system

Abstract

The system according to this embodiment aims to efficiently find reviews that match the user's preferences. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a matching unit, and a presentation unit. The collection unit collects review information. The analysis unit analyzes the review information collected by the collection unit. The matching unit matches the user's preferences with the reviewer's evaluation tendencies based on the information analyzed by the analysis unit. The presentation unit displays the reviews of the reviewers extracted by the matching unit.

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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to find a review that matches one's preferences from a large amount of review information.

[0005] The system according to the embodiment aims to efficiently find a review that matches the user's preferences.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an analysis unit, a matching unit, and a presentation unit. The collection unit collects review information. The analysis unit analyzes the review information collected by the collection unit. The matching unit matches the user's preferences with the reviewer's evaluation tendencies based on the information analyzed by the analysis unit. The presentation unit displays the reviews of the reviewers extracted by the matching unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently find reviews that match the user's preferences. [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, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied 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 receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The review extraction system according to an embodiment of the present invention is a system for efficiently finding reviews that match a user's preferences. This review extraction system summarizes the user's past reviews and preferences and matches them with the reviewer's evaluation tendencies to display reviews from highly suitable reviewers. For example, the review extraction system summarizes and categorizes a large amount of review information for each reviewer. In this process, it uses a generative AI to analyze the review content and understand each reviewer's evaluation tendencies. For example, if a certain reviewer tends to give high ratings to movies of a particular genre, that reviewer's reviews will be classified into the "Movies" category. Next, the review extraction system similarly summarizes the user's past reviews and preferences. The generative AI analyzes the reviews and ratings previously posted by the user to identify the user's preferences. For example, it extracts the characteristics of products and services that the user has previously given high ratings to and understands the user's preferences based on that. Based on this information, the generative AI matches the user's preferences with the reviewer's evaluation tendencies. Specifically, it finds reviewers that match the user's preferences and scores the content of those reviewers' reviews. Reviewers with high scores are deemed more likely to provide reviews that match the user's preferences. Finally, the review extraction system presents information on the shops and products recommended by highly suitable reviewers, or how those reviewers rate the product the user is currently viewing. For example, when a user is browsing a product, the ratings of highly suitable reviewers for that product are displayed. This allows the user to efficiently find reviews that match their preferences. For example, if a user is looking for a new restaurant, the generating AI displays the ratings of reviewers that match the user's preferences and presents restaurants recommended by those reviewers. This allows the user to efficiently find restaurants that match their preferences. In this way, the review extraction system allows users to efficiently find reviews that match their preferences.

[0029] The review extraction system according to the embodiment comprises a collection unit, an analysis unit, a matching unit, and a presentation unit. The collection unit collects review information. The collection unit can collect review information from, for example, review sites on the internet or social media. The collection unit can also automatically collect review information using generative AI. For example, the collection unit collects reviews containing specific keywords. The collection unit can also summarize and categorize review information by reviewer. For example, the collection unit classifies reviews into categories such as movies, restaurants, and products based on the reviewer's evaluation tendencies. The analysis unit analyzes the review information collected by the collection unit. The analysis unit analyzes the review information using generative AI. For example, the analysis unit analyzes the content of reviews using natural language processing technology. The analysis unit can also grasp the reviewer's evaluation tendencies. For example, the analysis unit extracts the characteristics of products and services that reviewers have given high ratings to in the past and grasps the reviewer's evaluation tendencies based on that. The matching unit matches user preferences with reviewer evaluation tendencies based on the information analyzed by the analysis unit. The matching unit uses generative AI to match user preferences with reviewer evaluation trends. For example, the matching unit analyzes the user's past reviews and evaluations to identify the user's preferences. The matching unit also finds reviewers that match the user's preferences and scores the content of those reviewers' reviews. The presentation unit displays the reviews of the reviewers extracted by the matching unit. The presentation unit uses generative AI to display reviews from reviewers with a high degree of suitability. For example, the presentation unit displays the evaluations of reviewers with a high degree of suitability for the product the user is viewing. The presentation unit can also display stores and products recommended by reviewers with a high degree of suitability. As a result, the review extraction system according to this embodiment allows users to efficiently find reviews that match their preferences.

[0030] The data collection unit collects review information. For example, it can collect review information from review sites and social media on the internet. Specifically, the data collection unit uses a web crawler to periodically scan specific review sites and social media pages, automatically collecting new review information. The data collection unit can also automatically collect review information using generative AI. Generative AI identifies reviews containing specific keywords or phrases and collects these reviews. For example, it collects reviews containing keywords such as "delicious," "recommended," and "best." Furthermore, the data collection unit can summarize and categorize review information by reviewer. Using natural language processing technology, the generative AI summarizes the content of reviews and classifies them into categories such as movies, restaurants, and products based on the reviewer's evaluation tendencies. For example, the data collection unit analyzes reviews previously posted by reviewers to identify which categories of reviews that reviewer primarily posts. This allows the data collection unit to efficiently collect and organize a wide range of review information. Additionally, the data collection unit stores the collected review information in a database, making it accessible to the analysis and matching units. The data collection unit can flexibly configure the frequency and target of review information collection, enabling data collection tailored to specific periods or events. This allows the data collection unit to always have access to the latest review information, improving the overall accuracy and reliability of the system.

[0031] The analysis unit analyzes the review information collected by the collection unit. The analysis unit uses generative AI to analyze the review information. Specifically, the generative AI uses natural language processing technology to analyze the content of the reviews and understand the reviewer's evaluation tendencies. For example, the analysis unit tokenizes the text data of the reviews and calculates the sentiment score for each token to evaluate the overall sentiment of the reviews. The generative AI also extracts the characteristics of products and services that reviewers have given high ratings to in the past and uses this to understand the reviewer's evaluation tendencies. For example, the analysis unit analyzes the reviews that reviewers have posted in the past and identifies whether those reviewers tend to give high ratings to products and services with specific categories or characteristics. This allows the analysis unit to understand the reviewer's evaluation tendencies in detail and generate basic data to provide reviews that match the user's preferences. Furthermore, the analysis unit can also evaluate the reliability and consistency of the review information. For example, the analysis unit analyzes the reviewer's past posting history and the consistency of their ratings to identify reliable reviewers. This allows the analysis unit to prioritize providing reliable review information and improve user satisfaction. The analysis unit can analyze the collected data in real time and always provide the latest information. This allows the analysis unit to respond quickly to user needs and improve the overall system performance.

[0032] The matching unit matches user preferences with reviewer evaluation trends based on information analyzed by the analysis unit. The matching unit uses generative AI to match user preferences with reviewer evaluation trends. Specifically, the matching unit analyzes the user's past reviews and ratings to identify user preferences. For example, the matching unit extracts the characteristics of products and services that the user has previously given high ratings to, and uses this to identify the user's preferences. The matching unit also finds reviewers that match the user's preferences and scores the content of their reviews. The generative AI compares user preferences with reviewer evaluation trends to identify the most suitable reviewer. For example, if a user likes a particular genre of movies, the AI ​​identifies reviewers who tend to give high ratings to that genre and prioritizes displaying their reviews. This allows the matching unit to efficiently provide reviews that match the user's preferences. Furthermore, the matching unit can collect user feedback and continuously improve the accuracy of its matching algorithm. For example, by having users rate the provided reviews, the matching unit adjusts its algorithm based on that rating, achieving more accurate matching. Furthermore, the matching function can analyze users' behavioral and search history to adapt to changes in user preferences. This allows the matching function to consistently provide reviews based on the latest user preferences, thereby improving user satisfaction.

[0033] The presentation section displays reviews from reviewers extracted by the matching section. The presentation section uses generative AI to display reviews from highly relevant reviewers. Specifically, it displays ratings from highly relevant reviewers for the product the user is viewing. For example, if a user is viewing a specific product page, it prioritizes displaying reviews from reviewers who have given that product a high rating. The presentation section can also display stores and products recommended by highly relevant reviewers. The generative AI selects and presents the most relevant reviews based on the reviewers' rating trends and the user's preferences. This allows users to efficiently find reviews that match their preferences. Furthermore, the presentation section can customize the user interface to make it easier for users to view reviews. For example, it can adjust the display order of reviews to the user's preferences, or display review summaries and highlights to help users quickly grasp important information. The presentation section can also collect user feedback and continuously improve the accuracy and effectiveness of its displayed content. For example, if a user gives a high rating to a particular review, the algorithm can be adjusted to prioritize displaying reviews from that reviewer. This allows the presentation unit to provide users with optimal review information and improve user satisfaction.

[0034] The preference identification unit identifies the user's past reviews and preferences. The preference identification unit uses generative AI to identify the user's past reviews and preferences. For example, the preference identification unit analyzes reviews and ratings previously posted by the user to identify the user's preferences. Furthermore, the preference identification unit extracts the characteristics of products and services that the user has previously given high ratings to, and uses this to understand the user's preferences. This allows for more accurate matching by identifying the user's past reviews and preferences. Some or all of the above processing in the preference identification unit may be performed using generative AI, or it may be performed without generative AI. For example, the preference identification unit can input the user's past reviews and ratings into the generative AI and have the generative AI perform the identification of the user's preferences.

[0035] The evaluation trend analysis unit understands the evaluation trends of reviewers. The evaluation trend analysis unit uses a generative AI to understand the evaluation trends of reviewers. For example, the evaluation trend analysis unit extracts the characteristics of products and services that reviewers have given high ratings to in the past and understands the reviewer's evaluation trends based on that. The evaluation trend analysis unit can also analyze the reviewer's past evaluation history and confirm the consistency of their evaluations. In this way, by understanding the reviewer's evaluation trends, it is possible to find reviewers that match the user's preferences. Some or all of the above processing in the evaluation trend analysis unit may be performed using a generative AI, or it may be performed without using a generative AI. For example, the evaluation trend analysis unit can input the reviewer's past evaluation history into a generative AI and have the generative AI perform the evaluation trend analysis.

[0036] The rating display unit displays reviewer ratings for the product the user is viewing. The rating display unit uses a generation AI to display reviewer ratings for the product the user is viewing. For example, when a user is viewing a product, the rating display unit displays the ratings of reviewers who are highly suitable for that product. The rating display unit can also display stores and products recommended by highly suitable reviewers. This allows the user to quickly check product ratings by displaying reviewer ratings for the product they are viewing. Some or all of the above processing in the rating display unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the rating display unit can input the reviewer ratings for the product the user is viewing into the generation AI and have the generation AI perform the display of the ratings.

[0037] The data collection unit can aggregate, summarize, and categorize review information for each reviewer. The data collection unit uses a generative AI to aggregate, summarize, and categorize review information for each reviewer. For example, the data collection unit classifies reviews into categories such as movies, restaurants, and products based on the reviewer's evaluation tendencies. The data collection unit can also summarize the content of each reviewer's review and classify it into each category. This makes it easier to organize review information by aggregating, summarizing, and categorizing review information for each reviewer. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit can input the content of a reviewer's review into a generative AI and have the generative AI perform the summarization and categorization.

[0038] The analysis unit can summarize a user's past reviews and preferences and match them with each category. The analysis unit uses generative AI to summarize a user's past reviews and preferences and match them with each category. For example, the analysis unit analyzes reviews and ratings previously posted by a user to identify the user's preferences. The analysis unit can also find reviewers that match the user's preferences and score the content of those reviewers' reviews. In this way, by summarizing a user's past reviews and preferences and matching them with each category, it is possible to find reviewers that match the user's preferences. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can input a user's past reviews and ratings into the generative AI and have the generative AI perform summarization and matching.

[0039] The matching unit can extract reviewers with high scores for suitability of preferences and review content. The matching unit uses a generative AI to extract reviewers with high scores for suitability of preferences and review content. For example, the matching unit finds reviewers that match the user's preferences and scores the content of those reviewers' reviews. The matching unit can also extract reviewers with high scores and determine that they are likely to provide reviews that match the user's preferences. In this way, by extracting reviewers with high scores for suitability of preferences and review content, it is possible to find reviewers that match the user's preferences. Some or all of the above processing in the matching unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the matching unit can input the user's preferences and the reviewer's evaluation tendencies into a generative AI and have the generative AI calculate the suitability score.

[0040] The display unit can present information on stores and products recommended by highly suitable reviewers, or how those reviewers rate the product they are currently viewing. The display unit uses a generative AI to present information on stores and products recommended by highly suitable reviewers, or how those reviewers rate the product they are currently viewing. For example, when a user is viewing a product, the display unit displays the ratings of highly suitable reviewers for that product. The display unit can also display stores and products recommended by highly suitable reviewers. By presenting information on stores and products recommended by highly suitable reviewers, or how those reviewers rate the product they are currently viewing, users can efficiently find reviews that suit their preferences. Some or all of the above processing in the display unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the display unit can input the evaluation information of highly suitable reviewers into a generative AI and have the generative AI determine the display content.

[0041] The data collection unit can prioritize collecting highly relevant reviews based on the user's past browsing history when collecting review information. The data collection unit uses a generation AI to prioritize collecting highly relevant reviews based on the user's past browsing history. For example, the data collection unit prioritizes collecting reviews related to products the user has previously viewed. The data collection unit can also prioritize collecting reviews in categories that the user frequently views. Furthermore, the data collection unit can prioritize collecting reviews from reviewers that the user has previously given high ratings to. By prioritizing the collection of highly relevant reviews based on the user's past browsing history, the data collection unit can efficiently collect review information that is beneficial to the user. Some or all of the above processing in the data collection unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the data collection unit can input the user's past browsing history into a generation AI and have the generation AI perform the collection of highly relevant reviews.

[0042] The data collection unit can evaluate the reliability of reviewers when collecting review information and prioritize the collection of reviews from highly reliable reviewers. The data collection unit uses generative AI to evaluate the reliability of reviewers when collecting review information and prioritize the collection of reviews from highly reliable reviewers. For example, the data collection unit can evaluate reliability based on a reviewer's past rating history and prioritize the collection of reviews from highly reliable reviewers. The data collection unit can also evaluate reliability based on a reviewer's number of followers and ratings and prioritize the collection of reviews from highly reliable reviewers. Furthermore, the data collection unit can evaluate reliability based on a reviewer's expertise and experience and prioritize the collection of reviews from highly reliable reviewers. By evaluating the reliability of reviewers and prioritizing the collection of reviews from highly reliable reviewers, the data collection unit can provide highly reliable review information. Some or all of the above processing in the data collection unit may be performed using generative AI or not. For example, the data collection unit can input the reviewer's trustworthiness into the generating AI, which can then perform the trustworthiness evaluation and review collection.

[0043] The data collection unit can prioritize collecting highly relevant reviews based on the user's geographical location when gathering review information. The data collection unit uses generative AI to prioritize collecting highly relevant reviews based on the user's geographical location. For example, the data collection unit prioritizes collecting reviews of stores and services near the user's current location. It can also prioritize collecting reviews related to places the user has visited in the past. Furthermore, it can prioritize collecting reviews related to travel destinations the user is planning. This allows for the efficient collection of useful review information by prioritizing the collection of highly relevant reviews based on the user's geographical location. Some or all of the above processing in the data collection unit may be performed using generative AI, or without it. For example, the data collection unit can input the user's geographical location information into the generative AI and have the generative AI collect highly relevant reviews.

[0044] The data collection unit can collect relevant reviews based on the user's social media activity when collecting review information. The data collection unit uses a generative AI to collect relevant reviews based on the user's social media activity when collecting review information. For example, the data collection unit can collect reviews related to products and services that the user has "liked" or shared on social media. The data collection unit can also collect reviews of products and services recommended by influencers that the user follows. Furthermore, the data collection unit can collect relevant reviews based on comments and opinions posted by the user on social media. In this way, useful review information can be efficiently collected for the user by collecting relevant reviews based on the user's social media activity. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit can input the user's social media activity data into a generative AI and have the generative AI perform the collection of relevant reviews.

[0045] The analysis unit can improve the accuracy of its analysis based on the reviewer's past evaluation history. The analysis unit uses a generative AI to improve the accuracy of its analysis based on the reviewer's past evaluation history. For example, the analysis unit can verify the consistency of evaluations based on the reviewer's past evaluation history to improve the accuracy of its analysis. The analysis unit can also identify evaluation trends for specific genres or categories from the reviewer's past evaluation history to improve the accuracy of its analysis. Furthermore, the analysis unit can analyze the reviewer's past evaluation history and prioritize the analysis of highly reliable evaluations. This allows for the provision of highly reliable analysis results by improving the accuracy of the analysis based on the reviewer's past evaluation history. Some or all of the above-described processes in the analysis unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the analysis unit can input the reviewer's past evaluation history into a generative AI and have the generative AI perform the analysis accuracy improvement.

[0046] The analysis unit can apply different analysis algorithms to each review category during analysis. The analysis unit uses a generative AI to apply different analysis algorithms to each review category during analysis. For example, the analysis unit can apply an analysis algorithm based on the movie genre, director, and cast to movie reviews. It can also apply an analysis algorithm based on the type of cuisine, service, and atmosphere to restaurant reviews. Furthermore, it can apply an analysis algorithm based on the product's features, design, and price to product reviews. By applying different analysis algorithms to each review category, the analysis unit can provide optimal analysis results for each category. Some or all of the above-described processes in the analysis unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the analysis unit can input review category information into a generative AI and have the generative AI execute the application of category-specific analysis algorithms.

[0047] The analysis unit can determine the priority of analysis based on the submission date of reviews during the analysis process. The analysis unit uses a generative AI to determine the priority of analysis based on the submission date of reviews during the analysis process. For example, the analysis unit can prioritize the analysis of the most recent reviews to provide the latest information. The analysis unit can also prioritize the analysis of reviews submitted in a concentrated period. Furthermore, the analysis unit can prioritize the analysis of the latest reviews from reviewers who have previously received high ratings from the user. This allows for the priority provision of the latest information by determining the priority of analysis based on the submission date of reviews. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit can input review submission date information into a generative AI and have the generative AI perform the determination of analysis priorities.

[0048] The analysis unit can adjust the order of analysis based on the relevance of the reviews during analysis. The analysis unit uses a generative AI to adjust the order of analysis based on the relevance of the reviews during analysis. For example, the analysis unit prioritizes analyzing reviews related to the product the user is currently viewing. The analysis unit can also prioritize analyzing reviews related to products that the user has previously given high ratings to. Furthermore, the analysis unit can prioritize analyzing reviews related to categories that the user is interested in. By adjusting the order of analysis based on the relevance of the reviews, the analysis unit can prioritize providing information that is useful to the user. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit can input review relevance information into a generative AI and have the generative AI perform the adjustment of the analysis order.

[0049] The matching unit can improve the accuracy of matching based on the user's past rating history. The matching unit uses a generative AI to improve the accuracy of matching based on the user's past rating history. For example, the matching unit prioritizes matching ratings from reviewers to whom the user has previously given high ratings. The matching unit can also improve the accuracy of matching by understanding the user's rating trends for specific genres or categories from their past rating history. Furthermore, the matching unit can analyze the user's past rating history and prioritize matching ratings that are highly reliable. By improving the accuracy of matching based on the user's past rating history, it is possible to provide highly reliable matching results. Some or all of the above processing in the matching unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the matching unit can input the user's past rating history into a generative AI and have the generative AI perform the matching accuracy improvement.

[0050] The matching unit can perform matching based on the reviewer's attribute information during the matching process. The matching unit uses a generative AI to perform matching based on the reviewer's attribute information during the matching process. For example, the matching unit can perform matching based on the reviewer's attribute information such as age, gender, and occupation. The matching unit can also perform matching considering the reviewer's place of residence and cultural background. Furthermore, the matching unit can perform matching based on the reviewer's hobbies and interests. In this way, by performing matching based on the reviewer's attribute information, it is possible to find reviewers that match the user's preferences. Some or all of the above processing in the matching unit may be performed using a generative AI, or it may be performed without using a generative AI. For example, the matching unit can input the reviewer's attribute information into a generative AI and have the generative AI perform the matching.

[0051] The matching unit can perform matching based on the geographical distribution of reviewers. The matching unit uses a generative AI to perform matching based on the geographical distribution of reviewers. For example, the matching unit prioritizes matching reviewers with ratings from reviewers who are geographically close based on their place of residence. The matching unit can also match relevant ratings based on the reviewers' travel destinations and places they have visited. Furthermore, the matching unit can consider the geographical distribution of reviewers to understand regional rating trends and perform matching accordingly. This allows for the understanding of regional rating trends and the provision of useful information to users by performing matching based on the geographical distribution of reviewers. Some or all of the above processing in the matching unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the matching unit can input the geographical distribution information of reviewers into a generative AI and have the generative AI perform the matching.

[0052] The matching unit can improve the accuracy of matching based on the reviewer's relevant literature during the matching process. The matching unit uses generative AI to improve the accuracy of matching based on the reviewer's relevant literature during the matching process. For example, the matching unit can refer to articles and blogs previously written by the reviewer to verify the consistency of their evaluations. The matching unit can also verify the reliability of evaluations based on the literature and reference materials cited by the reviewer. Furthermore, the matching unit can understand the background of evaluations by referring to information on events and seminars the reviewer has previously attended. This improves the accuracy of matching based on the reviewer's relevant literature, thereby providing highly reliable matching results. Some or all of the above-described processes in the matching unit may be performed using generative AI, or they may be performed without generative AI. For example, the matching unit can input the reviewer's relevant literature information into the generative AI and have the generative AI perform the matching accuracy improvement.

[0053] The presentation unit can select the optimal display method based on the user's past browsing history when presenting information. The presentation unit uses a generation AI to select the optimal display method based on the user's past browsing history when presenting information. For example, the presentation unit can prioritize displaying reviews related to products the user has previously viewed. The presentation unit can also prioritize displaying reviews in categories that the user frequently views. Furthermore, the presentation unit can prioritize displaying reviews from reviewers that the user has previously given high ratings to. By selecting the optimal display method based on the user's past browsing history, the presentation unit can efficiently display review information that is useful to the user. Some or all of the above processing in the presentation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the presentation unit can input the user's past browsing history into a generation AI and have the generation AI select the optimal display method.

[0054] The presentation unit can determine the priority of reviews to display based on the reviewer's trustworthiness at the time of presentation. The presentation unit uses a generative AI to determine the priority of reviews to display based on the reviewer's trustworthiness at the time of presentation. For example, the presentation unit can evaluate trustworthiness based on the reviewer's past rating history and prioritize the display of reviews from highly trustworthy reviewers. The presentation unit can also evaluate trustworthiness based on the number of followers and ratings of reviewers and prioritize the display of reviews from highly trustworthy reviewers. Furthermore, the presentation unit can evaluate trustworthiness based on the reviewer's expertise and experience and prioritize the display of reviews from highly trustworthy reviewers. In this way, by determining the priority of reviews to display based on the reviewer's trustworthiness, highly reliable review information can be provided. Some or all of the above processing in the presentation unit may be performed using a generative AI or not. For example, the presentation unit can input reviewer trustworthiness information into a generative AI and have the generative AI perform the determination of the priority of reviews to display.

[0055] The presentation unit can determine the display priority based on the submission date of the reviews at the time of presentation. The presentation unit uses a generative AI to determine the display priority based on the submission date of the reviews at the time of presentation. For example, the presentation unit can prioritize displaying the most recent reviews. It can also prioritize displaying reviews that were submitted in a concentrated period of time. Furthermore, it can prioritize displaying the latest reviews from reviewers that the user has previously given high ratings to. In this way, by determining the display priority based on the submission date of the reviews, the latest information can be provided preferentially. Some or all of the above processing in the presentation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the presentation unit can input review submission date information into a generative AI and have the generative AI perform the determination of the display priority.

[0056] The presentation unit can adjust the display order of reviews based on their relevance at the time of presentation. The presentation unit uses a generative AI to adjust the display order of reviews based on their relevance at the time of presentation. For example, the presentation unit can prioritize displaying reviews related to the product the user is currently viewing. The presentation unit can also prioritize displaying reviews related to products that the user has previously given high ratings to. Furthermore, the presentation unit can prioritize displaying reviews related to categories that the user is interested in. In this way, by adjusting the display order based on the relevance of reviews, the presentation unit can prioritize providing information that is useful to the user. Some or all of the above processing in the presentation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the presentation unit can input review relevance information into a generative AI and have the generative AI perform the adjustment of the display order.

[0057] The preference identification unit can select the optimal identification method based on the user's past evaluation history when identifying preferences. The preference identification unit uses a generation AI to select the optimal identification method based on the user's past evaluation history when identifying preferences. For example, the preference identification unit identifies preferences based on the characteristics of products and services that the user has given high ratings to in the past. The preference identification unit can also grasp preferences for specific genres or categories from the user's past evaluation history. Furthermore, the preference identification unit can analyze the user's past evaluation history to identify highly reliable preferences. As a result, by selecting the optimal identification method based on the user's past evaluation history, it becomes possible to identify highly reliable preferences. Some or all of the above processing in the preference identification unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the preference identification unit can input the user's past evaluation history into a generation AI and have the generation AI select the optimal identification method.

[0058] The preference identification unit can select the optimal identification method based on the user's geographical location information when identifying preferences. The preference identification unit uses a generation AI to select the optimal identification method based on the user's geographical location information when identifying preferences. For example, the preference identification unit identifies preferences for products and services that are geographically close to the user based on the user's current location. The preference identification unit can also identify preferences related to places the user has visited in the past. Furthermore, the preference identification unit can identify preferences related to travel destinations the user is planning. By selecting the optimal identification method based on the user's geographical location information, it becomes possible to identify preferences that are beneficial to the user. Some or all of the above processing in the preference identification unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the preference identification unit can input the user's geographical location information into a generation AI and have the generation AI select the optimal identification method.

[0059] The evaluation trend analysis unit can select the optimal analysis method based on the reviewer's past evaluation history when analyzing evaluation trends. The evaluation trend analysis unit uses a generation AI to select the optimal analysis method based on the reviewer's past evaluation history when analyzing evaluation trends. For example, the evaluation trend analysis unit can confirm the consistency of evaluations and understand evaluation trends based on the reviewer's past evaluation history. The evaluation trend analysis unit can also understand evaluation trends for specific genres or categories from the reviewer's past evaluation history. Furthermore, the evaluation trend analysis unit can analyze the reviewer's past evaluation history and understand highly reliable evaluation trends. As a result, by selecting the optimal analysis method based on the reviewer's past evaluation history, it becomes possible to understand evaluation trends with high reliability. Some or all of the above processing in the evaluation trend analysis unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the evaluation trend analysis unit can input the reviewer's past evaluation history into a generation AI and have the generation AI select the optimal analysis method.

[0060] The evaluation trend analysis unit can select the optimal analysis method based on the reviewer's geographical location information when analyzing evaluation trends. The evaluation trend analysis unit uses a generation AI to select the optimal analysis method based on the reviewer's geographical location information when analyzing evaluation trends. For example, the evaluation trend analysis unit can analyze the evaluation trends of geographically close reviewers based on their place of residence. The evaluation trend analysis unit can also analyze relevant evaluation trends based on the reviewer's travel destinations and places visited. Furthermore, the evaluation trend analysis unit can analyze evaluation trends by region, taking into account the geographical distribution of reviewers. By selecting the optimal analysis method based on the reviewer's geographical location information, it is possible to analyze evaluation trends by region and provide information that is useful to the user. Some or all of the above processing in the evaluation trend analysis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the evaluation trend analysis unit can input the reviewer's geographical location information into the generation AI and have the generation AI select the optimal analysis method.

[0061] The rating display unit can select the optimal display method based on the user's past browsing history when displaying ratings. The rating display unit uses a generation AI to select the optimal display method based on the user's past browsing history when displaying ratings. For example, the rating display unit can prioritize displaying ratings related to products the user has previously viewed. The rating display unit can also prioritize displaying ratings for categories the user frequently views. Furthermore, the rating display unit can prioritize displaying ratings from reviewers to whom the user has previously given high ratings. By selecting the optimal display method based on the user's past browsing history, useful rating information can be efficiently displayed to the user. Some or all of the above processing in the rating display unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the rating display unit can input the user's past browsing history into a generation AI and have the generation AI select the optimal display method.

[0062] The evaluation display unit can select the optimal display method based on the user's device information when displaying an evaluation. The evaluation display unit uses a generation AI to select the optimal display method based on the user's device information when displaying an evaluation. For example, if the user is using a smartphone, the evaluation display unit provides a display method that matches the screen size. The evaluation display unit can also provide a display method optimized for a larger screen if the user is using a tablet. Furthermore, if the user is using a smartwatch, the evaluation display unit can provide a concise and highly visible display method. By selecting the optimal display method based on the user's device information, the evaluation display unit can provide the user with highly visible evaluation information. Some or all of the above processing in the evaluation display unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the evaluation display unit can input the user's device information into the generation AI and have the generation AI select the optimal display method.

[0063] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0064] The review extraction system can further prioritize the display of highly relevant reviews based on the user's past browsing history. For example, it can prioritize reviews related to products the user has previously viewed. It can also prioritize reviews in categories the user frequently browses. Furthermore, it can prioritize reviews from reviewers the user has previously given high ratings to. By prioritizing highly relevant reviews based on the user's past browsing history, the system can efficiently provide users with useful review information.

[0065] The review extraction system can further evaluate the trustworthiness of reviewers and prioritize the display of reviews from highly trustworthy reviewers. For example, it can evaluate trustworthiness based on a reviewer's past rating history and prioritize the display of reviews from highly trustworthy reviewers. It can also evaluate trustworthiness based on the number of followers and ratings of reviewers and prioritize the display of reviews from highly trustworthy reviewers. Furthermore, it can evaluate trustworthiness based on the expertise and experience of reviewers and prioritize the display of reviews from highly trustworthy reviewers. In this way, by determining the priority of reviews to display based on the trustworthiness of reviewers, it is possible to provide highly reliable review information.

[0066] The review extraction system can further prioritize the display of highly relevant reviews based on the user's geographical location. For example, it can prioritize reviews of stores and services near the user's current location. It can also prioritize reviews related to places the user has visited in the past. Furthermore, it can prioritize reviews related to travel destinations the user is planning. By prioritizing the display of highly relevant reviews based on the user's geographical location, the system can efficiently provide users with useful review information.

[0067] The review extraction system can further display relevant reviews based on the user's social media activity. For example, it can display reviews related to products and services that the user has "liked" or shared on social media. It can also display reviews of products and services recommended by influencers that the user follows. Furthermore, it can display relevant reviews based on comments and opinions posted by the user on social media. In this way, by displaying relevant reviews based on the user's social media activity, it can efficiently provide users with useful review information.

[0068] The review extraction system can further improve the accuracy of its analysis based on the reviewer's past rating history. For example, it can verify the consistency of ratings based on the reviewer's past rating history, thereby improving the accuracy of the analysis. It can also identify rating trends for specific genres or categories from the reviewer's past rating history, further improving the accuracy of the analysis. In addition, it can analyze the reviewer's past rating history and prioritize the analysis of highly reliable ratings. By improving the accuracy of the analysis based on the reviewer's past rating history, it can provide highly reliable analysis results.

[0069] The following briefly describes the processing flow for example form 1.

[0070] Step 1: The collection unit collects review information. The collection unit can collect review information from review sites and social media on the internet. The collection unit uses generative AI to automatically collect reviews containing specific keywords. The collection unit can also aggregate, summarize, and categorize review information by reviewer. For example, the collection unit classifies reviews into categories such as movies, restaurants, and products based on the reviewer's evaluation tendencies. Step 2: The analysis unit analyzes the review information collected by the collection unit. The analysis unit uses generative AI and natural language processing technology to analyze the content of the reviews. In addition, the analysis unit extracts the characteristics of products and services that reviewers have given high ratings to in the past in order to understand the reviewers' evaluation trends. Step 3: The matching unit matches the user's preferences with the reviewer's evaluation tendencies based on the information analyzed by the analysis unit. The matching unit uses a generation AI to analyze the user's past reviews and evaluations to identify the user's preferences. Furthermore, it finds reviewers that match the user's preferences and scores the content of those reviewers' reviews. Step 4: The presentation section displays reviews from reviewers extracted by the matching section. The presentation section uses a generation AI to display reviews from highly relevant reviewers. For example, it displays ratings from highly relevant reviewers for the product the user is viewing, or stores and products recommended by highly relevant reviewers.

[0071] (Example of form 2) The review extraction system according to an embodiment of the present invention is a system for efficiently finding reviews that match a user's preferences. This review extraction system summarizes the user's past reviews and preferences and matches them with the reviewer's evaluation tendencies to display reviews from highly suitable reviewers. For example, the review extraction system summarizes and categorizes a large amount of review information for each reviewer. In this process, it uses a generative AI to analyze the review content and understand each reviewer's evaluation tendencies. For example, if a certain reviewer tends to give high ratings to movies of a particular genre, that reviewer's reviews will be classified into the "Movies" category. Next, the review extraction system similarly summarizes the user's past reviews and preferences. The generative AI analyzes the reviews and ratings previously posted by the user to identify the user's preferences. For example, it extracts the characteristics of products and services that the user has previously given high ratings to and understands the user's preferences based on that. Based on this information, the generative AI matches the user's preferences with the reviewer's evaluation tendencies. Specifically, it finds reviewers that match the user's preferences and scores the content of those reviewers' reviews. Reviewers with high scores are deemed more likely to provide reviews that match the user's preferences. Finally, the review extraction system presents information on the shops and products recommended by highly suitable reviewers, or how those reviewers rate the product the user is currently viewing. For example, when a user is browsing a product, the ratings of highly suitable reviewers for that product are displayed. This allows the user to efficiently find reviews that match their preferences. For example, if a user is looking for a new restaurant, the generating AI displays the ratings of reviewers that match the user's preferences and presents restaurants recommended by those reviewers. This allows the user to efficiently find restaurants that match their preferences. In this way, the review extraction system allows users to efficiently find reviews that match their preferences.

[0072] The review extraction system according to the embodiment comprises a collection unit, an analysis unit, a matching unit, and a presentation unit. The collection unit collects review information. The collection unit can collect review information from, for example, review sites on the internet or social media. The collection unit can also automatically collect review information using generative AI. For example, the collection unit collects reviews containing specific keywords. The collection unit can also summarize and categorize review information by reviewer. For example, the collection unit classifies reviews into categories such as movies, restaurants, and products based on the reviewer's evaluation tendencies. The analysis unit analyzes the review information collected by the collection unit. The analysis unit analyzes the review information using generative AI. For example, the analysis unit analyzes the content of reviews using natural language processing technology. The analysis unit can also grasp the reviewer's evaluation tendencies. For example, the analysis unit extracts the characteristics of products and services that reviewers have given high ratings to in the past and grasps the reviewer's evaluation tendencies based on that. The matching unit matches user preferences with reviewer evaluation tendencies based on the information analyzed by the analysis unit. The matching unit uses generative AI to match user preferences with reviewer evaluation trends. For example, the matching unit analyzes the user's past reviews and evaluations to identify the user's preferences. The matching unit also finds reviewers that match the user's preferences and scores the content of those reviewers' reviews. The presentation unit displays the reviews of the reviewers extracted by the matching unit. The presentation unit uses generative AI to display reviews from reviewers with a high degree of suitability. For example, the presentation unit displays the evaluations of reviewers with a high degree of suitability for the product the user is viewing. The presentation unit can also display stores and products recommended by reviewers with a high degree of suitability. As a result, the review extraction system according to this embodiment allows users to efficiently find reviews that match their preferences.

[0073] The data collection unit collects review information. For example, it can collect review information from review sites and social media on the internet. Specifically, the data collection unit uses a web crawler to periodically scan specific review sites and social media pages, automatically collecting new review information. The data collection unit can also automatically collect review information using generative AI. Generative AI identifies reviews containing specific keywords or phrases and collects these reviews. For example, it collects reviews containing keywords such as "delicious," "recommended," and "best." Furthermore, the data collection unit can summarize and categorize review information by reviewer. Using natural language processing technology, the generative AI summarizes the content of reviews and classifies them into categories such as movies, restaurants, and products based on the reviewer's evaluation tendencies. For example, the data collection unit analyzes reviews previously posted by reviewers to identify which categories of reviews that reviewer primarily posts. This allows the data collection unit to efficiently collect and organize a wide range of review information. Additionally, the data collection unit stores the collected review information in a database, making it accessible to the analysis and matching units. The data collection unit can flexibly configure the frequency and target of review information collection, enabling data collection tailored to specific periods or events. This allows the data collection unit to always have access to the latest review information, improving the overall accuracy and reliability of the system.

[0074] The analysis unit analyzes the review information collected by the data collection unit. The analysis unit uses generative AI to analyze the review information. Specifically, the generative AI uses natural language processing technology to analyze the content of the reviews and understand the reviewer's evaluation tendencies. For example, the analysis unit tokenizes the text data of the reviews and calculates a sentiment score for each token to evaluate the overall sentiment of the reviews. The generative AI also extracts the characteristics of products and services that reviewers have given high ratings to in the past and uses this to understand the reviewer's evaluation tendencies. For example, the analysis unit analyzes reviews posted by reviewers in the past and identifies whether those reviewers tend to give high ratings to products and services with specific categories or characteristics. This allows the analysis unit to understand the reviewer's evaluation tendencies in detail and generate basic data to provide reviews that match the user's preferences. Furthermore, the analysis unit can also evaluate the reliability and consistency of the review information. For example, the analysis unit analyzes the reviewer's past posting history and the consistency of their ratings to identify reliable reviewers. This allows the analysis unit to prioritize providing reliable review information and improve user satisfaction. The analysis unit can analyze collected data in real time and always provide the latest information. This allows the analysis unit to respond quickly to user needs and improve the overall system performance.

[0075] The matching unit matches user preferences with reviewer evaluation trends based on information analyzed by the analysis unit. The matching unit uses generative AI to match user preferences with reviewer evaluation trends. Specifically, the matching unit analyzes the user's past reviews and ratings to identify user preferences. For example, the matching unit extracts the characteristics of products and services that the user has previously given high ratings to, and uses this to identify the user's preferences. The matching unit also finds reviewers that match the user's preferences and scores the content of their reviews. The generative AI compares user preferences with reviewer evaluation trends to identify the most suitable reviewer. For example, if a user likes a particular genre of movies, the AI ​​identifies reviewers who tend to give high ratings to that genre and prioritizes displaying their reviews. This allows the matching unit to efficiently provide reviews that match the user's preferences. Furthermore, the matching unit can collect user feedback and continuously improve the accuracy of its matching algorithm. For example, by having users rate the provided reviews, the matching unit adjusts its algorithm based on that rating, achieving more accurate matching. Furthermore, the matching function can analyze users' behavioral and search history to adapt to changes in user preferences. This allows the matching function to consistently provide reviews based on the latest user preferences, thereby improving user satisfaction.

[0076] The presentation section displays reviews from reviewers extracted by the matching section. The presentation section uses generative AI to display reviews from highly relevant reviewers. Specifically, it displays ratings from highly relevant reviewers for the product the user is viewing. For example, if a user is viewing a specific product page, it prioritizes displaying reviews from reviewers who have given that product a high rating. The presentation section can also display stores and products recommended by highly relevant reviewers. The generative AI selects and presents the most relevant reviews based on the reviewers' rating trends and the user's preferences. This allows users to efficiently find reviews that match their preferences. Furthermore, the presentation section can customize the user interface to make it easier for users to view reviews. For example, it can adjust the display order of reviews to the user's preferences, or display review summaries and highlights to help users quickly grasp important information. The presentation section can also collect user feedback and continuously improve the accuracy and effectiveness of its displayed content. For example, if a user gives a high rating to a particular review, the algorithm can be adjusted to prioritize displaying reviews from that reviewer. This allows the presentation unit to provide users with optimal review information and improve user satisfaction.

[0077] The preference identification unit identifies the user's past reviews and preferences. The preference identification unit uses generative AI to identify the user's past reviews and preferences. For example, the preference identification unit analyzes reviews and ratings previously posted by the user to identify the user's preferences. Furthermore, the preference identification unit extracts the characteristics of products and services that the user has previously given high ratings to, and uses this to understand the user's preferences. This allows for more accurate matching by identifying the user's past reviews and preferences. Some or all of the above processing in the preference identification unit may be performed using generative AI, or it may be performed without generative AI. For example, the preference identification unit can input the user's past reviews and ratings into the generative AI and have the generative AI perform the identification of the user's preferences.

[0078] The evaluation trend analysis unit understands the evaluation trends of reviewers. The evaluation trend analysis unit uses a generative AI to understand the evaluation trends of reviewers. For example, the evaluation trend analysis unit extracts the characteristics of products and services that reviewers have given high ratings to in the past and understands the reviewer's evaluation trends based on that. The evaluation trend analysis unit can also analyze the reviewer's past evaluation history and confirm the consistency of their evaluations. In this way, by understanding the reviewer's evaluation trends, it is possible to find reviewers that match the user's preferences. Some or all of the above processing in the evaluation trend analysis unit may be performed using a generative AI, or it may be performed without using a generative AI. For example, the evaluation trend analysis unit can input the reviewer's past evaluation history into a generative AI and have the generative AI perform the evaluation trend analysis.

[0079] The rating display unit displays reviewer ratings for the product the user is viewing. The rating display unit uses a generation AI to display reviewer ratings for the product the user is viewing. For example, when a user is viewing a product, the rating display unit displays the ratings of reviewers who are highly suitable for that product. The rating display unit can also display stores and products recommended by highly suitable reviewers. This allows the user to quickly check product ratings by displaying reviewer ratings for the product they are viewing. Some or all of the above processing in the rating display unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the rating display unit can input the reviewer ratings for the product the user is viewing into the generation AI and have the generation AI perform the display of the ratings.

[0080] The data collection unit can aggregate, summarize, and categorize review information for each reviewer. The data collection unit uses a generative AI to aggregate, summarize, and categorize review information for each reviewer. For example, the data collection unit classifies reviews into categories such as movies, restaurants, and products based on the reviewer's evaluation tendencies. The data collection unit can also summarize the content of each reviewer's review and classify it into each category. This makes it easier to organize review information by aggregating, summarizing, and categorizing review information for each reviewer. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit can input the content of a reviewer's review into a generative AI and have the generative AI perform the summarization and categorization.

[0081] The analysis unit can summarize a user's past reviews and preferences and match them with each category. The analysis unit uses generative AI to summarize a user's past reviews and preferences and match them with each category. For example, the analysis unit analyzes reviews and ratings previously posted by a user to identify the user's preferences. The analysis unit can also find reviewers that match the user's preferences and score the content of those reviewers' reviews. In this way, by summarizing a user's past reviews and preferences and matching them with each category, it is possible to find reviewers that match the user's preferences. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can input a user's past reviews and ratings into the generative AI and have the generative AI perform summarization and matching.

[0082] The matching unit can extract reviewers with high scores for suitability of preferences and review content. The matching unit uses a generative AI to extract reviewers with high scores for suitability of preferences and review content. For example, the matching unit finds reviewers that match the user's preferences and scores the content of those reviewers' reviews. The matching unit can also extract reviewers with high scores and determine that they are likely to provide reviews that match the user's preferences. In this way, by extracting reviewers with high scores for suitability of preferences and review content, it is possible to find reviewers that match the user's preferences. Some or all of the above processing in the matching unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the matching unit can input the user's preferences and the reviewer's evaluation tendencies into a generative AI and have the generative AI calculate the suitability score.

[0083] The display unit can present information on stores and products recommended by highly suitable reviewers, or how those reviewers rate the product they are currently viewing. The display unit uses a generative AI to present information on stores and products recommended by highly suitable reviewers, or how those reviewers rate the product they are currently viewing. For example, when a user is viewing a product, the display unit displays the ratings of highly suitable reviewers for that product. The display unit can also display stores and products recommended by highly suitable reviewers. By presenting information on stores and products recommended by highly suitable reviewers, or how those reviewers rate the product they are currently viewing, users can efficiently find reviews that suit their preferences. Some or all of the above processing in the display unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the display unit can input the evaluation information of highly suitable reviewers into a generative AI and have the generative AI determine the display content.

[0084] The data collection unit can estimate the user's emotions and adjust the timing of review information collection based on the estimated emotions. The data collection unit uses generative AI to estimate the user's emotions and adjust the timing of review information collection based on the estimated emotions. For example, if the user is relaxed, the data collection unit can collect review information immediately. If the user is stressed, the data collection unit can delay the collection timing and collect the information when the user has calmed down. If the user is in a hurry, the data collection unit can prioritize collecting only important review information. In this way, by adjusting the timing of review information collection based on the user's emotions, review information can be collected at the optimal timing according to the user's situation. 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 these examples. Some or all of the above processing in the data collection unit may be performed using generative AI or not. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the collection timing.

[0085] The data collection unit can prioritize collecting highly relevant reviews based on the user's past browsing history when collecting review information. The data collection unit uses a generation AI to prioritize collecting highly relevant reviews based on the user's past browsing history. For example, the data collection unit prioritizes collecting reviews related to products the user has previously viewed. The data collection unit can also prioritize collecting reviews in categories that the user frequently views. Furthermore, the data collection unit can prioritize collecting reviews from reviewers that the user has previously given high ratings to. By prioritizing the collection of highly relevant reviews based on the user's past browsing history, the data collection unit can efficiently collect review information that is beneficial to the user. Some or all of the above processing in the data collection unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the data collection unit can input the user's past browsing history into a generation AI and have the generation AI perform the collection of highly relevant reviews.

[0086] The data collection unit can evaluate the reliability of reviewers when collecting review information and prioritize the collection of reviews from highly reliable reviewers. The data collection unit uses generative AI to evaluate the reliability of reviewers when collecting review information and prioritize the collection of reviews from highly reliable reviewers. For example, the data collection unit can evaluate reliability based on a reviewer's past rating history and prioritize the collection of reviews from highly reliable reviewers. The data collection unit can also evaluate reliability based on a reviewer's number of followers and ratings and prioritize the collection of reviews from highly reliable reviewers. Furthermore, the data collection unit can evaluate reliability based on a reviewer's expertise and experience and prioritize the collection of reviews from highly reliable reviewers. By evaluating the reliability of reviewers and prioritizing the collection of reviews from highly reliable reviewers, the data collection unit can provide highly reliable review information. Some or all of the above processing in the data collection unit may be performed using generative AI or not. For example, the data collection unit can input the reviewer's trustworthiness into the generating AI, which can then perform the trustworthiness evaluation and review collection.

[0087] The collection unit can estimate the user's emotions and determine the priority of review information to collect based on the estimated emotions. The collection unit uses generative AI to estimate the user's emotions and determine the priority of review information to collect based on the estimated emotions. For example, if the user is relaxed, the collection unit will prioritize collecting detailed review information. If the user is stressed, the collection unit can also prioritize collecting concise and to-the-point review information. If the user is in a hurry, the collection unit can also prioritize collecting review information containing only the important points. In this way, by determining the priority of review information to collect based on the user's emotions, the system can provide optimal review information tailored to the user's situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the collection unit may be performed using generative AI or not. For example, the data collection unit can input user sentiment data into a generating AI, which can then determine the priority of the review information to collect.

[0088] The data collection unit can prioritize collecting highly relevant reviews based on the user's geographical location when gathering review information. The data collection unit uses generative AI to prioritize collecting highly relevant reviews based on the user's geographical location. For example, the data collection unit prioritizes collecting reviews of stores and services near the user's current location. It can also prioritize collecting reviews related to places the user has visited in the past. Furthermore, it can prioritize collecting reviews related to travel destinations the user is planning. This allows for the efficient collection of useful review information by prioritizing the collection of highly relevant reviews based on the user's geographical location. Some or all of the above processing in the data collection unit may be performed using generative AI, or without it. For example, the data collection unit can input the user's geographical location information into the generative AI and have the generative AI collect highly relevant reviews.

[0089] The data collection unit can collect relevant reviews based on the user's social media activity when collecting review information. The data collection unit uses a generative AI to collect relevant reviews based on the user's social media activity when collecting review information. For example, the data collection unit can collect reviews related to products and services that the user has "liked" or shared on social media. The data collection unit can also collect reviews of products and services recommended by influencers that the user follows. Furthermore, the data collection unit can collect relevant reviews based on comments and opinions posted by the user on social media. In this way, useful review information can be efficiently collected for the user by collecting relevant reviews based on the user's social media activity. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit can input the user's social media activity data into a generative AI and have the generative AI perform the collection of relevant reviews.

[0090] The analysis unit can estimate the user's emotions and adjust the analysis method of the review information based on the estimated user emotions. The analysis unit uses generative AI to estimate the user's emotions and adjust the analysis method of the review information based on the estimated user emotions. For example, if the user is relaxed, the analysis unit can perform a detailed analysis and provide an overall picture of the review. If the user is stressed, the analysis unit can also provide a concise and to-the-point analysis result. If the user is in a hurry, the analysis unit can also provide an analysis result that includes only the important points. In this way, by adjusting the analysis method of the review information based on the user's emotions, the optimal analysis result can be provided according to the user's situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the analysis method.

[0091] The analysis unit can improve the accuracy of its analysis based on the reviewer's past evaluation history. The analysis unit uses a generative AI to improve the accuracy of its analysis based on the reviewer's past evaluation history. For example, the analysis unit can verify the consistency of evaluations based on the reviewer's past evaluation history to improve the accuracy of its analysis. The analysis unit can also identify evaluation trends for specific genres or categories from the reviewer's past evaluation history to improve the accuracy of its analysis. Furthermore, the analysis unit can analyze the reviewer's past evaluation history and prioritize the analysis of highly reliable evaluations. This allows for the provision of highly reliable analysis results by improving the accuracy of the analysis based on the reviewer's past evaluation history. Some or all of the above-described processes in the analysis unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the analysis unit can input the reviewer's past evaluation history into a generative AI and have the generative AI perform the analysis accuracy improvement.

[0092] The analysis unit can apply different analysis algorithms to each review category during analysis. The analysis unit uses a generative AI to apply different analysis algorithms to each review category during analysis. For example, the analysis unit can apply an analysis algorithm based on the movie genre, director, and cast to movie reviews. It can also apply an analysis algorithm based on the type of cuisine, service, and atmosphere to restaurant reviews. Furthermore, it can apply an analysis algorithm based on the product's features, design, and price to product reviews. By applying different analysis algorithms to each review category, the analysis unit can provide optimal analysis results for each category. Some or all of the above-described processes in the analysis unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the analysis unit can input review category information into a generative AI and have the generative AI execute the application of category-specific analysis algorithms.

[0093] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. The analysis unit uses a generative AI to estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is relaxed, the analysis unit displays detailed analysis results. If the user is stressed, the analysis unit can also display concise and to-the-point analysis results. If the user is in a hurry, the analysis unit can also display analysis results that include only the important points. In this way, by adjusting the display method of the analysis results based on the user's emotions, the system can provide the optimal display method according to the user's situation. Emotion estimation is achieved using an emotion estimation function, such as 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-described processes in the analysis unit may be performed using the generative AI or not. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI adjust the display method of the analysis results.

[0094] The analysis unit can determine the priority of analysis based on the submission date of reviews during the analysis process. The analysis unit uses a generative AI to determine the priority of analysis based on the submission date of reviews during the analysis process. For example, the analysis unit can prioritize the analysis of the most recent reviews to provide the latest information. The analysis unit can also prioritize the analysis of reviews submitted in a concentrated period. Furthermore, the analysis unit can prioritize the analysis of the latest reviews from reviewers who have previously received high ratings from the user. This allows for the priority provision of the latest information by determining the priority of analysis based on the submission date of reviews. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit can input review submission date information into a generative AI and have the generative AI perform the determination of analysis priorities.

[0095] The analysis unit can adjust the order of analysis based on the relevance of the reviews during analysis. The analysis unit uses a generative AI to adjust the order of analysis based on the relevance of the reviews during analysis. For example, the analysis unit prioritizes analyzing reviews related to the product the user is currently viewing. The analysis unit can also prioritize analyzing reviews related to products that the user has previously given high ratings to. Furthermore, the analysis unit can prioritize analyzing reviews related to categories that the user is interested in. By adjusting the order of analysis based on the relevance of the reviews, the analysis unit can prioritize providing information that is useful to the user. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit can input review relevance information into a generative AI and have the generative AI perform the adjustment of the analysis order.

[0096] The matching unit can estimate the user's emotions and adjust the matching criteria based on the estimated emotions. The matching unit uses generative AI to estimate the user's emotions and adjust the matching criteria based on the estimated emotions. For example, if the user is relaxed, the matching unit applies detailed matching criteria. If the user is stressed, the matching unit can also apply concise and to-the-point matching criteria. Furthermore, if the user is in a hurry, the matching unit can apply matching criteria that include only the essential points. This allows the system to provide optimal matching results tailored to the user's situation by adjusting the matching criteria based on their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, 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 matching unit may be performed using or without generative AI. For example, the matching unit can input user emotion data into the generative AI and have the generative AI adjust the matching criteria.

[0097] The matching unit can improve the accuracy of matching based on the user's past rating history. The matching unit uses a generative AI to improve the accuracy of matching based on the user's past rating history. For example, the matching unit prioritizes matching ratings from reviewers to whom the user has previously given high ratings. The matching unit can also improve the accuracy of matching by understanding the user's rating trends for specific genres or categories from their past rating history. Furthermore, the matching unit can analyze the user's past rating history and prioritize matching ratings that are highly reliable. By improving the accuracy of matching based on the user's past rating history, it is possible to provide highly reliable matching results. Some or all of the above processing in the matching unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the matching unit can input the user's past rating history into a generative AI and have the generative AI perform the matching accuracy improvement.

[0098] The matching unit can perform matching based on the reviewer's attribute information during the matching process. The matching unit uses a generative AI to perform matching based on the reviewer's attribute information during the matching process. For example, the matching unit can perform matching based on the reviewer's attribute information such as age, gender, and occupation. The matching unit can also perform matching considering the reviewer's place of residence and cultural background. Furthermore, the matching unit can perform matching based on the reviewer's hobbies and interests. In this way, by performing matching based on the reviewer's attribute information, it is possible to find reviewers that match the user's preferences. Some or all of the above processing in the matching unit may be performed using a generative AI, or it may be performed without using a generative AI. For example, the matching unit can input the reviewer's attribute information into a generative AI and have the generative AI perform the matching.

[0099] The matching unit can estimate the user's emotions and adjust the display order of the matching results based on the estimated emotions. The matching unit uses generative AI to estimate the user's emotions and adjust the display order of the matching results based on the estimated emotions. For example, if the user is relaxed, the matching unit displays detailed matching results. If the user is stressed, the matching unit can also display concise and to-the-point matching results. Furthermore, if the user is in a hurry, the matching unit can display matching results containing only the important points. This allows for the provision of an optimal display method tailored to the user's situation by adjusting the display order of matching results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the matching unit may be performed using or without generative AI. For example, the matching unit can input user emotion data into the generative AI and have the generative AI adjust the display order of the matching results.

[0100] The matching unit can perform matching based on the geographical distribution of reviewers. The matching unit uses a generative AI to perform matching based on the geographical distribution of reviewers. For example, the matching unit prioritizes matching reviewers with ratings from reviewers who are geographically close based on their place of residence. The matching unit can also match relevant ratings based on the reviewers' travel destinations and places they have visited. Furthermore, the matching unit can consider the geographical distribution of reviewers to understand regional rating trends and perform matching accordingly. This allows for the understanding of regional rating trends and the provision of useful information to users by performing matching based on the geographical distribution of reviewers. Some or all of the above processing in the matching unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the matching unit can input the geographical distribution information of reviewers into a generative AI and have the generative AI perform the matching.

[0101] The matching unit can improve the accuracy of matching based on the reviewer's relevant literature during the matching process. The matching unit uses generative AI to improve the accuracy of matching based on the reviewer's relevant literature during the matching process. For example, the matching unit can refer to articles and blogs previously written by the reviewer to verify the consistency of their evaluations. The matching unit can also verify the reliability of evaluations based on the literature and reference materials cited by the reviewer. Furthermore, the matching unit can understand the background of evaluations by referring to information on events and seminars the reviewer has previously attended. This improves the accuracy of matching based on the reviewer's relevant literature, thereby providing highly reliable matching results. Some or all of the above-described processes in the matching unit may be performed using generative AI, or they may be performed without generative AI. For example, the matching unit can input the reviewer's relevant literature information into the generative AI and have the generative AI perform the matching accuracy improvement.

[0102] The presentation unit can estimate the user's emotions and adjust how reviews are displayed based on those emotions. The presentation unit uses generative AI to estimate the user's emotions and adjust how reviews are displayed based on those emotions. For example, if the user is relaxed, the presentation unit can display detailed review information. If the user is stressed, it can display concise and to-the-point review information. If the user is in a hurry, it can display review information containing only the most important points. By adjusting how reviews are displayed based on the user's emotions, the presentation unit can provide the optimal display method tailored to the user's situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the presentation unit may be performed using generative AI or not. For example, the presentation unit can input user emotion data into a generative AI and have the generative AI adjust the display method.

[0103] The presentation unit can select the optimal display method based on the user's past browsing history when presenting information. The presentation unit uses a generation AI to select the optimal display method based on the user's past browsing history when presenting information. For example, the presentation unit can prioritize displaying reviews related to products the user has previously viewed. The presentation unit can also prioritize displaying reviews in categories that the user frequently views. Furthermore, the presentation unit can prioritize displaying reviews from reviewers that the user has previously given high ratings to. By selecting the optimal display method based on the user's past browsing history, the presentation unit can efficiently display review information that is useful to the user. Some or all of the above processing in the presentation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the presentation unit can input the user's past browsing history into a generation AI and have the generation AI select the optimal display method.

[0104] The presentation unit can determine the priority of reviews to display based on the reviewer's trustworthiness at the time of presentation. The presentation unit uses a generative AI to determine the priority of reviews to display based on the reviewer's trustworthiness at the time of presentation. For example, the presentation unit can evaluate trustworthiness based on the reviewer's past rating history and prioritize the display of reviews from highly trustworthy reviewers. The presentation unit can also evaluate trustworthiness based on the number of followers and ratings of reviewers and prioritize the display of reviews from highly trustworthy reviewers. Furthermore, the presentation unit can evaluate trustworthiness based on the reviewer's expertise and experience and prioritize the display of reviews from highly trustworthy reviewers. In this way, by determining the priority of reviews to display based on the reviewer's trustworthiness, highly reliable review information can be provided. Some or all of the above processing in the presentation unit may be performed using a generative AI or not. For example, the presentation unit can input reviewer trustworthiness information into a generative AI and have the generative AI perform the determination of the priority of reviews to display.

[0105] The presentation unit can estimate the user's emotions and adjust the length of the reviews it presents based on those emotions. The presentation unit uses generative AI to estimate the user's emotions and adjust the length of the reviews based on those emotions. For example, if the user is relaxed, the presentation unit displays a detailed review. If the user is stressed, it can display a concise, to-the-point review. If the user is in a hurry, it can display a short review containing only the important points. By adjusting the length of the reviews based on the user's emotions, the presentation unit can provide optimal review information tailored to the user's situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the presentation unit may be performed using or without generative AI. For example, the presentation unit can input user emotion data into a generative AI and have the generative AI adjust the length of the reviews.

[0106] The presentation unit can determine the display priority based on the submission date of the reviews at the time of presentation. The presentation unit uses a generative AI to determine the display priority based on the submission date of the reviews at the time of presentation. For example, the presentation unit can prioritize displaying the most recent reviews. It can also prioritize displaying reviews that were submitted in a concentrated period of time. Furthermore, it can prioritize displaying the latest reviews from reviewers that the user has previously given high ratings to. In this way, by determining the display priority based on the submission date of the reviews, the latest information can be provided preferentially. Some or all of the above processing in the presentation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the presentation unit can input review submission date information into a generative AI and have the generative AI perform the determination of the display priority.

[0107] The presentation unit can adjust the display order of reviews based on their relevance at the time of presentation. The presentation unit uses a generative AI to adjust the display order of reviews based on their relevance at the time of presentation. For example, the presentation unit can prioritize displaying reviews related to the product the user is currently viewing. The presentation unit can also prioritize displaying reviews related to products that the user has previously given high ratings to. Furthermore, the presentation unit can prioritize displaying reviews related to categories that the user is interested in. In this way, by adjusting the display order based on the relevance of reviews, the presentation unit can prioritize providing information that is useful to the user. Some or all of the above processing in the presentation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the presentation unit can input review relevance information into a generative AI and have the generative AI perform the adjustment of the display order.

[0108] The preference identification unit can estimate the user's emotions and adjust the preference identification method based on the estimated emotions. The preference identification unit uses generative AI to estimate the user's emotions and adjust the preference identification method based on the estimated emotions. For example, if the user is relaxed, the preference identification unit applies a detailed preference identification method. If the user is stressed, the preference identification unit can also apply a concise and to-the-point preference identification method. If the user is in a hurry, the preference identification unit can also apply a preference identification method that includes only the important points. By adjusting the preference identification method based on the user's emotions, it becomes possible to identify the optimal preferences according to the user's situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the preference identification unit may be performed using generative AI or not. For example, the preference identification unit can input user emotion data into a generating AI and have the generating AI adjust the method of identifying preferences.

[0109] The preference identification unit can select the optimal identification method based on the user's past evaluation history when identifying preferences. The preference identification unit uses a generation AI to select the optimal identification method based on the user's past evaluation history when identifying preferences. For example, the preference identification unit identifies preferences based on the characteristics of products and services that the user has given high ratings to in the past. The preference identification unit can also grasp preferences for specific genres or categories from the user's past evaluation history. Furthermore, the preference identification unit can analyze the user's past evaluation history to identify highly reliable preferences. As a result, by selecting the optimal identification method based on the user's past evaluation history, it becomes possible to identify highly reliable preferences. Some or all of the above processing in the preference identification unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the preference identification unit can input the user's past evaluation history into a generation AI and have the generation AI select the optimal identification method.

[0110] The preference identification unit can estimate the user's emotions and determine preference priorities based on those estimated emotions. The preference identification unit uses generative AI to estimate the user's emotions and determine preference priorities based on those estimated emotions. For example, if the user is relaxed, the preference identification unit can set detailed preference priorities. If the user is stressed, the preference identification unit can also set concise and to-the-point preference priorities. Furthermore, if the user is in a hurry, the preference identification unit can set preference priorities that include only the important points. This allows for the setting of optimal preference priorities tailored to the user's situation by determining preference priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the preference identification unit may be performed using or without generative AI. For example, the preference identification unit can input user emotion data into a generative AI and have the generative AI determine preference priorities.

[0111] The preference identification unit can select the optimal identification method based on the user's geographical location information when identifying preferences. The preference identification unit uses a generation AI to select the optimal identification method based on the user's geographical location information when identifying preferences. For example, the preference identification unit identifies preferences for products and services that are geographically close to the user based on the user's current location. The preference identification unit can also identify preferences related to places the user has visited in the past. Furthermore, the preference identification unit can identify preferences related to travel destinations the user is planning. By selecting the optimal identification method based on the user's geographical location information, it becomes possible to identify preferences that are beneficial to the user. Some or all of the above processing in the preference identification unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the preference identification unit can input the user's geographical location information into a generation AI and have the generation AI select the optimal identification method.

[0112] The evaluation trend recognition unit can estimate the user's emotions and adjust the evaluation trend recognition method based on the estimated user emotions. The evaluation trend recognition unit uses generative AI to estimate the user's emotions and adjusts the evaluation trend recognition method based on the estimated user emotions. For example, if the user is relaxed, the evaluation trend recognition unit applies a detailed evaluation trend recognition method. If the user is stressed, the evaluation trend recognition unit can also apply a concise and to-the-point evaluation trend recognition method. If the user is in a hurry, the evaluation trend recognition unit can also apply an evaluation trend recognition method that includes only the important points. By adjusting the evaluation trend recognition method based on the user's emotions, it becomes possible to grasp the optimal evaluation trend according to the user's situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation trend recognition unit may be performed using generative AI or not. For example, the evaluation trend recognition unit can input user emotion data into the generating AI and have the generating AI adjust the method for recognizing evaluation trends.

[0113] The evaluation trend analysis unit can select the optimal analysis method based on the reviewer's past evaluation history when analyzing evaluation trends. The evaluation trend analysis unit uses a generation AI to select the optimal analysis method based on the reviewer's past evaluation history when analyzing evaluation trends. For example, the evaluation trend analysis unit can confirm the consistency of evaluations and understand evaluation trends based on the reviewer's past evaluation history. The evaluation trend analysis unit can also understand evaluation trends for specific genres or categories from the reviewer's past evaluation history. Furthermore, the evaluation trend analysis unit can analyze the reviewer's past evaluation history and understand highly reliable evaluation trends. As a result, by selecting the optimal analysis method based on the reviewer's past evaluation history, it becomes possible to understand evaluation trends with high reliability. Some or all of the above processing in the evaluation trend analysis unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the evaluation trend analysis unit can input the reviewer's past evaluation history into a generation AI and have the generation AI select the optimal analysis method.

[0114] The evaluation trend recognition unit can estimate the user's emotions and determine the priority of evaluation trends based on the estimated user emotions. The evaluation trend recognition unit uses generative AI to estimate the user's emotions and determine the priority of evaluation trends based on the estimated user emotions. For example, if the user is relaxed, the evaluation trend recognition unit sets a detailed priority of evaluation trends. If the user is stressed, the evaluation trend recognition unit can also set a concise and to-the-point priority of evaluation trends. If the user is in a hurry, the evaluation trend recognition unit can also set a priority of evaluation trends that includes only the important points. In this way, by determining the priority of evaluation trends based on the user's emotions, the optimal priority of evaluation trends can be set according to the user's situation. Emotion estimation is achieved using an emotion estimation function using 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 evaluation trend recognition unit may be performed using generative AI or not using generative AI. For example, the evaluation trend recognition unit can input user emotion data into the generating AI and have the generating AI determine the priority of evaluation trends.

[0115] The evaluation trend analysis unit can select the optimal analysis method based on the reviewer's geographical location information when analyzing evaluation trends. The evaluation trend analysis unit uses a generation AI to select the optimal analysis method based on the reviewer's geographical location information when analyzing evaluation trends. For example, the evaluation trend analysis unit can analyze the evaluation trends of geographically close reviewers based on their place of residence. The evaluation trend analysis unit can also analyze relevant evaluation trends based on the reviewer's travel destinations and places visited. Furthermore, the evaluation trend analysis unit can analyze evaluation trends by region, taking into account the geographical distribution of reviewers. By selecting the optimal analysis method based on the reviewer's geographical location information, it is possible to analyze evaluation trends by region and provide information that is useful to the user. Some or all of the above processing in the evaluation trend analysis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the evaluation trend analysis unit can input the reviewer's geographical location information into the generation AI and have the generation AI select the optimal analysis method.

[0116] The evaluation display unit can estimate the user's emotions and adjust the evaluation display method based on the estimated emotions. The evaluation display unit uses a generative AI to estimate the user's emotions and adjust the evaluation display method based on the estimated emotions. For example, if the user is relaxed, the evaluation display unit can display detailed evaluation information. If the user is stressed, the evaluation display unit can also display concise and to-the-point evaluation information. If the user is in a hurry, the evaluation display unit can also display evaluation information containing only the important points. In this way, by adjusting the evaluation display method based on the user's emotions, the optimal display method according to the user's situation can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the evaluation display unit may be performed using a generative AI or not. For example, the evaluation display unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the display method.

[0117] The rating display unit can select the optimal display method based on the user's past browsing history when displaying ratings. The rating display unit uses a generation AI to select the optimal display method based on the user's past browsing history when displaying ratings. For example, the rating display unit can prioritize displaying ratings related to products the user has previously viewed. The rating display unit can also prioritize displaying ratings for categories the user frequently views. Furthermore, the rating display unit can prioritize displaying ratings from reviewers to whom the user has previously given high ratings. By selecting the optimal display method based on the user's past browsing history, useful rating information can be efficiently displayed to the user. Some or all of the above processing in the rating display unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the rating display unit can input the user's past browsing history into a generation AI and have the generation AI select the optimal display method.

[0118] The evaluation display unit can estimate the user's emotions and determine the priority of evaluations based on the estimated emotions. The evaluation display unit uses generative AI to estimate the user's emotions and determine the priority of evaluations based on the estimated emotions. For example, if the user is relaxed, the evaluation display unit can set a priority for detailed evaluations. If the user is stressed, the evaluation display unit can also set a priority for concise and to-the-point evaluations. If the user is in a hurry, the evaluation display unit can also set a priority for evaluations that include only the important points. In this way, by determining the priority of evaluations based on the user's emotions, the optimal priority of evaluations can be set according to the user's situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation display unit may be performed using generative AI or not. For example, the evaluation display unit can input user emotion data into the generative AI and have the generative AI perform the determination of the priority of evaluations.

[0119] The evaluation display unit can select the optimal display method based on the user's device information when displaying an evaluation. The evaluation display unit uses a generation AI to select the optimal display method based on the user's device information when displaying an evaluation. For example, if the user is using a smartphone, the evaluation display unit provides a display method that matches the screen size. The evaluation display unit can also provide a display method optimized for a larger screen if the user is using a tablet. Furthermore, if the user is using a smartwatch, the evaluation display unit can provide a concise and highly visible display method. By selecting the optimal display method based on the user's device information, the evaluation display unit can provide the user with highly visible evaluation information. Some or all of the above processing in the evaluation display unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the evaluation display unit can input the user's device information into the generation AI and have the generation AI select the optimal display method.

[0120] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0121] The review extraction system can further estimate the user's emotions and adjust the display order of reviews based on those emotions. For example, if the user is relaxed, detailed reviews will be prioritized. If the user is stressed, concise and to-the-point reviews will be prioritized. Furthermore, if the user is in a hurry, reviews containing only the most important points will be prioritized. By adjusting the display order of reviews based on the user's emotions, the system can provide optimal review information tailored to the user's situation.

[0122] The review extraction system can further prioritize the display of highly relevant reviews based on the user's past browsing history. For example, it can prioritize reviews related to products the user has previously viewed. It can also prioritize reviews in categories the user frequently browses. Furthermore, it can prioritize reviews from reviewers the user has previously given high ratings to. By prioritizing highly relevant reviews based on the user's past browsing history, the system can efficiently provide users with useful review information.

[0123] The review extraction system can further evaluate the trustworthiness of reviewers and prioritize the display of reviews from highly trustworthy reviewers. For example, it can evaluate trustworthiness based on a reviewer's past rating history and prioritize the display of reviews from highly trustworthy reviewers. It can also evaluate trustworthiness based on the number of followers and ratings of reviewers and prioritize the display of reviews from highly trustworthy reviewers. Furthermore, it can evaluate trustworthiness based on the expertise and experience of reviewers and prioritize the display of reviews from highly trustworthy reviewers. In this way, by determining the priority of reviews to display based on the trustworthiness of reviewers, it is possible to provide highly reliable review information.

[0124] The review extraction system can further prioritize the display of highly relevant reviews based on the user's geographical location. For example, it can prioritize reviews of stores and services near the user's current location. It can also prioritize reviews related to places the user has visited in the past. Furthermore, it can prioritize reviews related to travel destinations the user is planning. By prioritizing the display of highly relevant reviews based on the user's geographical location, the system can efficiently provide users with useful review information.

[0125] The review extraction system can further display relevant reviews based on the user's social media activity. For example, it can display reviews related to products and services that the user has "liked" or shared on social media. It can also display reviews of products and services recommended by influencers that the user follows. Furthermore, it can display relevant reviews based on comments and opinions posted by the user on social media. In this way, by displaying relevant reviews based on the user's social media activity, it can efficiently provide users with useful review information.

[0126] The review extraction system can further estimate the user's emotions and adjust the length of the reviews based on those emotions. For example, if the user is relaxed, it can display a detailed review. If the user is stressed, it can display a concise, to-the-point review. Furthermore, if the user is in a hurry, it can display a short review containing only the most important points. By adjusting the length of reviews based on the user's emotions, the system can provide optimal review information tailored to the user's situation.

[0127] The review extraction system can further estimate the user's emotions and adjust how reviews are displayed based on those emotions. For example, if the user is relaxed, detailed review information can be displayed. If the user is stressed, concise and to-the-point review information can be displayed. Furthermore, if the user is in a hurry, review information containing only the most important points can be displayed. In this way, by adjusting how reviews are displayed based on the user's emotions, the system can provide the most appropriate display method for each user's situation.

[0128] The review extraction system can further estimate the user's emotions and prioritize reviews based on those emotions. For example, if the user is relaxed, detailed reviews can be prioritized. If the user is stressed, concise and to-the-point reviews can be prioritized. Furthermore, if the user is in a hurry, reviews containing only the most important points can be prioritized. This allows for the setting of optimal review priorities tailored to the user's situation by prioritizing reviews based on their emotions.

[0129] The review extraction system can further estimate the user's emotions and adjust the review analysis method based on those estimated emotions. For example, if the user is relaxed, it can perform a detailed analysis and provide a comprehensive overview of the review. If the user is stressed, it can provide a concise and to-the-point analysis. Furthermore, if the user is in a hurry, it can provide an analysis that includes only the most important points. In this way, by adjusting the review analysis method based on the user's emotions, it can provide the most appropriate analysis results for the user's situation.

[0130] The review extraction system can further improve the accuracy of its analysis based on the reviewer's past rating history. For example, it can verify the consistency of ratings based on the reviewer's past rating history, thereby improving the accuracy of the analysis. It can also identify rating trends for specific genres or categories from the reviewer's past rating history, further improving the accuracy of the analysis. In addition, it can analyze the reviewer's past rating history and prioritize the analysis of highly reliable ratings. By improving the accuracy of the analysis based on the reviewer's past rating history, it can provide highly reliable analysis results.

[0131] The following briefly describes the processing flow for example form 2.

[0132] Step 1: The collection unit collects review information. The collection unit can collect review information from review sites and social media on the internet. The collection unit uses generative AI to automatically collect reviews containing specific keywords. The collection unit can also aggregate, summarize, and categorize review information by reviewer. For example, the collection unit classifies reviews into categories such as movies, restaurants, and products based on the reviewer's evaluation tendencies. Step 2: The analysis unit analyzes the review information collected by the collection unit. The analysis unit uses generative AI and natural language processing technology to analyze the content of the reviews. In addition, the analysis unit extracts the characteristics of products and services that reviewers have given high ratings to in the past in order to understand the reviewers' evaluation trends. Step 3: The matching unit matches the user's preferences with the reviewer's evaluation tendencies based on the information analyzed by the analysis unit. The matching unit uses a generation AI to analyze the user's past reviews and evaluations to identify the user's preferences. Furthermore, it finds reviewers that match the user's preferences and scores the content of those reviewers' reviews. Step 4: The presentation section displays reviews from reviewers extracted by the matching section. The presentation section uses a generation AI to display reviews from highly relevant reviewers. For example, it displays ratings from highly relevant reviewers for the product the user is viewing, or stores and products recommended by highly relevant reviewers.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] Each of the multiple elements described above, including the collection unit, analysis unit, matching unit, and presentation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit collects review information using the control unit 46A of the smart device 14 and analyzes the collected information using the identification processing unit 290 of the data processing unit 12. The analysis unit grasps the reviewer's evaluation tendencies using the identification processing unit 290 of the data processing unit 12, and the matching unit matches the user's preferences with the reviewer's evaluation tendencies. The presentation unit displays reviews from highly suitable reviewers using the control unit 46A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0137] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] Each of the multiple elements described above, including the collection unit, analysis unit, matching unit, and presentation 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 review information using the control unit 46A of the smart glasses 214 and analyzes the collected information using the identification processing unit 290 of the data processing unit 12. The analysis unit grasps the reviewer's evaluation tendencies using the identification processing unit 290 of the data processing unit 12, for example, and the matching unit matches the user's preferences with the reviewer's evaluation tendencies. The presentation unit displays reviews from highly suitable reviewers using the control unit 46A of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0153] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] Each of the multiple elements described above, including the collection unit, analysis unit, matching unit, and presentation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects review information using the control unit 46A of the headset terminal 314 and analyzes the collected information using the identification processing unit 290 of the data processing unit 12. The analysis unit grasps the reviewer's evaluation tendencies using the identification processing unit 290 of the data processing unit 12, and the matching unit matches the user's preferences with the reviewer's evaluation tendencies. The presentation unit displays reviews from highly suitable reviewers using the control unit 46A of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0169] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.).

[0182] 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.

[0183] 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.

[0184] 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.

[0185] Each of the multiple elements described above, including the collection unit, analysis unit, matching unit, and presentation unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects review information using the control unit 46A of the robot 414 and analyzes the collected information using the identification processing unit 290 of the data processing unit 12. The analysis unit grasps the reviewer's evaluation tendencies using the identification processing unit 290 of the data processing unit 12, for example, and the matching unit matches the user's preferences with the reviewer's evaluation tendencies. The presentation unit displays reviews from highly suitable reviewers using the control unit 46A of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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."

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] (Note 1) A collection department that collects review information, An analysis unit analyzes the review information collected by the aforementioned collection unit, A matching unit matches user preferences with reviewer evaluation trends based on the information analyzed by the aforementioned analysis unit, The system includes a display unit that displays the reviews of reviewers extracted by the matching unit. A system characterized by the following features. (Note 2) It includes a preference identification section that identifies the user's past reviews and preferences. The system described in Appendix 1, characterized by the features described herein. (Note 3) It is equipped with an evaluation trend recognition unit that grasps the evaluation trends of reviewers. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a rating display section that shows reviewer ratings for the product the user is viewing. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is Summarize and categorize review information by reviewer. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, Summarize the user's past reviews and preferences and match them with each category. The system described in Appendix 1, characterized by the features described herein. (Note 7) The matching unit is Extract reviewers with high scores for suitability of their preferences and review content. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned display unit is, This displays information about stores and products recommended by highly qualified reviewers, or how those reviewers rate the products they are currently viewing. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is We estimate user sentiment and adjust the timing of review information collection based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is When collecting review information, the system prioritizes collecting highly relevant reviews based on the user's past browsing history. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting review information, the reliability of reviewers is evaluated, and reviews from highly reliable reviewers are prioritized for collection. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is It estimates user sentiment and determines the priority of review information to collect based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is When collecting review information, the system prioritizes collecting highly relevant reviews based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned collection unit is When collecting review information, relevant reviews are gathered based on the user's social media activity. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, We estimate user sentiment and adjust the review information analysis method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, the accuracy of the analysis is improved based on the reviewer's past evaluation history. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, different analysis algorithms are applied to each review category. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During the analysis, the priority of analyses is determined based on the timing of review submissions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, During analysis, the order of analyses will be adjusted based on the relevance of the reviews. The system described in Appendix 1, characterized by the features described herein. (Note 21) The matching unit is It estimates the user's emotions and adjusts the matching criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The matching unit is During the matching process, the accuracy of the matching is improved based on the user's past rating history. The system described in Appendix 1, characterized by the features described herein. (Note 23) The matching unit is Matching is performed based on the reviewer's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 24) The matching unit is It estimates the user's emotions and adjusts the display order of matching results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The matching unit is Matching is performed based on the geographical distribution of reviewers. The system described in Appendix 1, characterized by the features described herein. (Note 26) The matching unit is During the matching process, the accuracy of the matching is improved based on the reviewer's relevant literature. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned display unit is, We estimate the user's sentiment and adjust how reviews are displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned display unit is, When presenting content, the system selects the optimal display method based on the user's past browsing history. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned display unit is, When presenting reviews, the priority of the reviews to display is determined based on the reviewer's credibility. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned display unit is, It estimates the user's sentiment and adjusts the length of the reviews presented based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned display unit is, When presenting, the priority of display will be determined based on the timing of review submission. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned display unit is, When presenting reviews, the display order will be adjusted based on their relevance. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned preference identification unit is It estimates the user's emotions and adjusts the method of identifying preferences based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned preference identification unit is When identifying preferences, the optimal identification method is selected based on the user's past evaluation history. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned preference identification unit is It estimates the user's emotions and determines preference priorities based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned preference identification unit is When identifying preferences, the optimal identification method is selected based on the user's geographical location information. The system described in Appendix 2, characterized by the features described herein. (Note 37) The aforementioned evaluation trend recognition unit is We estimate user emotions and adjust the method of understanding evaluation trends based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned evaluation trend recognition unit is When analyzing evaluation trends, the most appropriate method of analysis is selected based on the reviewer's past evaluation history. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned evaluation trend recognition unit is It estimates the user's emotions and determines the priority of evaluation trends based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned evaluation trend recognition unit is When analyzing evaluation trends, the most suitable method of analysis is selected based on the geographical location information of the reviewers. The system described in Appendix 3, characterized by the features described herein. (Note 41) The evaluation display unit is, It estimates the user's sentiment and adjusts how ratings are displayed based on that estimated sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 42) The evaluation display unit is, When displaying ratings, the system selects the optimal display method based on the user's past browsing history. The system described in Appendix 4, characterized by the features described herein. (Note 43) The evaluation display unit is, It estimates the user's emotions and determines the priority of evaluations based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 44) The evaluation display unit is, When displaying ratings, the optimal display method is selected based on the user's device information. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A collection department that collects review information, An analysis unit analyzes the review information collected by the aforementioned collection unit, A matching unit matches user preferences with reviewer evaluation trends based on the information analyzed by the aforementioned analysis unit, The system includes a display unit that displays the reviews of reviewers extracted by the matching unit. A system characterized by the following features.

2. It includes a preference identification section that identifies the user's past reviews and preferences. The system according to feature 1.

3. It is equipped with an evaluation trend recognition unit that grasps the evaluation trends of reviewers. The system according to feature 1.

4. It includes a rating display section that shows reviewer ratings for the product the user is viewing. The system according to feature 1.

5. The aforementioned collection unit is Summarize and categorize review information by reviewer. The system according to feature 1.

6. The aforementioned analysis unit, Summarize the user's past reviews and preferences and match them with each category. The system according to feature 1.

7. The matching unit is Extract reviewers with high scores for suitability of their preferences and review content. The system according to feature 1.

8. The aforementioned display unit is, This displays information about stores and products recommended by highly qualified reviewers, or how those reviewers rate the products they are currently viewing. The system according to feature 1.

9. The aforementioned collection unit is We estimate user sentiment and adjust the timing of review information collection based on the estimated user sentiment. The system according to feature 1.

10. The aforementioned collection unit is When collecting review information, the system prioritizes collecting highly relevant reviews based on the user's past browsing history. The system according to feature 1.

Images