System

Abstract

An object of a system according to an embodiment is to obtain deep insight by multilaterally understanding through a conversation with an answerer.SOLUTION: A system includes a reception unit, a generation unit, and an analysis unit. The receiving unit receives an input from a user. The generation unit analyzes the question received by the reception unit and presents the question to the answerer. The analysis unit analyzes the answer on the basis of the question generated by the generation unit. The generation unit generates a follow-up question based on the answer analyzed by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem that the information obtained through surveys and interviews is limited, making it difficult to obtain the respondents' essential needs or deep insights.

[0005] The system according to the embodiment aims to gain a multifaceted understanding and deep insight through conversation with respondents. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, and an analysis unit. The reception unit receives input from a user. The generation unit analyzes the question received by the reception unit and presents the question to the respondent. The analysis unit analyzes the answer based on the question generated by the generation unit. The generation unit generates a follow-up question based on the answer analyzed by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can obtain a multifaceted understanding and deep insight through conversations with respondents. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention utilizes generative AI to understand respondents' thoughts from multiple perspectives through conversations with them. This system accepts user input, and the generative AI generates questions and presents them to the respondent. When the respondent answers a question, the AI ​​analyzes the answer and determines the next question to ask. By repeating this process, the AI ​​can gain a deeper understanding of the respondent's thoughts and feelings. For example, when a user inputs a question such as "Tell me about your recent experience," the generative AI analyzes the question and presents it to the respondent. If the respondent answers, "I recently purchased a new product," the AI ​​may ask a follow-up question such as, "Which feature of that product did you like most?" This approach can reveal the respondent's true needs and feelings. Furthermore, the AI ​​can more accurately capture the respondent's emotions and intentions. For example, by analyzing the respondent's tone of voice and facial expression when answering, "I liked the design of that product most," it can determine the sincerity of the answer. This is expected to improve the quality and accuracy of market research. This allows the system to provide deeper insights not possible with conventional surveys and reveal the respondent's true needs. For example, this will enable more accurate information-based decision-making when developing new products or formulating marketing strategies. It is also expected that more accurate understanding of respondents' emotions and intentions will contribute to improving customer satisfaction and strengthening brand loyalty.

[0029] A conversation analysis system according to an embodiment includes a reception unit, a generation unit, an analysis unit, and a generation unit. The reception unit receives input from a user. The input from the user includes, but is not limited to, text input, voice input, and image input. The reception unit provides, for example, an interface for receiving the text input. The reception unit may also use a microphone or voice recognition technology to receive voice input. The reception unit may also use a camera or image analysis technology to receive image input. The generation unit uses a generation AI to analyze the question received by the reception unit and present it to the respondent. The generation AI generates a question using, for example, a text generation AI (e.g., LLM). The generation unit may also generate a question using a multimodal generation AI. The generation unit may also extract and generate important parts of a question using the generation AI. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, such as images and voice, in addition to text. The generation AI uses keyword extraction technology to extract particularly important information from the question and generates a question based on that information. The analysis unit analyzes the answer based on the question generated by the generation unit. Answer analysis includes, but is not limited to, emotion analysis, intent analysis, and content accuracy evaluation. The analysis unit analyzes the respondent's emotions using, for example, an emotion analysis algorithm. The analysis unit can also analyze the respondent's intent using intent recognition technology. The analysis unit can also use an algorithm for evaluating content accuracy. For example, an emotion analysis algorithm estimates emotions from the respondent's text or voice. Intent recognition technology is a technology for understanding the intent of the respondent's statements and uses natural language processing technology. Content accuracy evaluation is an index for evaluating the accuracy of the content of the answer, and includes, for example, fact checking and reliability evaluation. The generation unit generates follow-up questions based on the answers analyzed by the analysis unit. Generation of follow-up questions includes, but is not limited to, a question generation algorithm based on the content of the answer and adjustments based on user responses.The generation unit, for example, determines what question should be asked next based on the content of the answer. The generation unit can also adjust the content and timing of the question based on the user's reaction. The generation unit can also generate follow-up questions using a generation AI. For example, the generation unit analyzes the content of the answer and determines what question should be asked next based on the content. The generation unit monitors the user's reaction in real time and adjusts the content and timing of the question. The generation unit generates follow-up questions using a generation AI and presents them to the respondent. Thus, the conversation analysis system according to the embodiment can accept and analyze user input and generate follow-up questions, thereby understanding the respondent's thoughts and feelings from multiple perspectives. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate follow-up questions using an AI model that receives the answer analyzed by the analysis unit as input and outputs follow-up questions.

[0030] The analysis unit can analyze the respondent's emotions and intentions. The analysis unit, for example, analyzes the respondent's emotions using an emotion analysis algorithm. For example, the analysis unit infers emotions from the respondent's text or voice. The analysis unit can also analyze the respondent's intention using intent recognition technology. For example, the analysis unit uses natural language processing technology, which is technology for understanding the intention of the respondent's statements. The analysis unit can also combine emotion analysis and intent recognition to comprehensively analyze the respondent's emotions and intentions. For example, the analysis unit infers emotions from the respondent's text or voice and analyzes the intention based on the emotions. This allows deeper insights to be gained by analyzing the respondent's emotions and intentions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the respondent's text data into a generation AI and have the generation AI analyze the emotions and intentions.

[0031] The analysis unit can analyze the respondent's tone of voice and facial expression to determine the seriousness of the answer. The analysis unit can analyze the respondent's tone of voice using, for example, voice analysis technology. For example, the analysis unit can analyze the respondent's voice strength and tone changes to determine the seriousness of the answer. The analysis unit can also analyze the respondent's facial expression using facial expression recognition technology. For example, the analysis unit can analyze the respondent's facial expression changes to determine the seriousness of the answer. The analysis unit can also combine voice analysis and facial expression recognition to comprehensively determine the seriousness of the answer. For example, the analysis unit can analyze the respondent's tone of voice and facial expression changes and determine the seriousness of the answer based on the results. In this way, the seriousness of the answer can be determined by analyzing the respondent's tone of voice and facial expression. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the respondent's voice data and image data to the generation AI and have the generation AI analyze the voice tone and facial expression.

[0032] The generation unit can generate follow-up questions based on the respondent's response. The generation unit, for example, determines what question should be asked next based on the content of the response. For example, if the respondent answers, "I recently purchased a new product," the generation unit generates a follow-up question such as, "Which feature of that product do you like best?" The generation unit can also adjust the content and timing of the questions based on the user's response. For example, the generation unit monitors the respondent's response in real time and adjusts the content and timing of the questions. The generation unit can also generate follow-up questions using a generation AI. For example, the generation unit analyzes the content of the response and determines what question should be asked next based on the content. The generation unit monitors the user's response in real time and adjusts the content and timing of the questions. The generation unit uses a generation AI to generate follow-up questions and present them to the respondent. By generating follow-up questions based on the respondent's response, deeper insights can be obtained. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the respondent's response data into the generation AI and cause the generation AI to generate follow-up questions.

[0033] The reception unit can analyze the user's past question history and select the optimal reception method. The reception unit, for example, uses an algorithm for analyzing the past question history. For example, the reception unit prioritizes suggesting question formats that the user has frequently used in the past. The reception unit can also select the optimal reception method for a specific time period from the user's past question history. For example, if the user has submitted many questions during a specific time period in the past, the reception unit can suggest the optimal reception method for that time period. The reception unit can also analyze the user's past question history and suggest the most efficient reception method. For example, the reception unit analyzes the format in which the user has submitted questions in the past and selects the optimal reception method based on the format. In this way, the optimal reception method can be selected by analyzing the user's past question history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past question history data into a generation AI and cause the generation AI to select the optimal reception method.

[0034] The reception unit may filter questions based on the user's current areas of interest when receiving the questions. The reception unit may use, for example, an algorithm to identify the user's current areas of interest. For example, the reception unit may analyze the user's past search history or social media activity to identify the user's current areas of interest. The reception unit may also filter questions based on the identified areas of interest. For example, the reception unit may preferentially receive questions related to topics in which the user is currently interested. The reception unit may also filter and receive highly relevant questions based on the user's current areas of interest. For example, the reception unit may analyze the user's current areas of interest and suggest optimal questions. This allows questions to be filtered based on the user's current areas of interest, thereby receiving highly relevant questions. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit may input the user's area of ​​interest data into a generation AI and cause the generation AI to filter the questions.

[0035] When receiving a question, the reception unit can select the optimal reception means depending on the user's input method. The reception unit uses, for example, an algorithm to identify the user's input method. For example, if the user selects voice input, the reception unit can receive the question using voice recognition technology. Furthermore, if the user selects text input, the reception unit can also receive the question using text analysis technology. Furthermore, if the user selects image input, the reception unit can also receive the question using image analysis technology. For example, if the user selects voice input, the reception unit can receive the question using voice recognition technology. This allows for smooth reception of questions by selecting the optimal reception means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's input method data into a generation AI and have the generation AI select the optimal reception means.

[0036] When receiving a question, the reception unit can prioritize receiving highly relevant questions by taking into account the user's geographical location information. The reception unit uses, for example, technology for acquiring geographical location information. For example, the reception unit acquires the user's geographical location information using GPS data or an IP address. The reception unit can also prioritize receiving highly relevant questions based on the acquired geographical location information. For example, if the user is in a specific area, the reception unit prioritizes receiving questions related to that area. The reception unit can also filter and receive highly relevant questions based on the user's geographical location information. For example, the reception unit suggests optimal questions based on the user's current location. This allows highly relevant questions to be prioritized by taking the user's geographical location information into account. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's geographical location information data to a generation AI and cause the generation AI to select highly relevant questions.

[0037] The reception unit can analyze the user's social media activity when receiving a question and receive related questions. The reception unit, for example, uses an algorithm for analyzing social media activity. For example, the reception unit prioritizes receiving questions related to topics in which the user has shown interest on social media. The reception unit can also analyze the user's social media activity and filter and receive highly relevant questions. For example, the reception unit can suggest optimal questions based on the user's social media activity history. In this way, highly relevant questions can be received by analyzing the user's social media activity. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's social media activity data into a generation AI and cause the generation AI to select related questions.

[0038] When receiving a question, the reception unit can customize the reception method by reflecting the user's past feedback. The reception unit uses, for example, an algorithm for reflecting past feedback. For example, the reception unit proposes an optimal reception method based on feedback provided by the user in the past. The reception unit can also customize the question reception method by reflecting the user's past feedback. For example, the reception unit analyzes the user's feedback history and proposes the most efficient reception method. In this way, the optimal reception method can be proposed by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's feedback data into a generation AI and have the generation AI customize the reception method.

[0039] When generating a question, the generation unit can adjust the level of detail of the question based on the importance of the respondent. The generation unit uses, for example, an algorithm for evaluating the importance of the respondent. For example, the generation unit evaluates the importance based on the respondent's job title or level of expertise. The generation unit can also adjust the level of detail of the question based on the evaluated importance. For example, the generation unit generates detailed questions for important respondents. The generation unit can also generate simple questions for general respondents. The generation unit can also dynamically adjust the level of detail of the question according to the importance of the respondent. In this way, by adjusting the level of detail of the question based on the importance of the respondent, more appropriate questions can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the importance data of the respondent to the generation AI and cause the generation AI to adjust the level of detail of the question.

[0040] When generating questions, the generation unit can apply different question algorithms depending on the category of the respondent. The generation unit uses, for example, an algorithm for identifying the category of the respondent. For example, the generation unit identifies categories such as the respondent's industry, occupation, or years of experience. The generation unit can also apply different question algorithms depending on the identified category. For example, the generation unit applies a specialized question algorithm to experts. The generation unit can also apply a general question algorithm to general users. The generation unit can also select an optimal question algorithm depending on the category of the respondent. In this way, by applying different question algorithms depending on the category of the respondent, more appropriate questions can be generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input respondent category data into the generation AI and cause the generation AI to apply a question algorithm.

[0041] When generating a question, the generation unit can improve the accuracy of the question by referring to the user's past question results. The generation unit, for example, uses an algorithm for analyzing past question results. For example, the generation unit analyzes the user's past question results and generates an optimal question. The generation unit can also improve the accuracy of the question based on the user's past question results. For example, the generation unit generates a more specific question by referring to the user's past question results. In this way, the accuracy of the question can be improved by referring to the user's past question results. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's past question result data into the generation AI and cause the generation AI to improve the accuracy of the question.

[0042] When generating questions, the generation unit can determine the priority of questions based on the time of submission by the respondent. The generation unit uses, for example, an algorithm for evaluating the time of submission. For example, if the respondent submits a question early, the generation unit can prioritize generating a question. Also, if the respondent submits a question late, the generation unit can generate a question later. The generation unit can also dynamically adjust the priority of questions based on the time of submission by the respondent. In this way, more appropriate questions can be generated by determining the priority of questions based on the time of submission by the respondent. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the time of submission by the respondent to the generation AI and have the generation AI determine the priority of questions.

[0043] The generation unit can adjust the order of questions based on the relevance of the respondent when generating questions. The generation unit, for example, uses an algorithm for evaluating the relevance of the respondent. For example, the generation unit evaluates the relevance based on the expertise of the respondent and the quality of the answer. The generation unit can also adjust the order of questions based on the evaluated relevance. For example, the generation unit can generate questions for important respondents first. The generation unit can also generate questions for general respondents later. The generation unit can also dynamically adjust the order of questions based on the relevance of the respondent. In this way, more appropriate questions can be generated by adjusting the order of questions based on the relevance of the respondent. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input relevance data of the respondent to the generation AI and cause the generation AI to adjust the order of questions.

[0044] When generating a question, the generation unit can adjust the use of technical terms in the question according to the user's level of expertise. The generation unit, for example, uses an algorithm for assessing the user's level of expertise. For example, the generation unit assesses the user's level of expertise, such as beginner, intermediate, or expert. The generation unit can also adjust the use of technical terms in the question based on the assessed level of expertise. For example, the generation unit can generate questions that use a lot of technical terms for experts. The generation unit can also generate questions that avoid technical terms for general users. The generation unit can also dynamically adjust the use of technical terms in the question according to the user's level of expertise. This allows for the generation of more appropriate questions by adjusting the use of technical terms in the question according to the user's level of expertise. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms in the question.

[0045] When analyzing responses, the analysis unit can perform the analysis taking into account the respondent's attribute information. The analysis unit, for example, uses an algorithm for acquiring the respondent's attribute information. For example, the analysis unit performs the analysis taking into account the respondent's age and gender. The analysis unit can also perform the analysis taking into account the respondent's occupation and interests. The analysis unit can also select the optimal analysis method based on the respondent's attribute information. For example, the analysis unit performs the analysis based on the respondent's age and gender. This allows for more appropriate analysis by taking into account the respondent's attribute information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the respondent's attribute information data into the generation AI and have the generation AI perform the analysis.

[0046] When analyzing responses, the analysis unit can weight the analysis based on the frequency of submission by the respondent. The analysis unit uses, for example, an algorithm for evaluating the frequency of submission. For example, if the respondent frequently submits responses, the analysis unit can weight the responses higher. Also, if the respondent rarely submits responses, the analysis unit can weight the responses lower. The analysis unit can also dynamically adjust the weight of the analysis based on the frequency of submission by the respondent. This allows for more appropriate analysis by weighting the analysis based on the frequency of submission by the respondent. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the respondent's submission frequency data into the generation AI and have the generation AI perform the weighting of the analysis.

[0047] The analysis unit can take into account the geographical distribution of respondents when analyzing responses. The analysis unit uses, for example, an algorithm for evaluating the geographical distribution. For example, the analysis unit analyzes trends by region based on the geographical distribution of respondents. The analysis unit can also perform region-specific analysis by taking into account the geographical distribution of respondents. The analysis unit can also select an optimal analysis method based on the geographical distribution of respondents. This makes it possible to analyze trends by region by taking into account the geographical distribution of respondents. Some or all of the above-mentioned processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input geographical distribution data of respondents to a generation AI and have the generation AI perform the analysis.

[0048] When analyzing responses, the analysis unit can improve the accuracy of the analysis by referring to the respondent's related literature. The analysis unit, for example, uses an algorithm for referring to the related literature. For example, the analysis unit can improve the accuracy of the analysis by referring to the respondent's related literature. The analysis unit can also select an optimal analysis method based on the respondent's related literature. The analysis unit can also perform a more specific analysis by referring to the respondent's related literature. In this way, by referring to the respondent's related literature, the accuracy of the analysis can be improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the respondent's related literature data into a generation AI and have the generation AI perform the analysis.

[0049] The analysis unit can take into account the market value of the respondent when analyzing the responses. The analysis unit uses, for example, an algorithm for assessing market value. For example, the analysis unit assesses market value based on the respondent's reputation in the industry or economic influence. The analysis unit can also weight the analysis based on the assessed market value. For example, the analysis unit weights the analysis based on the respondent's market value. The analysis unit can also select an optimal analysis method taking into account the respondent's market value. The analysis unit can also adjust the display method of the analysis results based on the respondent's market value. This allows for more appropriate analysis by taking into account the respondent's market value. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the respondent's market value data into a generation AI and have the generation AI perform the analysis.

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

[0051] The analysis unit can estimate the knowledge level of the respondent based on the content of the respondent's answer and adjust the difficulty level of the next question based on the estimated knowledge level. For example, if the respondent uses a lot of technical terms, the analysis unit can estimate that the respondent's knowledge level is high and increase the difficulty level of the next question. Also, if the respondent uses basic terms, the analysis unit can estimate that the respondent's knowledge level is low and decrease the difficulty level of the next question. Furthermore, the analysis unit can narrow the content of the question to specialized topics based on the respondent's knowledge level. This makes it possible to generate appropriate questions according to the respondent's knowledge level.

[0052] The generation unit can estimate the respondent's interests based on the content of the respondent's answers and adjust the topic of the next question based on the estimated interests. For example, if the respondent provides a detailed answer about a particular topic, the generation unit can estimate that the respondent has a high interest in that topic and set the next question to be related to the same topic. Furthermore, if the respondent is interested in multiple topics, the generation unit can generate questions related to each topic in a balanced manner. Furthermore, the generation unit can customize the content of the questions based on the respondent's interests. This makes it possible to generate appropriate questions that match the respondent's interests.

[0053] The generation unit can evaluate the consistency of the respondent's answer based on the content of the respondent's answer, and generate additional confirmation questions if the consistency is low. For example, if the respondent's answer is inconsistent between contexts, the generation unit can generate confirmation questions to resolve the inconsistency. Furthermore, if the respondent's answer is ambiguous, the generation unit can generate specific questions to resolve the ambiguity. Furthermore, the generation unit can adjust the content of the next question based on the consistency of the respondent's answer. This makes it possible to generate appropriate questions to increase the consistency of the respondent's answer.

[0054] The generation unit evaluates the level of detail of the respondent's answer based on the content of the respondent's answer, and can generate additional detailed questions if the level of detail is low. For example, if the respondent only gives a simple answer, the generation unit can generate detailed questions to dig deeper into the answer. Also, if the respondent gives a detailed answer, the generation unit can generate questions to dig deeper into the details. Furthermore, the generation unit can adjust the content of the next question based on the level of detail of the respondent's answer. This makes it possible to generate appropriate questions according to the level of detail of the respondent's answer.

[0055] The analysis unit can evaluate the reliability of the respondent's answer based on the content of the respondent's answer, and generate additional confirmation questions if the reliability is low. For example, if the respondent's answer contradicts common knowledge, the analysis unit can generate confirmation questions to resolve the contradiction. Furthermore, if the respondent's answer is unclear, the analysis unit can generate specific questions to resolve the ambiguity. Furthermore, the analysis unit can adjust the content of the next question based on the reliability of the respondent's answer. This makes it possible to generate appropriate questions to increase the reliability of the respondent's answer.

[0056] The analysis unit can evaluate the consistency of the respondent's answer based on the content of the respondent's answer, and generate additional confirmation questions if the consistency is low. For example, if the respondent's answer is inconsistent between the previous and next answers, the analysis unit can generate confirmation questions to resolve the inconsistency. Furthermore, if the respondent's answer is ambiguous, the analysis unit can generate specific questions to resolve the ambiguity. Furthermore, the analysis unit can adjust the content of the next question based on the consistency of the respondent's answer. This makes it possible to generate appropriate questions to increase the consistency of the respondent's answer.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The reception unit receives input from the user. The input from the user includes text input, voice input, image input, etc. For example, an interface for receiving text input, a microphone and voice recognition technology for receiving voice input, and a camera and image analysis technology for receiving image input can be used. Step 2: The generation unit analyzes the questions received by the reception unit and presents them to the respondent. The generation AI generates questions, for example, using text generation AI (LLM) or multimodal generation AI. The generation AI extracts and generates important parts of the questions using keyword extraction technology. Step 3: The analysis unit analyzes the answers based on the questions generated by the generation unit. The analysis includes sentiment analysis, intent analysis, and content accuracy evaluation. For example, sentiment analysis algorithms, intent recognition technology, and content accuracy evaluation algorithms are used. Step 4: The generator generates follow-up questions based on the answers analyzed by the analyzer. The generator adjusts the question generation algorithm based on the content of the answers and the user's reactions, and generates follow-up questions using the generation AI.

[0059] (Example 2) A system according to an embodiment of the present invention utilizes generative AI to understand respondents' thoughts from multiple perspectives through conversations with them. This system accepts user input, and the generative AI generates questions and presents them to the respondent. When the respondent answers a question, the AI ​​analyzes the answer and determines the next question to ask. By repeating this process, the AI ​​can gain a deeper understanding of the respondent's thoughts and feelings. For example, when a user inputs a question such as "Tell me about your recent experience," the generative AI analyzes the question and presents it to the respondent. If the respondent answers, "I recently purchased a new product," the AI ​​may ask a follow-up question such as, "Which feature of that product did you like most?" This approach can reveal the respondent's true needs and feelings. Furthermore, the AI ​​can more accurately capture the respondent's emotions and intentions. For example, by analyzing the respondent's tone of voice and facial expression when answering, "I liked the design of that product most," it can determine the sincerity of the answer. This is expected to improve the quality and accuracy of market research. This allows the system to provide deeper insights not possible with conventional surveys and reveal the respondent's true needs. For example, this will enable more accurate information-based decision-making when developing new products or formulating marketing strategies. It is also expected that more accurate understanding of respondents' emotions and intentions will contribute to improving customer satisfaction and strengthening brand loyalty.

[0060] A conversation analysis system according to an embodiment includes a reception unit, a generation unit, an analysis unit, and a generation unit. The reception unit receives input from a user. The input from the user includes, but is not limited to, text input, voice input, and image input. The reception unit provides, for example, an interface for receiving the text input. The reception unit may also use a microphone or voice recognition technology to receive voice input. The reception unit may also use a camera or image analysis technology to receive image input. The generation unit uses a generation AI to analyze the question received by the reception unit and present it to the respondent. The generation AI generates a question using, for example, a text generation AI (e.g., LLM). The generation unit may also generate a question using a multimodal generation AI. The generation unit may also extract and generate important parts of a question using the generation AI. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, such as images and voice, in addition to text. The generation AI uses keyword extraction technology to extract particularly important information from the question and generates a question based on that information. The analysis unit analyzes the answer based on the question generated by the generation unit. Answer analysis includes, but is not limited to, emotion analysis, intent analysis, and content accuracy evaluation. The analysis unit analyzes the respondent's emotions using, for example, an emotion analysis algorithm. The analysis unit can also analyze the respondent's intent using intent recognition technology. The analysis unit can also use an algorithm for evaluating content accuracy. For example, an emotion analysis algorithm estimates emotions from the respondent's text or voice. Intent recognition technology is a technology for understanding the intent of the respondent's statements and uses natural language processing technology. Content accuracy evaluation is an index for evaluating the accuracy of the content of the answer, and includes, for example, fact checking and reliability evaluation. The generation unit generates follow-up questions based on the answers analyzed by the analysis unit. Generation of follow-up questions includes, but is not limited to, a question generation algorithm based on the content of the answer and adjustments based on user responses.The generation unit, for example, determines what question should be asked next based on the content of the answer. The generation unit can also adjust the content and timing of the question based on the user's reaction. The generation unit can also generate follow-up questions using a generation AI. For example, the generation unit analyzes the content of the answer and determines what question should be asked next based on the content. The generation unit monitors the user's reaction in real time and adjusts the content and timing of the question. The generation unit generates follow-up questions using a generation AI and presents them to the respondent. Thus, the conversation analysis system according to the embodiment can accept and analyze user input and generate follow-up questions, thereby understanding the respondent's thoughts and feelings from multiple perspectives. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate follow-up questions using an AI model that receives the answer analyzed by the analysis unit as input and outputs follow-up questions.

[0061] The analysis unit can analyze the respondent's emotions and intentions. The analysis unit, for example, analyzes the respondent's emotions using an emotion analysis algorithm. For example, the analysis unit infers emotions from the respondent's text or voice. The analysis unit can also analyze the respondent's intention using intent recognition technology. For example, the analysis unit uses natural language processing technology, which is technology for understanding the intention of the respondent's statements. The analysis unit can also combine emotion analysis and intent recognition to comprehensively analyze the respondent's emotions and intentions. For example, the analysis unit infers emotions from the respondent's text or voice and analyzes the intention based on the emotions. This allows deeper insights to be gained by analyzing the respondent's emotions and intentions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the respondent's text data into a generation AI and have the generation AI analyze the emotions and intentions.

[0062] The analysis unit can analyze the respondent's tone of voice and facial expression to determine the seriousness of the answer. The analysis unit can analyze the respondent's tone of voice using, for example, voice analysis technology. For example, the analysis unit can analyze the respondent's voice strength and tone changes to determine the seriousness of the answer. The analysis unit can also analyze the respondent's facial expression using facial expression recognition technology. For example, the analysis unit can analyze the respondent's facial expression changes to determine the seriousness of the answer. The analysis unit can also combine voice analysis and facial expression recognition to comprehensively determine the seriousness of the answer. For example, the analysis unit can analyze the respondent's tone of voice and facial expression changes and determine the seriousness of the answer based on the results. In this way, the seriousness of the answer can be determined by analyzing the respondent's tone of voice and facial expression. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the respondent's voice data and image data to the generation AI and have the generation AI analyze the voice tone and facial expression.

[0063] The generation unit can generate follow-up questions based on the respondent's response. The generation unit, for example, determines what question should be asked next based on the content of the response. For example, if the respondent answers, "I recently purchased a new product," the generation unit generates a follow-up question such as, "Which feature of that product do you like best?" The generation unit can also adjust the content and timing of the questions based on the user's response. For example, the generation unit monitors the respondent's response in real time and adjusts the content and timing of the questions. The generation unit can also generate follow-up questions using a generation AI. For example, the generation unit analyzes the content of the response and determines what question should be asked next based on the content. The generation unit monitors the user's response in real time and adjusts the content and timing of the questions. The generation unit uses a generation AI to generate follow-up questions and present them to the respondent. By generating follow-up questions based on the respondent's response, deeper insights can be obtained. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the respondent's response data into the generation AI and cause the generation AI to generate follow-up questions.

[0064] The reception unit can estimate the user's emotions and adjust the timing of question acceptance based on the estimated user emotions. The reception unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, the reception unit estimates the user's emotions from the user's facial expressions and voice. The reception unit can also adjust the timing of question acceptance based on the estimated user emotions. For example, if the user is stressed, the reception unit can delay the timing of question acceptance to accept the question in a relaxed state. If the user is relaxed, the reception unit can accelerate the timing of question acceptance to accept the question smoothly. If the user is in a hurry, the reception unit can immediately accept the question to accept the question quickly. In this way, by adjusting the timing of question acceptance based on the user's emotions, questions can be accepted at a more appropriate time. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input the user's facial expression data and voice data to the generation AI and cause the generation AI to estimate the user's emotions.

[0065] The reception unit can analyze the user's past question history and select the optimal reception method. The reception unit, for example, uses an algorithm for analyzing the past question history. For example, the reception unit prioritizes suggesting question formats that the user has frequently used in the past. The reception unit can also select the optimal reception method for a specific time period from the user's past question history. For example, if the user has submitted many questions during a specific time period in the past, the reception unit can suggest the optimal reception method for that time period. The reception unit can also analyze the user's past question history and suggest the most efficient reception method. For example, the reception unit analyzes the format in which the user has submitted questions in the past and selects the optimal reception method based on the format. In this way, the optimal reception method can be selected by analyzing the user's past question history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past question history data into a generation AI and cause the generation AI to select the optimal reception method.

[0066] The reception unit may filter questions based on the user's current areas of interest when receiving the questions. The reception unit may use, for example, an algorithm to identify the user's current areas of interest. For example, the reception unit may analyze the user's past search history or social media activity to identify the user's current areas of interest. The reception unit may also filter questions based on the identified areas of interest. For example, the reception unit may preferentially receive questions related to topics in which the user is currently interested. The reception unit may also filter and receive highly relevant questions based on the user's current areas of interest. For example, the reception unit may analyze the user's current areas of interest and suggest optimal questions. This allows questions to be filtered based on the user's current areas of interest, thereby receiving highly relevant questions. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit may input the user's area of ​​interest data into a generation AI and cause the generation AI to filter the questions.

[0067] When receiving a question, the reception unit can select the optimal reception means depending on the user's input method. The reception unit uses, for example, an algorithm to identify the user's input method. For example, if the user selects voice input, the reception unit can receive the question using voice recognition technology. Furthermore, if the user selects text input, the reception unit can also receive the question using text analysis technology. Furthermore, if the user selects image input, the reception unit can also receive the question using image analysis technology. For example, if the user selects voice input, the reception unit can receive the question using voice recognition technology. This allows for smooth reception of questions by selecting the optimal reception means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's input method data into a generation AI and have the generation AI select the optimal reception means.

[0068] The reception unit can estimate the user's emotions and determine the priority of questions to be received based on the estimated user emotions. The reception unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, the reception unit estimates the user's emotions from the user's facial expressions and voice. The reception unit can also determine the priority of questions to be received based on the estimated user emotions. For example, when the user is stressed, the reception unit postpones questions of low importance. When the user is relaxed, the reception unit can also prioritize questions of high importance. When the user is in a hurry, the reception unit can also prioritize questions that require a quick answer. In this way, by determining the priority of questions based on the user's emotions, important questions can be received preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's facial expression data and voice data into the generation AI and have the generation AI estimate emotions.

[0069] When receiving a question, the reception unit can prioritize receiving highly relevant questions by taking into account the user's geographical location information. The reception unit uses, for example, technology for acquiring geographical location information. For example, the reception unit acquires the user's geographical location information using GPS data or an IP address. The reception unit can also prioritize receiving highly relevant questions based on the acquired geographical location information. For example, if the user is in a specific area, the reception unit prioritizes receiving questions related to that area. The reception unit can also filter and receive highly relevant questions based on the user's geographical location information. For example, the reception unit suggests optimal questions based on the user's current location. This allows highly relevant questions to be prioritized by taking the user's geographical location information into account. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's geographical location information data to a generation AI and cause the generation AI to select highly relevant questions.

[0070] The reception unit can analyze the user's social media activity when receiving a question and receive related questions. The reception unit, for example, uses an algorithm for analyzing social media activity. For example, the reception unit prioritizes receiving questions related to topics in which the user has shown interest on social media. The reception unit can also analyze the user's social media activity and filter and receive highly relevant questions. For example, the reception unit can suggest optimal questions based on the user's social media activity history. In this way, highly relevant questions can be received by analyzing the user's social media activity. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's social media activity data into a generation AI and cause the generation AI to select related questions.

[0071] When receiving a question, the reception unit can customize the reception method by reflecting the user's past feedback. The reception unit uses, for example, an algorithm for reflecting past feedback. For example, the reception unit proposes an optimal reception method based on feedback provided by the user in the past. The reception unit can also customize the question reception method by reflecting the user's past feedback. For example, the reception unit analyzes the user's feedback history and proposes the most efficient reception method. In this way, the optimal reception method can be proposed by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's feedback data into a generation AI and have the generation AI customize the reception method.

[0072] The generation unit can estimate the user's emotion and adjust the way the question is phrased based on the estimated user's emotion. The generation unit estimates the user's emotion using, for example, an emotion analysis algorithm. For example, the generation unit estimates the emotion from the user's facial expression or voice. The generation unit can also adjust the way the question is phrased based on the estimated user's emotion. For example, the generation unit can generate a question using soft language when the user is relaxed. The generation unit can also generate a question using simple and clear language when the user is stressed. The generation unit can also generate a question using visually stimulating language when the user is excited. This allows for the generation of more appropriate questions by adjusting the way the question is phrased based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's facial expression data and voice data into the generation AI and have the generation AI adjust the way the question is expressed.

[0073] When generating a question, the generation unit can adjust the level of detail of the question based on the importance of the respondent. The generation unit uses, for example, an algorithm for evaluating the importance of the respondent. For example, the generation unit evaluates the importance based on the respondent's job title or level of expertise. The generation unit can also adjust the level of detail of the question based on the evaluated importance. For example, the generation unit generates detailed questions for important respondents. The generation unit can also generate simple questions for general respondents. The generation unit can also dynamically adjust the level of detail of the question according to the importance of the respondent. In this way, by adjusting the level of detail of the question based on the importance of the respondent, more appropriate questions can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the importance data of the respondent to the generation AI and cause the generation AI to adjust the level of detail of the question.

[0074] When generating questions, the generation unit can apply different question algorithms depending on the category of the respondent. The generation unit uses, for example, an algorithm for identifying the category of the respondent. For example, the generation unit identifies categories such as the respondent's industry, occupation, or years of experience. The generation unit can also apply different question algorithms depending on the identified category. For example, the generation unit applies a specialized question algorithm to experts. The generation unit can also apply a general question algorithm to general users. The generation unit can also select an optimal question algorithm depending on the category of the respondent. In this way, by applying different question algorithms depending on the category of the respondent, more appropriate questions can be generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input respondent category data into the generation AI and cause the generation AI to apply a question algorithm.

[0075] When generating a question, the generation unit can improve the accuracy of the question by referring to the user's past question results. The generation unit, for example, uses an algorithm for analyzing past question results. For example, the generation unit analyzes the user's past question results and generates an optimal question. The generation unit can also improve the accuracy of the question based on the user's past question results. For example, the generation unit generates a more specific question by referring to the user's past question results. In this way, the accuracy of the question can be improved by referring to the user's past question results. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's past question result data into the generation AI and cause the generation AI to improve the accuracy of the question.

[0076] The generation unit can estimate the user's emotion and adjust the length of the question based on the estimated user's emotion. The generation unit estimates the user's emotion using, for example, an emotion analysis algorithm. For example, the generation unit estimates the emotion from the user's facial expression or voice. The generation unit can also adjust the length of the question based on the estimated user's emotion. For example, the generation unit can generate a short, to-the-point question when the user is in a hurry. The generation unit can also generate a longer question with detailed explanations when the user is relaxed. The generation unit can also generate a question with a visually stimulating effect when the user is excited. This allows for the generation of more appropriate questions by adjusting the length of the question based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's facial expression data and voice data into the generation AI and have the generation AI adjust the length of the question.

[0077] When generating questions, the generation unit can determine the priority of questions based on the time of submission by the respondent. The generation unit uses, for example, an algorithm for evaluating the time of submission. For example, if the respondent submits a question early, the generation unit can prioritize generating a question. Also, if the respondent submits a question late, the generation unit can generate a question later. The generation unit can also dynamically adjust the priority of questions based on the time of submission by the respondent. In this way, more appropriate questions can be generated by determining the priority of questions based on the time of submission by the respondent. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the time of submission by the respondent to the generation AI and have the generation AI determine the priority of questions.

[0078] The generation unit can adjust the order of questions based on the relevance of the respondent when generating questions. The generation unit, for example, uses an algorithm for evaluating the relevance of the respondent. For example, the generation unit evaluates the relevance based on the expertise of the respondent and the quality of the answer. The generation unit can also adjust the order of questions based on the evaluated relevance. For example, the generation unit can generate questions for important respondents first. The generation unit can also generate questions for general respondents later. The generation unit can also dynamically adjust the order of questions based on the relevance of the respondent. In this way, more appropriate questions can be generated by adjusting the order of questions based on the relevance of the respondent. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input relevance data of the respondent to the generation AI and cause the generation AI to adjust the order of questions.

[0079] When generating a question, the generation unit can adjust the use of technical terms in the question according to the user's level of expertise. The generation unit, for example, uses an algorithm for assessing the user's level of expertise. For example, the generation unit assesses the user's level of expertise, such as beginner, intermediate, or expert. The generation unit can also adjust the use of technical terms in the question based on the assessed level of expertise. For example, the generation unit can generate questions that use a lot of technical terms for experts. The generation unit can also generate questions that avoid technical terms for general users. The generation unit can also dynamically adjust the use of technical terms in the question according to the user's level of expertise. This allows for the generation of more appropriate questions by adjusting the use of technical terms in the question according to the user's level of expertise. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms in the question.

[0080] The analysis unit can estimate the user's emotions and adjust the answer analysis method based on the estimated user emotions. The analysis unit, for example, estimates the user's emotions using an emotion analysis algorithm. For example, the analysis unit estimates emotions from the user's facial expressions and voice. The analysis unit can also adjust the answer analysis method based on the estimated user emotions. For example, the analysis unit performs a detailed analysis when the user is relaxed. The analysis unit can also perform a simple analysis when the user is stressed. The analysis unit can also perform an analysis that adds visually stimulating effects when the user is excited. This allows for more appropriate analysis by adjusting the answer analysis method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's facial expression data and voice data into the generation AI and have the generation AI adjust the method of analyzing the answers.

[0081] When analyzing responses, the analysis unit can perform the analysis taking into account the respondent's attribute information. The analysis unit, for example, uses an algorithm for acquiring the respondent's attribute information. For example, the analysis unit performs the analysis taking into account the respondent's age and gender. The analysis unit can also perform the analysis taking into account the respondent's occupation and interests. The analysis unit can also select the optimal analysis method based on the respondent's attribute information. For example, the analysis unit performs the analysis based on the respondent's age and gender. This allows for more appropriate analysis by taking into account the respondent's attribute information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the respondent's attribute information data into the generation AI and have the generation AI perform the analysis.

[0082] When analyzing responses, the analysis unit can weight the analysis based on the frequency of submission by the respondent. The analysis unit uses, for example, an algorithm for evaluating the frequency of submission. For example, if the respondent frequently submits responses, the analysis unit can weight the responses higher. Also, if the respondent rarely submits responses, the analysis unit can weight the responses lower. The analysis unit can also dynamically adjust the weight of the analysis based on the frequency of submission by the respondent. This allows for more appropriate analysis by weighting the analysis based on the frequency of submission by the respondent. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the respondent's submission frequency data into the generation AI and have the generation AI perform the weighting of the analysis.

[0083] The analysis unit can estimate the user's emotion and adjust the display method of the analysis results based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion using an emotion analysis algorithm. For example, the analysis unit estimates the emotion from the user's facial expression or voice. The analysis unit can also adjust the display method of the analysis results based on the estimated user's emotion. For example, the analysis unit can display detailed analysis results when the user is relaxed. The analysis unit can also display simple analysis results when the user is stressed. The analysis unit can also display analysis results with visually stimulating effects when the user is excited. In this way, by adjusting the display method of the analysis results based on the user's emotion, more appropriate analysis results can be displayed. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's facial expression data and voice data into the generation AI and have the generation AI adjust the way the analysis results are displayed.

[0084] The analysis unit can take into account the geographical distribution of respondents when analyzing responses. The analysis unit uses, for example, an algorithm for evaluating the geographical distribution. For example, the analysis unit analyzes trends by region based on the geographical distribution of respondents. The analysis unit can also perform region-specific analysis by taking into account the geographical distribution of respondents. The analysis unit can also select an optimal analysis method based on the geographical distribution of respondents. This makes it possible to analyze trends by region by taking into account the geographical distribution of respondents. Some or all of the above-mentioned processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input geographical distribution data of respondents to a generation AI and have the generation AI perform the analysis.

[0085] When analyzing responses, the analysis unit can improve the accuracy of the analysis by referring to the respondent's related literature. The analysis unit, for example, uses an algorithm for referring to the related literature. For example, the analysis unit can improve the accuracy of the analysis by referring to the respondent's related literature. The analysis unit can also select an optimal analysis method based on the respondent's related literature. The analysis unit can also perform a more specific analysis by referring to the respondent's related literature. In this way, by referring to the respondent's related literature, the accuracy of the analysis can be improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the respondent's related literature data into a generation AI and have the generation AI perform the analysis.

[0086] The analysis unit can take into account the market value of the respondent when analyzing the responses. The analysis unit uses, for example, an algorithm for assessing market value. For example, the analysis unit assesses market value based on the respondent's reputation in the industry or economic influence. The analysis unit can also weight the analysis based on the assessed market value. For example, the analysis unit weights the analysis based on the respondent's market value. The analysis unit can also select an optimal analysis method taking into account the respondent's market value. The analysis unit can also adjust the display method of the analysis results based on the respondent's market value. This allows for more appropriate analysis by taking into account the respondent's market value. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the respondent's market value data into a generation AI and have the generation AI perform the analysis. === Hard Collateral 1-1 === Each of the above-described reception unit, generation unit, analysis unit, and multiple elements including the generation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit receives input from a user using a touch panel 38A or a microphone 38B of the smart device 14. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a question using a generation AI. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the answer. The generation unit generates a follow-up question based on the answer analyzed by the analysis unit. === Hard Collateral 1-2 === Each of the above-described elements including the reception unit, generation unit, analysis unit, and generation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit receives voice input from a user using the microphone 238 of the smart glasses 214. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates questions using a generation AI. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes answers. The generation unit generates follow-up questions based on the answers analyzed by the analysis unit. === Hard Collateral 1-3 === Each of the above-described multiple elements including the reception unit, generation unit, analysis unit, and generation unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit receives voice input from the user using the microphone 238 of the headset-type terminal 314. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates questions using a generation AI. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes answers. The generation unit generates follow-up questions based on the answers analyzed by the analysis unit. === Hard Collateral 1-4 === Each of the above-described multiple elements including the reception unit, generation unit, analysis unit, and generation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit receives voice input from a user using the microphone 238 of the robot 414. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates questions using a generation AI. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes answers. The generation unit generates follow-up questions based on the answers analyzed by the analysis unit.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] The analysis unit can estimate the knowledge level of the respondent based on the content of the respondent's answer and adjust the difficulty level of the next question based on the estimated knowledge level. For example, if the respondent uses a lot of technical terms, the analysis unit can estimate that the respondent's knowledge level is high and increase the difficulty level of the next question. Also, if the respondent uses basic terms, the analysis unit can estimate that the respondent's knowledge level is low and decrease the difficulty level of the next question. Furthermore, the analysis unit can narrow the content of the question to specialized topics based on the respondent's knowledge level. This makes it possible to generate appropriate questions according to the respondent's knowledge level.

[0089] The generation unit can estimate the respondent's interests based on the content of the respondent's answers and adjust the topic of the next question based on the estimated interests. For example, if the respondent provides a detailed answer about a particular topic, the generation unit can estimate that the respondent has a high interest in that topic and set the next question to be related to the same topic. Furthermore, if the respondent is interested in multiple topics, the generation unit can generate questions related to each topic in a balanced manner. Furthermore, the generation unit can customize the content of the questions based on the respondent's interests. This makes it possible to generate appropriate questions that match the respondent's interests.

[0090] The analysis unit can estimate the stress level of the respondent based on the content of the respondent's answer and adjust the format of the next question based on the estimated stress level. For example, if the analysis unit estimates that the respondent is feeling stressed, it can make the next question a simple multiple-choice question. Alternatively, if the analysis unit estimates that the respondent is relaxed, it can make the next question a detailed descriptive question. Furthermore, the analysis unit can adjust the timing of the question based on the respondent's stress level. This makes it possible to generate appropriate questions according to the respondent's stress level.

[0091] The generation unit can evaluate the consistency of the respondent's answer based on the content of the respondent's answer, and generate additional confirmation questions if the consistency is low. For example, if the respondent's answer is inconsistent between contexts, the generation unit can generate confirmation questions to resolve the inconsistency. Furthermore, if the respondent's answer is ambiguous, the generation unit can generate specific questions to resolve the ambiguity. Furthermore, the generation unit can adjust the content of the next question based on the consistency of the respondent's answer. This makes it possible to generate appropriate questions to increase the consistency of the respondent's answer.

[0092] The analysis unit can track changes in the respondent's emotions based on the content of the respondent's answers and adjust the content of the next question based on those changes. For example, if the analysis unit estimates that the respondent was initially relaxed but gradually began to feel stressed, it can change the next question to one that will relax the respondent. Also, if the analysis unit estimates that the respondent is excited, it can generate stimulating questions to maintain that excitement. Furthermore, the analysis unit can adjust the timing of questions based on changes in the respondent's emotions. This makes it possible to generate appropriate questions that correspond to changes in the respondent's emotions.

[0093] The generation unit evaluates the level of detail of the respondent's answer based on the content of the respondent's answer, and can generate additional detailed questions if the level of detail is low. For example, if the respondent only gives a simple answer, the generation unit can generate detailed questions to dig deeper into the answer. Also, if the respondent gives a detailed answer, the generation unit can generate questions to dig deeper into the details. Furthermore, the generation unit can adjust the content of the next question based on the level of detail of the respondent's answer. This makes it possible to generate appropriate questions according to the level of detail of the respondent's answer.

[0094] The analysis unit can evaluate the reliability of the respondent's answer based on the content of the respondent's answer, and generate additional confirmation questions if the reliability is low. For example, if the respondent's answer contradicts common knowledge, the analysis unit can generate confirmation questions to resolve the contradiction. Furthermore, if the respondent's answer is unclear, the analysis unit can generate specific questions to resolve the ambiguity. Furthermore, the analysis unit can adjust the content of the next question based on the reliability of the respondent's answer. This makes it possible to generate appropriate questions to increase the reliability of the respondent's answer.

[0095] The generation unit can evaluate the emotional tone of the respondent's answer based on the content of the respondent's answer, and adjust the way the next question is phrased based on the tone. For example, if the respondent answers in a positive tone, the generation unit can generate the next question with positive wording to maintain that tone. Also, if the respondent answers in a negative tone, the generation unit can generate the next question with gentle wording to tone down the tone. Furthermore, the generation unit can adjust the content of the question based on the respondent's emotional tone. This makes it possible to generate an appropriate question according to the respondent's emotional tone.

[0096] The analysis unit can evaluate the consistency of the respondent's answer based on the content of the respondent's answer, and generate additional confirmation questions if the consistency is low. For example, if the respondent's answer is inconsistent between the previous and next answers, the analysis unit can generate confirmation questions to resolve the inconsistency. Furthermore, if the respondent's answer is ambiguous, the analysis unit can generate specific questions to resolve the ambiguity. Furthermore, the analysis unit can adjust the content of the next question based on the consistency of the respondent's answer. This makes it possible to generate appropriate questions to increase the consistency of the respondent's answer.

[0097] The generation unit can evaluate the emotional tone of the respondent's answer based on the content of the respondent's answer, and adjust the way the next question is phrased based on the tone. For example, if the respondent answers in a positive tone, the generation unit can generate the next question with positive wording to maintain that tone. Also, if the respondent answers in a negative tone, the generation unit can generate the next question with gentle wording to tone down the tone. Furthermore, the generation unit can adjust the content of the question based on the respondent's emotional tone. This makes it possible to generate an appropriate question according to the respondent's emotional tone.

[0098] The processing flow of the second embodiment will be briefly explained below.

[0099] Step 1: The reception unit receives input from the user. The input from the user includes text input, voice input, image input, etc. For example, an interface for receiving text input, a microphone and voice recognition technology for receiving voice input, and a camera and image analysis technology for receiving image input can be used. Step 2: The generation unit analyzes the questions received by the reception unit and presents them to the respondent. The generation AI generates questions, for example, using text generation AI (LLM) or multimodal generation AI. The generation AI extracts and generates important parts of the questions using keyword extraction technology. Step 3: The analysis unit analyzes the answers based on the questions generated by the generation unit. The analysis includes sentiment analysis, intent analysis, and content accuracy evaluation. For example, sentiment analysis algorithms, intent recognition technology, and content accuracy evaluation algorithms are used. Step 4: The generator generates follow-up questions based on the answers analyzed by the analyzer. The generator adjusts the question generation algorithm based on the content of the answers and the user's reactions, and generates follow-up questions using the generation AI.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0104] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0105] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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).

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

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

[0137] 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.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the robot 414, the 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.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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."

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] [Explanation of symbols]

[0172] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives input from a user; a generation unit that analyzes the questions received by the reception unit and presents them to the respondent; an analysis unit that analyzes answers based on the questions generated by the generation unit; a generation unit that generates follow-up questions based on the answers analyzed by the analysis unit. A system characterized by:

2. The analysis unit Analyzing respondent sentiment and intent 2. The system of claim 1.

3. The analysis unit Analyze the respondent's tone of voice and facial expression to determine the seriousness of the response 2. The system of claim 1.

4. The generation unit Generate follow-up questions based on respondent responses 2. The system of claim 1.

5. The reception unit Estimates the user's emotions and adjusts the timing of accepting questions based on the estimated user emotions.

2. The system of claim 1.

6. The reception unit Analyze the user's past question history and select the optimal reception method 2. The system of claim 1.

7. The reception unit When questions are asked, they are filtered based on the user's current interests.

2. The system of claim 1.

8. The reception unit When accepting a question, select the most appropriate method of acceptance depending on the user's input method.

2. The system of claim 1.

Images