system

Abstract

The system according to this embodiment aims to extract important feedback from a large number of comments and visualize trends in opinions. [Solution] The system according to the embodiment comprises an analysis unit, a summarization unit, a reporting unit, a sentiment analysis unit, and a visualization unit. The analysis unit analyzes the comments. The summarization unit summarizes the comments analyzed by the analysis unit. The reporting unit compiles the feedback summarized by the summarization unit into a report. The sentiment analysis unit performs sentiment analysis based on the report compiled by the reporting unit. The visualization unit visualizes the opinions classified by the sentiment analysis unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to efficiently extract important feedback from a large number of comments and grasp the trend of opinions.

[0005] The system according to the embodiment aims to extract important feedback from a large number of comments and visualize the trend of opinions.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a summarization unit, a reporting unit, a sentiment analysis unit, and a visualization unit. The analysis unit analyzes comments. The summarization unit summarizes the comments analyzed by the analysis unit. The reporting unit compiles the feedback summarized by the summarization unit into a report. The sentiment analysis unit performs sentiment analysis based on the report compiled by the reporting unit. The visualization unit visualizes the opinions classified by the sentiment analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can extract important feedback from a large number of comments and visualize trends in opinions. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of 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), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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. <C000095> The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The questionnaire analysis system according to an embodiment of the present invention is a tool that automatically summarizes the free-comment portion of a questionnaire using AI, allowing users to quickly grasp key points and opinions. This questionnaire analysis system extracts particularly important feedback from a large volume of comments and compiles it into a summarized report. Furthermore, it uses sentiment analysis functionality to classify opinions into positive, negative, and neutral categories and provides a visual representation of opinion trends. For example, the questionnaire analysis system uses AI to analyze the free-comment portion of a questionnaire. In this process, the AI ​​analyzes each comment in detail and extracts key points and opinions. For example, it can extract problems and areas for improvement that are pointed out by many customers from comments in a customer satisfaction survey. This allows for efficient identification of important feedback from a large volume of comments. Next, the extracted feedback is summarized and compiled into a report. The AI ​​summarizes the extracted feedback and compiles it into a concise report. For example, it can summarize the results of a customer satisfaction survey and include key problems and areas for improvement in the report. This allows for quick grasp of key points and opinions. Furthermore, it uses sentiment analysis functionality to classify opinions into positive, negative, and neutral categories. The AI ​​analyzes the sentiment of each comment and classifies them into positive, negative, and neutral opinions. For example, from comments in a customer satisfaction survey, it can classify positive opinions as "the service was good," negative opinions as "the waiting time was long," and neutral opinions as "it was average." This allows for an understanding of opinion trends. Finally, it provides a visualization of opinion trends. The AI ​​presents the classified opinions in visual formats such as graphs and charts. For example, it can display the percentage of positive, negative, and neutral opinions in a pie chart. This allows for an at-a-glance understanding of opinion trends. This enables efficient analysis of the free-comment section of surveys, allowing for a quick grasp of key points and opinions. Furthermore, by using the sentiment analysis function in conjunction, opinion trends can be visualized and presented in a more easily understandable way.For example, efficiently analyzing the results of customer satisfaction surveys and identifying key problems and areas for improvement can be used to enhance services.

[0029] The questionnaire analysis system according to this embodiment comprises an analysis unit, a summarization unit, a reporting unit, an emotion analysis unit, and a visualization unit. The analysis unit analyzes comments. The analysis unit analyzes, for example, the free comment section of the questionnaire and extracts key points and opinions. The analysis unit analyzes comments using, for example, text mining technology. The analysis unit analyzes comments using, for example, natural language processing technology. The analysis unit analyzes comments using, for example, emotion analysis technology. The summarization unit performs a summary based on the comments analyzed by the analysis unit. The summarization unit summarizes the extracted feedback and compiles it into a concise report. The summarization unit performs the summary using, for example, text generation AI. The summarization unit performs the summary using, for example, a summarization algorithm. The summarization unit performs the summary using, for example, natural language processing technology. The reporting unit compiles the feedback summarized by the summarization unit into a report. The reporting unit compiles the summarized feedback into a text report. The reporting unit compiles the summarized feedback into a graph report. The reporting unit, for example, compiles summarized feedback into a dashboard. The sentiment analysis unit performs sentiment analysis based on the report compiled by the reporting unit. The sentiment analysis unit, for example, analyzes the sentiment of each comment and classifies them into positive, negative, and neutral opinions. The sentiment analysis unit analyzes sentiment using sentiment scores, for example. The sentiment analysis unit analyzes sentiment using keyword frequency, for example. The sentiment analysis unit analyzes sentiment using natural language processing techniques, for example. The visualization unit visualizes the opinions classified by the sentiment analysis unit. The visualization unit provides the classified opinions in visual formats such as graphs and charts, for example. The visualization unit visualizes opinions using bar graphs, for example. The visualization unit visualizes opinions using pie charts, for example. The visualization unit visualizes opinions using heatmaps, for example. As a result, the survey analysis system according to this embodiment can efficiently analyze comments, summarize them, create reports, perform sentiment analysis, and visualize them.

[0030] The analysis unit analyzes comments. For example, the analysis unit analyzes the free-response section of a survey and extracts key points and opinions. The analysis unit analyzes comments using text mining techniques, for example. Specifically, it uses text mining techniques to extract frequently occurring words and phrases in comments and analyzes their frequency of appearance to identify main themes and topics. Furthermore, it analyzes comments using natural language processing techniques. By using natural language processing techniques, it is possible to understand the context and meaning of comments and perform more accurate analysis. For example, by performing morphological analysis to identify the part of speech of each word and analyzing the sentence structure, it is possible to grasp the intent and emotion of the comments. It also analyzes comments using sentiment analysis techniques. By using sentiment analysis techniques, it captures the emotional nuances of comments and classifies them into positive, negative, and neutral emotions. This allows the analysis unit to analyze the content of comments from multiple angles and extract key points and opinions. Furthermore, the analysis unit can also perform comment classification and clustering using machine learning algorithms. For example, supervised learning is used to train a model based on pre-labeled data and automatically classify new comments. Alternatively, unsupervised learning is used to cluster comments based on their similarity, grouping comments with common themes or topics. This allows the analysis unit to improve the accuracy of comment analysis and efficiently extract key points and opinions.

[0031] The summarization unit performs summaries based on comments analyzed by the analysis unit. For example, the summarization unit summarizes extracted feedback and compiles it into a concise report. Specifically, it uses text generation AI for summarization. The text generation AI utilizes natural language processing technology to extract important information from long comments and generate a concise summary. For example, the generation AI extracts the main points and opinions of a comment and integrates them to generate a summary. It also uses a summarization algorithm. The summarization algorithm evaluates the importance of the comments, extracts the important parts, and generates a summary. For example, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to identify important words and phrases in the comments and generates a summary based on them. Furthermore, it uses natural language processing technology for summarization. By using natural language processing technology, it is possible to understand the context and meaning of the comments and generate more accurate summaries. For example, it analyzes the structure of sentences, extracts the main points, and generates a summary. As a result, the summarization unit can efficiently summarize the analyzed comments and compile them into a concise report. Furthermore, the summarization unit can evaluate the quality of the generated summaries and make corrections as needed. For example, it can check the consistency and grammatical accuracy of the summaries and automatically correct them if necessary. This allows the summarization unit to generate high-quality summaries and improve the efficiency of report creation.

[0032] The reporting unit compiles the feedback summarized by the summarizing unit into a report. For example, the reporting unit compiles the summarized feedback into a text report. Specifically, it organizes the summarized feedback and compiles it into a text report in an easy-to-read format. For example, it categorizes each piece of feedback and highlights important points to make it easy for the reader to understand. It also compiles the summarized feedback into a graph report. Graph reports visually represent the content of the feedback, allowing for an intuitive understanding of data trends and patterns. For example, bar graphs and pie charts are used to show the proportion and frequency of feedback in each category. Furthermore, the summarized feedback is compiled into a dashboard. A dashboard consolidates multiple graphs and charts onto a single screen and updates the data in real time, allowing for an at-a-glance understanding of the feedback situation. For example, it includes line graphs showing feedback trends and fluctuations, and numerical displays showing important indicators. This allows the reporting unit to compile the summarized feedback into reports in various formats, making it easy for the reader to understand. In addition, the reporting unit can automatically update the report content to reflect the latest feedback. For example, if new feedback is added, the reporting department automatically updates the report to provide the latest information. This allows the reporting department to always provide reports based on the most up-to-date information, supporting quick and appropriate decision-making.

[0033] The Sentiment Analysis Department performs sentiment analysis based on reports compiled by the Reporting Department. For example, the Sentiment Analysis Department analyzes the sentiment of each comment and classifies them into positive, negative, or neutral opinions. Specifically, it analyzes sentiment using sentiment scores. Sentiment scores quantify the emotional intensity of each comment and classify them as positive, negative, or neutral. For example, positive comments are given high scores, and negative comments are given low scores. It also analyzes sentiment using keyword frequency. By analyzing keyword frequency, it identifies emotional words and phrases within the comments and classifies the sentiment based on their frequency. For example, comments that frequently use positive keywords such as "good" and "great" are classified as positive opinions. Furthermore, it analyzes sentiment using natural language processing techniques. By using natural language processing techniques, it is possible to understand the context and meaning of comments and perform more accurate sentiment analysis. For example, by analyzing the sentence structure and capturing emotional nuances, the sentiment of the comments can be accurately classified. As a result, the Sentiment Analysis Department can analyze the sentiment of each comment from multiple angles based on the reports and classify them into positive, negative, or neutral opinions. Furthermore, the sentiment analysis department can also evaluate the overall emotional trend of the feedback based on the results of the sentiment analysis. For example, it can calculate the proportion of positive and negative opinions among all comments to show the overall emotional trend of the feedback. This allows the sentiment analysis department to grasp the emotional aspects of the feedback and propose appropriate responses and improvement measures.

[0034] The visualization unit visualizes the opinions classified by the sentiment analysis unit. The visualization unit provides the classified opinions in visual formats such as graphs and charts. Specifically, it visualizes opinions using bar graphs. Bar graphs are suitable for showing the proportion and frequency of opinions in each category, allowing for an intuitive understanding of the distribution of positive, negative, and neutral opinions. It also visualizes opinions using pie charts. Pie charts are suitable for showing the proportion of each category of opinion within the whole, allowing for an at-a-glance understanding of the overall sentiment trend of the feedback. Furthermore, it visualizes opinions using heatmaps. Heatmaps visually indicate areas where specific opinions or emotions are concentrated by representing the density and intensity of data with color. For example, by highlighting areas where specific keywords or phrases appear frequently, important opinions and emotions can be intuitively grasped. This allows the visualization unit to visualize the opinions classified by the sentiment analysis unit in diverse formats, enabling an intuitive understanding of data trends and patterns. Furthermore, the visualization unit can also provide the visualized data in an interactive format. For example, the system provides a feature that allows users to click on graphs and charts to display detailed data and related comments. This enables the visualization unit to allow users to delve deeper into the data for analysis and obtain more detailed information. This allows the visualization unit to effectively visualize the results of sentiment analysis and facilitate understanding of the data.

[0035] The analysis unit can analyze the free-comment section of a questionnaire and extract key points and opinions. For example, the analysis unit can analyze the free-comment section of the questionnaire using text mining techniques. For example, the analysis unit can analyze the comments using natural language processing techniques. For example, the analysis unit can analyze the comments using sentiment analysis techniques. This allows the analysis unit to extract key points and opinions from the free-comment section of the questionnaire. The criteria and methods for extracting key points and opinions can be clearly defined, for example, using frequently occurring keywords or importance scores. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the free-comment section of the questionnaire into a generating AI and have the generating AI perform the extraction of key points and opinions.

[0036] The summarization unit can summarize the extracted feedback and compile it into a concise report. For example, the summarization unit can summarize the extracted feedback using a text generation AI. For example, the summarization unit can summarize using a summarization algorithm. For example, the summarization unit can summarize using natural language processing technology. This allows the extracted feedback to be summarized concisely and compiled into a report. Specific criteria and methods for conciseness can be clarified, for example, using the length of the summary or the information compression ratio. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the extracted feedback into a generation AI and have the generation AI perform the summarization.

[0037] The sentiment analysis unit can analyze the sentiment of each comment and classify it into positive, negative, or neutral opinions. For example, the sentiment analysis unit can analyze the sentiment of each comment using a sentiment score. Alternatively, it can analyze sentiment using keyword frequency. Or, it can analyze sentiment using natural language processing techniques. This allows for the analysis of the sentiment of each comment and the classification of opinions. The classification criteria and methods for positive, negative, and neutral opinions can be clearly defined, for example, using sentiment scores or keyword frequency. Sentiment estimation is achieved using a sentiment estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the sentiment analysis unit may be performed using AI, or not. For example, the sentiment analysis unit can input each comment into a generative AI and have the generative AI perform the sentiment analysis.

[0038] The visualization unit can provide classified opinions in visual formats such as graphs and charts. For example, the visualization unit can visualize classified opinions using a bar graph. For example, the visualization unit can visualize classified opinions using a pie chart. For example, the visualization unit can visualize classified opinions using a heatmap. This allows the classified opinions to be provided visually. The specific types and methods of visual formats can be clarified using, for example, bar graphs, pie charts, scatter plots, etc. Some or all of the above processing in the visualization unit may be performed using, for example, AI, or not using AI. For example, the visualization unit can input classified opinions into a generating AI and have the generating AI perform the visualization.

[0039] The analysis unit can improve the accuracy of its analysis by considering the frequency of specific keywords and phrases when analyzing comments. For example, the analysis unit may prioritize the analysis of comments in which specific keywords frequently appear. For example, the analysis unit may extract important comments based on the frequency of phrase occurrences. For example, the analysis unit may analyze comments with high relevance by considering combinations of keywords. This allows for improved analysis accuracy by considering the frequency of specific keywords and phrases. The criteria and methods for selecting specific keywords and phrases can be clearly defined, for example, using frequency or importance scores. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input specific keywords and phrases into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0040] The analysis unit can optimize its analysis algorithm by referring to past analysis results when analyzing comments. For example, the analysis unit adjusts the analysis algorithm based on past analysis results. For example, the analysis unit learns from past analysis results to improve analysis accuracy. For example, the analysis unit finds specific patterns by referring to past analysis results. This allows the analysis algorithm to be optimized by referring to past analysis results. The method and criteria for referring to past analysis results can be clarified, for example, using past datasets or methods for adjusting the analysis algorithm. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past analysis results into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0041] The analysis unit can prioritize the analysis of highly relevant comments by considering the user's geographical location information when analyzing comments. For example, the analysis unit can prioritize the analysis of region-specific comments based on the user's geographical location information. For example, the analysis unit can extract comments from a specific region by considering geographical location information. For example, the analysis unit can analyze highly relevant comments based on geographical location information. This allows for the prioritization of highly relevant comments by considering the user's geographical location information. The method for acquiring and analyzing geographical location information can be clearly defined, for example, by using GPS data or IP addresses. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the user's geographical location information into a generating AI and have the generating AI perform the analysis of highly relevant comments.

[0042] The analysis unit can analyze a user's social media activity and analyze relevant comments when analyzing comments. For example, the analysis unit can extract relevant comments based on the user's social media activity. For example, the analysis unit can analyze important comments considering social media activity. For example, the analysis unit can analyze highly relevant comments based on social media activity. This allows the analysis of a user's social media activity and the analysis of relevant comments. Specific methods and criteria for analyzing social media activity can be clearly defined, for example, using posting frequency or engagement score. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user social media activity data into a generating AI and have the generating AI perform the analysis of relevant comments.

[0043] The summarization unit can adjust the level of detail in the summary based on the importance of the comments during summary generation. For example, the summarization unit may summarize important comments in detail. For example, the summarization unit may summarize less important comments concisely. The summarization unit adjusts the level of detail in the summary according to the importance of the comments. This allows the level of detail in the summary to be adjusted based on the importance of the comments. The criteria and methods for evaluating the importance of comments can be clearly defined, for example, using frequency or impact scores. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input comment importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0044] The summarization unit can apply different summarization algorithms depending on the comment category when generating summaries. For example, the summarization unit can apply a positive summarization algorithm to positive comments, a negative summarization algorithm to negative comments, and a neutral summarization algorithm to neutral comments. This allows for the application of different summarization algorithms depending on the comment category. The criteria and methods for classifying comment categories can be clearly defined, for example, using topic classification or sentiment classification. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input comment category data into a generating AI and have the generating AI perform the application of the summarization algorithm.

[0045] The summarization unit can determine the priority of summaries based on the submission date of the comments when generating summaries. For example, the summarization unit may prioritize summarizing the most recent comments. For example, the summarization unit may postpone summarizing older comments. The summarization unit determines the priority of summaries based on the submission date. This allows the summarization unit to determine the priority of summaries based on the submission date of the comments. The method for obtaining and analyzing the submission date of comments can be clearly defined, for example, by using a timestamp or submission date and time. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without using AI. For example, the summarization unit can input the comment submission date data into a generation AI and have the generation AI perform the determination of the summary priority.

[0046] The summarization unit can adjust the order of summaries based on the relevance of comments during summary generation. For example, the summarization unit prioritizes summarizing highly relevant comments. For example, the summarization unit postpones summarizing less relevant comments. The summarization unit adjusts the order of summaries based on the relevance of comments. This allows the order of summaries to be adjusted based on the relevance of comments. The criteria and methods for evaluating comment relevance can be clarified, for example, using a co-occurrence network or similarity score. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input comment relevance data into a generation AI and have the generation AI perform the adjustment of the summary order.

[0047] The reporting unit can adjust the level of detail in a report based on the importance of the summarized feedback when generating the report. For example, the reporting unit may report important feedback in detail. For example, the reporting unit may report less important feedback concisely. The reporting unit can adjust the level of detail in a report according to the importance of the feedback. This allows the level of detail in a report to be adjusted based on the importance of the summarized feedback. The criteria and methods for evaluating the importance of feedback can be clearly defined, for example, using frequency or impact scores. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit can input feedback importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in the report.

[0048] The reporting unit can apply different report formats depending on the feedback category when generating reports. For example, the reporting unit can apply a positive report format to positive feedback, a negative report format to negative feedback, and a neutral report format to neutral feedback. This allows for the application of different report formats depending on the feedback category. The criteria and methods for classifying feedback categories can be clarified using, for example, topic classification or sentiment classification. Some or all of the above processing in the reporting unit may be performed using, for example, AI, or not using AI. For example, the reporting unit can input feedback category data into a generating AI and have the generating AI apply the report format.

[0049] The reporting unit can prioritize reports based on the timing of feedback submission when generating reports. For example, the reporting unit prioritizes reporting the most recent feedback. For example, the reporting unit postpones reporting older feedback. The reporting unit determines the priority of reports based on the submission timing. This allows the reporting unit to determine the priority of reports based on the timing of feedback submission. The method for obtaining and analyzing the timing of feedback submission can be clearly defined, for example, using timestamps or submission dates. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit can input feedback submission timing data into a generation AI and have the generation AI perform the determination of report priorities.

[0050] The reporting unit can adjust the order of reports based on the relevance of the feedback when generating reports. For example, the reporting unit prioritizes reporting highly relevant feedback. For example, the reporting unit postpones reporting less relevant feedback. The reporting unit adjusts the order of reports based on the relevance of the feedback. This allows the order of reports to be adjusted based on the relevance of the feedback. The criteria and methods for evaluating the relevance of feedback can be clarified, for example, using a co-occurrence network or similarity score. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit can input feedback relevance data into a generating AI and have the generating AI perform the adjustment of the report order.

[0051] The sentiment analysis unit can improve the accuracy of sentiment classification by considering the context of the comment during sentiment analysis. For example, the sentiment analysis unit accurately classifies emotions by considering the context before and after the comment. For example, the sentiment analysis unit evaluates the intensity of emotions based on the context. For example, the sentiment analysis unit captures the nuances of emotions by considering the context. This allows for improved accuracy of sentiment classification by considering the context of the comment. The method and criteria for analyzing the context of a comment can be clarified, for example, by using the surrounding text or related topics. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input the contextual data of the comment into a generating AI and have the generating AI perform the task of improving the accuracy of sentiment classification.

[0052] The sentiment analysis unit can optimize its analysis algorithm by referring to past sentiment analysis results during sentiment analysis. For example, the sentiment analysis unit adjusts the analysis algorithm based on past sentiment analysis results. For example, the sentiment analysis unit learns from past sentiment analysis results to improve analysis accuracy. For example, the sentiment analysis unit finds specific patterns by referring to past sentiment analysis results. This allows the analysis algorithm to be optimized by referring to past sentiment analysis results. The method and criteria for referring to past sentiment analysis results can be clarified, for example, using past datasets or methods for adjusting the analysis algorithm. Some or all of the above processes in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input past sentiment analysis results into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0053] The sentiment analysis unit can classify emotions while considering the geographical distribution of comments during sentiment analysis. For example, the sentiment analysis unit can classify region-specific emotions based on geographical distribution. For example, the sentiment analysis unit can extract emotions from a specific region while considering geographical distribution. For example, the sentiment analysis unit can classify highly relevant emotions based on geographical distribution. This allows for the classification of emotions while considering the geographical distribution of comments. The method for obtaining and analyzing geographical distribution can be clearly defined, for example, by using GPS data or IP addresses. Some or all of the above-described processes in the sentiment analysis unit may be performed using AI, for example, or without using AI. For example, the sentiment analysis unit can input geographical distribution data of comments into a generating AI and have the generating AI perform the emotion classification.

[0054] The sentiment analysis unit can improve the accuracy of sentiment classification by referring to relevant literature for comments during sentiment analysis. For example, the sentiment analysis unit adjusts the sentiment classification criteria based on relevant literature. For example, the sentiment analysis unit evaluates the intensity of emotions by referring to relevant literature. For example, the sentiment analysis unit captures the nuances of emotions based on relevant literature. This allows the sentiment analysis unit to improve the accuracy of sentiment classification by referring to relevant literature for comments. The method and criteria for referring to relevant literature can be clarified, for example, by using academic papers or technical reports. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without using AI. For example, the sentiment analysis unit can input the relevant literature data for comments into a generating AI and have the generating AI perform the task of improving the accuracy of sentiment classification.

[0055] The visualization unit can adjust the level of detail of the visualization based on the importance of the feedback during visualization. For example, the visualization unit visualizes important feedback in detail. For example, the visualization unit visualizes less important feedback concisely. The visualization unit adjusts the level of detail of the visualization according to the importance of the feedback. This allows the level of detail of the visualization to be adjusted based on the importance of the feedback. The criteria and methods for adjusting the level of detail of the visualization can be clarified, for example, using the information compression rate or the number of displayed items. Some or all of the above processing in the visualization unit may be performed using AI, for example, or without AI. For example, the visualization unit can input feedback importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the visualization.

[0056] The visualization unit can apply different visualization methods depending on the category of feedback during visualization. For example, the visualization unit can apply a positive visualization method to positive feedback. For example, the visualization unit can apply a negative visualization method to negative feedback. For example, the visualization unit can apply a neutral visualization method to neutral feedback. This allows for the application of different visualization methods depending on the category of feedback. The specific types and application methods of visualization methods can be clearly shown using, for example, bar graphs, pie charts, scatter plots, etc. Some or all of the above-described processing in the visualization unit may be performed using, for example, AI, or not using AI. For example, the visualization unit can input feedback category data into a generating AI and have the generating AI execute the application of visualization methods.

[0057] The visualization unit can adjust the order of visualizations based on the submission date of the feedback during visualization. For example, the visualization unit may prioritize visualizing the most recent feedback. For example, the visualization unit may postpone older feedback. The visualization unit adjusts the order of visualizations based on the submission date. This allows the order of visualizations to be adjusted based on the submission date of the feedback. The method for obtaining and analyzing the submission date of feedback can be clarified, for example, by using a timestamp or submission date and time. Some or all of the above processing in the visualization unit may be performed using AI, for example, or without using AI. For example, the visualization unit can input the feedback submission date data into a generating AI and have the generating AI perform the adjustment of the visualization order.

[0058] The visualization unit can adjust the visualization format based on the relevance of the feedback during visualization. For example, the visualization unit prioritizes visualizing highly relevant feedback. For example, the visualization unit postpones visualizing less relevant feedback. The visualization unit adjusts the visualization format based on the relevance of the feedback. This allows the visualization format to be adjusted based on the relevance of the feedback. The criteria and methods for evaluating the relevance of feedback can be clarified, for example, using a co-occurrence network or similarity score. Some or all of the above processing in the visualization unit may be performed using AI, for example, or without AI. For example, the visualization unit can input feedback relevance data into a generating AI and have the generating AI perform the adjustment of the visualization format.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The analysis unit can improve the accuracy of its analysis by considering the frequency of specific keywords and phrases when analyzing comments. For example, it can prioritize the analysis of comments where specific keywords frequently appear. It can extract important comments based on the frequency of phrase occurrences. It can analyze highly relevant comments by considering keyword combinations. This allows for improved analysis accuracy by considering the frequency of specific keywords and phrases. The criteria and methods for selecting specific keywords and phrases can be clearly defined using frequency or importance scores. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input specific keywords and phrases into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0061] The summarization unit can adjust the level of detail in the summary based on the importance of the comments during summary generation. For example, important comments can be summarized in detail, while less important comments can be summarized concisely. The level of detail in the summary can be adjusted according to the importance of the comments. This allows the level of detail in the summary to be adjusted based on the importance of the comments. The criteria and methods for evaluating the importance of comments can be clearly defined using frequency or impact scores. Some or all of the above processing in the summarization unit may be performed using AI or not. For example, the summarization unit can input comment importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0062] The reporting unit can adjust the level of detail in a report based on the importance of the summarized feedback during report generation. For example, important feedback can be reported in detail, while less important feedback can be reported concisely. The level of detail in the report can be adjusted according to the importance of the feedback. This allows the level of detail in the report to be adjusted based on the importance of the summarized feedback. The criteria and methods for evaluating the importance of feedback can be clearly defined using frequency or impact scores. Some or all of the above processing in the reporting unit may be performed using AI or not. For example, the reporting unit can input feedback importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in the report.

[0063] The visualization unit can adjust the level of detail of the visualization based on the importance of the feedback during visualization. For example, important feedback can be visualized in detail, while less important feedback can be visualized concisely. The level of detail of the visualization can be adjusted according to the importance of the feedback. This allows the level of detail of the visualization to be adjusted based on the importance of the feedback. The criteria and methods for adjusting the level of detail of the visualization can be clarified using information compression ratios, the number of displayed items, etc. Some or all of the above processing in the visualization unit may be performed using AI, or not using AI. For example, the visualization unit can input feedback importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the visualization.

[0064] The analysis unit can optimize its analysis algorithm by referring to past analysis results when analyzing comments. For example, it can adjust the analysis algorithm based on past analysis results. It can learn from past analysis results and improve analysis accuracy. It can find specific patterns by referring to past analysis results. This allows the analysis algorithm to be optimized by referring to past analysis results. The method and criteria for referring to past analysis results can be clearly defined using past datasets or methods for adjusting the analysis algorithm. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input past analysis results into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The analysis unit analyzes the comments. For example, the analysis unit analyzes the free-response section of a questionnaire and extracts key points and opinions. The analysis unit analyzes the comments using text mining technology, natural language processing technology, and sentiment analysis technology. Step 2: The summarization unit performs a summary based on the comments analyzed by the analysis unit. The summarization unit summarizes the extracted feedback and compiles it into a concise report. The summarization unit performs the summary using text generation AI, summarization algorithms, and natural language processing technology. Step 3: The reporting team compiles the feedback summarized by the summarizing team into a report. The reporting team compiles the summarized feedback into a text report, graph report, and dashboard. Step 4: The Sentiment Analysis Department performs sentiment analysis based on the report compiled by the Reporting Department. The Sentiment Analysis Department analyzes the sentiment of each comment and classifies them into positive, negative, and neutral opinions. Sentiment is analyzed using sentiment scores, keyword frequency, and natural language processing techniques. Step 5: The visualization unit visualizes the opinions classified by the sentiment analysis unit. The visualization unit provides the classified opinions in a visual format such as graphs and charts. Opinions are visualized using bar graphs, pie charts, and heatmaps.

[0067] (Example of form 2) The questionnaire analysis system according to an embodiment of the present invention is a tool that automatically summarizes the free-comment portion of a questionnaire using AI, allowing users to quickly grasp key points and opinions. This questionnaire analysis system extracts particularly important feedback from a large volume of comments and compiles it into a summarized report. Furthermore, it uses sentiment analysis functionality to classify opinions into positive, negative, and neutral categories and provides a visual representation of opinion trends. For example, the questionnaire analysis system uses AI to analyze the free-comment portion of a questionnaire. In this process, the AI ​​analyzes each comment in detail and extracts key points and opinions. For example, it can extract problems and areas for improvement that are pointed out by many customers from comments in a customer satisfaction survey. This allows for efficient identification of important feedback from a large volume of comments. Next, the extracted feedback is summarized and compiled into a report. The AI ​​summarizes the extracted feedback and compiles it into a concise report. For example, it can summarize the results of a customer satisfaction survey and include key problems and areas for improvement in the report. This allows for quick grasp of key points and opinions. Furthermore, it uses sentiment analysis functionality to classify opinions into positive, negative, and neutral categories. The AI ​​analyzes the sentiment of each comment and classifies them into positive, negative, and neutral opinions. For example, from comments in a customer satisfaction survey, it can classify positive opinions as "the service was good," negative opinions as "the waiting time was long," and neutral opinions as "it was average." This allows for an understanding of opinion trends. Finally, it provides a visualization of opinion trends. The AI ​​presents the classified opinions in visual formats such as graphs and charts. For example, it can display the percentage of positive, negative, and neutral opinions in a pie chart. This allows for an at-a-glance understanding of opinion trends. This enables efficient analysis of the free-comment section of surveys, allowing for a quick grasp of key points and opinions. Furthermore, by using the sentiment analysis function in conjunction, opinion trends can be visualized and presented in a more easily understandable way.For example, efficiently analyzing the results of customer satisfaction surveys and identifying key problems and areas for improvement can be used to enhance services.

[0068] The questionnaire analysis system according to this embodiment comprises an analysis unit, a summarization unit, a reporting unit, an emotion analysis unit, and a visualization unit. The analysis unit analyzes comments. The analysis unit analyzes, for example, the free comment section of the questionnaire and extracts key points and opinions. The analysis unit analyzes comments using, for example, text mining technology. The analysis unit analyzes comments using, for example, natural language processing technology. The analysis unit analyzes comments using, for example, emotion analysis technology. The summarization unit performs a summary based on the comments analyzed by the analysis unit. The summarization unit summarizes the extracted feedback and compiles it into a concise report. The summarization unit performs the summary using, for example, text generation AI. The summarization unit performs the summary using, for example, a summarization algorithm. The summarization unit performs the summary using, for example, natural language processing technology. The reporting unit compiles the feedback summarized by the summarization unit into a report. The reporting unit compiles the summarized feedback into a text report. The reporting unit compiles the summarized feedback into a graph report. The reporting unit, for example, compiles summarized feedback into a dashboard. The sentiment analysis unit performs sentiment analysis based on the report compiled by the reporting unit. The sentiment analysis unit, for example, analyzes the sentiment of each comment and classifies them into positive, negative, and neutral opinions. The sentiment analysis unit analyzes sentiment using sentiment scores, for example. The sentiment analysis unit analyzes sentiment using keyword frequency, for example. The sentiment analysis unit analyzes sentiment using natural language processing techniques, for example. The visualization unit visualizes the opinions classified by the sentiment analysis unit. The visualization unit provides the classified opinions in visual formats such as graphs and charts, for example. The visualization unit visualizes opinions using bar graphs, for example. The visualization unit visualizes opinions using pie charts, for example. The visualization unit visualizes opinions using heatmaps, for example. As a result, the survey analysis system according to this embodiment can efficiently analyze comments, summarize them, create reports, perform sentiment analysis, and visualize them.

[0069] The analysis unit analyzes comments. For example, the analysis unit analyzes the free-response section of a survey and extracts key points and opinions. The analysis unit analyzes comments using text mining techniques, for example. Specifically, it uses text mining techniques to extract frequently occurring words and phrases in comments and analyzes their frequency of appearance to identify main themes and topics. Furthermore, it analyzes comments using natural language processing techniques. By using natural language processing techniques, it is possible to understand the context and meaning of comments and perform more accurate analysis. For example, by performing morphological analysis to identify the part of speech of each word and analyzing the sentence structure, it is possible to grasp the intent and emotion of the comments. It also analyzes comments using sentiment analysis techniques. By using sentiment analysis techniques, it captures the emotional nuances of comments and classifies them into positive, negative, and neutral emotions. This allows the analysis unit to analyze the content of comments from multiple angles and extract key points and opinions. Furthermore, the analysis unit can also perform comment classification and clustering using machine learning algorithms. For example, supervised learning is used to train a model based on pre-labeled data and automatically classify new comments. Alternatively, unsupervised learning is used to cluster comments based on their similarity, grouping comments with common themes or topics. This allows the analysis unit to improve the accuracy of comment analysis and efficiently extract key points and opinions.

[0070] The summarization unit performs summaries based on comments analyzed by the analysis unit. For example, the summarization unit summarizes extracted feedback and compiles it into a concise report. Specifically, it uses text generation AI for summarization. The text generation AI utilizes natural language processing technology to extract important information from long comments and generate a concise summary. For example, the generation AI extracts the main points and opinions of a comment and integrates them to generate a summary. It also uses a summarization algorithm. The summarization algorithm evaluates the importance of the comments, extracts the important parts, and generates a summary. For example, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to identify important words and phrases in the comments and generates a summary based on them. Furthermore, it uses natural language processing technology for summarization. By using natural language processing technology, it is possible to understand the context and meaning of the comments and generate more accurate summaries. For example, it analyzes the structure of sentences, extracts the main points, and generates a summary. As a result, the summarization unit can efficiently summarize the analyzed comments and compile them into a concise report. Furthermore, the summarization unit can evaluate the quality of the generated summaries and make corrections as needed. For example, it can check the consistency and grammatical accuracy of the summaries and automatically correct them if necessary. This allows the summarization unit to generate high-quality summaries and improve the efficiency of report creation.

[0071] The reporting unit compiles the feedback summarized by the summarizing unit into a report. For example, the reporting unit compiles the summarized feedback into a text report. Specifically, it organizes the summarized feedback and compiles it into a text report in an easy-to-read format. For example, it categorizes each piece of feedback and highlights important points to make it easy for the reader to understand. It also compiles the summarized feedback into a graph report. Graph reports visually represent the content of the feedback, allowing for an intuitive understanding of data trends and patterns. For example, bar graphs and pie charts are used to show the proportion and frequency of feedback in each category. Furthermore, the summarized feedback is compiled into a dashboard. A dashboard consolidates multiple graphs and charts onto a single screen and updates the data in real time, allowing for an at-a-glance understanding of the feedback situation. For example, it includes line graphs showing feedback trends and fluctuations, and numerical displays showing important indicators. This allows the reporting unit to compile the summarized feedback into reports in various formats, making it easy for the reader to understand. In addition, the reporting unit can automatically update the report content to reflect the latest feedback. For example, if new feedback is added, the reporting department automatically updates the report to provide the latest information. This allows the reporting department to always provide reports based on the most up-to-date information, supporting quick and appropriate decision-making.

[0072] The Sentiment Analysis Department performs sentiment analysis based on reports compiled by the Reporting Department. For example, the Sentiment Analysis Department analyzes the sentiment of each comment and classifies them into positive, negative, or neutral opinions. Specifically, it analyzes sentiment using sentiment scores. Sentiment scores quantify the emotional intensity of each comment and classify them as positive, negative, or neutral. For example, positive comments are given high scores, and negative comments are given low scores. It also analyzes sentiment using keyword frequency. By analyzing keyword frequency, it identifies emotional words and phrases within the comments and classifies the sentiment based on their frequency. For example, comments that frequently use positive keywords such as "good" and "great" are classified as positive opinions. Furthermore, it analyzes sentiment using natural language processing techniques. By using natural language processing techniques, it is possible to understand the context and meaning of comments and perform more accurate sentiment analysis. For example, by analyzing the sentence structure and capturing emotional nuances, the sentiment of the comments can be accurately classified. As a result, the Sentiment Analysis Department can analyze the sentiment of each comment from multiple angles based on the reports and classify them into positive, negative, or neutral opinions. Furthermore, the sentiment analysis department can also evaluate the overall emotional trend of the feedback based on the results of the sentiment analysis. For example, it can calculate the proportion of positive and negative opinions among all comments to show the overall emotional trend of the feedback. This allows the sentiment analysis department to grasp the emotional aspects of the feedback and propose appropriate responses and improvement measures.

[0073] The visualization unit visualizes the opinions classified by the sentiment analysis unit. The visualization unit provides the classified opinions in visual formats such as graphs and charts. Specifically, it visualizes opinions using bar graphs. Bar graphs are suitable for showing the proportion and frequency of opinions in each category, allowing for an intuitive understanding of the distribution of positive, negative, and neutral opinions. It also visualizes opinions using pie charts. Pie charts are suitable for showing the proportion of each category of opinion within the whole, allowing for an at-a-glance understanding of the overall sentiment trend of the feedback. Furthermore, it visualizes opinions using heatmaps. Heatmaps visually indicate areas where specific opinions or emotions are concentrated by representing the density and intensity of data with color. For example, by highlighting areas where specific keywords or phrases appear frequently, important opinions and emotions can be intuitively grasped. This allows the visualization unit to visualize the opinions classified by the sentiment analysis unit in diverse formats, enabling an intuitive understanding of data trends and patterns. Furthermore, the visualization unit can also provide the visualized data in an interactive format. For example, the system provides a feature that allows users to click on graphs and charts to display detailed data and related comments. This enables the visualization unit to allow users to delve deeper into the data for analysis and obtain more detailed information. This allows the visualization unit to effectively visualize the results of sentiment analysis and facilitate understanding of the data.

[0074] The analysis unit can analyze the free-comment section of a questionnaire and extract key points and opinions. For example, the analysis unit can analyze the free-comment section of the questionnaire using text mining techniques. For example, the analysis unit can analyze the comments using natural language processing techniques. For example, the analysis unit can analyze the comments using sentiment analysis techniques. This allows the analysis unit to extract key points and opinions from the free-comment section of the questionnaire. The criteria and methods for extracting key points and opinions can be clearly defined, for example, using frequently occurring keywords or importance scores. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the free-comment section of the questionnaire into a generating AI and have the generating AI perform the extraction of key points and opinions.

[0075] The summarization unit can summarize the extracted feedback and compile it into a concise report. For example, the summarization unit can summarize the extracted feedback using a text generation AI. For example, the summarization unit can summarize using a summarization algorithm. For example, the summarization unit can summarize using natural language processing technology. This allows the extracted feedback to be summarized concisely and compiled into a report. Specific criteria and methods for conciseness can be clarified, for example, using the length of the summary or the information compression ratio. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the extracted feedback into a generation AI and have the generation AI perform the summarization.

[0076] The sentiment analysis unit can analyze the sentiment of each comment and classify it into positive, negative, or neutral opinions. For example, the sentiment analysis unit can analyze the sentiment of each comment using a sentiment score. Alternatively, it can analyze sentiment using keyword frequency. Or, it can analyze sentiment using natural language processing techniques. This allows for the analysis of the sentiment of each comment and the classification of opinions. The classification criteria and methods for positive, negative, and neutral opinions can be clearly defined, for example, using sentiment scores or keyword frequency. Sentiment estimation is achieved using a sentiment estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the sentiment analysis unit may be performed using AI, or not. For example, the sentiment analysis unit can input each comment into a generative AI and have the generative AI perform the sentiment analysis.

[0077] The visualization unit can provide classified opinions in visual formats such as graphs and charts. For example, the visualization unit can visualize classified opinions using a bar graph. For example, the visualization unit can visualize classified opinions using a pie chart. For example, the visualization unit can visualize classified opinions using a heatmap. This allows the classified opinions to be provided visually. The specific types and methods of visual formats can be clarified using, for example, bar graphs, pie charts, scatter plots, etc. Some or all of the above processing in the visualization unit may be performed using, for example, AI, or not using AI. For example, the visualization unit can input classified opinions into a generating AI and have the generating AI perform the visualization.

[0078] The analysis unit can estimate the user's emotions and adjust the comment analysis method based on the estimated user emotions. For example, if the user has positive emotions, the analysis unit will prioritize analyzing positive comments. For example, if the user has negative emotions, the analysis unit will prioritize analyzing negative comments. For example, if the user has neutral emotions, the analysis unit will consider the overall balance during the analysis. This allows the comment analysis method to be adjusted based on the user's emotions. The method and criteria for estimating the user's emotions can be clarified using, for example, an emotion analysis algorithm or an emotion score. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI adjust the comment analysis method.

[0079] The analysis unit can improve the accuracy of its analysis by considering the frequency of specific keywords and phrases when analyzing comments. For example, the analysis unit may prioritize the analysis of comments in which specific keywords frequently appear. For example, the analysis unit may extract important comments based on the frequency of phrase occurrences. For example, the analysis unit may analyze comments with high relevance by considering combinations of keywords. This allows for improved analysis accuracy by considering the frequency of specific keywords and phrases. The criteria and methods for selecting specific keywords and phrases can be clearly defined, for example, using frequency or importance scores. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input specific keywords and phrases into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0080] The analysis unit can optimize its analysis algorithm by referring to past analysis results when analyzing comments. For example, the analysis unit adjusts the analysis algorithm based on past analysis results. For example, the analysis unit learns from past analysis results to improve analysis accuracy. For example, the analysis unit finds specific patterns by referring to past analysis results. This allows the analysis algorithm to be optimized by referring to past analysis results. The method and criteria for referring to past analysis results can be clarified, for example, using past datasets or methods for adjusting the analysis algorithm. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past analysis results into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0081] The analysis unit can estimate the user's emotions and determine the priority of comments to analyze based on the estimated user emotions. For example, if the user has positive emotions, the analysis unit will prioritize analyzing positive comments. For example, if the user has negative emotions, the analysis unit will prioritize analyzing negative comments. For example, if the user has neutral emotions, the analysis unit will analyze while considering the overall balance. This allows the analysis unit to determine the priority of comments to analyze based on the user's emotions. The criteria and methods for determining the priority of comments to analyze can be clearly defined, for example, using an emotion score or importance score. Emotion estimation is implemented using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform the determination of comment priority.

[0082] The analysis unit can prioritize the analysis of highly relevant comments by considering the user's geographical location information when analyzing comments. For example, the analysis unit can prioritize the analysis of region-specific comments based on the user's geographical location information. For example, the analysis unit can extract comments from a specific region by considering geographical location information. For example, the analysis unit can analyze highly relevant comments based on geographical location information. This allows for the prioritization of highly relevant comments by considering the user's geographical location information. The method for acquiring and analyzing geographical location information can be clearly defined, for example, by using GPS data or IP addresses. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the user's geographical location information into a generating AI and have the generating AI perform the analysis of highly relevant comments.

[0083] The analysis unit can analyze a user's social media activity and analyze relevant comments when analyzing comments. For example, the analysis unit can extract relevant comments based on the user's social media activity. For example, the analysis unit can analyze important comments considering social media activity. For example, the analysis unit can analyze highly relevant comments based on social media activity. This allows the analysis of a user's social media activity and the analysis of relevant comments. Specific methods and criteria for analyzing social media activity can be clearly defined, for example, using posting frequency or engagement score. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user social media activity data into a generating AI and have the generating AI perform the analysis of relevant comments.

[0084] The summarization unit can estimate the user's emotions and adjust the way the summary is expressed based on the estimated emotions. For example, if the user has positive emotions, the summarization unit will use positive language in the summary. For example, if the user has negative emotions, the summarization unit will use negative language in the summary. For example, if the user has neutral emotions, the summarization unit will use neutral language in the summary. This allows the summarization unit to adjust the way the summary is expressed based on the user's emotions. The criteria and methods for adjusting the way the summary is expressed can be clarified, for example, using positive language or negative language. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is 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 processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input user emotion data into the generative AI and have the generative AI adjust the way the summary is expressed.

[0085] The summarization unit can adjust the level of detail in the summary based on the importance of the comments during summary generation. For example, the summarization unit may summarize important comments in detail. For example, the summarization unit may summarize less important comments concisely. The summarization unit adjusts the level of detail in the summary according to the importance of the comments. This allows the level of detail in the summary to be adjusted based on the importance of the comments. The criteria and methods for evaluating the importance of comments can be clearly defined, for example, using frequency or impact scores. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input comment importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0086] The summarization unit can apply different summarization algorithms depending on the comment category when generating summaries. For example, the summarization unit can apply a positive summarization algorithm to positive comments, a negative summarization algorithm to negative comments, and a neutral summarization algorithm to neutral comments. This allows for the application of different summarization algorithms depending on the comment category. The criteria and methods for classifying comment categories can be clearly defined, for example, using topic classification or sentiment classification. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input comment category data into a generating AI and have the generating AI perform the application of the summarization algorithm.

[0087] The summarization unit can estimate the user's emotions and adjust the length of the summary based on the estimated emotions. For example, if the user has positive emotions, the summarization unit will provide a longer summary. For example, if the user has negative emotions, the summarization unit will provide a shorter summary. For example, if the user has neutral emotions, the summarization unit will provide a summary of appropriate length. This allows the length of the summary to be adjusted based on the user's emotions. The criteria and methods for adjusting the length of the summary can be clearly defined, for example, using the number of characters or the information compression rate. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is 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 processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the summary length.

[0088] The summarization unit can determine the priority of summaries based on the submission date of the comments when generating summaries. For example, the summarization unit may prioritize summarizing the most recent comments. For example, the summarization unit may postpone summarizing older comments. The summarization unit determines the priority of summaries based on the submission date. This allows the summarization unit to determine the priority of summaries based on the submission date of the comments. The method for obtaining and analyzing the submission date of comments can be clearly defined, for example, by using a timestamp or submission date and time. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without using AI. For example, the summarization unit can input the comment submission date data into a generation AI and have the generation AI perform the determination of the summary priority.

[0089] The summarization unit can adjust the order of summaries based on the relevance of comments during summary generation. For example, the summarization unit prioritizes summarizing highly relevant comments. For example, the summarization unit postpones summarizing less relevant comments. The summarization unit adjusts the order of summaries based on the relevance of comments. This allows the order of summaries to be adjusted based on the relevance of comments. The criteria and methods for evaluating comment relevance can be clarified, for example, using a co-occurrence network or similarity score. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input comment relevance data into a generation AI and have the generation AI perform the adjustment of the summary order.

[0090] The reporting unit can estimate the user's emotions and adjust the way the report is presented based on the estimated emotions. For example, if the user has positive emotions, the reporting unit will create a report using positive language. For example, if the user has negative emotions, the reporting unit will create a report using negative language. For example, if the user has neutral emotions, the reporting unit will create a report using neutral language. This allows the reporting unit to adjust the way the report is presented based on the user's emotions. The criteria and methods for adjusting the report's presentation can be clarified, for example, using positive or negative language. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit can input user emotion data into a generative AI and have the generative AI adjust the way the report is presented.

[0091] The reporting unit can adjust the level of detail in a report based on the importance of the summarized feedback when generating the report. For example, the reporting unit may report important feedback in detail. For example, the reporting unit may report less important feedback concisely. The reporting unit can adjust the level of detail in a report according to the importance of the feedback. This allows the level of detail in a report to be adjusted based on the importance of the summarized feedback. The criteria and methods for evaluating the importance of feedback can be clearly defined, for example, using frequency or impact scores. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit can input feedback importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in the report.

[0092] The reporting unit can apply different report formats depending on the feedback category when generating reports. For example, the reporting unit can apply a positive report format to positive feedback, a negative report format to negative feedback, and a neutral report format to neutral feedback. This allows for the application of different report formats depending on the feedback category. The criteria and methods for classifying feedback categories can be clarified using, for example, topic classification or sentiment classification. Some or all of the above processing in the reporting unit may be performed using, for example, AI, or not using AI. For example, the reporting unit can input feedback category data into a generating AI and have the generating AI apply the report format.

[0093] The reporting unit can estimate the user's emotions and adjust the length of the report based on the estimated emotions. For example, if the user has positive emotions, the reporting unit will provide a longer report. For example, if the user has negative emotions, the reporting unit will provide a shorter report. For example, if the user has neutral emotions, the reporting unit will provide a report of appropriate length. This allows the length of the report to be adjusted based on the user's emotions. The criteria and methods for adjusting the length of the report can be clearly defined, for example, using the number of characters or the compression rate of the information. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is 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 processing in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit can input user emotion data into the generative AI and have the generative AI adjust the length of the report.

[0094] The reporting unit can prioritize reports based on the timing of feedback submission when generating reports. For example, the reporting unit prioritizes reporting the most recent feedback. For example, the reporting unit postpones reporting older feedback. The reporting unit determines the priority of reports based on the submission timing. This allows the reporting unit to determine the priority of reports based on the timing of feedback submission. The method for obtaining and analyzing the timing of feedback submission can be clearly defined, for example, using timestamps or submission dates. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit can input feedback submission timing data into a generation AI and have the generation AI perform the determination of report priorities.

[0095] The reporting unit can adjust the order of reports based on the relevance of the feedback when generating reports. For example, the reporting unit prioritizes reporting highly relevant feedback. For example, the reporting unit postpones reporting less relevant feedback. The reporting unit adjusts the order of reports based on the relevance of the feedback. This allows the order of reports to be adjusted based on the relevance of the feedback. The criteria and methods for evaluating the relevance of feedback can be clarified, for example, using a co-occurrence network or similarity score. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit can input feedback relevance data into a generating AI and have the generating AI perform the adjustment of the report order.

[0096] The sentiment analysis unit can estimate the user's emotions and adjust the criteria for sentiment analysis based on the estimated user emotions. For example, if the user has positive emotions, the sentiment analysis unit will emphasize positive criteria. For example, if the user has negative emotions, the sentiment analysis unit will emphasize negative criteria. For example, if the user has neutral emotions, the sentiment analysis unit will use neutral criteria. This allows the criteria for sentiment analysis to be adjusted based on the user's emotions. The method and criteria for adjusting the sentiment analysis criteria can be clarified, for example, using emotion scores or classification criteria. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the sentiment analysis criteria.

[0097] The sentiment analysis unit can improve the accuracy of sentiment classification by considering the context of the comment during sentiment analysis. For example, the sentiment analysis unit accurately classifies emotions by considering the context before and after the comment. For example, the sentiment analysis unit evaluates the intensity of emotions based on the context. For example, the sentiment analysis unit captures the nuances of emotions by considering the context. This allows for improved accuracy of sentiment classification by considering the context of the comment. The method and criteria for analyzing the context of a comment can be clarified, for example, by using the surrounding text or related topics. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input the contextual data of the comment into a generating AI and have the generating AI perform the task of improving the accuracy of sentiment classification.

[0098] The sentiment analysis unit can optimize its analysis algorithm by referring to past sentiment analysis results during sentiment analysis. For example, the sentiment analysis unit adjusts the analysis algorithm based on past sentiment analysis results. For example, the sentiment analysis unit learns from past sentiment analysis results to improve analysis accuracy. For example, the sentiment analysis unit finds specific patterns by referring to past sentiment analysis results. This allows the analysis algorithm to be optimized by referring to past sentiment analysis results. The method and criteria for referring to past sentiment analysis results can be clarified, for example, using past datasets or methods for adjusting the analysis algorithm. Some or all of the above processes in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input past sentiment analysis results into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0099] The sentiment analysis unit can estimate the user's emotions and adjust the order in which the sentiment analysis results are displayed based on the estimated user emotions. For example, if the user has positive emotions, the sentiment analysis unit will prioritize displaying positive results. For example, if the user has negative emotions, the sentiment analysis unit will prioritize displaying negative results. For example, if the user has neutral emotions, the sentiment analysis unit will display results considering the overall balance. This allows the order in which the sentiment analysis results are displayed to be adjusted based on the user's emotions. The criteria and methods for adjusting the order in which the sentiment analysis results are displayed can be clarified, for example, using emotion scores or importance scores. Emotion estimation is implemented using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input user emotion data into the generative AI and have the generative AI adjust the display order of the sentiment analysis results.

[0100] The sentiment analysis unit can classify emotions while considering the geographical distribution of comments during sentiment analysis. For example, the sentiment analysis unit can classify region-specific emotions based on geographical distribution. For example, the sentiment analysis unit can extract emotions from a specific region while considering geographical distribution. For example, the sentiment analysis unit can classify highly relevant emotions based on geographical distribution. This allows for the classification of emotions while considering the geographical distribution of comments. The method for obtaining and analyzing geographical distribution can be clearly defined, for example, by using GPS data or IP addresses. Some or all of the above-described processes in the sentiment analysis unit may be performed using AI, for example, or without using AI. For example, the sentiment analysis unit can input geographical distribution data of comments into a generating AI and have the generating AI perform the emotion classification.

[0101] The sentiment analysis unit can improve the accuracy of sentiment classification by referring to relevant literature for comments during sentiment analysis. For example, the sentiment analysis unit adjusts the sentiment classification criteria based on relevant literature. For example, the sentiment analysis unit evaluates the intensity of emotions by referring to relevant literature. For example, the sentiment analysis unit captures the nuances of emotions based on relevant literature. This allows the sentiment analysis unit to improve the accuracy of sentiment classification by referring to relevant literature for comments. The method and criteria for referring to relevant literature can be clarified, for example, by using academic papers or technical reports. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without using AI. For example, the sentiment analysis unit can input the relevant literature data for comments into a generating AI and have the generating AI perform the task of improving the accuracy of sentiment classification.

[0102] The visualization unit can estimate the user's emotions and adjust the visualization method based on the estimated emotions. For example, if the user has positive emotions, the visualization unit provides a graph with bright colors. For example, if the user has negative emotions, the visualization unit provides a graph with calm colors. For example, if the user has neutral emotions, the visualization unit provides a graph with neutral colors. This allows the visualization method to be adjusted based on the user's emotions. The criteria and methods for adjusting the visualization method can be clearly defined, for example, using graphs, charts, heatmaps, etc. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the visualization unit may be performed using AI, for example, or without AI. For example, the visualization unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the visualization method.

[0103] The visualization unit can adjust the level of detail of the visualization based on the importance of the feedback during visualization. For example, the visualization unit visualizes important feedback in detail. For example, the visualization unit visualizes less important feedback concisely. The visualization unit adjusts the level of detail of the visualization according to the importance of the feedback. This allows the level of detail of the visualization to be adjusted based on the importance of the feedback. The criteria and methods for adjusting the level of detail of the visualization can be clarified, for example, using the information compression rate or the number of displayed items. Some or all of the above processing in the visualization unit may be performed using AI, for example, or without AI. For example, the visualization unit can input feedback importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the visualization.

[0104] The visualization unit can apply different visualization methods depending on the category of feedback during visualization. For example, the visualization unit can apply a positive visualization method to positive feedback. For example, the visualization unit can apply a negative visualization method to negative feedback. For example, the visualization unit can apply a neutral visualization method to neutral feedback. This allows for the application of different visualization methods depending on the category of feedback. The specific types and application methods of visualization methods can be clearly shown using, for example, bar graphs, pie charts, scatter plots, etc. Some or all of the above-described processing in the visualization unit may be performed using, for example, AI, or not using AI. For example, the visualization unit can input feedback category data into a generating AI and have the generating AI execute the application of visualization methods.

[0105] The visualization unit can estimate the user's emotions and determine the priority of visualizations based on the estimated user emotions. For example, if the user has positive emotions, the visualization unit will prioritize visualizing positive feedback. For example, if the user has negative emotions, the visualization unit will prioritize visualizing negative feedback. For example, if the user has neutral emotions, the visualization unit will consider the overall balance when visualizing. This allows the visualization unit to determine the priority of visualizations based on the user's emotions. The criteria and methods for determining the priority of visualizations can be clarified, for example, using emotion scores or importance scores. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the visualization unit may be performed using AI, for example, or without AI. For example, the visualization unit can input user emotion data into the generative AI and have the generative AI perform the determination of the priority of visualizations.

[0106] The visualization unit can adjust the order of visualizations based on the submission date of the feedback during visualization. For example, the visualization unit may prioritize visualizing the most recent feedback. For example, the visualization unit may postpone older feedback. The visualization unit adjusts the order of visualizations based on the submission date. This allows the order of visualizations to be adjusted based on the submission date of the feedback. The method for obtaining and analyzing the submission date of feedback can be clarified, for example, by using a timestamp or submission date and time. Some or all of the above processing in the visualization unit may be performed using AI, for example, or without using AI. For example, the visualization unit can input the feedback submission date data into a generating AI and have the generating AI perform the adjustment of the visualization order.

[0107] The visualization unit can adjust the visualization format based on the relevance of the feedback during visualization. For example, the visualization unit prioritizes visualizing highly relevant feedback. For example, the visualization unit postpones visualizing less relevant feedback. The visualization unit adjusts the visualization format based on the relevance of the feedback. This allows the visualization format to be adjusted based on the relevance of the feedback. The criteria and methods for evaluating the relevance of feedback can be clarified, for example, using a co-occurrence network or similarity score. Some or all of the above processing in the visualization unit may be performed using AI, for example, or without AI. For example, the visualization unit can input feedback relevance data into a generating AI and have the generating AI perform the adjustment of the visualization format.

[0108] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0109] The analysis unit can estimate the user's emotions and adjust the analysis priority based on the estimated emotions. For example, if the user has positive emotions, positive comments can be prioritized for analysis. If the user has negative emotions, negative comments can be prioritized for analysis. If the user has neutral emotions, the analysis can be performed considering the overall balance. This allows the analysis priority to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI adjust the analysis priority.

[0110] The analysis unit can improve the accuracy of its analysis by considering the frequency of specific keywords and phrases when analyzing comments. For example, it can prioritize the analysis of comments where specific keywords frequently appear. It can extract important comments based on the frequency of phrase occurrences. It can analyze highly relevant comments by considering keyword combinations. This allows for improved analysis accuracy by considering the frequency of specific keywords and phrases. The criteria and methods for selecting specific keywords and phrases can be clearly defined using frequency or importance scores. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input specific keywords and phrases into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0111] The summarization unit can estimate the user's emotions and adjust the way the summary is expressed based on those emotions. For example, if the user has positive emotions, the summary can be expressed using positive language. If the user has negative emotions, the summary can be expressed using negative language. If the user has neutral emotions, the summary can be expressed using neutral language. This allows the summary to be expressed based on the user's emotions. The criteria and methods for adjusting the summary's expression can be clearly defined using positive or negative language. Emotion estimation is achieved using an emotion engine or generative AI. The generative AI is, but is not limited to, text-generating AI or multimodal-generating AI. Some or all of the above-described processes in the summarization unit may be performed using AI or not. For example, the summarization unit can input user emotion data into the generative AI and have the generative AI adjust the summary's expression.

[0112] The summarization unit can adjust the level of detail in the summary based on the importance of the comments during summary generation. For example, important comments can be summarized in detail, while less important comments can be summarized concisely. The level of detail in the summary can be adjusted according to the importance of the comments. This allows the level of detail in the summary to be adjusted based on the importance of the comments. The criteria and methods for evaluating the importance of comments can be clearly defined using frequency or impact scores. Some or all of the above processing in the summarization unit may be performed using AI or not. For example, the summarization unit can input comment importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0113] The reporting unit can estimate the user's emotions and adjust the report's presentation based on those emotions. For example, if the user has positive emotions, the report can be written using positive language. If the user has negative emotions, the report can be written using negative language. If the user has neutral emotions, the report can be written using neutral language. This allows the report's presentation to be adjusted based on the user's emotions. The criteria and methods for adjusting the report's presentation can be clearly defined using positive or negative language. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI may include, but is not limited to, text-generating AI or multimodal-generating AI. Some or all of the above-described processes in the reporting unit may be performed using AI or not. For example, the reporting unit can input user emotion data into a generative AI and have the generative AI adjust the report's presentation.

[0114] The reporting unit can adjust the level of detail in a report based on the importance of the summarized feedback during report generation. For example, important feedback can be reported in detail, while less important feedback can be reported concisely. The level of detail in the report can be adjusted according to the importance of the feedback. This allows the level of detail in the report to be adjusted based on the importance of the summarized feedback. The criteria and methods for evaluating the importance of feedback can be clearly defined using frequency or impact scores. Some or all of the above processing in the reporting unit may be performed using AI or not. For example, the reporting unit can input feedback importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in the report.

[0115] The visualization unit can estimate the user's emotions and adjust the visualization method based on the estimated emotions. For example, if the user has positive emotions, a graph with bright colors can be provided. If the user has negative emotions, a graph with calm colors can be provided. If the user has neutral emotions, a graph with neutral colors can be provided. This allows the visualization method to be adjusted based on the user's emotions. The criteria and methods for adjusting the visualization method can be clearly defined using graphs, charts, heatmaps, etc. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the visualization unit may be performed using AI or not. For example, the visualization unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the visualization method.

[0116] The visualization unit can adjust the level of detail of the visualization based on the importance of the feedback during visualization. For example, important feedback can be visualized in detail, while less important feedback can be visualized concisely. The level of detail of the visualization can be adjusted according to the importance of the feedback. This allows the level of detail of the visualization to be adjusted based on the importance of the feedback. The criteria and methods for adjusting the level of detail of the visualization can be clarified using information compression ratios, the number of displayed items, etc. Some or all of the above processing in the visualization unit may be performed using AI, or not using AI. For example, the visualization unit can input feedback importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the visualization.

[0117] The analysis unit can optimize its analysis algorithm by referring to past analysis results when analyzing comments. For example, it can adjust the analysis algorithm based on past analysis results. It can learn from past analysis results and improve analysis accuracy. It can find specific patterns by referring to past analysis results. This allows the analysis algorithm to be optimized by referring to past analysis results. The method and criteria for referring to past analysis results can be clearly defined using past datasets or methods for adjusting the analysis algorithm. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input past analysis results into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0118] The visualization unit can estimate the user's emotions and determine visualization priorities based on the estimated emotions. For example, if the user has positive emotions, positive feedback can be visualized preferentially. If the user has negative emotions, negative feedback can be visualized preferentially. If the user has neutral emotions, visualizations can be made considering the overall balance. This allows the visualization priorities to be determined based on the user's emotions. The criteria and methods for determining visualization priorities can be clearly defined using emotion scores, importance scores, etc. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the visualization unit may be performed using AI or not. For example, the visualization unit can input user emotion data into a generative AI and have the generative AI determine the visualization priorities.

[0119] The following briefly describes the processing flow for example form 2.

[0120] Step 1: The analysis unit analyzes the comments. For example, the analysis unit analyzes the free-response section of a questionnaire and extracts key points and opinions. The analysis unit analyzes the comments using text mining technology, natural language processing technology, and sentiment analysis technology. Step 2: The summarization unit performs a summary based on the comments analyzed by the analysis unit. The summarization unit summarizes the extracted feedback and compiles it into a concise report. The summarization unit performs the summary using text generation AI, summarization algorithms, and natural language processing technology. Step 3: The reporting team compiles the feedback summarized by the summarizing team into a report. The reporting team compiles the summarized feedback into a text report, graph report, and dashboard. Step 4: The Sentiment Analysis Department performs sentiment analysis based on the report compiled by the Reporting Department. The Sentiment Analysis Department analyzes the sentiment of each comment and classifies them into positive, negative, and neutral opinions. Sentiment is analyzed using sentiment scores, keyword frequency, and natural language processing techniques. Step 5: The visualization unit visualizes the opinions classified by the sentiment analysis unit. The visualization unit provides the classified opinions in a visual format such as graphs and charts. Opinions are visualized using bar graphs, pie charts, and heatmaps.

[0121] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0122] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0123] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0124] Each of the multiple elements described above, including the analysis unit, summarization unit, reporting unit, sentiment analysis unit, and visualization unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 and analyzes the free comment portion of the questionnaire, extracting key points and opinions. The summarization unit is implemented by the identification processing unit 290 of the data processing unit 12 and summarizes the extracted feedback, compiling it into a concise report. The reporting unit is implemented by the control unit 46A of the smart device 14 and compiles the summarized feedback into a text report or graph report. The sentiment analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the sentiment of each comment, classifying it into positive, negative, or neutral opinions. The visualization unit is implemented by the control unit 46A of the smart device 14 and provides the classified opinions in a visual format such as a graph or chart. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0125] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0126] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0128] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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

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

[0131] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0132] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0133] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0135] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0136] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0137] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0138] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0139] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements described above, including the analysis unit, summarization unit, reporting unit, sentiment analysis unit, and visualization unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 and analyzes the free comment portion of the questionnaire, extracting key points and opinions. The summarization unit is implemented by the identification processing unit 290 of the data processing unit 12 and summarizes the extracted feedback, compiling it into a concise report. The reporting unit is implemented by the control unit 46A of the smart glasses 214 and compiles the summarized feedback into a text report or graph report. The sentiment analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the sentiment of each comment, classifying it into positive, negative, or neutral opinions. The visualization unit is implemented by the control unit 46A of the smart glasses 214 and provides the classified opinions in a visual format such as a graph or chart. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0141] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0142] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0144] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

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

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0147] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0148] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0149] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0150] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0151] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0153] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0154] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0155] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements described above, including the analysis unit, summarization unit, reporting unit, sentiment analysis unit, and visualization unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 and analyzes the free comment portion of the questionnaire, extracting key points and opinions. The summarization unit is implemented by the identification processing unit 290 of the data processing unit 12 and summarizes the extracted feedback, compiling it into a concise report. The reporting unit is implemented by the control unit 46A of the headset terminal 314 and compiles the summarized feedback into a text report or graph report. The sentiment analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the sentiment of each comment, classifying it into positive, negative, or neutral opinions. The visualization unit is implemented by the control unit 46A of the headset terminal 314 and provides the classified opinions in a visual format such as a graph or chart. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0157] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0158] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0159] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0160] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0161] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0163] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0164] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0165] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0166] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0167] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0168] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0169] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0170] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0171] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0172] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0173] Each of the multiple elements described above, including the analysis unit, summarization unit, reporting unit, sentiment analysis unit, and visualization unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 and analyzes the free comment portion of the questionnaire, extracting key points and opinions. The summarization unit is implemented by the identification processing unit 290 of the data processing unit 12 and summarizes the extracted feedback, compiling it into a concise report. The reporting unit is implemented by the control unit 46A of the robot 414 and compiles the summarized feedback into a text report or graph report. The sentiment analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the sentiment of each comment, classifying it into positive, negative, or neutral opinions. The visualization unit is implemented by the control unit 46A of the robot 414 and provides the classified opinions in a visual format such as a graph or chart. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0174] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0175] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0176] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0177] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0178] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0179] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0180] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0181] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0182] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0183] 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.

[0184] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0185] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0186] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0187] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0188] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0189] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0190] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0191] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0192] (Note 1) The analysis unit analyzes the comments, A summarization unit performs summarization based on comments analyzed by the aforementioned analysis unit, The report section compiles the feedback summarized by the summary section into a report, The emotion analysis department conducts emotion analysis based on the report compiled by the aforementioned report department, The system comprises a visualization unit that visualizes the opinions classified by the aforementioned sentiment analysis unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Analyze the free-response section of the survey to extract key points and opinions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The summary section above is, Summarize the extracted feedback and compile it into a concise report. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned emotion analysis unit, Analyze the sentiment behind each comment and classify them into positive, negative, or neutral opinions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The visualization unit is, The categorized opinions are presented in visual formats such as graphs and charts. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, We estimate the user's sentiment and adjust the comment analysis method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, When analyzing comments, consider the frequency of specific keywords and phrases to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When analyzing comments, the analysis algorithm is optimized by referring to past analysis results. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, It estimates the user's sentiment and determines the priority of comments to analyze based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, When analyzing comments, the system prioritizes analyzing comments that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When analyzing comments, the system analyzes the user's social media activity and identifies relevant comments. The system described in Appendix 1, characterized by the features described herein. (Note 12) The summary section above is, It estimates the user's emotions and adjusts the way the summary is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The summary section above is, When generating a summary, adjust the level of detail in the summary based on the importance of the comments. The system described in Appendix 1, characterized by the features described herein. (Note 14) The summary section above is, When generating summaries, different summarization algorithms are applied depending on the category of the comment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The summary section above is, It estimates the user's sentiment and adjusts the length of the summary based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The summary section above is, When generating summaries, prioritize summaries based on when comments were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 17) The summary section above is, When generating summaries, the order of summaries is adjusted based on the relevance of the comments. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned report section is, It estimates user sentiment and adjusts the way reports are presented based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned report section is, When generating a report, adjust the level of detail in the report based on the importance of the summarized feedback. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned report section is, When generating reports, different report formats are applied depending on the feedback category. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned report section is, It estimates the user's sentiment and adjusts the length of the report based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned report section is, When generating reports, prioritize reports based on when feedback was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned report section is, When generating reports, the order of reports is adjusted based on the relevance of the feedback. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned emotion analysis unit, It estimates the user's emotions and adjusts the criteria for sentiment analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned emotion analysis unit, When performing sentiment analysis, consider the context of the comment to improve the accuracy of sentiment classification. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned emotion analysis unit, During sentiment analysis, the analysis algorithm is optimized by referring to past sentiment analysis results. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned emotion analysis unit, It estimates the user's emotions and adjusts the order in which the sentiment analysis results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned emotion analysis unit, When performing sentiment analysis, the geographical distribution of comments is taken into consideration when classifying sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned emotion analysis unit, When performing sentiment analysis, referencing relevant literature for comments improves the accuracy of sentiment classification. The system described in Appendix 1, characterized by the features described herein. (Note 30) The visualization unit is, It estimates the user's emotions and adjusts the visualization method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The visualization unit is, When creating visualizations, adjust the level of detail based on the importance of the feedback. The system described in Appendix 1, characterized by the features described herein. (Note 32) The visualization unit is, When visualizing, apply different visualization techniques depending on the feedback category. The system described in Appendix 1, characterized by the features described herein. (Note 33) The visualization unit is, It estimates the user's emotions and determines the priority of visualizations based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The visualization unit is, When creating visualizations, adjust the order of visualizations based on when feedback is submitted. The system described in Appendix 1, characterized by the features described herein. (Note 35) The visualization unit is, When creating visualizations, adjust the visualization format based on the relevance of the feedback. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0193] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis unit analyzes the comments, A summarization unit performs summarization based on comments analyzed by the aforementioned analysis unit, The report section compiles the feedback summarized by the summary section into a report, The emotion analysis department conducts emotion analysis based on the report compiled by the aforementioned report department, The system comprises a visualization unit that visualizes the opinions classified by the aforementioned sentiment analysis unit. A system characterized by the following features.

2. The aforementioned analysis unit, Analyze the free-response section of the survey to extract key points and opinions. The system according to feature 1.

3. The summary section above is, Summarize the extracted feedback and compile it into a concise report. The system according to feature 1.

4. The aforementioned emotion analysis unit, Analyze the sentiment behind each comment and classify them into positive, negative, or neutral opinions. The system according to feature 1.

5. The visualization unit, The categorized opinions are presented in visual formats such as graphs and charts. The system according to feature 1.

6. The aforementioned analysis unit, We estimate the user's sentiment and adjust the comment analysis method based on the estimated user sentiment. The system according to feature 1.

7. The aforementioned analysis unit, When analyzing comments, consider the frequency of specific keywords and phrases to improve the accuracy of the analysis. The system according to feature 1.

8. The aforementioned analysis unit, When analyzing comments, the analysis algorithm is optimized by referring to past analysis results. The system according to feature 1.

Images