system

Abstract

The system according to this embodiment aims to efficiently extract useful information from a vast amount of review data and provide it to the user. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a display unit, and a sentiment analysis unit. The collection unit collects word-of-mouth data. The analysis unit analyzes the word-of-mouth data collected by the collection unit and extracts key points. The display unit displays the number of comments and specific examples for the elements extracted by the analysis unit. The sentiment analysis unit analyzes the sentiment of each review and classifies them into positive and negative opinions.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 conventional technology, there is a problem that it is difficult to efficiently extract useful information from a huge amount of reviews and provide it to users.

[0005] The system according to the embodiment aims to efficiently extract useful information from a huge amount of reviews and provide it to users.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an analysis unit, a display unit, and a sentiment analysis unit. The collection unit collects word-of-mouth data. The analysis unit analyzes the word-of-mouth data collected by the collection unit and extracts key points. The display unit displays the number of comments and specific examples for the elements extracted by the analysis unit. The sentiment analysis unit analyzes the sentiment of each review and classifies them into positive and negative opinions. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently extract useful information from a vast amount of review data and provide it to the user. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applicable to the communication I / F 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 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The review analysis system according to an embodiment of the present invention is a system that automatically summarizes online reviews using generative AI and provides multidimensional review insights. This review analysis system allows users to grasp detailed review content in a short time without being overwhelmed by the vast volume of reviews. For example, the review analysis system collects word-of-mouth data, and the generative AI analyzes that data to extract key points. If the generative AI mentions, for example, the element "high price" in many reviews, it will extract that element and include it in the summary. Next, the review analysis system displays the number of comments and specific examples for the extracted element. For example, it will display what specific comments were made about the element "high price". Furthermore, the review analysis system analyzes the sentiment of each review and classifies positive and negative opinions. For example, it will display the ratio of positive to negative opinions for the element "high price". This allows users to grasp the overall evaluation trend. The review analysis system is targeted at users of gourmet and shopping sites, busy people who want to organize information in a short time, and consumers who seek deeper review analysis. In terms of market size, the online review market is growing rapidly amidst the increasing need for consumer opinion research, and the present invention meets that need. This allows the review analysis system to significantly reduce the time spent gathering information, as users can quickly grasp the detailed content of reviews.

[0029] The review analysis system according to this embodiment comprises a collection unit, an analysis unit, a display unit, and a sentiment analysis unit. The collection unit collects word-of-mouth data. Word-of-mouth data includes, but is not limited to, text, images, and videos. The collection unit scrapes word-of-mouth data from websites, for example. The collection unit can also obtain word-of-mouth data through an API. Furthermore, the collection unit can allow users to directly input word-of-mouth data. For example, the collection unit provides an interface for users to post reviews. The analysis unit analyzes the word-of-mouth data collected by the collection unit using a generation AI and extracts key points. The extraction of key points is based on, for example, importance, frequency, and relevance, but is not limited to these examples. For example, the generation AI analyzes word-of-mouth data using a text generation AI (e.g., LLM) and extracts key points. The analysis unit can also extract key points from word-of-mouth data using a multimodal generation AI. Furthermore, the analysis unit can use a generation AI to extract and summarize particularly important information from the word-of-mouth data. For example, text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. Multimodal generation AI can handle multiple modals, including not only text but also images and audio. Generation AI uses keyword extraction technology to pick out particularly important information from review data and summarizes it based on that information. The display unit shows the number of comments and specific examples for the elements extracted by the analysis unit. The number of comments is calculated by methods such as the number of comments within a certain period or the number of comments under specific conditions, but is not limited to these examples. The display unit can display the number of comments for the extracted elements as a graph or chart, for example. The display unit can also display specific examples in list format. The display unit can also display the number of comments and specific examples for the extracted elements in table format. For example, the display unit can display the number of comments for the extracted elements as a bar graph and display specific examples in list format. The sentiment analysis unit analyzes the sentiment of each review and classifies them into positive and negative opinions.Sentiment analysis can be performed, for example, by classifying reviews as positive, negative, or neutral, but is not limited to such examples. The sentiment analysis unit can analyze the sentiment of each review using, for example, natural language processing technology. The sentiment analysis unit can also analyze sentiment using machine learning algorithms. Furthermore, the sentiment analysis unit can analyze the sentiment of each review and apply algorithms to classify positive and negative opinions. For example, the sentiment analysis unit can classify the sentiment of each review as positive, negative, or neutral using natural language processing technology. The machine learning algorithm learns sentiment data from past reviews and classifies the sentiment of new reviews with high accuracy. Some or all of the above processing in the sentiment analysis unit may be performed using, for example, AI, or not using AI. For example, the sentiment analysis unit can input the text data of each review into a generating AI and have the generating AI perform the sentiment analysis. This enables the review analysis system according to the embodiment to efficiently collect, analyze, display, and perform sentiment analysis on word-of-mouth data.

[0030] The data collection unit collects review data. This review data includes, but is not limited to, text, images, and videos. The data collection unit scrapes review data from websites, for example. Specifically, it uses a web crawler to automatically collect review data by visiting pages on specified websites. The web crawler analyzes the HTML structure and extracts the necessary data. The data collection unit can also obtain review data through APIs. For example, it can use APIs provided by social media and review sites to obtain review data in real time. Using APIs allows for efficient and accurate data acquisition. Furthermore, the data collection unit can also receive review data directly from users. For example, the data collection unit provides an interface for users to post reviews. The interface is implemented as a web form or mobile application, allowing users to easily input review data. The data entered by users is sent to the data collection unit and stored in a database. This allows the data collection unit to collect review data in diverse ways and build a comprehensive database. The collected data is used for processing in the analysis unit and sentiment analysis unit, so the accuracy and diversity of the data are important. The data collection unit also includes filtering functions to eliminate data duplication and maintain data quality. This enables the data collection unit to achieve efficient and high-quality data collection, improving the overall system performance.

[0031] The analysis unit uses a generative AI to analyze the word-of-mouth data collected by the collection unit and extract key points. Key point extraction is based on, for example, importance, frequency, and relevance, but is not limited to these examples. Specifically, the generative AI uses a text generation AI (e.g., LLM) to analyze the word-of-mouth data and extract key points. The text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. For example, it can extract frequently occurring keywords and phrases from the word-of-mouth data and evaluate their importance. The analysis unit can also use a multimodal generative AI to extract key points from the word-of-mouth data. The multimodal generative AI can handle multiple modals, including not only text but also images and audio. For example, it can use image analysis technology to extract important information from images included in the word-of-mouth data and integrate it with text data to summarize the key points. Furthermore, the analysis unit can use the generative AI to extract and summarize particularly important information from the word-of-mouth data. The generative AI uses keyword extraction technology to pick out particularly important information from the word-of-mouth data and summarizes it based on that information. This allows the analysis unit to efficiently extract key points from vast amounts of user review data and provide useful information to users. Furthermore, the analysis unit organizes the extracted key points by category, making it easy for users to search for information. As a result, the analysis unit can perform user review data analysis efficiently and with high accuracy, improving the overall performance of the system.

[0032] The display unit shows the number of comments and specific examples for elements extracted by the analysis unit. The number of comments is calculated using methods such as the number of comments within a certain period or the number of comments under specific conditions, but is not limited to these examples. The display unit displays the number of comments for extracted elements as graphs or charts. Specifically, it uses bar graphs or pie charts to visually show the distribution of the number of comments for each element. The display unit can also display specific examples in list format. For example, it can select representative comments from reviews of a particular element and display them in list format. This allows users to easily grasp specific opinions and examples for each element. The display unit can also display the number of comments and specific examples for extracted elements in table format. For example, it can organize the number of comments and specific examples for each element in a table format to make it easy for users to compare them. Furthermore, the display unit has interactive functions, and when a user clicks on a specific element, detailed information is displayed. This allows the display unit to provide information to the user visually and intuitively, deepening their understanding of the review data. The display unit is customizable according to user needs, and the display format and content can be flexibly changed. This allows the display unit to provide users with optimal information and improve the overall usability of the system.

[0033] The sentiment analysis unit analyzes the sentiment of each review and classifies it into positive and negative opinions. Sentiment analysis is performed using methods such as positive, negative, and neutral, but is not limited to these examples. For example, the sentiment analysis unit uses natural language processing techniques to analyze the sentiment of each review. Specifically, it uses text analysis techniques to analyze the context and vocabulary of each review and evaluate the sentiment trend. The sentiment analysis unit can also analyze sentiment using machine learning algorithms. These machine learning algorithms learn from sentiment data of past reviews and classify the sentiment of new reviews with high accuracy. For example, the sentiment analysis unit can input the text data of each review into a generative AI and have the generative AI perform the sentiment analysis. The generative AI analyzes the text data and classifies it as positive, negative, or neutral. This allows the sentiment analysis unit to classify the sentiment of each review quickly and accurately. Furthermore, the sentiment analysis unit has a function to visually display the sentiment analysis results. For example, it can display the proportion of positive and negative opinions in a pie chart, or show the sentiment score of each review in a heatmap. This allows users to grasp the overall emotional trends at a glance. The emotion analysis unit can also utilize the results of the emotional analysis in collaboration with other departments. For example, it can work with the analysis unit and the display unit to extract and display key points based on emotional trends. In this way, the emotion analysis unit can improve the overall performance of the system and provide useful information to users.

[0034] The analysis unit can analyze word-of-mouth data using a generative AI and extract key points. For example, the analysis unit can use a generative AI to analyze word-of-mouth data and extract key points. For example, the analysis unit can use a generative AI to analyze word-of-mouth data and extract important information. The analysis unit can also use a generative AI to extract and summarize particularly important information from the word-of-mouth data. For example, the generative AI can use a text generation AI (e.g., LLM) to analyze word-of-mouth data and extract key points. This improves the accuracy of word-of-mouth data analysis by using a generative AI. For example, the generative AI takes word-of-mouth data as input, receives a prompt to output key points, and extracts the key points.

[0035] The display unit can display the number of comments and specific examples for the extracted elements. For example, the display unit can display the number of comments for the extracted elements as a graph or chart. For example, the display unit can display the number of comments for the extracted elements as a bar graph. The display unit can also display specific examples in list format. For example, the display unit can display specific examples for the extracted elements in list format. The display unit can also display the number of comments and specific examples for the extracted elements in table format. For example, the display unit can display the number of comments for the extracted elements in table format and specific examples in list format. This makes it easier for users to obtain detailed information by displaying the number of comments and specific examples for the extracted elements. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the number of comments and specific examples for the extracted elements into a generating AI and have the generating AI execute the display content.

[0036] The sentiment analysis unit can analyze the sentiment of each review and classify it into positive and negative opinions. For example, the sentiment analysis unit can use natural language processing techniques to analyze the sentiment of each review. For example, the sentiment analysis unit can use natural language processing techniques to classify the sentiment of each review as positive, negative, or neutral. The sentiment analysis unit can also analyze sentiment using machine learning algorithms. For example, the sentiment analysis unit can use machine learning algorithms to classify the sentiment of each review as positive, negative, or neutral. Furthermore, the sentiment analysis unit can apply algorithms to analyze the sentiment of each review and classify it into positive and negative opinions. For example, the sentiment analysis unit can use natural language processing techniques to classify the sentiment of each review as positive, negative, or neutral. This makes it easier to grasp the overall evaluation trend by analyzing the sentiment of each review and classifying the opinions. Some or all of the above processing in the sentiment analysis unit may be performed using AI, or not. For example, the sentiment analysis unit can input the text data of each review into a generating AI and have the generating AI perform the sentiment analysis.

[0037] The data collection unit can analyze a user's past review posting history and select the optimal collection method. For example, the data collection unit can collect review data according to the time slots in which the user frequently posted in the past. The data collection unit can also select the optimal collection method based on the devices the user has used in the past. The data collection unit can also prioritize collecting review data related to specific topics based on the user's past posts. For example, the data collection unit can prioritize collecting review data related to specific topics based on the user's past posts. This allows the optimal collection method to be selected by analyzing 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 review posting history into a generating AI and have the generating AI select the optimal collection method.

[0038] The data collection unit can filter review data based on the user's current areas of interest and purchase history. For example, the data collection unit can prioritize collecting review data related to products the user has recently purchased. The data collection unit can also filter relevant review data based on categories the user has shown interest in. The data collection unit can also collect review data about specific brands based on the user's purchase history. This allows for the collection of highly relevant review data by filtering based on the user's areas of interest and purchase 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 areas of interest and purchase history into a generating AI and have the generating AI perform the filtering.

[0039] The data collection unit can prioritize collecting highly relevant data based on the user's geographical location when collecting review data. For example, the data collection unit can prioritize collecting review data about stores and services near the user's current location. The data collection unit can also collect review data related to the user's travel destination if the user is traveling. The data collection unit can also collect review data about region-specific campaigns and events based on the user's geographical location. This allows for the provision of region-specific information by collecting highly relevant data based on the user's geographical location. 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 geographical location information into a generating AI and have the generating AI collect highly relevant data.

[0040] The data collection unit can analyze users' social media activity and collect relevant data when collecting word-of-mouth data. For example, the data collection unit can collect word-of-mouth data related to brands and influencers that users follow on social media. The data collection unit can also collect relevant word-of-mouth data based on content that users have shared on social media. The data collection unit can also collect word-of-mouth data that users are likely to be interested in based on their social media activity history. This allows for the efficient collection of relevant word-of-mouth data by analyzing users' social media activity. 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 social media activity data into a generating AI and have the generating AI collect relevant data.

[0041] The analysis unit can adjust the level of detail of the key points based on the importance of the review data during analysis. For example, the analysis unit can extract detailed key points for review data with high importance. The analysis unit can also extract concise key points for review data with low importance. The analysis unit can also extract key points with an appropriate level of detail for review data of medium importance. By adjusting the level of detail of the key points based on the importance of the review data, it is possible to extract key points with an appropriate level of detail. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the importance of the review data into a generating AI and have the generating AI perform the adjustment of the level of detail of the key points.

[0042] The analysis unit can apply different analysis algorithms depending on the category of the review data during analysis. For example, in the case of product reviews, the analysis unit can apply an algorithm that extracts key points regarding the quality and price of the product. The analysis unit can also apply an algorithm that extracts key points regarding the responsiveness and convenience of the service in the case of service reviews. The analysis unit can also apply an algorithm that extracts key points regarding the taste of the food and the atmosphere in the case of restaurant reviews. By applying different analysis algorithms depending on the category of the review data, more appropriate key points can be extracted. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the categories of the review data into a generating AI and have the generating AI execute the application of the analysis algorithm.

[0043] The analysis unit can determine the priority of key points based on the posting date of the review data during analysis. For example, the analysis unit can prioritize the extraction of key points from the most recent review data. The analysis unit can also lower the priority of key points from older review data. The analysis unit can also extract key points with a moderate priority for review data posted at a moderate time. By determining the priority of key points based on the posting date of the review data, the latest information can be extracted preferentially. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the posting date of the review data into a generating AI and have the generating AI determine the priority of key points.

[0044] The analysis unit can adjust the method of extracting key points based on the relevance of the review data during analysis. For example, the analysis unit can extract detailed key points for highly relevant review data. For example, the analysis unit can extract concise key points for low-relevance review data. For example, the analysis unit can extract concise key points for low-relevance review data. For example, the analysis unit can extract key points with a moderate level of detail for moderately relevant review data. By adjusting the method of extracting key points based on the relevance of the review data, more relevant key points can be extracted. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the relevance of the review data into a generating AI and have the generating AI adjust the method of extracting key points.

[0045] The display unit can adjust the level of detail displayed based on the importance of the extracted elements during display. For example, the display unit can display detailed information for elements of high importance. The display unit can also display concise information for elements of low importance. The display unit can also display information of moderate importance with appropriate detail. By adjusting the level of detail of the display based on the importance of the extracted elements, information with the appropriate level of detail can be displayed. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the importance of the extracted elements into a generating AI and have the generating AI perform the adjustment of the level of detail of the display.

[0046] The display unit can apply different display formats depending on the category of the extracted elements during display. For example, in the case of a product review, the display unit can display product images and price information. For example, in the case of a service review, the display unit can display service details and user ratings. For example, in the case of a restaurant review, the display unit can display food photos and menu information. By applying different display formats depending on the category of the extracted elements, information can be displayed in a more appropriate format. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the categories of the extracted elements into a generating AI and have the generating AI apply the display format.

[0047] The display unit can determine the display priority based on the posting date of the extracted elements when displaying them. For example, the display unit can prioritize the display of the most recent elements. The display unit can also lower the display priority of older elements. The display unit can also display elements with a moderate posting date with a moderate priority. In this way, by determining the display priority based on the posting date of the extracted elements, the latest information can be displayed preferentially. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the posting dates of the extracted elements into a generating AI and have the generating AI determine the display priority.

[0048] The display unit can adjust the display method based on the relevance of the extracted elements during display. For example, the display unit can display detailed information for elements with high relevance. The display unit can also display concise information for elements with low relevance. The display unit can also display information with a moderate level of detail for elements with moderate relevance. By adjusting the display method based on the relevance of the extracted elements, more relevant information can be displayed. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the relevance of the extracted elements into a generating AI and have the generating AI adjust the display method.

[0049] The sentiment analysis unit can optimize its analysis algorithm by referring to past sentiment data during sentiment analysis. For example, the sentiment analysis unit can adjust its current sentiment analysis algorithm based on the user's past sentiment data. The sentiment analysis unit can also detect specific patterns by referring to past sentiment data and optimize its analysis algorithm. The sentiment analysis unit can also improve the accuracy of sentiment analysis by utilizing past sentiment data. As a result, the accuracy of sentiment analysis is improved by optimizing the analysis algorithm by referring to past sentiment data. Some or all of the above processes in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input past sentiment data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0050] The sentiment analysis unit can apply different sentiment analysis methods to each category of review data during sentiment analysis. For example, in the case of product reviews, the sentiment analysis unit can apply sentiment analysis methods related to product quality and price. For example, in the case of service reviews, the sentiment analysis unit can apply sentiment analysis methods related to service responsiveness and convenience. For example, in the case of restaurant reviews, the sentiment analysis unit can apply sentiment analysis methods related to the taste of the food and atmosphere. By applying different sentiment analysis methods to each category of review data, more appropriate sentiment analysis becomes possible. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input the categories of the review data into a generating AI and have the generating AI execute the application of sentiment analysis methods.

[0051] The sentiment analysis unit can analyze changes in sentiment based on the posting date of the review data during sentiment analysis. For example, the sentiment analysis unit can prioritize the analysis of changes in sentiment for the most recent review data. The sentiment analysis unit can also postpone the analysis of changes in sentiment for older review data. The sentiment analysis unit can also analyze changes in sentiment for review data posted at a moderate timeframe with appropriate priority. This makes it easier to understand changes in sentiment by analyzing them based on the posting date of the review data. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input the posting date of the review data into a generating AI and have the generating AI perform the analysis of changes in sentiment.

[0052] The sentiment analysis unit can analyze sentiment by referring to relevant market data for word-of-mouth data during sentiment analysis. For example, the sentiment analysis unit can analyze sentiment related to a specific trend based on relevant market data. The sentiment analysis unit can also analyze sentiment towards a specific product or service by referring to relevant market data. The sentiment analysis unit can also improve the accuracy of sentiment analysis by using relevant market data. This makes it possible to perform more accurate sentiment analysis by analyzing sentiment by referring to relevant market data for word-of-mouth data. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input relevant market data into a generating AI and have the generating AI perform the sentiment analysis.

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

[0054] The data collection unit can analyze a user's past review posting history and select the optimal collection method. For example, it can collect review data based on the time slots the user frequently posted in the past. It can also select the optimal collection method based on the devices the user has used in the past. Furthermore, it can prioritize the collection of review data related to specific topics based on the user's past posting content. In this way, the optimal collection method can be selected by analyzing past posting history.

[0055] The data collection unit can filter user reviews based on their current areas of interest and purchase history. For example, it can prioritize collecting reviews related to products the user has recently purchased. It can also filter relevant reviews based on categories the user has shown interest in. Furthermore, it can collect reviews related to specific brands based on the user's purchase history. This allows for the collection of highly relevant review data by filtering based on the user's areas of interest and purchase history.

[0056] The analysis unit can adjust the level of detail of the key points based on the importance of the review data during analysis. For example, it can extract detailed key points from highly important review data. Conversely, it can extract concise key points from less important review data. Furthermore, it can extract key points with an appropriate level of detail from moderately important review data. In this way, by adjusting the level of detail of the key points based on the importance of the review data, it is possible to extract key points with the appropriate level of detail.

[0057] The display unit can adjust the level of detail based on the importance of the extracted elements during display. For example, it can display detailed information for high-importance elements, concise information for low-importance elements, and information of moderate importance for elements of moderate importance. By adjusting the level of detail based on the importance of the extracted elements, it is possible to display information with an appropriate level of detail.

[0058] The analysis unit can apply different analysis algorithms depending on the category of the review data during analysis. For example, in the case of product reviews, it can apply an algorithm that extracts key points regarding product quality and price. Similarly, in the case of service reviews, it can apply an algorithm that extracts key points regarding service responsiveness and convenience. Furthermore, in the case of restaurant reviews, it can apply an algorithm that extracts key points regarding the taste of the food and the atmosphere. By applying different analysis algorithms depending on the category of the review data, it is possible to extract more appropriate key points.

[0059] The following briefly describes the processing flow for example form 1.

[0060] Step 1: The collection unit collects review data. This review data includes text, images, videos, etc. The collection unit uses methods such as scraping review data from websites, obtaining it through APIs, or having users directly input review data. For example, the collection unit provides an interface for users to post reviews. Step 2: The analysis unit uses a generation AI to analyze the word-of-mouth data collected by the collection unit and extract key points. Key points are extracted based on importance, frequency, and relevance. For example, word-of-mouth data can be analyzed and key points extracted using a text generation AI (LLM) or a multimodal generation AI. It is also possible to use a generation AI to extract and summarize particularly important information from the word-of-mouth data. Step 3: The display unit shows the number of comments and specific examples for the elements extracted by the analysis unit. The number of comments is calculated using methods such as the number of comments within a certain period or the number of comments under specific conditions. The display unit shows the number of comments for the extracted elements as a graph or chart, and displays specific examples in list or table format. Step 4: The sentiment analysis unit analyzes the sentiment of each review and classifies it into positive and negative opinions. Sentiment analysis is performed using methods such as positive, negative, and neutral. The sentiment analysis unit uses natural language processing techniques and machine learning algorithms to analyze sentiment and classify positive and negative opinions. For example, the sentiment analysis unit can input the text data of each review into a generating AI and have the generating AI perform the sentiment analysis.

[0061] (Example of form 2) The review analysis system according to an embodiment of the present invention is a system that automatically summarizes online reviews using generative AI and provides multidimensional review insights. This review analysis system allows users to grasp detailed review content in a short time without being overwhelmed by the vast volume of reviews. For example, the review analysis system collects word-of-mouth data, and the generative AI analyzes that data to extract key points. If the generative AI mentions, for example, the element "high price" in many reviews, it will extract that element and include it in the summary. Next, the review analysis system displays the number of comments and specific examples for the extracted element. For example, it will display what specific comments were made about the element "high price". Furthermore, the review analysis system analyzes the sentiment of each review and classifies positive and negative opinions. For example, it will display the ratio of positive to negative opinions for the element "high price". This allows users to grasp the overall evaluation trend. The review analysis system is targeted at users of gourmet and shopping sites, busy people who want to organize information in a short time, and consumers who seek deeper review analysis. In terms of market size, the online review market is growing rapidly amidst the increasing need for consumer opinion research, and the present invention meets that need. This allows the review analysis system to significantly reduce the time spent gathering information, as users can quickly grasp the detailed content of reviews.

[0062] The review analysis system according to this embodiment comprises a collection unit, an analysis unit, a display unit, and a sentiment analysis unit. The collection unit collects word-of-mouth data. Word-of-mouth data includes, but is not limited to, text, images, and videos. The collection unit scrapes word-of-mouth data from websites, for example. The collection unit can also obtain word-of-mouth data through an API. Furthermore, the collection unit can allow users to directly input word-of-mouth data. For example, the collection unit provides an interface for users to post reviews. The analysis unit analyzes the word-of-mouth data collected by the collection unit using a generation AI and extracts key points. The extraction of key points is based on, for example, importance, frequency, and relevance, but is not limited to these examples. For example, the generation AI analyzes word-of-mouth data using a text generation AI (e.g., LLM) and extracts key points. The analysis unit can also extract key points from word-of-mouth data using a multimodal generation AI. Furthermore, the analysis unit can use a generation AI to extract and summarize particularly important information from the word-of-mouth data. For example, text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. Multimodal generation AI can handle multiple modals, including not only text but also images and audio. Generation AI uses keyword extraction technology to pick out particularly important information from review data and summarizes it based on that information. The display unit shows the number of comments and specific examples for the elements extracted by the analysis unit. The number of comments is calculated by methods such as the number of comments within a certain period or the number of comments under specific conditions, but is not limited to these examples. The display unit can display the number of comments for the extracted elements as a graph or chart, for example. The display unit can also display specific examples in list format. The display unit can also display the number of comments and specific examples for the extracted elements in table format. For example, the display unit can display the number of comments for the extracted elements as a bar graph and display specific examples in list format. The sentiment analysis unit analyzes the sentiment of each review and classifies them into positive and negative opinions.Sentiment analysis can be performed, for example, by classifying reviews as positive, negative, or neutral, but is not limited to such examples. The sentiment analysis unit can analyze the sentiment of each review using, for example, natural language processing technology. The sentiment analysis unit can also analyze sentiment using machine learning algorithms. Furthermore, the sentiment analysis unit can analyze the sentiment of each review and apply algorithms to classify positive and negative opinions. For example, the sentiment analysis unit can classify the sentiment of each review as positive, negative, or neutral using natural language processing technology. The machine learning algorithm learns sentiment data from past reviews and classifies the sentiment of new reviews with high accuracy. Some or all of the above processing in the sentiment analysis unit may be performed using, for example, AI, or not using AI. For example, the sentiment analysis unit can input the text data of each review into a generating AI and have the generating AI perform the sentiment analysis. This enables the review analysis system according to the embodiment to efficiently collect, analyze, display, and perform sentiment analysis on word-of-mouth data.

[0063] The data collection unit collects review data. This review data includes, but is not limited to, text, images, and videos. The data collection unit scrapes review data from websites, for example. Specifically, it uses a web crawler to automatically collect review data by visiting pages on specified websites. The web crawler analyzes the HTML structure and extracts the necessary data. The data collection unit can also obtain review data through APIs. For example, it can use APIs provided by social media and review sites to obtain review data in real time. Using APIs allows for efficient and accurate data acquisition. Furthermore, the data collection unit can also receive review data directly from users. For example, the data collection unit provides an interface for users to post reviews. The interface is implemented as a web form or mobile application, allowing users to easily input review data. The data entered by users is sent to the data collection unit and stored in a database. This allows the data collection unit to collect review data in diverse ways and build a comprehensive database. The collected data is used for processing in the analysis unit and sentiment analysis unit, so the accuracy and diversity of the data are important. The data collection unit also includes filtering functions to eliminate data duplication and maintain data quality. This enables the data collection unit to achieve efficient and high-quality data collection, improving the overall system performance.

[0064] The analysis unit uses a generative AI to analyze the word-of-mouth data collected by the collection unit and extract key points. Key point extraction is based on, for example, importance, frequency, and relevance, but is not limited to these examples. Specifically, the generative AI uses a text generation AI (e.g., LLM) to analyze the word-of-mouth data and extract key points. The text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. For example, it can extract frequently occurring keywords and phrases from the word-of-mouth data and evaluate their importance. The analysis unit can also use a multimodal generative AI to extract key points from the word-of-mouth data. The multimodal generative AI can handle multiple modals, including not only text but also images and audio. For example, it can use image analysis technology to extract important information from images included in the word-of-mouth data and integrate it with text data to summarize the key points. Furthermore, the analysis unit can use the generative AI to extract and summarize particularly important information from the word-of-mouth data. The generative AI uses keyword extraction technology to pick out particularly important information from the word-of-mouth data and summarizes it based on that information. This allows the analysis unit to efficiently extract key points from vast amounts of user review data and provide useful information to users. Furthermore, the analysis unit organizes the extracted key points by category, making it easy for users to search for information. As a result, the analysis unit can perform user review data analysis efficiently and with high accuracy, improving the overall performance of the system.

[0065] The display unit shows the number of comments and specific examples for elements extracted by the analysis unit. The number of comments is calculated using methods such as the number of comments within a certain period or the number of comments under specific conditions, but is not limited to these examples. The display unit displays the number of comments for extracted elements as graphs or charts. Specifically, it uses bar graphs or pie charts to visually show the distribution of the number of comments for each element. The display unit can also display specific examples in list format. For example, it can select representative comments from reviews of a particular element and display them in list format. This allows users to easily grasp specific opinions and examples for each element. The display unit can also display the number of comments and specific examples for extracted elements in table format. For example, it can organize the number of comments and specific examples for each element in a table format to make it easy for users to compare them. Furthermore, the display unit has interactive functions, and when a user clicks on a specific element, detailed information is displayed. This allows the display unit to provide information to the user visually and intuitively, deepening their understanding of the review data. The display unit is customizable according to user needs, and the display format and content can be flexibly changed. This allows the display unit to provide users with optimal information and improve the overall usability of the system.

[0066] The sentiment analysis unit analyzes the sentiment of each review and classifies it into positive and negative opinions. Sentiment analysis is performed using methods such as positive, negative, and neutral, but is not limited to these examples. For example, the sentiment analysis unit uses natural language processing techniques to analyze the sentiment of each review. Specifically, it uses text analysis techniques to analyze the context and vocabulary of each review and evaluate the sentiment trend. The sentiment analysis unit can also analyze sentiment using machine learning algorithms. These machine learning algorithms learn from sentiment data of past reviews and classify the sentiment of new reviews with high accuracy. For example, the sentiment analysis unit can input the text data of each review into a generative AI and have the generative AI perform the sentiment analysis. The generative AI analyzes the text data and classifies it as positive, negative, or neutral. This allows the sentiment analysis unit to classify the sentiment of each review quickly and accurately. Furthermore, the sentiment analysis unit has a function to visually display the sentiment analysis results. For example, it can display the proportion of positive and negative opinions in a pie chart, or show the sentiment score of each review in a heatmap. This allows users to grasp the overall emotional trends at a glance. The emotion analysis unit can also utilize the results of the emotional analysis in collaboration with other departments. For example, it can work with the analysis unit and the display unit to extract and display key points based on emotional trends. In this way, the emotion analysis unit can improve the overall performance of the system and provide useful information to users.

[0067] The analysis unit can analyze word-of-mouth data using a generative AI and extract key points. For example, the analysis unit can use a generative AI to analyze word-of-mouth data and extract key points. For example, the analysis unit can use a generative AI to analyze word-of-mouth data and extract important information. The analysis unit can also use a generative AI to extract and summarize particularly important information from the word-of-mouth data. For example, the generative AI can use a text generation AI (e.g., LLM) to analyze word-of-mouth data and extract key points. This improves the accuracy of word-of-mouth data analysis by using a generative AI. For example, the generative AI takes word-of-mouth data as input, receives a prompt to output key points, and extracts the key points.

[0068] The display unit can display the number of comments and specific examples for the extracted elements. For example, the display unit can display the number of comments for the extracted elements as a graph or chart. For example, the display unit can display the number of comments for the extracted elements as a bar graph. The display unit can also display specific examples in list format. For example, the display unit can display specific examples for the extracted elements in list format. The display unit can also display the number of comments and specific examples for the extracted elements in table format. For example, the display unit can display the number of comments for the extracted elements in table format and specific examples in list format. This makes it easier for users to obtain detailed information by displaying the number of comments and specific examples for the extracted elements. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the number of comments and specific examples for the extracted elements into a generating AI and have the generating AI execute the display content.

[0069] The sentiment analysis unit can analyze the sentiment of each review and classify it into positive and negative opinions. For example, the sentiment analysis unit can use natural language processing techniques to analyze the sentiment of each review. For example, the sentiment analysis unit can use natural language processing techniques to classify the sentiment of each review as positive, negative, or neutral. The sentiment analysis unit can also analyze sentiment using machine learning algorithms. For example, the sentiment analysis unit can use machine learning algorithms to classify the sentiment of each review as positive, negative, or neutral. Furthermore, the sentiment analysis unit can apply algorithms to analyze the sentiment of each review and classify it into positive and negative opinions. For example, the sentiment analysis unit can use natural language processing techniques to classify the sentiment of each review as positive, negative, or neutral. This makes it easier to grasp the overall evaluation trend by analyzing the sentiment of each review and classifying the opinions. Some or all of the above processing in the sentiment analysis unit may be performed using AI, or not. For example, the sentiment analysis unit can input the text data of each review into a generating AI and have the generating AI perform the sentiment analysis.

[0070] The data collection unit can estimate the user's emotions and adjust the timing of collecting review data based on the estimated emotions. For example, if the user has positive emotions, the data collection unit can immediately collect the review data. For example, if the user has positive emotions, the data collection unit can immediately collect the review data. The data collection unit can also collect the review data after a certain period of time if the user has negative emotions. For example, if the user has negative emotions, the data collection unit can collect the review data after a certain period of time. The data collection unit can also set the collection timing randomly if the user has neutral emotions. For example, if the user has neutral emotions, the collection timing can be set randomly. By adjusting the collection timing according to the user's emotions, review data can be collected at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. 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 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 generating AI, allowing the generating AI to perform emotion estimation.

[0071] The data collection unit can analyze a user's past review posting history and select the optimal collection method. For example, the data collection unit can collect review data according to the time slots in which the user frequently posted in the past. The data collection unit can also select the optimal collection method based on the devices the user has used in the past. The data collection unit can also prioritize collecting review data related to specific topics based on the user's past posts. For example, the data collection unit can prioritize collecting review data related to specific topics based on the user's past posts. This allows the optimal collection method to be selected by analyzing 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 review posting history into a generating AI and have the generating AI select the optimal collection method.

[0072] The data collection unit can filter review data based on the user's current areas of interest and purchase history. For example, the data collection unit can prioritize collecting review data related to products the user has recently purchased. The data collection unit can also filter relevant review data based on categories the user has shown interest in. The data collection unit can also collect review data about specific brands based on the user's purchase history. This allows for the collection of highly relevant review data by filtering based on the user's areas of interest and purchase 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 areas of interest and purchase history into a generating AI and have the generating AI perform the filtering.

[0073] The data collection unit can estimate the user's emotions and determine the priority of the review data to collect based on the estimated user emotions. For example, if the user has positive emotions, the data collection unit will prioritize collecting positive review data. The data collection unit can also prioritize collecting negative review data if the user has negative emotions. For example, if the user has negative emotions, the data collection unit will prioritize collecting negative review data. The data collection unit can also collect balanced review data if the user has neutral emotions. For example, if the data collection unit has neutral emotions, the data collection unit will collect balanced review data. This allows for the collection of more appropriate data by determining the priority of the review data to collect according to 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 not limited to, but may include, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above 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 generating AI and have the generating AI perform emotion estimation.

[0074] The data collection unit can prioritize collecting highly relevant data based on the user's geographical location when collecting review data. For example, the data collection unit can prioritize collecting review data about stores and services near the user's current location. The data collection unit can also collect review data related to the user's travel destination if the user is traveling. The data collection unit can also collect review data about region-specific campaigns and events based on the user's geographical location. This allows for the provision of region-specific information by collecting highly relevant data based on the user's geographical location. 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 geographical location information into a generating AI and have the generating AI collect highly relevant data.

[0075] The data collection unit can analyze users' social media activity and collect relevant data when collecting word-of-mouth data. For example, the data collection unit can collect word-of-mouth data related to brands and influencers that users follow on social media. The data collection unit can also collect relevant word-of-mouth data based on content that users have shared on social media. The data collection unit can also collect word-of-mouth data that users are likely to be interested in based on their social media activity history. This allows for the efficient collection of relevant word-of-mouth data by analyzing users' social media activity. 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 social media activity data into a generating AI and have the generating AI collect relevant data.

[0076] The analysis unit can estimate the user's emotions and adjust the method of extracting key points based on the estimated emotions. For example, if the user has positive emotions, the analysis unit will prioritize extracting positive key points. The analysis unit can also prioritize extracting negative key points if the user has negative emotions. The analysis unit can also prioritize extracting balanced key points if the user has neutral emotions. By adjusting the method of extracting key points according to the user's emotions, more appropriate key points can be extracted. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generating AI and have the generating AI adjust the method for extracting key points.

[0077] The analysis unit can adjust the level of detail of the key points based on the importance of the review data during analysis. For example, the analysis unit can extract detailed key points for review data with high importance. The analysis unit can also extract concise key points for review data with low importance. The analysis unit can also extract key points with an appropriate level of detail for review data of medium importance. By adjusting the level of detail of the key points based on the importance of the review data, it is possible to extract key points with an appropriate level of detail. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the importance of the review data into a generating AI and have the generating AI perform the adjustment of the level of detail of the key points.

[0078] The analysis unit can apply different analysis algorithms depending on the category of the review data during analysis. For example, in the case of product reviews, the analysis unit can apply an algorithm that extracts key points regarding the quality and price of the product. The analysis unit can also apply an algorithm that extracts key points regarding the responsiveness and convenience of the service in the case of service reviews. The analysis unit can also apply an algorithm that extracts key points regarding the taste of the food and the atmosphere in the case of restaurant reviews. By applying different analysis algorithms depending on the category of the review data, more appropriate key points can be extracted. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the categories of the review data into a generating AI and have the generating AI execute the application of the analysis algorithm.

[0079] The analysis unit can estimate the user's emotions and adjust the order in which key points are extracted based on the estimated emotions. For example, if the user has positive emotions, the analysis unit will extract positive key points first. Similarly, if the user has negative emotions, the analysis unit can extract negative key points first. Furthermore, if the user has neutral emotions, the analysis unit can extract key points in a balanced order. This allows for the extraction of key points in a more appropriate order by adjusting the order according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generating AI and have the generating AI adjust the order in which key points are extracted.

[0080] The analysis unit can determine the priority of key points based on the posting date of the review data during analysis. For example, the analysis unit can prioritize the extraction of key points from the most recent review data. The analysis unit can also lower the priority of key points from older review data. The analysis unit can also extract key points with a moderate priority for review data posted at a moderate time. By determining the priority of key points based on the posting date of the review data, the latest information can be extracted preferentially. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the posting date of the review data into a generating AI and have the generating AI determine the priority of key points.

[0081] The analysis unit can adjust the method of extracting key points based on the relevance of the review data during analysis. For example, the analysis unit can extract detailed key points for highly relevant review data. For example, the analysis unit can extract concise key points for low-relevance review data. For example, the analysis unit can extract concise key points for low-relevance review data. For example, the analysis unit can extract key points with a moderate level of detail for moderately relevant review data. By adjusting the method of extracting key points based on the relevance of the review data, more relevant key points can be extracted. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the relevance of the review data into a generating AI and have the generating AI adjust the method of extracting key points.

[0082] The display unit can estimate the user's emotions and adjust the display method based on the estimated emotions. For example, if the user has positive emotions, the display unit can provide a display method with bright colors. For example, if the user has positive emotions, the display unit can provide a display method with bright colors. The display unit can also provide a display method with calm colors if the user has negative emotions. For example, if the user has negative emotions, the display unit can provide a display method with calm colors. The display unit can also provide a display method with standard colors if the user has neutral emotions. For example, if the display unit has neutral emotions, the display unit can provide a display method with standard colors. By adjusting the display method according to the user's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input user emotion data into a generating AI and have the AI ​​adjust the display method.

[0083] The display unit can adjust the level of detail displayed based on the importance of the extracted elements during display. For example, the display unit can display detailed information for elements of high importance. The display unit can also display concise information for elements of low importance. The display unit can also display information of moderate importance with appropriate detail. By adjusting the level of detail of the display based on the importance of the extracted elements, information with the appropriate level of detail can be displayed. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the importance of the extracted elements into a generating AI and have the generating AI perform the adjustment of the level of detail of the display.

[0084] The display unit can apply different display formats depending on the category of the extracted elements during display. For example, in the case of a product review, the display unit can display product images and price information. For example, in the case of a service review, the display unit can display service details and user ratings. For example, in the case of a restaurant review, the display unit can display food photos and menu information. By applying different display formats depending on the category of the extracted elements, information can be displayed in a more appropriate format. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the categories of the extracted elements into a generating AI and have the generating AI apply the display format.

[0085] The display unit can estimate the user's emotions and adjust the display order based on the estimated emotions. For example, if the user has positive emotions, the display unit will display positive elements first. The display unit can also display negative elements first if the user has negative emotions. The display unit can also display elements in a balanced order if the user has neutral emotions. By adjusting the display order according to the user's emotions, information can be displayed in a more appropriate order. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input user emotion data into a generating AI and have the generating AI adjust the display order.

[0086] The display unit can determine the display priority based on the posting date of the extracted elements when displaying them. For example, the display unit can prioritize the display of the most recent elements. The display unit can also lower the display priority of older elements. The display unit can also display elements with a moderate posting date with a moderate priority. In this way, by determining the display priority based on the posting date of the extracted elements, the latest information can be displayed preferentially. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the posting dates of the extracted elements into a generating AI and have the generating AI determine the display priority.

[0087] The display unit can adjust the display method based on the relevance of the extracted elements during display. For example, the display unit can display detailed information for elements with high relevance. The display unit can also display concise information for elements with low relevance. The display unit can also display information with a moderate level of detail for elements with moderate relevance. By adjusting the display method based on the relevance of the extracted elements, more relevant information can be displayed. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the relevance of the extracted elements into a generating AI and have the generating AI adjust the display method.

[0088] The sentiment analysis unit can estimate the user's emotions and adjust the sentiment analysis method based on the estimated emotions. For example, if the user has positive emotions, the sentiment analysis unit can apply an analysis method that emphasizes those positive emotions. For example, if the user has negative emotions, the sentiment analysis unit can apply an analysis method that emphasizes those negative emotions. For example, if the user has negative emotions, the sentiment analysis unit can apply an analysis method that emphasizes those negative emotions. For example, if the user has neutral emotions, the sentiment analysis unit can apply a balanced sentiment analysis method. For example, if the user has neutral emotions, the sentiment analysis unit can apply a balanced sentiment analysis method. By adjusting the sentiment analysis method according to the user's emotions, more appropriate sentiment analysis becomes possible. 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-described processes in the emotion analysis unit may be performed using AI, for example, or without AI. For example, the emotion analysis unit can input the user's emotion data into a generating AI and have the generating AI adjust the emotion analysis method.

[0089] The sentiment analysis unit can optimize its analysis algorithm by referring to past sentiment data during sentiment analysis. For example, the sentiment analysis unit can adjust its current sentiment analysis algorithm based on the user's past sentiment data. The sentiment analysis unit can also detect specific patterns by referring to past sentiment data and optimize its analysis algorithm. The sentiment analysis unit can also improve the accuracy of sentiment analysis by utilizing past sentiment data. As a result, the accuracy of sentiment analysis is improved by optimizing the analysis algorithm by referring to past sentiment data. Some or all of the above processes in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input past sentiment data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0090] The sentiment analysis unit can apply different sentiment analysis methods to each category of review data during sentiment analysis. For example, in the case of product reviews, the sentiment analysis unit can apply sentiment analysis methods related to product quality and price. For example, in the case of service reviews, the sentiment analysis unit can apply sentiment analysis methods related to service responsiveness and convenience. For example, in the case of restaurant reviews, the sentiment analysis unit can apply sentiment analysis methods related to the taste of the food and atmosphere. By applying different sentiment analysis methods to each category of review data, more appropriate sentiment analysis becomes possible. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input the categories of the review data into a generating AI and have the generating AI execute the application of sentiment analysis methods.

[0091] The sentiment analysis unit can estimate the user's emotions and adjust the order in which the sentiment analysis results are displayed based on the estimated emotions. For example, if the user has positive emotions, the sentiment analysis unit will display positive sentiment analysis results first. The sentiment analysis unit can also display negative sentiment analysis results first if the user has negative emotions. Furthermore, if the user has neutral emotions, the sentiment analysis unit can display the results in a balanced order. This allows for the display of information in a more appropriate order by adjusting the order in which the sentiment analysis results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the emotion analysis unit may be performed using AI, for example, or without AI. For example, the emotion analysis unit can input the user's emotion data into a generating AI and have the generating AI adjust the display order of the emotion analysis results.

[0092] The sentiment analysis unit can analyze changes in sentiment based on the posting date of the review data during sentiment analysis. For example, the sentiment analysis unit can prioritize the analysis of changes in sentiment for the most recent review data. The sentiment analysis unit can also postpone the analysis of changes in sentiment for older review data. The sentiment analysis unit can also analyze changes in sentiment for review data posted at a moderate timeframe with appropriate priority. This makes it easier to understand changes in sentiment by analyzing them based on the posting date of the review data. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input the posting date of the review data into a generating AI and have the generating AI perform the analysis of changes in sentiment.

[0093] The sentiment analysis unit can analyze sentiment by referring to relevant market data for word-of-mouth data during sentiment analysis. For example, the sentiment analysis unit can analyze sentiment related to a specific trend based on relevant market data. The sentiment analysis unit can also analyze sentiment towards a specific product or service by referring to relevant market data. The sentiment analysis unit can also improve the accuracy of sentiment analysis by using relevant market data. This makes it possible to perform more accurate sentiment analysis by analyzing sentiment by referring to relevant market data for word-of-mouth data. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can input relevant market data into a generating AI and have the generating AI perform the sentiment analysis.

[0094] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0095] The analysis unit can estimate the user's emotions and adjust the method of extracting key points based on the estimated emotions. For example, if the user has positive emotions, positive key points can be prioritized for extraction. If the user has negative emotions, negative key points can be prioritized for extraction. Furthermore, if the user has neutral emotions, balanced key points can be extracted. In this way, by adjusting the key point extraction method according to the user's emotions, more appropriate key points can be extracted.

[0096] The data collection unit can analyze a user's past review posting history and select the optimal collection method. For example, it can collect review data based on the time slots the user frequently posted in the past. It can also select the optimal collection method based on the devices the user has used in the past. Furthermore, it can prioritize the collection of review data related to specific topics based on the user's past posting content. In this way, the optimal collection method can be selected by analyzing past posting history.

[0097] The display unit can estimate the user's emotions and adjust the display method based on those emotions. For example, if the user has positive emotions, it can provide a display method with bright colors. If the user has negative emotions, it can provide a display method with calm colors. Furthermore, if the user has neutral emotions, it can provide a display method with standard colors. By adjusting the display method according to the user's emotions, a more appropriate display becomes possible.

[0098] The data collection unit can filter user reviews based on their current areas of interest and purchase history. For example, it can prioritize collecting reviews related to products the user has recently purchased. It can also filter relevant reviews based on categories the user has shown interest in. Furthermore, it can collect reviews related to specific brands based on the user's purchase history. This allows for the collection of highly relevant review data by filtering based on the user's areas of interest and purchase history.

[0099] The sentiment analysis unit can estimate the user's emotions and adjust the sentiment analysis method based on the estimated emotions. For example, if the user has positive emotions, an analysis method that emphasizes positive emotions can be applied. If the user has negative emotions, an analysis method that emphasizes negative emotions can be applied. Furthermore, if the user has neutral emotions, a balanced sentiment analysis method can be applied. By adjusting the sentiment analysis method according to the user's emotions, more appropriate sentiment analysis becomes possible.

[0100] The analysis unit can adjust the level of detail of the key points based on the importance of the review data during analysis. For example, it can extract detailed key points from highly important review data. Conversely, it can extract concise key points from less important review data. Furthermore, it can extract key points with an appropriate level of detail from moderately important review data. In this way, by adjusting the level of detail of the key points based on the importance of the review data, it is possible to extract key points with the appropriate level of detail.

[0101] The display unit can adjust the level of detail based on the importance of the extracted elements during display. For example, it can display detailed information for high-importance elements, concise information for low-importance elements, and information of moderate importance for elements of moderate importance. By adjusting the level of detail based on the importance of the extracted elements, it is possible to display information with an appropriate level of detail.

[0102] The data collection unit can estimate the user's emotions and determine the priority of the review data to collect based on those estimated emotions. For example, if a user has positive emotions, positive review data can be prioritized for collection. Similarly, if a user has negative emotions, negative review data can be prioritized for collection. Furthermore, if a user has neutral emotions, balanced review data can be collected. This allows for the collection of more relevant data by prioritizing the review data to be collected according to the user's emotions.

[0103] The analysis unit can apply different analysis algorithms depending on the category of the review data during analysis. For example, in the case of product reviews, it can apply an algorithm that extracts key points regarding product quality and price. Similarly, in the case of service reviews, it can apply an algorithm that extracts key points regarding service responsiveness and convenience. Furthermore, in the case of restaurant reviews, it can apply an algorithm that extracts key points regarding the taste of the food and the atmosphere. By applying different analysis algorithms depending on the category of the review data, it is possible to extract more appropriate key points.

[0104] The display unit can estimate the user's emotions and adjust the display order based on those emotions. For example, if the user has positive emotions, positive elements can be displayed first. If the user has negative emotions, negative elements can be displayed first. Furthermore, if the user has neutral emotions, elements can be displayed in a balanced order. By adjusting the display order according to the user's emotions, information can be displayed in a more appropriate order.

[0105] The following briefly describes the processing flow for example form 2.

[0106] Step 1: The collection unit collects review data. This review data includes text, images, videos, etc. The collection unit uses methods such as scraping review data from websites, obtaining it through APIs, or having users directly input review data. For example, the collection unit provides an interface for users to post reviews. Step 2: The analysis unit uses a generation AI to analyze the word-of-mouth data collected by the collection unit and extract key points. Key points are extracted based on importance, frequency, and relevance. For example, word-of-mouth data can be analyzed and key points extracted using a text generation AI (LLM) or a multimodal generation AI. It is also possible to use a generation AI to extract and summarize particularly important information from the word-of-mouth data. Step 3: The display unit shows the number of comments and specific examples for the elements extracted by the analysis unit. The number of comments is calculated using methods such as the number of comments within a certain period or the number of comments under specific conditions. The display unit shows the number of comments for the extracted elements as a graph or chart, and displays specific examples in list or table format. Step 4: The sentiment analysis unit analyzes the sentiment of each review and classifies it into positive and negative opinions. Sentiment analysis is performed using methods such as positive, negative, and neutral. The sentiment analysis unit uses natural language processing techniques and machine learning algorithms to analyze sentiment and classify positive and negative opinions. For example, the sentiment analysis unit can input the text data of each review into a generating AI and have the generating AI perform the sentiment analysis.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] Each of the multiple elements described above, including the collection unit, analysis unit, display unit, and sentiment analysis unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit collects word-of-mouth data via the communication I / F 44 of the smart device 14 and processes the collected data by the identification processing unit 290 of the data processing unit 12. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the word-of-mouth data using a generation AI to extract key points. The display unit is implemented in the display 40A of the smart device 14 and displays the number of comments and specific examples for the extracted elements. The sentiment analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the sentiment of each review and classifies them into positive and negative opinions. 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.

[0111] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] Each of the multiple elements described above, including the collection unit, analysis unit, display unit, and sentiment analysis unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit collects word-of-mouth data via the communication I / F 44 of the smart glasses 214 and processes the collected data by the identification processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and analyzes the word-of-mouth data using generating AI and extracts key points. The display unit is implemented, for example, by the display of the smart glasses 214, and displays the number of comments and specific examples for the extracted elements. The sentiment analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and analyzes the sentiment of each review and classifies them into positive and negative opinions. 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.

[0127] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements described above, including the collection unit, analysis unit, display unit, and sentiment analysis unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects word-of-mouth data via the communication I / F 44 of the headset terminal 314 and processes the collected data by the identification processing unit 290 of the data processing unit 12. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the word-of-mouth data using a generation AI to extract key points. The display unit is implemented in the display 343 of the headset terminal 314 and displays the number of comments and specific examples for the extracted elements. The sentiment analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the sentiment of each review and classifies positive and negative opinions. 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.

[0143] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] Each of the multiple elements described above, including the collection unit, analysis unit, display unit, and sentiment analysis unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects word-of-mouth data via the robot 414's communication I / F 44 and processes the collected data with the identification processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, with the identification processing unit 290 of the data processing unit 12, which analyzes the word-of-mouth data using a generating AI and extracts key points. The display unit is implemented, for example, with the robot 414's display, which displays the number of comments and specific examples for the extracted elements. The sentiment analysis unit is implemented, for example, with the identification processing unit 290 of the data processing unit 12, which analyzes the sentiment of each review and classifies them into positive and negative opinions. 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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."

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] (Note 1) The collection department collects word-of-mouth data, The analysis unit analyzes the word-of-mouth data collected by the aforementioned collection unit and extracts key points, A display unit that shows the number of comments and specific examples for the elements extracted by the analysis unit, It includes a sentiment analysis unit that analyzes the sentiment of each review and classifies positive and negative opinions. A system characterized by the following features. (Note 2) The aforementioned analysis unit, The AI ​​generates and analyzes word-of-mouth data, extracting key points. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned display unit is Display the number of comments and specific examples for the extracted elements. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned emotion analysis unit, Analyze the sentiment of each review and categorize them into positive and negative opinions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is We estimate user sentiment and adjust the timing of collecting word-of-mouth data based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is Analyze the user's past review posting history to select the optimal collection method. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is When collecting user review data, filtering is performed based on the user's current areas of interest and purchase history. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is It estimates user sentiment and determines the priority of the word-of-mouth data to collect based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting user review data, the system prioritizes collecting highly relevant data based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is When collecting word-of-mouth data, we analyze users' social media activity and collect relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, We estimate the user's emotions and adjust the method of extracting key points based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During analysis, the level of detail in the key points is adjusted based on the importance of the word-of-mouth data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the review data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, It estimates the user's emotions and adjusts the order in which key points are extracted based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, the priority of key points is determined based on when the user reviews were posted. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, the method of extracting key points is adjusted based on the relevance of the word-of-mouth data. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned display unit is It estimates the user's emotions and adjusts the display method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned display unit is When displaying, adjust the level of detail based on the importance of the extracted elements. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned display unit is When displaying, apply different display formats depending on the category of the extracted elements. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned display unit is It estimates the user's emotions and adjusts the display order based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned display unit is When displaying, the display priority is determined based on the posting date of the extracted elements. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned display unit is When displaying, adjust the display method based on the relevance of the extracted elements. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned emotion analysis unit, It estimates the user's emotions and adjusts the emotion analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned emotion analysis unit, During sentiment analysis, the analysis algorithm is optimized by referring to past sentiment data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned emotion analysis unit, When performing sentiment analysis, different sentiment analysis methods are applied to each category of review data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned emotion analysis unit, It estimates the user's emotions and adjusts the order in which the sentiment analysis results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned emotion analysis unit, When analyzing sentiment, we analyze changes in sentiment based on when the review data was posted. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned emotion analysis unit, When performing sentiment analysis, we analyze sentiment by referring to relevant market data from word-of-mouth data. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0179] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The collection department collects word-of-mouth data, The analysis unit analyzes the word-of-mouth data collected by the aforementioned collection unit and extracts key points, A display unit that shows the number of comments and specific examples for the elements extracted by the analysis unit, It includes a sentiment analysis unit that analyzes the sentiment of each review and classifies positive and negative opinions. A system characterized by the following features.

2. The aforementioned analysis unit, The AI ​​generates the data to analyze word-of-mouth reviews and extract key points. The system according to feature 1.

3. The aforementioned display unit is Display the number of comments and specific examples for the extracted elements. The system according to feature 1.

4. The aforementioned emotion analysis unit, Analyze the sentiment of each review and categorize them into positive and negative opinions. The system according to feature 1.

5. The aforementioned collection unit is We estimate user sentiment and adjust the timing of collecting word-of-mouth data based on the estimated user sentiment. The system according to feature 1.

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

7. The aforementioned collection unit is When collecting user review data, filtering is performed based on the user's current areas of interest and purchase history. The system according to feature 1.

8. The aforementioned collection unit is It estimates user sentiment and determines the priority of the word-of-mouth data to collect based on the estimated user sentiment. The system according to feature 1.

Images