system

Abstract

The system according to this embodiment aims to efficiently collect, analyze, and visually understand opinions on social media. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a classification unit, and a visualization unit. The collection unit collects opinions from social media. The analysis unit analyzes the opinions collected by the collection unit. The classification unit classifies the opinions analyzed by the analysis unit. The visualization unit maps and visualizes the opinions classified by the classification 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to efficiently collect and analyze a huge number of opinions on SNS and visually grasp them.

[0005] The system according to the embodiment aims to efficiently collect and analyze opinions on SNS and visually grasp them.

Means for Solving the Problems

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a classification unit, and a visualization unit. The collection unit collects opinions on SNS. The analysis unit analyzes the opinions collected by the collection unit. The classification unit classifies the opinions analyzed by the analysis unit. The visualization unit maps and visualizes the opinions classified by the classification unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently collect and analyze opinions on social media and grasp them visually. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage device 32. The processor 28, the RAM 30, and the storage device 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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage device 50. The processor 46, the RAM 48, and the storage device 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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 opinion aggregation system according to an embodiment of the present invention is a system that uses AI to aggregate, map, and visualize various opinions posted on social media. This opinion aggregation system allows for an overview of what kinds of opinions and evaluations are being made. This enables a multifaceted understanding of user voices. For example, the opinion aggregation system first collects opinions posted on social media. Next, the AI ​​analyzes the collected opinions and classifies their content and evaluations. The classified opinions are then mapped and visualized by the opinion aggregation system. This allows for a quick grasp of user opinions and evaluations. For example, it allows for an overview of the overall picture of opinions, similar to a news program that provides an overview of social media reactions to an election. Furthermore, the opinion aggregation system can be used to improve products and services by providing an overview of social media evaluations of a company's services. By classifying opinions into positive, neutral, and negative, and providing example comments, it is possible to capture user voices from multiple perspectives. This eliminates human bias during aggregation and allows for the confirmation of a wide range of opinions. As a result, the opinion aggregation system can capture user voices from multiple perspectives and use this to improve products and services.

[0029] The opinion aggregation system according to this embodiment comprises a collection unit, an analysis unit, a classification unit, and a visualization unit. The collection unit collects opinions from social networking services (SNS). The collection unit can collect opinions from, for example, SNS platforms. The collection unit can collect opinions using APIs. The collection unit can also collect opinions using scraping techniques. For example, the collection unit can collect posts containing specific hashtags using SNS APIs. The collection unit can also collect posts containing specific keywords using SNS APIs. Furthermore, the collection unit can also collect posts containing specific hashtags using SNS APIs. The analysis unit analyzes the opinions collected by the collection unit. The analysis unit can analyze opinions using, for example, text mining techniques. The analysis unit can also analyze the sentiment of opinions using sentiment analysis techniques. The analysis unit can also analyze the topics of opinions using topic modeling techniques. For example, the analysis unit can extract important keywords from opinions using text mining techniques. The analysis unit can also classify the sentiment of opinions into positive, neutral, and negative using sentiment analysis techniques. Furthermore, the analysis unit can automatically classify the topics of opinions using topic modeling techniques. The classification unit classifies the opinions analyzed by the analysis unit. The classification unit can classify opinions using, for example, machine learning algorithms. The classification unit can also classify opinions using rule-based methods. For example, the classification unit can classify opinions into positive, neutral, and negative using machine learning algorithms. The classification unit can also classify opinions containing specific keywords into specific categories using rule-based methods. The visualization unit maps and visualizes the opinions classified by the classification unit. The visualization unit can visualize opinions using, for example, graphs and charts. The visualization unit can also visualize opinions using heatmaps. For example, the visualization unit can display the proportion of positive, neutral, and negative opinions in a pie chart. The visualization unit can also display the distribution of opinions by topic in a bar graph. Furthermore, the visualization unit can display changes in the sentiment of opinions using a heatmap.As a result, the opinion aggregation system according to this embodiment can efficiently collect, analyze, classify, and visualize opinions on social media.

[0030] The data collection unit collects opinions from social media. For example, it can collect opinions from social media platforms. It can also collect opinions using APIs. Furthermore, it can collect opinions using scraping techniques. Specifically, the data collection unit can use social media APIs to collect posts containing specific hashtags. For example, by specifying hashtags such as #environmentalissues or #socialissues, it can efficiently collect relevant posts. The data collection unit can also use social media APIs to collect posts containing specific keywords. For example, by specifying keywords such as "climate change" or "energy policy," it can collect relevant posts. Additionally, the data collection unit can use social media APIs to collect posts containing specific hashtags. For example, by specifying hashtags such as #sustainability or #ecolife, it can collect relevant posts. By using these APIs, the data collection unit can efficiently collect a large volume of opinions in real time. Furthermore, the data collection unit can use scraping techniques to collect opinions from platforms that do not provide APIs. For example, it can extract opinions from specific websites or forums by analyzing their HTML structure. This allows the data collection unit to gather diverse opinions from a wide range of sources. Furthermore, the data collection unit stores the collected opinions in a database, making them accessible to subsequent analysis and classification units. The data collection unit also performs filtering to eliminate data duplication and maintain data integrity. As a result, the data collection unit can collect opinions efficiently and accurately, improving the overall system performance.

[0031] The analysis unit analyzes the opinions collected by the collection unit. For example, the analysis unit can analyze opinions using text mining techniques. Specifically, it can extract important keywords from the opinions using text mining techniques. For instance, by extracting keywords such as "environmental protection" or "renewable energy," the content of the opinions can be understood. The analysis unit can also analyze the sentiment of the opinions using sentiment analysis techniques. Sentiment analysis techniques allow for the classification of opinions into positive, neutral, and negative categories. For example, it can detect positive expressions such as "excellent" and "good," and negative expressions such as "bad" and "problem." Furthermore, the analysis unit can analyze the topics of the opinions using topic modeling techniques. Topic modeling techniques allow for the automatic classification of opinion topics. For example, opinions can be classified into topics such as "environmental issues" or "energy policy." By combining these techniques, the analysis unit can analyze the collected opinions from multiple perspectives, understanding their content, sentiment, and topics. Additionally, the analysis unit can utilize past data and statistical information to analyze long-term trends and patterns. For example, by analyzing changes in opinions on a specific topic based on past opinion data, it is possible to predict future trends. This allows the analysis unit to handle not only real-time opinion analysis but also long-term opinion fluctuations and trend analysis.

[0032] The classification unit classifies the opinions analyzed by the analysis unit. The classification unit can classify opinions using, for example, machine learning algorithms. Specifically, it can classify opinions into positive, neutral, and negative categories using machine learning algorithms. For example, it can classify the sentiment of opinions using algorithms such as Support Vector Machines (SVM) and Random Forests. The classification unit can also classify opinions using rule-based methods. For example, it can classify opinions containing specific keywords into specific categories. For example, it can classify opinions containing the keyword "environmental protection" into the "environmental issues" category. By combining these techniques, the classification unit can classify opinions from multiple perspectives and grasp the content, sentiment, and topic of the opinions. Furthermore, the classification unit stores the classification results in a database so that the subsequent visualization unit can access them. To improve the accuracy of the classification results, the classification unit periodically retrains its models and reviews its rules. This allows the classification unit to classify opinions efficiently and accurately, improving the overall system performance.

[0033] The visualization unit maps and visualizes opinions classified by the classification unit. The visualization unit can visualize opinions using graphs and charts, for example. Specifically, it can display the proportion of positive, neutral, and negative opinions in a pie chart. For example, it can visually display a pie chart showing that 60% of opinions are positive, 30% are neutral, and 10% are negative. The visualization unit can also display the distribution of opinions by topic in a bar graph. For example, it can display a bar graph showing that 40% of opinions are on "environmental issues," 30% on "energy policy," and 20% on "social issues." Furthermore, the visualization unit can display changes in the sentiment of opinions using a heatmap. For example, it can visually display the increase or decrease in positive or negative opinions over a specific period using a heatmap. By combining these visualization technologies, the visualization unit can provide a multifaceted understanding of the content, sentiment, and topics of opinions. In addition, the visualization unit provides a user-customizable dashboard, enabling users to quickly obtain necessary information. This allows the visualization unit to efficiently and effectively visualize opinions, thereby improving the overall performance of the system.

[0034] The classification unit can categorize opinions into positive, neutral, and negative. For example, the classification unit can categorize positive opinions based on positive keywords. The classification unit can also categorize neutral opinions based on keywords that are neither positive nor negative. The classification unit can also categorize negative opinions based on negative keywords. This makes it easier to grasp opinion trends by classifying opinions into positive, neutral, and negative. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can use an AI model to classify keywords in order to categorize positive, neutral, and negative opinions.

[0035] The visualization unit can display specific comment examples. For example, the visualization unit can display randomly selected comment examples. For example, the visualization unit can display representative comment examples. For example, the visualization unit can display positive comment examples, neutral comment examples, and negative comment examples, respectively. In this way, the visualization unit can provide specific comment examples, allowing for a more concrete understanding of the content of the opinions. 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 use an AI model to extract and display representative comment examples from the opinions.

[0036] The collection unit can collect opinions posted on social media. The collection unit can collect opinions from social media platforms, for example. The collection unit can collect opinions using APIs, for example. The collection unit can also collect opinions using scraping techniques, for example. This allows the collection unit to gather a wide range of opinions by collecting opinions posted on social media. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can automatically collect opinions on social media using an AI model.

[0037] The analysis unit can analyze the collected opinions. The analysis unit can analyze opinions using, for example, text mining techniques. The analysis unit can also analyze the sentiment of opinions using, for example, sentiment analysis techniques. The analysis unit can also analyze the topic of opinions using, for example, topic modeling techniques. In this way, the analysis unit makes the content of the opinions easier to understand by analyzing the collected opinions. 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 use an AI model to analyze the sentiment of the collected opinions.

[0038] The visualization unit can map and visualize the classified opinions. The visualization unit can visualize opinions using graphs or charts, for example. The visualization unit can also visualize opinions using heatmaps, for example. In this way, the visualization unit makes it easier to grasp the overall picture of opinions by mapping and visualizing the classified opinions. 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 perform opinion mapping and visualization using an AI model.

[0039] The data collection unit can analyze a user's past posting history and select the optimal data collection method. For example, the data collection unit can analyze the time periods when a user frequently posted in the past and collect opinions during those times. For example, the data collection unit can analyze the content of a user's past posts and prioritize collecting opinions on specific topics. For example, the data collection unit can analyze a user's posting frequency and prioritize collecting opinions from active users. In this way, the data collection unit can select the optimal data collection method by analyzing a user's past posting history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's past posting history data into a generating AI and have the generating AI select the optimal data collection method.

[0040] The collection unit can filter opinions based on specific keywords or hashtags. For example, the collection unit can collect only posts containing specific keywords to gather highly relevant opinions. The collection unit can also filter opinions based on hashtags to collect opinions on specific topics. The collection unit can also use combinations of keywords and hashtags to collect opinions with greater accuracy. This allows the collection unit to collect highly relevant opinions by filtering based on specific keywords or hashtags. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input posts containing specific keywords or hashtags into a generating AI and have the generating AI perform the filtering.

[0041] The collection unit can prioritize collecting highly relevant opinions by considering the user's geographical location information when gathering opinions. For example, the collection unit can prioritize collecting opinions related to a region based on the user's current location. The collection unit can also, for example, collect opinions about a specific region and understand the trends in opinions for each region. The collection unit can also, for example, prioritize collecting opinions related to events or incidents based on geographical location information. In this way, the collection unit can prioritize collecting opinions related to a region by considering the user's geographical location information. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's geographical location information into a generating AI and have the generating AI perform the collection of highly relevant opinions.

[0042] The collection unit can analyze a user's social media activity and collect relevant opinions when gathering opinions. For example, the collection unit can prioritize collecting influential opinions based on a user's follower count and engagement rate. The collection unit can also analyze a user's past posts and collect relevant opinions. For example, the collection unit can prioritize collecting opinions from active users based on the frequency of their social media activity. In this way, the collection unit can collect relevant opinions by analyzing a user's social media activity. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input user social media activity data into a generating AI and have the generating AI collect relevant opinions.

[0043] The analysis unit can adjust the level of detail of the analysis based on the importance of the opinions during the analysis. For example, the analysis unit can perform a detailed analysis on highly important opinions and suggest specific areas for improvement. For example, the analysis unit can perform a simplified analysis on less important opinions to grasp the overall trend. For example, the analysis unit can perform an analysis with an appropriate level of detail on opinions of moderate importance to provide a balanced analysis result. In this way, the analysis unit can analyze important opinions in detail by adjusting the level of detail of the analysis based on the importance of the opinions. 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 opinion importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0044] The analysis unit can apply different analysis algorithms depending on the category of the opinion during analysis. For example, the analysis unit can apply a sentiment analysis algorithm to positive opinions to extract specific positive elements. For example, the analysis unit can apply a problem identification algorithm to negative opinions to suggest specific areas for improvement. For example, the analysis unit can apply a topic classification algorithm to neutral opinions to grasp the overall picture of the opinion. In this way, the analysis unit can provide more accurate analysis results by applying different analysis algorithms depending on the category of the opinion. 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 opinion category data into a generating AI and have the generating AI execute the application of different analysis algorithms.

[0045] The analysis unit can determine the priority of analysis based on the timing of opinion submissions during the analysis process. For example, the analysis unit can prioritize the analysis of the most recent opinions to grasp real-time trends in opinions. The analysis unit can also analyze past opinions to grasp long-term changes in opinions. The analysis unit can also prioritize the analysis of opinions related to specific events or incidents to grasp the impact of those events. As a result, the analysis unit can prioritize the analysis of the most recent opinions by determining the priority of analysis based on the timing of opinion submissions. 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 opinion submission timing data into a generating AI and have the generating AI perform the determination of analysis priorities.

[0046] The analysis unit can adjust the order of analysis based on the relevance of opinions during the analysis process. For example, the analysis unit can prioritize the analysis of highly relevant opinions to grasp the overall trend of opinions. For example, the analysis unit can postpone the analysis of less relevant opinions and prioritize the analysis of important opinions. For example, the analysis unit can dynamically adjust the order of analysis based on the relevance of opinions to perform efficient analysis. This enables efficient analysis by adjusting the order of analysis based on the relevance of opinions. 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 opinion relevance data into a generating AI and have the generating AI perform the adjustment of the analysis order.

[0047] The classification unit can improve the accuracy of classification by considering the interrelationships between opinions during the classification process. For example, the classification unit can analyze the interrelationships between opinions, group related opinions together, and classify them. For example, the classification unit can also improve the accuracy of classification by eliminating duplicate opinions based on the interrelationships between opinions. For example, the classification unit can classify opinions in a way that makes it easier to grasp the overall picture of opinions by considering the interrelationships between opinions. In this way, the classification unit improves the accuracy of classification by considering the interrelationships between opinions. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input the interrelationship data of opinions into a generating AI and have the generating AI perform the improvement of classification accuracy.

[0048] The classification unit can perform classification while considering the attribute information of the opinion poster. For example, the classification unit can classify opinions by attribute based on the poster's age and gender. For example, the classification unit can also classify opinions by region based on the poster's regional information. For example, the classification unit can classify related opinions based on the poster's interests. This allows the classification unit to perform more detailed classification by considering the attribute information of the opinion poster. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input the poster's attribute information data into a generating AI and have the generating AI perform the classification.

[0049] The classification unit can perform classification while considering the geographical distribution of opinions. For example, the classification unit can classify opinions by region based on geographical distribution. The classification unit can also grasp the trends in opinions by region by considering geographical distribution. For example, the classification unit can clarify the differences in opinions by region based on geographical distribution. In this way, the classification unit makes it easier to grasp the trends in opinions by region by considering the geographical distribution of opinions. Some or all of the above processing in the classification unit may be performed using AI, for example, or without using AI. For example, the classification unit can input geographical distribution data of opinions into a generating AI and have the generating AI perform the classification.

[0050] The classification unit can improve the accuracy of its classification by referring to relevant literature for the opinions during the classification process. For example, the classification unit sets classification criteria for opinions based on relevant literature. The classification unit can also improve the accuracy of opinion classification by referring to relevant literature. The classification unit can also verify the classification results of opinions based on relevant literature. As a result, the classification unit improves the accuracy of its classification by referring to relevant literature for the opinions. Some or all of the above processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input relevant literature data for opinions into a generating AI and have the generating AI perform the task of improving the accuracy of the classification.

[0051] The visualization unit can optimize the current visualization by referring to past visualization data during visualization. For example, the visualization unit can adjust the display method of the current visualization based on past visualization data. For example, the visualization unit can also provide a visualization tailored to the user's preferences by referring to past visualization data. For example, the visualization unit can improve the accuracy of the current visualization based on past visualization data. In this way, the visualization unit improves the accuracy of the current visualization by referring to past visualization data. Some or all of the above processes in the visualization unit may be performed using AI, for example, or without using AI. For example, the visualization unit can input past visualization data into a generating AI and have the generating AI perform the optimization of the current visualization.

[0052] The visualization unit can apply different visualization methods to each category of opinion during visualization. For example, the visualization unit can provide visualizations using bright colors and positive expressions for positive opinions. For example, the visualization unit can provide visualizations that highlight problems and clarify areas for improvement for negative opinions. For example, the visualization unit can provide visualizations based on objective data for neutral opinions. This allows the visualization unit to provide more appropriate visualizations by applying different visualization methods to each category of opinion. 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 opinion category data into a generating AI and have the generating AI execute the application of different visualization methods.

[0053] The visualization unit can analyze changes in the visualization based on the timing of opinion submissions during visualization. For example, the visualization unit can visualize real-time opinion trends based on the latest opinions. The visualization unit can also visualize long-term changes in opinions based on past opinions. For example, the visualization unit can visualize the impact of an event based on opinions related to a specific event or incident. This makes it easier to understand changes in opinions by analyzing changes in the visualization based on the timing of opinion submissions. 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 opinion submission timing data into a generating AI and have the generating AI perform an analysis of changes in the visualization.

[0054] The visualization unit can analyze the visualization by referring to relevant market data for the opinions during the visualization process. For example, the visualization unit can visualize opinion trends based on market data. The visualization unit can also visualize the relationships between opinions by referring to market data. For example, the visualization unit can also visualize the impact of opinions based on market data. This improves the accuracy of the visualization by allowing the visualization unit to refer to relevant market data for the opinions. 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 relevant market data for opinions into a generating AI and have the generating AI perform the visualization analysis.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The opinion aggregation system may also include a reliability evaluation unit that analyzes the user's past behavior history and evaluates the reliability of opinions. For example, the reliability evaluation unit can rate the reliability of an opinion highly if the user has consistently posted positive opinions in the past. Conversely, it can rate the reliability of an opinion low if the user has posted many negative opinions in the past. This allows the reliability evaluation unit to prioritize highly reliable opinions by evaluating their reliability based on the user's past behavior history. For example, if the reliability evaluation unit has consistently posted positive opinions in the past, it can rate the reliability of that opinion highly and highlight the positive aspects of the product or service. Conversely, if the reliability evaluation unit has posted many negative opinions in the past, it can rate the reliability of that opinion low and identify problems early. Furthermore, if the reliability evaluation unit has posted many neutral opinions in the past, it can rate the reliability of that opinion moderately and provide objective data.

[0057] The opinion aggregation system may also include a geographic information collection unit that collects opinions while considering the user's geographic location. For example, the geographic information collection unit can prioritize collecting opinions related to a specific region based on the user's current location. Furthermore, the geographic information collection unit can collect opinions on a specific region and understand the trends in opinions for each region. This allows the geographic information collection unit to prioritize collecting opinions related to a specific region by considering the user's geographic location. For example, the geographic information collection unit can prioritize collecting opinions related to a specific region based on the user's current location and understand the trends in opinions for each region. The geographic information collection unit can also collect opinions on a specific region and clarify the differences in opinions for each region. Additionally, the geographic information collection unit can prioritize collecting opinions related to events and occurrences based on geographic location information.

[0058] The opinion aggregation system may further include a collection method selection unit that analyzes the user's past posting history and selects the optimal collection method. For example, the collection method selection unit can analyze the time periods when the user frequently posted in the past and collect opinions during those times. Furthermore, the collection method selection unit can analyze the content of the user's past posts and prioritize the collection of opinions on specific topics. Thus, the collection method selection unit can select the optimal collection method by analyzing the user's past posting history. For example, the collection method selection unit can analyze the time periods when the user frequently posted in the past and collect opinions during those times. Furthermore, the collection method selection unit can analyze the content of the user's past posts and prioritize the collection of opinions on specific topics. In addition, the collection method selection unit can analyze the user's posting frequency and prioritize the collection of opinions from active users.

[0059] The opinion aggregation system can further include a social media analysis unit that analyzes users' social media activity and collects relevant opinions. The social media analysis unit can, for example, prioritize collecting influential opinions based on a user's follower count and engagement rate. It can also analyze a user's past posts and collect relevant opinions. Thus, the social media analysis unit can collect relevant opinions by analyzing a user's social media activity. For example, the social media analysis unit can prioritize collecting influential opinions based on a user's follower count and engagement rate. It can also analyze a user's past posts and collect relevant opinions. Furthermore, the social media analysis unit can prioritize collecting opinions from active users based on the frequency of their social media activity.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The collection unit collects opinions from social media. The collection unit can collect opinions from social media platforms, for example. The collection unit can collect opinions using APIs. The collection unit can also collect opinions using scraping techniques. For example, the collection unit can use social media APIs to collect posts containing specific hashtags. The collection unit can also use social media APIs to collect posts containing specific keywords. Furthermore, the collection unit can use social media APIs to collect posts containing specific hashtags. Step 2: The analysis unit analyzes the opinions collected by the collection unit. The analysis unit can analyze opinions using, for example, text mining techniques. The analysis unit can also analyze the sentiment of opinions using sentiment analysis techniques. Furthermore, the analysis unit can analyze the topic of opinions using topic modeling techniques. For example, the analysis unit can extract important keywords from opinions using text mining techniques. The analysis unit can also classify the sentiment of opinions into positive, neutral, and negative using sentiment analysis techniques. In addition, the analysis unit can automatically classify the topic of opinions using topic modeling techniques. Step 3: The classification unit classifies the opinions analyzed by the analysis unit. The classification unit can classify opinions using, for example, a machine learning algorithm. The classification unit can also classify opinions using a rule-based approach. For example, the classification unit can classify opinions into positive, neutral, and negative using a machine learning algorithm. Alternatively, the classification unit can classify opinions containing specific keywords into specific categories using a rule-based approach. Step 4: The visualization unit maps and visualizes the opinions classified by the classification unit. The visualization unit can visualize opinions using graphs and charts, for example. The visualization unit can also visualize opinions using heatmaps. For example, the visualization unit can display the proportion of positive, neutral, and negative opinions in a pie chart. The visualization unit can also display the distribution of opinions by topic in a bar graph. Furthermore, the visualization unit can display changes in the sentiment of opinions using a heatmap.

[0062] (Example of form 2) The opinion aggregation system according to an embodiment of the present invention is a system that uses AI to aggregate, map, and visualize various opinions posted on social media. This opinion aggregation system allows for an overview of what kinds of opinions and evaluations are being made. This enables a multifaceted understanding of user voices. For example, the opinion aggregation system first collects opinions posted on social media. Next, the AI ​​analyzes the collected opinions and classifies their content and evaluations. The classified opinions are then mapped and visualized by the opinion aggregation system. This allows for a quick grasp of user opinions and evaluations. For example, it allows for an overview of the overall picture of opinions, similar to a news program that provides an overview of social media reactions to an election. Furthermore, the opinion aggregation system can be used to improve products and services by providing an overview of social media evaluations of a company's services. By classifying opinions into positive, neutral, and negative, and providing example comments, it is possible to capture user voices from multiple perspectives. This eliminates human bias during aggregation and allows for the confirmation of a wide range of opinions. As a result, the opinion aggregation system can capture user voices from multiple perspectives and use this to improve products and services.

[0063] The opinion aggregation system according to this embodiment comprises a collection unit, an analysis unit, a classification unit, and a visualization unit. The collection unit collects opinions from social networking services (SNS). The collection unit can collect opinions from, for example, SNS platforms. The collection unit can collect opinions using APIs. The collection unit can also collect opinions using scraping techniques. For example, the collection unit can collect posts containing specific hashtags using SNS APIs. The collection unit can also collect posts containing specific keywords using SNS APIs. Furthermore, the collection unit can also collect posts containing specific hashtags using SNS APIs. The analysis unit analyzes the opinions collected by the collection unit. The analysis unit can analyze opinions using, for example, text mining techniques. The analysis unit can also analyze the sentiment of opinions using sentiment analysis techniques. The analysis unit can also analyze the topics of opinions using topic modeling techniques. For example, the analysis unit can extract important keywords from opinions using text mining techniques. The analysis unit can also classify the sentiment of opinions into positive, neutral, and negative using sentiment analysis techniques. Furthermore, the analysis unit can automatically classify the topics of opinions using topic modeling techniques. The classification unit classifies the opinions analyzed by the analysis unit. The classification unit can classify opinions using, for example, machine learning algorithms. The classification unit can also classify opinions using rule-based methods. For example, the classification unit can classify opinions into positive, neutral, and negative using machine learning algorithms. The classification unit can also classify opinions containing specific keywords into specific categories using rule-based methods. The visualization unit maps and visualizes the opinions classified by the classification unit. The visualization unit can visualize opinions using, for example, graphs and charts. The visualization unit can also visualize opinions using heatmaps. For example, the visualization unit can display the proportion of positive, neutral, and negative opinions in a pie chart. The visualization unit can also display the distribution of opinions by topic in a bar graph. Furthermore, the visualization unit can display changes in the sentiment of opinions using a heatmap.As a result, the opinion aggregation system according to this embodiment can efficiently collect, analyze, classify, and visualize opinions on social media.

[0064] The data collection unit collects opinions from social media. For example, it can collect opinions from social media platforms. It can also collect opinions using APIs. Furthermore, it can collect opinions using scraping techniques. Specifically, the data collection unit can use social media APIs to collect posts containing specific hashtags. For example, by specifying hashtags such as #environmentalissues or #socialissues, it can efficiently collect relevant posts. The data collection unit can also use social media APIs to collect posts containing specific keywords. For example, by specifying keywords such as "climate change" or "energy policy," it can collect relevant posts. Additionally, the data collection unit can use social media APIs to collect posts containing specific hashtags. For example, by specifying hashtags such as #sustainability or #ecolife, it can collect relevant posts. By using these APIs, the data collection unit can efficiently collect a large volume of opinions in real time. Furthermore, the data collection unit can use scraping techniques to collect opinions from platforms that do not provide APIs. For example, it can analyze the HTML structure of specific websites or forums to extract opinions. This allows the data collection unit to gather diverse opinions from a wide range of sources. Furthermore, the data collection unit stores the collected opinions in a database, making them accessible to subsequent analysis and classification units. The data collection unit also performs filtering to eliminate data duplication and maintain data integrity. As a result, the data collection unit can collect opinions efficiently and accurately, improving the overall system performance.

[0065] The analysis unit analyzes the opinions collected by the collection unit. For example, the analysis unit can analyze opinions using text mining techniques. Specifically, it can extract important keywords from the opinions using text mining techniques. For instance, by extracting keywords such as "environmental protection" or "renewable energy," the content of the opinions can be understood. The analysis unit can also analyze the sentiment of the opinions using sentiment analysis techniques. Sentiment analysis techniques allow for the classification of opinions into positive, neutral, and negative categories. For example, it can detect positive expressions such as "excellent" and "good," and negative expressions such as "bad" and "problem." Furthermore, the analysis unit can analyze the topics of the opinions using topic modeling techniques. Topic modeling techniques allow for the automatic classification of opinion topics. For example, opinions can be classified into topics such as "environmental issues" or "energy policy." By combining these techniques, the analysis unit can analyze the collected opinions from multiple perspectives, understanding their content, sentiment, and topics. Additionally, the analysis unit can utilize past data and statistical information to analyze long-term trends and patterns. For example, by analyzing changes in opinions on a specific topic based on past opinion data, it is possible to predict future trends. This allows the analysis unit to handle not only real-time opinion analysis but also long-term opinion fluctuations and trend analysis.

[0066] The classification unit classifies the opinions analyzed by the analysis unit. The classification unit can classify opinions using, for example, machine learning algorithms. Specifically, it can classify opinions into positive, neutral, and negative categories using machine learning algorithms. For example, it can classify the sentiment of opinions using algorithms such as Support Vector Machines (SVM) and Random Forests. The classification unit can also classify opinions using rule-based methods. For example, it can classify opinions containing specific keywords into specific categories. For example, it can classify opinions containing the keyword "environmental protection" into the "environmental issues" category. By combining these techniques, the classification unit can classify opinions from multiple perspectives and grasp the content, sentiment, and topic of the opinions. Furthermore, the classification unit stores the classification results in a database so that the subsequent visualization unit can access them. To improve the accuracy of the classification results, the classification unit periodically retrains its models and reviews its rules. This allows the classification unit to classify opinions efficiently and accurately, improving the overall system performance.

[0067] The visualization unit maps and visualizes opinions classified by the classification unit. The visualization unit can visualize opinions using graphs and charts, for example. Specifically, it can display the proportion of positive, neutral, and negative opinions in a pie chart. For example, it can visually display a pie chart showing that 60% of opinions are positive, 30% are neutral, and 10% are negative. The visualization unit can also display the distribution of opinions by topic in a bar graph. For example, it can display a bar graph showing that 40% of opinions are on "environmental issues," 30% on "energy policy," and 20% on "social issues." Furthermore, the visualization unit can display changes in the sentiment of opinions using a heatmap. For example, it can visually display the increase or decrease in positive or negative opinions over a specific period using a heatmap. By combining these visualization technologies, the visualization unit can provide a multifaceted understanding of the content, sentiment, and topics of opinions. In addition, the visualization unit provides a user-customizable dashboard, enabling users to quickly obtain necessary information. This allows the visualization unit to efficiently and effectively visualize opinions, thereby improving the overall performance of the system.

[0068] The classification unit can categorize opinions into positive, neutral, and negative. For example, the classification unit can categorize positive opinions based on positive keywords. The classification unit can also categorize neutral opinions based on keywords that are neither positive nor negative. The classification unit can also categorize negative opinions based on negative keywords. This makes it easier to grasp opinion trends by classifying opinions into positive, neutral, and negative. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can use an AI model to classify keywords in order to categorize positive, neutral, and negative opinions.

[0069] The visualization unit can display specific comment examples. For example, the visualization unit can display randomly selected comment examples. For example, the visualization unit can display representative comment examples. For example, the visualization unit can display positive comment examples, neutral comment examples, and negative comment examples, respectively. In this way, the visualization unit can provide specific comment examples, allowing for a more concrete understanding of the content of the opinions. 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 use an AI model to extract and display representative comment examples from the opinions.

[0070] The collection unit can collect opinions posted on social media. The collection unit can collect opinions from social media platforms, for example. The collection unit can collect opinions using APIs, for example. The collection unit can also collect opinions using scraping techniques, for example. This allows the collection unit to gather a wide range of opinions by collecting opinions posted on social media. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can automatically collect opinions on social media using an AI model.

[0071] The analysis unit can analyze the collected opinions. The analysis unit can analyze opinions using, for example, text mining techniques. The analysis unit can also analyze the sentiment of opinions using, for example, sentiment analysis techniques. The analysis unit can also analyze the topic of opinions using, for example, topic modeling techniques. In this way, the analysis unit makes the content of the opinions easier to understand by analyzing the collected opinions. 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 use an AI model to analyze the sentiment of the collected opinions.

[0072] The visualization unit can map and visualize the classified opinions. The visualization unit can visualize opinions using graphs or charts, for example. The visualization unit can also visualize opinions using heatmaps, for example. In this way, the visualization unit makes it easier to grasp the overall picture of opinions by mapping and visualizing the classified opinions. 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 perform opinion mapping and visualization using an AI model.

[0073] The data collection unit can estimate the user's emotions and adjust the timing of opinion collection based on the estimated emotions. For example, if the user is showing positive emotions, the data collection unit can collect opinions immediately and reflect them in real time. For example, if the user is showing negative emotions, the data collection unit can collect opinions after a certain period of time and observe changes in emotions. For example, if the user is showing neutral emotions, the data collection unit can collect opinions periodically to obtain stable data. This allows the data collection unit to collect opinions at a more appropriate time by adjusting the timing of opinion collection based on the user's emotions. 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 data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0074] The data collection unit can analyze a user's past posting history and select the optimal data collection method. For example, the data collection unit can analyze the time periods when a user frequently posted in the past and collect opinions during those times. For example, the data collection unit can analyze the content of a user's past posts and prioritize collecting opinions on specific topics. For example, the data collection unit can analyze a user's posting frequency and prioritize collecting opinions from active users. In this way, the data collection unit can select the optimal data collection method by analyzing a user's past posting history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's past posting history data into a generating AI and have the generating AI select the optimal data collection method.

[0075] The collection unit can filter opinions based on specific keywords or hashtags. For example, the collection unit can collect only posts containing specific keywords to gather highly relevant opinions. The collection unit can also filter opinions based on hashtags to collect opinions on specific topics. The collection unit can also use combinations of keywords and hashtags to collect opinions with greater accuracy. This allows the collection unit to collect highly relevant opinions by filtering based on specific keywords or hashtags. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input posts containing specific keywords or hashtags into a generating AI and have the generating AI perform the filtering.

[0076] The data collection unit can estimate the user's emotions and determine the priority of opinions to collect based on the estimated emotions. For example, the data collection unit can prioritize collecting opinions from users who express positive emotions to balance the overall opinions. For example, the data collection unit can prioritize collecting opinions from users who express negative emotions to identify problems early. For example, the data collection unit can prioritize collecting opinions from users who express neutral emotions to obtain objective data. In this way, the data collection unit can prioritize collecting important opinions by determining the priority of opinions to collect based on the user's emotions. 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 data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform the determination of opinion priorities.

[0077] The collection unit can prioritize collecting highly relevant opinions by considering the user's geographical location information when gathering opinions. For example, the collection unit can prioritize collecting opinions related to a region based on the user's current location. The collection unit can also, for example, collect opinions about a specific region and understand the trends in opinions for each region. The collection unit can also, for example, prioritize collecting opinions related to events or incidents based on geographical location information. In this way, the collection unit can prioritize collecting opinions related to a region by considering the user's geographical location information. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's geographical location information into a generating AI and have the generating AI perform the collection of highly relevant opinions.

[0078] The collection unit can analyze a user's social media activity and collect relevant opinions when gathering opinions. For example, the collection unit can prioritize collecting influential opinions based on a user's follower count and engagement rate. The collection unit can also analyze a user's past posts and collect relevant opinions. For example, the collection unit can prioritize collecting opinions from active users based on the frequency of their social media activity. In this way, the collection unit can collect relevant opinions by analyzing a user's social media activity. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input user social media activity data into a generating AI and have the generating AI collect relevant opinions.

[0079] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, the analysis unit can display analysis results using bright colors and positive expressions for opinions indicating positive emotions. For example, the analysis unit can also display analysis results that highlight problems and clarify areas for improvement for opinions indicating negative emotions. For example, the analysis unit can display analysis results based on objective data for opinions indicating neutral emotions. In this way, the analysis unit can provide more appropriate analysis results by adjusting the presentation of the analysis based on the user's emotions. 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 analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI adjust the presentation of the analysis.

[0080] The analysis unit can adjust the level of detail of the analysis based on the importance of the opinions during the analysis. For example, the analysis unit can perform a detailed analysis on highly important opinions and suggest specific areas for improvement. For example, the analysis unit can perform a simplified analysis on less important opinions to grasp the overall trend. For example, the analysis unit can perform an analysis with an appropriate level of detail on opinions of moderate importance to provide a balanced analysis result. In this way, the analysis unit can analyze important opinions in detail by adjusting the level of detail of the analysis based on the importance of the opinions. 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 opinion importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0081] The analysis unit can apply different analysis algorithms depending on the category of the opinion during analysis. For example, the analysis unit can apply a sentiment analysis algorithm to positive opinions to extract specific positive elements. For example, the analysis unit can apply a problem identification algorithm to negative opinions to suggest specific areas for improvement. For example, the analysis unit can apply a topic classification algorithm to neutral opinions to grasp the overall picture of the opinion. In this way, the analysis unit can provide more accurate analysis results by applying different analysis algorithms depending on the category of the opinion. 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 opinion category data into a generating AI and have the generating AI execute the application of different analysis algorithms.

[0082] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated emotions. For example, the analysis unit can provide a short, concise analysis of opinions indicating positive emotions. For example, the analysis unit can perform a detailed analysis of opinions indicating negative emotions and suggest specific areas for improvement. For example, the analysis unit can perform an analysis of a moderate length for opinions indicating neutral emotions and provide a balanced analysis result. In this way, the analysis unit can provide more appropriate analysis results by adjusting the length of the analysis based on the user's emotions. 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 analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI adjust the length of the analysis.

[0083] The analysis unit can determine the priority of analysis based on the timing of opinion submissions during the analysis process. For example, the analysis unit can prioritize the analysis of the most recent opinions to grasp real-time trends in opinions. The analysis unit can also analyze past opinions to grasp long-term changes in opinions. The analysis unit can also prioritize the analysis of opinions related to specific events or incidents to grasp the impact of those events. As a result, the analysis unit can prioritize the analysis of the most recent opinions by determining the priority of analysis based on the timing of opinion submissions. 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 opinion submission timing data into a generating AI and have the generating AI perform the determination of analysis priorities.

[0084] The analysis unit can adjust the order of analysis based on the relevance of opinions during the analysis process. For example, the analysis unit can prioritize the analysis of highly relevant opinions to grasp the overall trend of opinions. For example, the analysis unit can postpone the analysis of less relevant opinions and prioritize the analysis of important opinions. For example, the analysis unit can dynamically adjust the order of analysis based on the relevance of opinions to perform efficient analysis. This enables efficient analysis by adjusting the order of analysis based on the relevance of opinions. 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 opinion relevance data into a generating AI and have the generating AI perform the adjustment of the analysis order.

[0085] The classification unit can estimate the user's emotions and adjust the classification criteria based on the estimated emotions. For example, the classification unit may classify opinions that express positive emotions by emphasizing the positive elements. For example, the classification unit may classify opinions that express negative emotions by emphasizing the problems. For example, the classification unit may classify opinions that express neutral emotions using objective criteria. This allows the classification unit to perform more appropriate classifications by adjusting the classification criteria based on the user's emotions. 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 classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the classification criteria.

[0086] The classification unit can improve the accuracy of classification by considering the interrelationships between opinions during the classification process. For example, the classification unit can analyze the interrelationships between opinions, group related opinions together, and classify them. For example, the classification unit can also improve the accuracy of classification by eliminating duplicate opinions based on the interrelationships between opinions. For example, the classification unit can classify opinions in a way that makes it easier to grasp the overall picture of opinions by considering the interrelationships between opinions. In this way, the classification unit improves the accuracy of classification by considering the interrelationships between opinions. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input the interrelationship data of opinions into a generating AI and have the generating AI perform the improvement of classification accuracy.

[0087] The classification unit can perform classification while considering the attribute information of the opinion poster. For example, the classification unit can classify opinions by attribute based on the poster's age and gender. For example, the classification unit can also classify opinions by region based on the poster's regional information. For example, the classification unit can classify related opinions based on the poster's interests. This allows the classification unit to perform more detailed classification by considering the attribute information of the opinion poster. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input the poster's attribute information data into a generating AI and have the generating AI perform the classification.

[0088] The classification unit can estimate the user's emotions and adjust the order in which the classification results are displayed based on the estimated emotions. For example, the classification unit can prioritize the display of opinions showing positive emotions to balance the overall opinions. For example, the classification unit can prioritize the display of opinions showing negative emotions to identify problems early. For example, the classification unit can prioritize the display of opinions showing neutral emotions to provide objective data. This allows the classification unit to display more appropriate results by adjusting the order in which the classification results are displayed based on the user's emotions. 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 classification unit may be performed using AI, for example, or not using AI. For example, the classification unit can input user emotion data into the generative AI and have the generative AI adjust the display order of the classification results.

[0089] The classification unit can perform classification while considering the geographical distribution of opinions. For example, the classification unit can classify opinions by region based on geographical distribution. The classification unit can also grasp the trends in opinions by region by considering geographical distribution. For example, the classification unit can clarify the differences in opinions by region based on geographical distribution. In this way, the classification unit makes it easier to grasp the trends in opinions by region by considering the geographical distribution of opinions. Some or all of the above processing in the classification unit may be performed using AI, for example, or without using AI. For example, the classification unit can input geographical distribution data of opinions into a generating AI and have the generating AI perform the classification.

[0090] The classification unit can improve the accuracy of its classification by referring to relevant literature for the opinions during the classification process. For example, the classification unit sets classification criteria for opinions based on relevant literature. The classification unit can also improve the accuracy of opinion classification by referring to relevant literature. The classification unit can also verify the classification results of opinions based on relevant literature. As a result, the classification unit improves the accuracy of its classification by referring to relevant literature for the opinions. Some or all of the above processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input relevant literature data for opinions into a generating AI and have the generating AI perform the task of improving the accuracy of the classification.

[0091] The visualization unit can estimate the user's emotions and adjust the display method of the visualization based on the estimated user emotions. For example, the visualization unit can provide a visualization using bright colors and positive expressions to a user who exhibits positive emotions. For example, the visualization unit can also provide a visualization that highlights problems and clarifies areas for improvement to a user who exhibits negative emotions. For example, the visualization unit can provide a visualization based on objective data to a user who exhibits neutral emotions. In this way, the visualization unit can provide a more appropriate visualization by adjusting the display method of the visualization based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 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 adjust the display method of the visualization.

[0092] The visualization unit can optimize the current visualization by referring to past visualization data during visualization. For example, the visualization unit can adjust the display method of the current visualization based on past visualization data. For example, the visualization unit can also provide a visualization tailored to the user's preferences by referring to past visualization data. For example, the visualization unit can improve the accuracy of the current visualization based on past visualization data. In this way, the visualization unit improves the accuracy of the current visualization by referring to past visualization data. Some or all of the above processes in the visualization unit may be performed using AI, for example, or without using AI. For example, the visualization unit can input past visualization data into a generating AI and have the generating AI perform the optimization of the current visualization.

[0093] The visualization unit can apply different visualization methods to each category of opinion during visualization. For example, the visualization unit can provide visualizations using bright colors and positive expressions for positive opinions. For example, the visualization unit can provide visualizations that highlight problems and clarify areas for improvement for negative opinions. For example, the visualization unit can provide visualizations based on objective data for neutral opinions. This allows the visualization unit to provide more appropriate visualizations by applying different visualization methods to each category of opinion. 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 opinion category data into a generating AI and have the generating AI execute the application of different visualization methods.

[0094] The visualization unit can estimate the user's emotions and adjust the importance of visualizations based on the estimated user emotions. For example, the visualization unit can provide visualizations that emphasize positive opinions to users who exhibit positive emotions. For example, the visualization unit can also provide visualizations that emphasize problems to users who exhibit negative emotions. For example, the visualization unit can provide balanced visualizations to users who exhibit neutral emotions. This allows the visualization unit to provide more appropriate visualizations by adjusting the importance of visualizations based on the user's emotions. 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 a generative AI and have the generative AI adjust the importance of visualizations.

[0095] The visualization unit can analyze changes in the visualization based on the timing of opinion submissions during visualization. For example, the visualization unit can visualize real-time opinion trends based on the latest opinions. The visualization unit can also visualize long-term changes in opinions based on past opinions. For example, the visualization unit can visualize the impact of an event based on opinions related to a specific event or incident. This makes it easier to understand changes in opinions by analyzing changes in the visualization based on the timing of opinion submissions. 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 opinion submission timing data into a generating AI and have the generating AI perform an analysis of changes in the visualization.

[0096] The visualization unit can analyze the visualization by referring to relevant market data for the opinions during the visualization process. For example, the visualization unit can visualize opinion trends based on market data. The visualization unit can also visualize the relationships between opinions by referring to market data. For example, the visualization unit can also visualize the impact of opinions based on market data. This improves the accuracy of the visualization by allowing the visualization unit to refer to relevant market data for the opinions. 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 relevant market data for opinions into a generating AI and have the generating AI perform the visualization analysis.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] The opinion aggregation system may further include an evaluation unit that estimates user emotions and evaluates the importance of opinions based on those estimated emotions. The evaluation unit can, for example, highly value opinions expressing positive emotions and low value opinions expressing negative emotions. It can also moderately value opinions expressing neutral emotions. This allows the evaluation unit to prioritize important opinions by evaluating their importance based on user emotions. For example, the evaluation unit can highly value opinions expressing positive emotions to highlight the positive aspects of a product or service. It can also moderately value opinions expressing negative emotions to identify problems early. Furthermore, the evaluation unit can moderately value opinions expressing neutral emotions to provide objective data.

[0099] The opinion aggregation system may also include a reliability evaluation unit that analyzes the user's past behavior history and evaluates the reliability of opinions. For example, the reliability evaluation unit can rate the reliability of an opinion highly if the user has consistently posted positive opinions in the past. Conversely, it can rate the reliability of an opinion low if the user has posted many negative opinions in the past. This allows the reliability evaluation unit to prioritize highly reliable opinions by evaluating their reliability based on the user's past behavior history. For example, if the reliability evaluation unit has consistently posted positive opinions in the past, it can rate the reliability of that opinion highly and highlight the positive aspects of the product or service. Conversely, if the reliability evaluation unit has posted many negative opinions in the past, it can rate the reliability of that opinion low and identify problems early. Furthermore, if the reliability evaluation unit has posted many neutral opinions in the past, it can rate the reliability of that opinion moderately and provide objective data.

[0100] The opinion aggregation system may further include a display adjustment unit that estimates the user's emotions and adjusts how opinions are displayed based on those estimated emotions. For example, the display adjustment unit can display opinions indicating positive emotions in bright colors and opinions indicating negative emotions in dark colors. It can also display opinions indicating neutral emotions in neutral colors. This allows the display adjustment unit to provide a visually easy-to-understand display by adjusting how opinions are displayed based on the user's emotions. For example, the display adjustment unit can display opinions indicating positive emotions in bright colors to highlight the good points of a product or service. It can also display opinions indicating negative emotions in dark colors to help identify problems early. Furthermore, the display adjustment unit can display opinions indicating neutral emotions in neutral colors to provide objective data.

[0101] The opinion aggregation system may also include a geographic information collection unit that collects opinions while considering the user's geographic location. For example, the geographic information collection unit can prioritize collecting opinions related to a specific region based on the user's current location. Furthermore, the geographic information collection unit can collect opinions on a specific region and understand the trends in opinions for each region. This allows the geographic information collection unit to prioritize collecting opinions related to a specific region by considering the user's geographic location. For example, the geographic information collection unit can prioritize collecting opinions related to a specific region based on the user's current location and understand the trends in opinions for each region. The geographic information collection unit can also collect opinions on a specific region and clarify the differences in opinions for each region. Additionally, the geographic information collection unit can prioritize collecting opinions related to events and occurrences based on geographic location information.

[0102] The opinion aggregation system may further include a collection timing adjustment unit that estimates the user's emotions and adjusts the timing of opinion collection based on the estimated emotions. For example, if the user is showing positive emotions, the collection timing adjustment unit can collect opinions immediately and reflect them in real time. Also, if the user is showing negative emotions, the collection timing adjustment unit can collect opinions after a certain period of time and observe the change in emotions. In this way, the collection timing adjustment unit can collect opinions at a more appropriate time by adjusting the timing of opinion collection based on the user's emotions. For example, if the collection timing adjustment unit is showing positive emotions, it can collect opinions immediately and reflect them in real time. Also, if the user is showing negative emotions, the collection timing adjustment unit can collect opinions after a certain period of time and observe the change in emotions. Furthermore, if the user is showing neutral emotions, the collection timing adjustment unit can collect opinions periodically and obtain stable data.

[0103] The opinion aggregation system may further include a collection method selection unit that analyzes the user's past posting history and selects the optimal collection method. For example, the collection method selection unit can analyze the time periods when the user frequently posted in the past and collect opinions during those times. Furthermore, the collection method selection unit can analyze the content of the user's past posts and prioritize the collection of opinions on specific topics. Thus, the collection method selection unit can select the optimal collection method by analyzing the user's past posting history. For example, the collection method selection unit can analyze the time periods when the user frequently posted in the past and collect opinions during those times. Furthermore, the collection method selection unit can analyze the content of the user's past posts and prioritize the collection of opinions on specific topics. In addition, the collection method selection unit can analyze the user's posting frequency and prioritize the collection of opinions from active users.

[0104] The opinion aggregation system may further include a priority determination unit that estimates user emotions and determines the priority of opinions to collect based on the estimated emotions. For example, the priority determination unit can prioritize collecting opinions from users exhibiting positive emotions to balance the overall opinions. It can also prioritize collecting opinions from users exhibiting negative emotions to identify problems early. Thus, by determining the priority of opinions to collect based on user emotions, the priority determination unit can prioritize the collection of important opinions. For example, it can prioritize collecting opinions from users exhibiting positive emotions to balance the overall opinions. It can also prioritize collecting opinions from users exhibiting negative emotions to identify problems early. Furthermore, it can prioritize collecting opinions from users exhibiting neutral emotions to provide objective data.

[0105] The opinion aggregation system can further include a social media analysis unit that analyzes users' social media activity and collects relevant opinions. The social media analysis unit can, for example, prioritize collecting influential opinions based on a user's follower count and engagement rate. It can also analyze a user's past posts and collect relevant opinions. Thus, the social media analysis unit can collect relevant opinions by analyzing a user's social media activity. For example, the social media analysis unit can prioritize collecting influential opinions based on a user's follower count and engagement rate. It can also analyze a user's past posts and collect relevant opinions. Furthermore, the social media analysis unit can prioritize collecting opinions from active users based on the frequency of their social media activity.

[0106] The opinion aggregation system may further include an expression adjustment unit that estimates the user's emotions and adjusts the presentation of the analysis based on the estimated emotions. For example, the expression adjustment unit can display analysis results for opinions showing positive emotions using bright colors and positive expressions. It can also display analysis results for opinions showing negative emotions that highlight problems and clarify areas for improvement. In this way, the expression adjustment unit can provide more appropriate analysis results by adjusting the presentation of the analysis based on the user's emotions. For example, the expression adjustment unit can display analysis results for opinions showing positive emotions using bright colors and positive expressions. It can also display analysis results for opinions showing negative emotions that highlight problems and clarify areas for improvement. Furthermore, the expression adjustment unit can also display analysis results for opinions showing neutral emotions based on objective data.

[0107] The opinion aggregation system may further include a length adjustment unit that estimates the user's emotions and adjusts the length of the analysis based on the estimated emotions. For example, the length adjustment unit can provide short, concise analysis results for opinions showing positive emotions. It can also perform a detailed analysis for opinions showing negative emotions and suggest specific areas for improvement. In this way, the length adjustment unit can provide more appropriate analysis results by adjusting the length of the analysis based on the user's emotions. For example, the length adjustment unit can provide short, concise analysis results for opinions showing positive emotions. It can also perform a detailed analysis for opinions showing negative emotions and suggest specific areas for improvement. Furthermore, the length adjustment unit can analyze opinions showing neutral emotions at an appropriate length and provide balanced analysis results.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The collection unit collects opinions from social media. The collection unit can collect opinions from social media platforms, for example. The collection unit can collect opinions using APIs. The collection unit can also collect opinions using scraping techniques. For example, the collection unit can use social media APIs to collect posts containing specific hashtags. The collection unit can also use social media APIs to collect posts containing specific keywords. Furthermore, the collection unit can use social media APIs to collect posts containing specific hashtags. Step 2: The analysis unit analyzes the opinions collected by the collection unit. The analysis unit can analyze opinions using, for example, text mining techniques. The analysis unit can also analyze the sentiment of opinions using sentiment analysis techniques. Furthermore, the analysis unit can analyze the topic of opinions using topic modeling techniques. For example, the analysis unit can extract important keywords from opinions using text mining techniques. The analysis unit can also classify the sentiment of opinions into positive, neutral, and negative using sentiment analysis techniques. In addition, the analysis unit can automatically classify the topic of opinions using topic modeling techniques. Step 3: The classification unit classifies the opinions analyzed by the analysis unit. The classification unit can classify opinions using, for example, a machine learning algorithm. The classification unit can also classify opinions using a rule-based approach. For example, the classification unit can classify opinions into positive, neutral, and negative using a machine learning algorithm. Alternatively, the classification unit can classify opinions containing specific keywords into specific categories using a rule-based approach. Step 4: The visualization unit maps and visualizes the opinions classified by the classification unit. The visualization unit can visualize opinions using graphs and charts, for example. The visualization unit can also visualize opinions using heatmaps. For example, the visualization unit can display the proportion of positive, neutral, and negative opinions in a pie chart. The visualization unit can also display the distribution of opinions by topic in a bar graph. Furthermore, the visualization unit can display changes in the sentiment of opinions using a heatmap.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] Each of the multiple elements described above, including the collection unit, analysis unit, classification unit, and visualization unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit can collect opinions on social media using the communication I / F 44 of the smart device 14. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the collected opinions using text mining techniques and sentiment analysis techniques. The classification unit is implemented in the identification processing unit 290 of the data processing unit 12 and classifies the analyzed opinions using machine learning algorithms. The visualization unit can visualize the classified opinions in graphs and charts using the display 40A of the smart device 14. 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.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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).

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] Each of the multiple elements described above, including the collection unit, analysis unit, classification unit, and visualization unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit can collect opinions on social media using the communication I / F 44 of the smart glasses 214. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the collected opinions using text mining techniques and sentiment analysis techniques. The classification unit is implemented in the identification processing unit 290 of the data processing unit 12 and classifies the analyzed opinions using machine learning algorithms. The visualization unit can visualize the classified opinions in graphs and charts using the display of the smart glasses 214. 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.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] Each of the multiple elements described above, including the collection unit, analysis unit, classification unit, and visualization unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit can collect opinions on social media using the communication I / F 44 of the headset terminal 314. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the collected opinions using text mining techniques and sentiment analysis techniques. The classification unit is implemented in the identification processing unit 290 of the data processing unit 12 and classifies the analyzed opinions using machine learning algorithms. The visualization unit can visualize the classified opinions in graphs and charts using the display 343 of the headset terminal 314. 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.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] Each of the multiple elements described above, including the collection unit, analysis unit, classification unit, and visualization unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the collection unit can collect opinions on social media using the communication I / F 44 of the robot 414. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the collected opinions using text mining techniques and sentiment analysis techniques. The classification unit is implemented in the identification processing unit 290 of the data processing unit 12 and classifies the analyzed opinions using machine learning algorithms. The visualization unit can visualize the classified opinions in graphs and charts using the display of the robot 414. 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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."

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] (Note 1) A collection department that gathers opinions from social media, An analysis unit analyzes the opinions collected by the aforementioned collection unit, A classification unit that classifies the opinions analyzed by the aforementioned analysis unit, A visualization unit maps and visualizes the opinions classified by the classification unit, Equipped with A system characterized by the following features. (Note 2) The aforementioned classification unit is Classify opinions into positive, neutral, and negative categories. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned visualization unit, Here are some specific examples of comments. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is Collect opinions posted on social media. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit, Analyze the collected opinions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned visualization unit, Map and visualize the classified opinions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of opinion collection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Analyze the user's past posting history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting opinions, filter them based on specific keywords or hashtags. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates user sentiment and determines the priority of opinions to collect based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting opinions, the system prioritizes collecting highly relevant opinions by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting opinions, we analyze users' social media activity and gather relevant opinions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During the analysis, adjust the level of detail based on the importance of each opinion. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the opinion. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts the length of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During the analysis, the priority of the analysis is determined based on when the opinions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During the analysis, the order of analysis will be adjusted based on the relevance of the opinions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned classification unit is It estimates the user's emotions and adjusts the classification criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned classification unit is When classifying, consider the interrelationships between opinions to improve the accuracy of the classification. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned classification unit is When classifying, the attribute information of the commenter is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned classification unit is It estimates the user's emotions and adjusts the order in which the classification results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned classification unit is When classifying opinions, consider the geographical distribution of those opinions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned classification unit is When classifying, we improve the accuracy of the classification by referring to relevant literature for each opinion. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned visualization unit, It estimates the user's emotions and adjusts the display method of the visualization based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned visualization unit, When visualizing data, the current visualization is optimized by referring to past visualization data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned visualization unit, When visualizing, different visualization methods are applied to each category of opinion. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned visualization unit, It estimates the user's emotions and adjusts the importance of visualizations based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned visualization unit, When visualizing data, analyze changes in the visualization based on when the opinions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned visualization unit, When visualizing, we analyze the visualization by referring to relevant market data for the opinions. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0182] 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. A collection department that gathers opinions from social media, An analysis unit analyzes the opinions collected by the aforementioned collection unit, A classification unit that classifies the opinions analyzed by the aforementioned analysis unit, A visualization unit maps and visualizes the opinions classified by the classification unit, Equipped with A system characterized by the following features.

2. The aforementioned classification unit is Classify opinions into positive, neutral, and negative categories. The system according to feature 1.

3. The aforementioned visualization unit, Here are some specific examples of comments. The system according to feature 1.

4. The aforementioned collection unit is Collect opinions posted on social media. The system according to feature 1.

5. The aforementioned analysis unit, Analyze the collected opinions. The system according to feature 1.

6. The aforementioned visualization unit, Map and visualize the classified opinions. The system according to feature 1.

7. The aforementioned collection unit is We estimate the user's emotions and adjust the timing of opinion collection based on the estimated user emotions. The system according to feature 1.

8. The aforementioned collection unit is Analyze the user's past posting history and select the optimal data collection method. The system according to feature 1.

9. The aforementioned collection unit is When collecting opinions, filter them based on specific keywords or hashtags. The system according to feature 1.

10. The aforementioned collection unit is It estimates user sentiment and determines the priority of opinions to collect based on the estimated user sentiment. The system according to feature 1.

Images