System

Abstract

To provide a system for improving the usability and reliability of a gourmet site.SOLUTION: A system according to an embodiment includes a comment aggregation unit, a reviewer matching unit, and an overall evaluation unit. The comment aggregation unit aggregates comments. The reviewer matching unit matches a reliable reviewer. The comprehensive evaluation unit generates a comprehensive evaluation based on the comment and the information of the reviewer.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, gourmet sites are difficult to use and have low credibility, and there is room for improvement.

[0005] The system according to the embodiment aims to improve the usability and credibility of gourmet sites. [Means for solving the problem]

[0006] The system according to the embodiment includes a comment aggregation unit, a reviewer matching unit, and an overall evaluation unit. The comment aggregation unit aggregates comments. The reviewer matching unit matches reliable reviewers. The overall evaluation unit generates an overall evaluation based on the comments and reviewer information. [Effects of the Invention]

[0007] The system according to the embodiment can improve the usability and credibility of gourmet sites. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The gourmet site system according to the embodiment of the present invention aggregates comments posted by users, matches them with reliable reviewers, and performs comprehensive evaluations using AI. This allows users to obtain reliable information, improving the usability of the gourmet site.

[0029] The gourmet website system according to the embodiment includes a comment aggregation unit, a reviewer matching unit, and an overall evaluation unit. The comment aggregation unit aggregates comments posted by users. For example, the comment aggregation unit uses a generation AI to extract positive and negative evaluations, each with a score of 5. The comment aggregation unit can also use the generation AI to analyze the content of the comments and classify them based on specific keywords. The comment aggregation unit can also use the generation AI to perform sentiment analysis of the comments and aggregate them while taking into account the balance between positive and negative sentiment. The reviewer matching unit matches reliable reviewers. For example, the reviewer matching unit uses the generation AI to analyze a user's past ratings and comment history to identify reviewers with similar tastes and evaluation criteria. The reviewer matching unit can also use the generation AI to evaluate the reliability of reviewers' past comments and prioritize matching reliable reviewers. The reviewer matching unit can also analyze the reviewer's expertise and experience to match a user with a reviewer who is knowledgeable in a specific field. The overall evaluation unit generates an overall evaluation based on the comments and reviewer information. For example, the overall evaluation unit uses a generation AI to analyze the content of the comments and the credibility of the reviewer to generate an overall evaluation. The overall evaluation unit can also use a generation AI to analyze the emotions of the comments and the reviewer to generate an overall evaluation that is likely to resonate with the reader emotionally. The overall evaluation unit can also use a generation AI to analyze the content of the comments and the credibility of the reviewer to generate an overall evaluation that emphasizes specific evaluation criteria. This allows the gourmet site system according to the embodiment to provide users with reliable information and improve the usability of the gourmet site. For example, when choosing a restaurant, users can refer to comments from reliable reviewers to make a more satisfying choice. Furthermore, aggregating comments allows users to understand a large number of comments at a glance, saving time. Furthermore, the overall evaluation by AI allows users to obtain a more detailed evaluation without relying on star ratings.

[0030] The comment aggregating unit can analyze the content of comments, classify them based on specific keywords, and prioritize displaying information that interests the user. The comment aggregating unit, for example, analyzes the content of comments and extracts specific keywords. For example, it classifies comments based on keywords such as "sushi" and "customer service." The comment aggregating unit also classifies comments based on keywords and prioritizes displaying information that interests the user. For example, it prioritizes displaying comments related to "quality of food." The comment aggregating unit also analyzes the content of comments and builds a system that automatically extracts keywords that interest the user. For example, it identifies keywords of interest based on the user's past search history and browsing history. This allows the user to obtain information that interests them preferentially.

[0031] The comment aggregating unit can provide the aggregated results of comments to the user in audio or video format, allowing the user to obtain information visually or aurally. For example, the comment aggregating unit can provide the aggregated results of comments in audio format, allowing the user to obtain information aurally. For example, the comments can be read aloud using voice synthesis technology. The comment aggregating unit can also provide the aggregated results of comments in video format, allowing the user to obtain information visually and aurally. For example, a video can be generated that displays comments in text and audio. The comment aggregating unit can also build a comment aggregating system that provides the results in audio or video format, allowing the user to obtain information visually or aurally. For example, a combination of voice synthesis technology and video generation technology can be provided. This allows the user to obtain information visually and aurally.

[0032] The comment aggregator can automatically translate comments posted in different languages, making it possible to accommodate international users. The comment aggregator, for example, builds a system that automatically translates comments posted in different languages, making it possible to accommodate international users. For example, it translates into multiple languages, such as English, French, and Chinese. The comment aggregator also aggregates comments based on the automatically translated comments so that they are easy for international users to understand. For example, technical terms and slang are taken into consideration to improve translation accuracy. The comment aggregator also automatically translates comments posted in different languages ​​in real time, making it possible to accommodate international users. For example, it uses a translation engine to instantly translate comments. This makes it possible to accommodate international users.

[0033] The reviewer matching unit can use generation AI to evaluate the reliability of reviewers' past comments and prioritize matching of highly reliable reviewers. The reviewer matching unit, for example, uses generation AI to build a system that evaluates the reliability of reviewers' past comments. For example, it analyzes the content of comments and rating history and calculates a reliability score. The reviewer matching unit also adjusts the matching algorithm based on the reviewer's reliability score in order to prioritize matching of highly reliable reviewers. For example, it preferentially displays reviewers with high reliability scores. The reviewer matching unit also evaluates the reliability of reviewers' past comments and develops a system to identify highly reliable reviewers. For example, it evaluates the accuracy and consistency of past comments. This allows users to obtain highly reliable information by preferentially matching highly reliable reviewers.

[0034] The reviewer matching unit can analyze the reviewer's expertise and experience and match a reviewer who is knowledgeable in a specific field to a user. The reviewer matching unit, for example, analyzes the reviewer's expertise and experience and builds a system that matches a reviewer who is knowledgeable in a specific field to a user. For example, the reviewer is identified based on the type of cuisine or the genre of the restaurant. The reviewer matching unit also matches the reviewer who will be most useful to the user based on the reviewer's expertise and experience. For example, reviewers who are knowledgeable in a specific cuisine or service are preferentially displayed. The reviewer matching unit also analyzes the reviewer's expertise and experience to develop a system that automatically identifies a reviewer who is knowledgeable in a specific field. For example, the reviewer's past comments and rating history are analyzed. This allows the user to obtain more specialized information by matching with a reviewer who is knowledgeable in a specific field.

[0035] The reviewer matching unit can link the reviewer matching results with the user's social network and prioritize displaying ratings from friends or acquaintances. The reviewer matching unit, for example, builds a system that links the reviewer matching results with the user's social network and prioritizes displaying ratings from friends and acquaintances. For example, it displays ratings from friends using SNS data. The reviewer matching unit also analyzes the user's social network and prioritizes displaying ratings from friends and acquaintances. For example, it displays ratings in collaboration with the user's SNS account. The reviewer matching unit also develops a system that links the reviewer matching results with the social network and automatically displays ratings from friends and acquaintances. For example, it acquires and displays SNS data in real time. This allows the user to prioritize ratings from friends and acquaintances.

[0036] The reviewer matching unit can integrate reviewer matching results with different platforms to provide comprehensive ratings. The reviewer matching unit, for example, builds a system that integrates reviewer matching results with different platforms to provide comprehensive ratings. For example, it integrates rating data from travel sites and shopping sites. The reviewer matching unit also analyzes data from different platforms to provide comprehensive ratings of reviewers. For example, it evaluates the reliability of reviewers based on ratings from multiple platforms. The reviewer matching unit also develops a system that links reviewer matching results with different platforms to automatically provide comprehensive ratings. For example, it integrates data using an API. This allows users to obtain comprehensive ratings by integrating ratings from different platforms.

[0037] The overall evaluation unit can use the generation AI to analyze the content of the comments and the credibility of the reviewer, and emphasize specific evaluation criteria when generating an overall rating. For example, the overall evaluation unit uses the generation AI to analyze the content of the comments and the credibility of the reviewer, and generates an overall rating with emphasis on specific evaluation criteria (e.g., quality of food, quality of service). For example, it may prioritize analysis of comments related to food quality. The overall evaluation unit also builds a system that generates an overall rating with emphasis on specific evaluation criteria based on the content of the comments and the credibility of the reviewer. For example, it may prioritize comments related to service quality. The overall evaluation unit also uses the generation AI to develop an algorithm that generates an overall rating with emphasis on specific evaluation criteria. For example, it may prioritize analysis of comments related to food quality and service quality. In this way, by emphasizing specific evaluation criteria, an overall rating based on evaluation criteria that the user is interested in can be obtained.

[0038] When generating an overall rating, the overall rating unit can refer to past rating history and trend information and take long-term rating into consideration. The overall rating unit, for example, uses a generation AI to build a system that references past rating history and trend information and generates an overall rating taking long-term rating into consideration. For example, it analyzes trends based on past rating data. The overall rating unit also generates an overall rating taking long-term rating into consideration based on past rating history and trend information. For example, it analyzes rating data over a long period of time and reflects it in the overall rating. The overall rating unit also uses a generation AI to develop an algorithm that references past rating history and trend information and generates an overall rating taking long-term rating into consideration. For example, it analyzes rating fluctuations and reflects them in the overall rating. In this way, by taking long-term rating into consideration, users can obtain a more reliable overall rating.

[0039] The overall evaluation department can convert the overall evaluation into a visual note or mind map to make it easier to understand visually. For example, the overall evaluation department uses generative AI to convert the overall evaluation into a visual note and build a system that makes it easier to understand visually. For example, it could show the key points of the evaluation using diagrams or icons. The overall evaluation department could also convert the overall evaluation into a mind map format to visually organize related keywords and concepts. This allows the overall picture of the evaluation to be understood at a glance. The overall evaluation department could also develop tools that automatically generate visual notes and mind maps, allowing users to easily visually display the overall evaluation. For example, it could provide a function to visualize the evaluation using drag and drop. This would provide an overall evaluation that is easy to understand visually, allowing users to intuitively understand the evaluation.

[0040] The overall evaluation unit can automatically translate the overall evaluation into different languages ​​to provide an evaluation from an international perspective. For example, the overall evaluation unit uses generative AI to automatically translate the overall evaluation into different languages ​​and build a system to provide an evaluation from an international perspective. For example, it translates into multiple languages ​​such as English, French, and Chinese. The overall evaluation unit also provides an evaluation based on the automatically translated overall evaluation in a way that is easy for international users to understand. For example, it takes into account technical terms and slang to improve translation accuracy. The overall evaluation unit also automatically translates the overall evaluation translated into different languages ​​in real time to accommodate international users. For example, it uses a translation engine to instantly translate the evaluation. This allows for the provision of an evaluation from an international perspective, making it possible to accommodate users who speak different languages.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The comment aggregator can analyze a user's past browsing history and search history and prioritize the display of comments based on the user's interests and concerns. For example, if a user has previously searched for keywords such as "sushi" or "Italian," comments related to these keywords will be prioritized. The comment aggregator can also prioritize the display of comments about restaurants that the user has given high ratings to, based on the user's past rating history. Furthermore, the comment aggregator can analyze the user's geographic location information and prioritize the display of comments about nearby restaurants. This allows users to efficiently obtain information based on their own interests and concerns.

[0043] The reviewer matching unit can analyze the user's social network and prioritize displaying ratings from friends and acquaintances. For example, by linking with the user's social media account, comments and ratings posted by friends can be prioritized. The reviewer matching unit can also prioritize matching reviewers with many mutual friends based on the user's social network. Furthermore, the reviewer matching unit can also build a system that analyzes the user's social network and displays ratings from friends and acquaintances in real time. This allows the user to refer to ratings from trusted friends and acquaintances.

[0044] The overall rating unit can generate an overall rating by taking into account long-term ratings, referencing the user's past rating history and trend information. For example, it can analyze trends based on past rating data and reflect long-term rating data in the overall rating. The overall rating unit can also emphasize ratings of restaurants that the user has given high ratings to in the past, based on the user's rating history. Furthermore, the overall rating unit can generate an overall rating by taking into account current popularity and rating fluctuations, based on trend information. This allows the user to obtain a reliable overall rating from a long-term perspective.

[0045] The comment aggregator can automatically translate comments posted in different languages ​​to accommodate international users. For example, the comment aggregator can translate into multiple languages, such as English, French, and Chinese, and aggregate the comments so that they are easy for international users to understand. The comment aggregator can also take technical terms and slang into account to improve translation accuracy. Furthermore, the comment aggregator can automatically translate comments posted in different languages ​​in real time, building a system that can accommodate international users. This allows international users to obtain information across language barriers.

[0046] The overall evaluation department can convert the overall evaluation into a visual note or mind map to make it easier to understand visually. For example, it can use generative AI to convert the overall evaluation into a visual note, showing the key points of the evaluation with diagrams and icons. The overall evaluation department can also convert the overall evaluation into a mind map format to visually organize related keywords and concepts. Furthermore, the overall evaluation department can develop tools that automatically generate visual notes and mind maps, allowing users to easily visually display the overall evaluation. This makes it easier for users to intuitively understand the evaluation.

[0047] The comment aggregating unit may provide the aggregated results of comments to the user in audio or video format, allowing the user to obtain the information visually or audibly. For example, the aggregated results of comments may be provided in audio format, allowing the user to obtain the information audibly. The comment aggregating unit may also provide the aggregated results of comments in video format, allowing the user to obtain the information visually and audibly. Furthermore, the comment aggregating unit may build a comment aggregating system that provides the results in audio or video format, allowing the user to obtain the information visually and audibly. This allows the user to obtain the information visually and audibly.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The comment aggregator aggregates comments posted by users. For example, the comment aggregator uses a generation AI to extract five positive and five negative ratings. The comment aggregator can also use the generation AI to analyze the content of comments and classify them based on specific keywords. Furthermore, the comment aggregator can use the generation AI to perform sentiment analysis of comments and aggregate them taking into account the balance between positive and negative sentiment. Step 2: The reviewer matching unit matches reliable reviewers. For example, the reviewer matching unit uses generation AI to analyze a user's past ratings and comment history to identify reviewers with similar tastes and evaluation criteria. The reviewer matching unit can also use generation AI to evaluate the reliability of reviewers' past comments and prioritize matching reliable reviewers. Furthermore, the reviewer matching unit can analyze reviewers' expertise and experience to match users with reviewers who are knowledgeable in specific fields. Step 3: The overall evaluation unit generates an overall rating based on the comment and reviewer information. For example, the overall evaluation unit uses a generation AI to analyze the content of the comment and the credibility of the reviewer to generate an overall rating. The overall evaluation unit can also use a generation AI to analyze the emotions of the comment and the reviewer to generate an overall rating that is likely to resonate emotionally. Furthermore, the overall evaluation unit can use a generation AI to analyze the content of the comment and the credibility of the reviewer to generate an overall rating that emphasizes specific evaluation criteria.

[0050] (Example 2) The gourmet site system according to the embodiment of the present invention aggregates comments posted by users, matches them with reliable reviewers, and performs comprehensive evaluations using AI. This allows users to obtain reliable information, improving the usability of the gourmet site.

[0051] The gourmet website system according to the embodiment includes a comment aggregation unit, a reviewer matching unit, and an overall evaluation unit. The comment aggregation unit aggregates comments posted by users. For example, the comment aggregation unit uses a generation AI to extract positive and negative evaluations, each with a score of 5. The comment aggregation unit can also use the generation AI to analyze the content of the comments and classify them based on specific keywords. The comment aggregation unit can also use the generation AI to perform sentiment analysis of the comments and aggregate them while taking into account the balance between positive and negative sentiment. The reviewer matching unit matches reliable reviewers. For example, the reviewer matching unit uses the generation AI to analyze a user's past ratings and comment history to identify reviewers with similar tastes and evaluation criteria. The reviewer matching unit can also use the generation AI to evaluate the reliability of reviewers' past comments and prioritize matching reliable reviewers. The reviewer matching unit can also analyze the reviewer's expertise and experience to match a user with a reviewer who is knowledgeable in a specific field. The overall evaluation unit generates an overall evaluation based on the comments and reviewer information. For example, the overall evaluation unit uses a generation AI to analyze the content of the comments and the credibility of the reviewer to generate an overall evaluation. The overall evaluation unit can also use a generation AI to analyze the emotions of the comments and the reviewer to generate an overall evaluation that is likely to resonate with the reader emotionally. The overall evaluation unit can also use a generation AI to analyze the content of the comments and the credibility of the reviewer to generate an overall evaluation that emphasizes specific evaluation criteria. This allows the gourmet site system according to the embodiment to provide users with reliable information and improve the usability of the gourmet site. For example, when choosing a restaurant, users can refer to comments from reliable reviewers to make a more satisfying choice. Furthermore, aggregating comments allows users to understand a large number of comments at a glance, saving time. Furthermore, the overall evaluation by AI allows users to obtain a more detailed evaluation without relying on star ratings.

[0052] The comment aggregation unit uses generative AI to perform sentiment analysis of comments and aggregate them while taking into account the balance between positive and negative emotions. For example, the comment aggregation unit performs sentiment analysis on each comment and classifies them into positive and negative comments based on the sentiment score. For example, it aggregates comments that express joy or satisfaction separately from comments that express dissatisfaction or anger. The comment aggregation unit also selects the comments that are most useful to users based on the results of the sentiment analysis, taking into account the balance between positive and negative emotions. For example, it extracts positive comments and negative comments each with a score of 5. The comment aggregation unit also uses the sentiment score to evaluate the emotional intensity of comments and prioritize aggregation of emotionally strong comments. For example, it selects very positive comments and very negative comments. This allows users to obtain emotionally balanced comments.

[0053] The comment aggregating unit can analyze the content of comments, classify them based on specific keywords, and prioritize displaying information that interests the user. The comment aggregating unit, for example, analyzes the content of comments and extracts specific keywords. For example, it classifies comments based on keywords such as "sushi" and "customer service." The comment aggregating unit also classifies comments based on keywords and prioritizes displaying information that interests the user. For example, it prioritizes displaying comments related to "quality of food." The comment aggregating unit also analyzes the content of comments and builds a system that automatically extracts keywords that interest the user. For example, it identifies keywords of interest based on the user's past search history and browsing history. This allows the user to obtain information that interests them preferentially.

[0054] The comment aggregating unit can use the emotion estimation function to analyze the emotions of the comment poster and prioritize aggregating comments that are likely to be emotionally relatable. The comment aggregating unit, for example, uses the emotion estimation function to analyze the emotions of the comment poster and identify comments that are likely to be emotionally relatable. For example, it prioritizes aggregating comments that have a high degree of relatability. The comment aggregating unit also analyzes the emotions of the comment poster and builds a system that prioritizes displaying emotionally strong comments. For example, it prioritizes displaying comments with a high emotion score. The comment aggregating unit also uses the emotion estimation function to analyze the emotions of the comment poster in real time and automatically select comments that are likely to be emotionally relatable. For example, it prioritizes displaying comments with a strong positive emotion. This allows users to preferentially obtain comments that are likely to be relatable.

[0055] The comment aggregating unit can provide the aggregated results of comments to the user in audio or video format, allowing the user to obtain information visually or aurally. For example, the comment aggregating unit can provide the aggregated results of comments in audio format, allowing the user to obtain information aurally. For example, the comments can be read aloud using voice synthesis technology. The comment aggregating unit can also provide the aggregated results of comments in video format, allowing the user to obtain information visually and aurally. For example, a video can be generated that displays comments in text and audio. The comment aggregating unit can also build a comment aggregating system that provides the results in audio or video format, allowing the user to obtain information visually or aurally. For example, a combination of voice synthesis technology and video generation technology can be provided. This allows the user to obtain information visually and aurally.

[0056] The comment aggregator can automatically translate comments posted in different languages, making it possible to accommodate international users. The comment aggregator, for example, builds a system that automatically translates comments posted in different languages, making it possible to accommodate international users. For example, it translates into multiple languages, such as English, French, and Chinese. The comment aggregator also aggregates comments based on the automatically translated comments so that they are easy for international users to understand. For example, technical terms and slang are taken into consideration to improve translation accuracy. The comment aggregator also automatically translates comments posted in different languages ​​in real time, making it possible to accommodate international users. For example, it uses a translation engine to instantly translate comments. This makes it possible to accommodate international users.

[0057] The comment aggregating unit can use the emotion estimation function to analyze the emotion of a user when viewing comments in real time, and preferentially display comments that elicit positive emotions. The comment aggregating unit, for example, uses the emotion estimation function to analyze the emotion of a user when viewing comments in real time, and build a system that preferentially displays comments that elicit positive emotions. For example, the comment aggregating unit analyzes the user's facial expressions and voice. The comment aggregating unit also preferentially displays comments that elicit positive emotions based on the user's emotional response. For example, comments with high emotion scores are preferentially displayed. The comment aggregating unit also uses the emotion estimation function to analyze the emotion of a user when viewing comments in real time, and provides feedback to elicit positive emotions. For example, positive comments are highlighted. This allows the user to preferentially obtain comments that elicit positive emotions.

[0058] The reviewer matching unit can use generation AI to evaluate the reliability of reviewers' past comments and prioritize matching of highly reliable reviewers. The reviewer matching unit, for example, uses generation AI to build a system that evaluates the reliability of reviewers' past comments. For example, it analyzes the content of comments and rating history and calculates a reliability score. The reviewer matching unit also adjusts the matching algorithm based on the reviewer's reliability score in order to prioritize matching of highly reliable reviewers. For example, it preferentially displays reviewers with high reliability scores. The reviewer matching unit also evaluates the reliability of reviewers' past comments and develops a system to identify highly reliable reviewers. For example, it evaluates the accuracy and consistency of past comments. This allows users to obtain highly reliable information by preferentially matching highly reliable reviewers.

[0059] The reviewer matching unit can analyze the reviewer's expertise and experience and match a reviewer who is knowledgeable in a specific field to a user. The reviewer matching unit, for example, analyzes the reviewer's expertise and experience and builds a system that matches a reviewer who is knowledgeable in a specific field to a user. For example, the reviewer is identified based on the type of cuisine or the genre of the restaurant. The reviewer matching unit also matches the reviewer who will be most useful to the user based on the reviewer's expertise and experience. For example, reviewers who are knowledgeable in a specific cuisine or service are preferentially displayed. The reviewer matching unit also analyzes the reviewer's expertise and experience to develop a system that automatically identifies a reviewer who is knowledgeable in a specific field. For example, the reviewer's past comments and rating history are analyzed. This allows the user to obtain more specialized information by matching with a reviewer who is knowledgeable in a specific field.

[0060] The reviewer matching unit can use the emotion estimation function to analyze the emotions of reviewers and prioritize matching reviewers who are likely to be emotionally empathetic. The reviewer matching unit, for example, uses the emotion estimation function to analyze the emotions of reviewers and build a system to identify reviewers who are likely to be emotionally empathetic. For example, it analyzes the reviewer's facial expressions and voice. The reviewer matching unit also prioritizes matching reviewers who are likely to be emotionally empathetic based on the reviewer's emotions. For example, it prioritizes displaying reviewers with strong positive emotions. The reviewer matching unit also uses the emotion estimation function to analyze the reviewer's emotions in real time and automatically identify reviewers who are likely to be emotionally empathetic. For example, it prioritizes displaying reviewers with high emotion scores. In this way, by preferentially matching reviewers who are likely to be emotionally empathetic, users can obtain information that they can easily empathize with.

[0061] The reviewer matching unit can link the reviewer matching results with the user's social network and prioritize displaying ratings from friends or acquaintances. The reviewer matching unit, for example, builds a system that links the reviewer matching results with the user's social network and prioritizes displaying ratings from friends and acquaintances. For example, it displays ratings from friends using SNS data. The reviewer matching unit also analyzes the user's social network and prioritizes displaying ratings from friends and acquaintances. For example, it displays ratings in collaboration with the user's SNS account. The reviewer matching unit also develops a system that links the reviewer matching results with the social network and automatically displays ratings from friends and acquaintances. For example, it acquires and displays SNS data in real time. This allows the user to prioritize ratings from friends and acquaintances.

[0062] The reviewer matching unit can integrate reviewer matching results with different platforms to provide comprehensive ratings. The reviewer matching unit, for example, builds a system that integrates reviewer matching results with different platforms to provide comprehensive ratings. For example, it integrates rating data from travel sites and shopping sites. The reviewer matching unit also analyzes data from different platforms to provide comprehensive ratings of reviewers. For example, it evaluates the reliability of reviewers based on ratings from multiple platforms. The reviewer matching unit also develops a system that links reviewer matching results with different platforms to automatically provide comprehensive ratings. For example, it integrates data using an API. This allows users to obtain comprehensive ratings by integrating ratings from different platforms.

[0063] The reviewer matching unit can use the emotion estimation function to analyze the emotions of users when viewing reviewer comments in real time, and preferentially display reviewers who elicit positive emotions. The reviewer matching unit, for example, uses the emotion estimation function to build a system that analyzes the emotions of users when viewing reviewer comments in real time, and preferentially displays reviewers who elicit positive emotions. For example, the reviewer matching unit analyzes the user's facial expressions and voice. The reviewer matching unit also preferentially displays reviewers who elicit positive emotions based on the user's emotional response. For example, reviewers with high emotion scores are preferentially displayed. The reviewer matching unit also uses the emotion estimation function to analyze the emotions of users when viewing reviewer comments in real time, and provides feedback to elicit positive emotions. For example, positive comments are highlighted. This allows the user to preferentially obtain reviewers who elicit positive emotions.

[0064] The overall evaluation unit can use the generation AI to analyze the content of the comments and the credibility of the reviewer, and emphasize specific evaluation criteria when generating an overall rating. For example, the overall evaluation unit uses the generation AI to analyze the content of the comments and the credibility of the reviewer, and generates an overall rating with emphasis on specific evaluation criteria (e.g., quality of food, quality of service). For example, it may prioritize analysis of comments related to food quality. The overall evaluation unit also builds a system that generates an overall rating with emphasis on specific evaluation criteria based on the content of the comments and the credibility of the reviewer. For example, it may prioritize comments related to service quality. The overall evaluation unit also uses the generation AI to develop an algorithm that generates an overall rating with emphasis on specific evaluation criteria. For example, it may prioritize analysis of comments related to food quality and service quality. In this way, by emphasizing specific evaluation criteria, an overall rating based on evaluation criteria that the user is interested in can be obtained.

[0065] When generating an overall rating, the overall rating unit can refer to past rating history and trend information and take long-term rating into consideration. The overall rating unit, for example, uses a generation AI to build a system that references past rating history and trend information and generates an overall rating taking long-term rating into consideration. For example, it analyzes trends based on past rating data. The overall rating unit also generates an overall rating taking long-term rating into consideration based on past rating history and trend information. For example, it analyzes rating data over a long period of time and reflects it in the overall rating. The overall rating unit also uses a generation AI to develop an algorithm that references past rating history and trend information and generates an overall rating taking long-term rating into consideration. For example, it analyzes rating fluctuations and reflects them in the overall rating. In this way, by taking long-term rating into consideration, users can obtain a more reliable overall rating.

[0066] The overall evaluation unit can use the emotion estimation function to analyze the emotions of comments and reviewers and generate an overall rating that is easy to empathize with emotionally. The overall evaluation unit, for example, uses the emotion estimation function to analyze the emotions of comments and reviewers and build a system that generates an overall rating that is easy to empathize with emotionally. For example, it places emphasis on comments with strong positive emotions. The overall evaluation unit also generates an overall rating that is easy to empathize with emotionally based on the emotions of comments and reviewers. For example, it prioritizes analysis of comments with high emotion scores. The overall evaluation unit also uses the emotion estimation function to analyze the emotions of comments and reviewers in real time and develops an algorithm that generates an overall rating that is easy to empathize with emotionally. For example, it places emphasis on comments with strong positive emotions. In this way, an overall rating that is easy to empathize with emotionally can be generated, allowing users to obtain a rating that is easy to empathize with.

[0067] The overall evaluation department can convert the overall evaluation into a visual note or mind map to make it easier to understand visually. For example, the overall evaluation department uses generative AI to convert the overall evaluation into a visual note and build a system that makes it easier to understand visually. For example, it could show the key points of the evaluation using diagrams or icons. The overall evaluation department could also convert the overall evaluation into a mind map format to visually organize related keywords and concepts. This allows the overall picture of the evaluation to be understood at a glance. The overall evaluation department could also develop tools that automatically generate visual notes and mind maps, allowing users to easily visually display the overall evaluation. For example, it could provide a function to visualize the evaluation using drag and drop. This would provide an overall evaluation that is easy to understand visually, allowing users to intuitively understand the evaluation.

[0068] The overall evaluation unit can automatically translate the overall evaluation into different languages ​​to provide an evaluation from an international perspective. For example, the overall evaluation unit uses generative AI to automatically translate the overall evaluation into different languages ​​and build a system to provide an evaluation from an international perspective. For example, it translates into multiple languages ​​such as English, French, and Chinese. The overall evaluation unit also provides an evaluation based on the automatically translated overall evaluation in a way that is easy for international users to understand. For example, it takes into account technical terms and slang to improve translation accuracy. The overall evaluation unit also automatically translates the overall evaluation translated into different languages ​​in real time to accommodate international users. For example, it uses a translation engine to instantly translate the evaluation. This allows for the provision of an evaluation from an international perspective, making it possible to accommodate users who speak different languages.

[0069] The overall evaluation unit uses the emotion estimation function to analyze the emotion of the user when viewing the overall evaluation in real time, and can prioritize displaying evaluations that elicit positive emotions. The overall evaluation unit, for example, uses the emotion estimation function to analyze the emotion of the user when viewing the overall evaluation in real time, and builds a system that prioritizes displaying evaluations that elicit positive emotions. For example, the overall evaluation unit analyzes the user's facial expressions and voice. The overall evaluation unit also prioritizes displaying evaluations that elicit positive emotions based on the user's emotional response. For example, it prioritizes displaying evaluations with high emotion scores. The overall evaluation unit also uses the emotion estimation function to analyze the emotion of the user when viewing the overall evaluation in real time, and provides feedback to elicit positive emotions. For example, it highlights positive evaluations. This allows the user to preferentially obtain overall evaluations that elicit positive emotions.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The comment aggregator can analyze a user's past browsing history and search history and prioritize the display of comments based on the user's interests and concerns. For example, if a user has previously searched for keywords such as "sushi" or "Italian," comments related to these keywords will be prioritized. The comment aggregator can also prioritize the display of comments about restaurants that the user has given high ratings to, based on the user's past rating history. Furthermore, the comment aggregator can analyze the user's geographic location information and prioritize the display of comments about nearby restaurants. This allows users to efficiently obtain information based on their own interests and concerns.

[0072] The reviewer matching unit can analyze the user's social network and prioritize displaying ratings from friends and acquaintances. For example, by linking with the user's social media account, comments and ratings posted by friends can be prioritized. The reviewer matching unit can also prioritize matching reviewers with many mutual friends based on the user's social network. Furthermore, the reviewer matching unit can also build a system that analyzes the user's social network and displays ratings from friends and acquaintances in real time. This allows the user to refer to ratings from trusted friends and acquaintances.

[0073] The overall rating unit can generate an overall rating by taking into account long-term ratings, referencing the user's past rating history and trend information. For example, it can analyze trends based on past rating data and reflect long-term rating data in the overall rating. The overall rating unit can also emphasize ratings of restaurants that the user has given high ratings to in the past, based on the user's rating history. Furthermore, the overall rating unit can generate an overall rating by taking into account current popularity and rating fluctuations, based on trend information. This allows the user to obtain a reliable overall rating from a long-term perspective.

[0074] The comment aggregator can automatically translate comments posted in different languages ​​to accommodate international users. For example, the comment aggregator can translate into multiple languages, such as English, French, and Chinese, and aggregate the comments so that they are easy for international users to understand. The comment aggregator can also take technical terms and slang into account to improve translation accuracy. Furthermore, the comment aggregator can automatically translate comments posted in different languages ​​in real time, building a system that can accommodate international users. This allows international users to obtain information across language barriers.

[0075] The overall evaluation department can convert the overall evaluation into a visual note or mind map to make it easier to understand visually. For example, it can use generative AI to convert the overall evaluation into a visual note, showing the key points of the evaluation with diagrams and icons. The overall evaluation department can also convert the overall evaluation into a mind map format to visually organize related keywords and concepts. Furthermore, the overall evaluation department can develop tools that automatically generate visual notes and mind maps, allowing users to easily visually display the overall evaluation. This makes it easier for users to intuitively understand the evaluation.

[0076] The comment aggregating unit can use the emotion estimation function to analyze the emotion of a user when viewing comments in real time and preferentially display comments that elicit positive emotions. For example, the comment aggregating unit can analyze the user's facial expressions and voice to identify comments that elicit positive emotions. The comment aggregating unit can also preferentially display comments that elicit positive emotions based on the user's emotional response. Furthermore, the comment aggregating unit can also use the emotion estimation function to analyze the emotion of a user when viewing comments in real time and provide feedback to elicit positive emotions. This allows the user to preferentially obtain comments that elicit positive emotions.

[0077] The reviewer matching unit can use the emotion estimation function to analyze the emotions of reviewers and prioritize matching reviewers who are likely to empathize emotionally. For example, it can analyze the reviewer's facial expressions and voice to identify reviewers who are likely to empathize emotionally. The reviewer matching unit can also prioritize matching reviewers who are likely to empathize emotionally based on the reviewer's emotions. Furthermore, the reviewer matching unit can also use the emotion estimation function to analyze the reviewer's emotions in real time and automatically identify reviewers who are likely to empathize emotionally. This allows the user to obtain information about reviewers who are likely to empathize emotionally.

[0078] The overall evaluation unit can use the emotion estimation function to analyze the emotions of comments and reviewers and generate an overall evaluation that is easy to empathize with emotionally. For example, it can emphasize comments with strong positive emotions and generate an overall evaluation that is easy to empathize with emotionally. The overall evaluation unit can also build a system that generates an overall evaluation that is easy to empathize with emotionally based on the emotions of comments and reviewers. Furthermore, the overall evaluation unit can use the emotion estimation function to develop an algorithm that analyzes the emotions of comments and reviewers in real time and generates an overall evaluation that is easy to empathize with emotionally. This allows users to obtain an evaluation that is easy to empathize with.

[0079] The overall evaluation unit can use the emotion estimation function to analyze the user's emotions in real time when viewing the overall evaluation, and prioritize displaying evaluations that evoke positive emotions. For example, the overall evaluation unit can analyze the user's facial expressions and voice to identify evaluations that evoke positive emotions. The overall evaluation unit can also prioritize displaying evaluations that evoke positive emotions based on the user's emotional response. Furthermore, the overall evaluation unit can also use the emotion estimation function to analyze the user's emotions in real time when viewing the overall evaluation, and provide feedback to evoke positive emotions. This allows the user to prioritize overall evaluations that evoke positive emotions.

[0080] The comment aggregating unit may provide the aggregated results of comments to the user in audio or video format, allowing the user to obtain the information visually or audibly. For example, the aggregated results of comments may be provided in audio format, allowing the user to obtain the information audibly. The comment aggregating unit may also provide the aggregated results of comments in video format, allowing the user to obtain the information visually and audibly. Furthermore, the comment aggregating unit may build a comment aggregating system that provides the results in audio or video format, allowing the user to obtain the information visually and audibly. This allows the user to obtain the information visually and audibly.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The comment aggregator aggregates comments posted by users. For example, the comment aggregator uses a generation AI to extract five positive and five negative ratings. The comment aggregator can also use the generation AI to analyze the content of comments and classify them based on specific keywords. Furthermore, the comment aggregator can use the generation AI to perform sentiment analysis of comments and aggregate them taking into account the balance between positive and negative sentiment. Step 2: The reviewer matching unit matches reliable reviewers. For example, the reviewer matching unit uses generation AI to analyze a user's past ratings and comment history to identify reviewers with similar tastes and evaluation criteria. The reviewer matching unit can also use generation AI to evaluate the reliability of reviewers' past comments and prioritize matching reliable reviewers. Furthermore, the reviewer matching unit can analyze reviewers' expertise and experience to match users with reviewers who are knowledgeable in specific fields. Step 3: The overall evaluation unit generates an overall rating based on the comment and reviewer information. For example, the overall evaluation unit uses a generation AI to analyze the content of the comment and the credibility of the reviewer to generate an overall rating. The overall evaluation unit can also use a generation AI to analyze the emotions of the comment and the reviewer to generate an overall rating that is likely to resonate emotionally. Furthermore, the overall evaluation unit can use a generation AI to analyze the content of the comment and the credibility of the reviewer to generate an overall rating that emphasizes specific evaluation criteria.

[0083] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0084] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0085] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0088] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0089] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0090] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0091] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0092] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0093] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0094] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0096] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0097] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0100] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0108] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0111] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 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.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0124] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0133] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0134] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0135] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0136] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0137] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0138] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0139] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0140] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0141] 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.

[0142] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0143] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0144] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0145] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0146] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0147] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0148] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0149] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0150] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a comment aggregation unit that aggregates comments; A reviewer matching department that matches reliable reviewers; and a comprehensive evaluation unit that generates a comprehensive evaluation based on the comments and reviewer information. A system characterized by:

2. The comment aggregating unit The generative AI is used to analyze the sentiment of comments and aggregate them while taking into account the balance of positive and negative sentiment.

2. The system of claim 1.

3. The comment aggregating unit Analyzes the content of comments, categorizes them based on keywords, and prioritizes displaying information that users are interested in.

2. The system of claim 1.

4. The comment aggregating unit Analyze the emotions of commenters and prioritize comments that are likely to resonate with them 2. The system of claim 1.

5. The comment aggregating unit The aggregated results of comments may be provided to users in audio or video format, allowing them to obtain information visually or aurally.

2. The system of claim 1.

6. The comment aggregating unit Automatically translate comments posted in different languages ​​to accommodate international users 2. The system of claim 1.

7. The comment aggregating unit Analyzes emotions in real time as users view comments, and prioritizes comments that evoke positive emotions.

2. The system of claim 1.

8. The reviewer matching unit The generation AI is used to evaluate the reliability of the reviewer's past comments, and the highly reliable reviewers are given priority in matching.

2. The system of claim 1.

Images