the visitor's emotions.

[0125] The processing flow of the second embodiment will be briefly explained below.

[0126] Step 1: The questioning section asks survey questions. The questioning section can ask multiple choice or open-ended questions, and can also ask questions in a dialogue format to elicit the emotions and opinions of the audience. For example, they might ask questions such as, "Which part of the game impressed you the most?" or "Was there anything during the game that made you feel dissatisfied?" Step 2: The analysis department analyzes the survey data collected by the questioning department. The analysis department uses statistical analysis and text mining to analyze the survey data and dig deeper into the emotions and opinions of visitors by analyzing their responses. For example, if a visitor answers "I was dissatisfied with the progress of the game," the analysis department asks additional questions such as "Which part of the game did you find particularly dissatisfying?" to identify specific problems. Step 3: The Proposal Department proposes improvement measures based on the analysis results obtained by the Analysis Department. The Proposal Department proposes specific action plans and recommendations, and proposes improvement measures based on a comprehensive analysis of the emotions and opinions of spectators based on the collected data. For example, they make specific suggestions such as "shortening the interval time to ensure smooth progress in the match."

[0127] 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.

[0128] 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.

[0129] 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.

[0130] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0131] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0163] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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).

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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).

[0184] 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.

[0185] 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."

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] [Explanation of symbols]

[0199] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a questioning section that asks survey questions; an analysis unit that analyzes the questionnaire data collected by the questioning unit; a proposal unit that proposes improvement measures based on the analysis results obtained by the analysis unit; Equipped with A system characterized by:

2. Equipped with a follow-up question section that asks additional questions to investigate visitor emotions in detail 2. The system of claim 1.

3. Equipped with a display that shows survey results in real time 2. The system of claim 1.

4. The interrogation unit Ask questions in a conversational format to gather attendee sentiment and opinions 2. The system of claim 1.

5. The analysis unit Analyze attendee responses to explore emotions and opinions in detail 2. The system of claim 1.

6. The proposal unit Based on the collected data, we conduct a detailed analysis of visitor sentiment and opinions and propose improvements.

2. The system of claim 1.

7. The interrogation unit Estimate visitor sentiment and adjust question order based on estimated visitor sentiment 2. The system of claim 1.

8. The interrogation unit When asking a question, the most appropriate question is selected by referring to the visitor's past survey response history.

2. The system of claim 1.

9. The interrogation unit When asking questions, customize the questions based on the visitor's demographic information such as age, gender, and occupation.

2. The system of claim 1.

Images