System

Abstract

An object of a system according to an embodiment is to enable a user to easily find sake that suits the user's preference.SOLUTION: A system includes a data-making part, a recommendation part, a shared part, a distribution part, an crowdfunding part, and a tasting party information part. A data-making part collects data on Japanese sake brand and taste. The recommendation unit recommends sake that suits the user's preference based on the data collected by the data generation unit. The sharing unit shares the word-of-mouth information on sake recommended by the recommendation unit and the voice of the brewer. A distribution part distributes a brand voting contest once a year through a network LIVE. The crowdfunding Department provides crowdfunding recruitment information for New Shuzo. A test-drinking session information part provides test-drinking session holding information of each place.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, it was difficult to centrally collect and share information on sake brands, flavors, and reviews, making it difficult for users to find sake that suited their tastes.

[0005] The system according to the embodiment aims to enable users to easily find sake that suits their tastes. [Means for solving the problem]

[0006] The system according to the embodiment comprises a data conversion unit, a recommendation unit, a sharing unit, a distribution unit, a crowdfunding unit, and a tasting event information unit. The data conversion unit collects data on sake brands and flavors. The recommendation unit recommends sake that suits the user's preferences based on the data collected by the data conversion unit. The sharing unit shares word-of-mouth reviews and comments from sake brewers about the sake recommended by the recommendation unit. The distribution unit broadcasts an annual brand voting contest live online. The crowdfunding unit provides information on crowdfunding solicitations for new sake breweries. The tasting event information unit provides information on tasting events held in various locations. [Effects of the Invention]

[0007] The system according to the embodiment allows users to easily find sake that suits their tastes. [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 sake recommendation system according to an embodiment of the present invention is a system that digitizes local sake brands, flavors, and reviews from around the country, allowing users to select sake that suits their tastes from the AI ​​data. This allows users to easily find sake that suits their tastes, contributing to the spread and development of sake culture.

[0029] A sake recommendation system according to an embodiment includes a data conversion unit, a recommendation unit, a sharing unit, a distribution unit, a crowdfunding unit, and a tasting event information unit. The data conversion unit collects data on sake brands and flavors. For example, the data conversion unit collects information on sake brands from all over Japan and registers it in a database. The data conversion unit can also analyze the flavor characteristics of each brand and register it in the database. For example, the data conversion unit analyzes taste elements such as sweetness, sourness, and bitterness and registers them in the database. The recommendation unit recommends sake that matches the user's preferences based on the data collected by the data conversion unit. For example, the recommendation unit analyzes preference information entered by the user and recommends corresponding sake. The recommendation unit can also analyze the user's past drinking history and predict future changes in preferences before making recommendations. For example, the recommendation unit collects data on the brands and flavors of sake the user has drunk in the past and analyzes changes in preferences over time. The sharing unit shares word-of-mouth reviews and comments from sake brewers about the sake recommended by the recommendation unit. For example, the sharing section registers users' impressions and reviews of sake they have tried in a database and shares them with other users. The sharing section can also collect the opinions of sake brewers and provide them to users. For example, the sharing section collects interviews and comments from sake brewers and registers them in a database. The distribution section broadcasts an annual brand voting contest live online. For example, the distribution section holds a voting contest for sake brands from all over the country and broadcasts the event live online. The distribution section can also analyze the voting results in real time and display them in ranking form. The crowdfunding section provides information on crowdfunding campaigns for new sake breweries. For example, the crowdfunding section lists crowdfunding campaigns for new sake breweries and provides video presentations for each brewery. The crowdfunding section can also use generative AI to predict the success rate of crowdfunding projects and provide the results to users. The tasting event information section provides information on tasting events held in various locations. For example, the tasting event information section shares a list of information on sake tasting events held across the country. The tasting information department can also use generative AI to analyze past tasting participant data and recommend tasting information based on participants' preferences.As a result, the sake recommendation system according to the embodiment allows users to easily find sake that suits their tastes, thereby contributing to the spread and development of sake culture.

[0030] The recommendation unit analyzes the user's past drinking history and changes in preferences, and can predict and recommend future changes in preferences. For example, using a generation AI, the recommendation unit collects data on the brands and flavors of sake the user has drunk in the past and analyzes changes in preferences. For example, if a user previously preferred fruity sake but has recently started to prefer dry sake, the recommendation unit predicts future preferences based on this change. The recommendation unit also analyzes the user's drinking history and predicts changes in preferences based on seasons and events. For example, if a user tends to prefer refreshing sake in the summer and rich sake in the winter, the recommendation unit can make recommendations for each season based on this information. The recommendation unit also uses a generation AI to compare the user's drinking history with data from other users and predict future changes in preferences. For example, the recommendation unit recommends brands that other users with similar preferences are likely to prefer next. This allows the recommendation unit to predict future changes in the user's preferences and recommend the most suitable sake.

[0031] The data conversion unit collects sake component analysis data, and the generation AI analyzes the correlation between components and taste, enabling scientifically based recommendations. For example, the data conversion unit collects sake component analysis data, and the generation AI analyzes the correlation between components and taste. For example, it can find a correlation, such as sake with a high content of a specific component having a stronger fruity aroma, and make recommendations based on that information. The generation AI also scientifically recommends sake that suits the user's preferences based on the component analysis data. For example, if a user prefers a fruity aroma, it will recommend brands that contain a high content of components that bring out that aroma. The generation AI also uses the component analysis data to provide information that is useful for developing new sake. For example, if sake with a high content of a specific component is highly rated, a new brand can be developed by increasing that component. This makes it possible to recommend sake based on scientific evidence.

[0032] The data generation unit also collects data on alcoholic beverages other than sake, allowing the generation AI to analyze the correlation of preferences between different beverages and make recommendations. The data generation unit, for example, collects data on alcoholic beverages other than sake (wine, beer, etc.), and the generation AI analyzes the correlation of preferences between different beverages. For example, for a user who likes the fruity aroma of wine, it recommends sake with a similar aroma. The generation AI also finds correlations between different beverages based on the user's preferred alcoholic beverage data and makes recommendations. For example, for a user who likes the bitterness of beer, it recommends sake with a similar bitterness. The generation AI also integrates data on different alcoholic beverages and analyzes the user's overall preferences. For example, it understands the user's overall preferences based on data on wine, beer, and sake and recommends the most suitable sake. This allows the correlation of preferences between different alcoholic beverages to be analyzed and the most suitable sake to be recommended.

[0033] The recommendation unit digitizes sake pairing information, allowing the generation AI to recommend the optimal sake based on the user's meal details. The recommendation unit, for example, digitizes sake pairing information, allowing the generation AI to recommend the optimal sake based on the user's meal details. For example, it may recommend a fruity sake for sushi and a dry sake for yakiniku. The generation AI also analyzes the meal details entered by the user and recommends sake that matches it. For example, if the user enters "fish dishes," it will recommend sake that goes well with fish dishes. Furthermore, based on the pairing information, the generation AI suggests new combinations of food and sake. For example, if the user enters "cheese," it will recommend sake that goes well with cheese. This makes it possible to recommend the optimal sake based on the user's meal details.

[0034] The sharing unit can use the generation AI to evaluate the reliability of reviews and prioritize the display of highly reliable reviews. For example, the sharing unit uses the generation AI to analyze the content of the review and information about the poster to evaluate reliability. For example, if the poster has received many high ratings in the past, the review is judged to be highly reliable. In addition, to evaluate the reliability of the review, the generation AI analyzes the poster's past posting history and ratings. For example, reviews from users who have posted highly reliable reviews in the past are displayed preferentially. The generation AI also analyzes the content of the review and extracts highly reliable information. For example, reviews that include specific taste characteristics and detailed impressions are judged to be highly reliable. In this way, highly reliable reviews are displayed preferentially, allowing users to obtain reliable information.

[0035] The sharing section collects the voices of sake brewers not only in text format, but also in audio and video format, and the generation AI can analyze them and provide them to users. For example, the sharing section collects the voices of sake brewers in audio and video format, and the generation AI analyzes them and provides them to users. For example, a video presentation may be presented in which a sake brewer talks about the characteristics and production process of sake. The generation AI may also analyze audio and video data, extract important information, and provide it in text format. For example, a summary of key points from a video interview with a sake brewer may be displayed. The voices of sake brewers may also be collected in various formats, and the generation AI may integrate them and provide them to users. For example, text, audio, and video information may be combined to provide a comprehensive presentation of the voices of sake brewers. This allows the voices of sake brewers to be collected in various formats and provided to users.

[0036] The sharing unit supports multiple languages ​​for review data, and the generation AI can automatically translate and provide reviews in different languages. The sharing unit, for example, uses the generation AI to support multiple languages ​​for review data, and automatically translate and provide reviews in different languages. For example, Japanese reviews are translated into English or Chinese and displayed. A system is also built that collects multilingual review data and uses the generation AI to perform automatic translation. For example, English reviews are translated into Japanese and displayed. The generation AI also translates reviews in different languages ​​in real time and provides them to users. For example, reviews in foreign languages ​​are instantly translated and displayed. This makes it possible to provide multilingual review data.

[0037] The sharing section can provide the voices of sake brewers in an interactive format and add a function that allows users to ask questions directly. For example, the sharing section can provide the voices of sake brewers in an interactive format and add a function that allows users to ask questions directly. For example, questions can be sent to sake brewers in real time and answers can be obtained. The generation AI can also analyze users' questions and automatically generate appropriate questions for sake brewers. For example, if a user asks, "What are the characteristics of this sake?", the generation AI can send that question to the sake brewer. A system can also be built that provides the voices of sake brewers in an interactive format and allows users to interact directly. For example, interacting with sake brewers through live chat or video calls. This can provide an interactive format that allows users to ask sake brewers questions directly.

[0038] The distribution unit can use the generation AI to analyze the voter's past voting history and preferences and predict the voting results. For example, the distribution unit uses the generation AI to analyze the voter's past voting history and preferences and predict the voting results. For example, the distribution unit predicts this year's voting results based on data from users who have voted for a specific brand in the past. The generation AI also analyzes the voter's preferences and predicts the trend in the voting results. For example, if there are many voters who prefer dry sake, the voting results are predicted based on that trend. The generation AI also makes real-time predictions of the voting results based on the voter's past data. For example, as voting progresses, the final results are predicted based on current voting trends. This makes it possible to predict the voting results based on the voter's past voting history and preferences.

[0039] The distribution unit analyzes the results of the voting contest in real time, and the generation AI can visualize voting trends and changes in popularity. The distribution unit, for example, uses the generation AI to analyze the results of the voting contest in real time and visualize voting trends and changes in popularity. For example, it displays the increase or decrease in the number of votes in a graph. It also builds a system that analyzes the voting results in real time and the generation AI visualizes changes in popularity. For example, it shows changes in the number of votes using color or size. The generation AI also analyzes the results of the voting contest in real time and visualizes voting trends. For example, it highlights stocks with a large number of votes. This makes it possible to visualize voting trends and changes in popularity in real time.

[0040] The distribution unit can make the results of the voting contest multilingual, and the generation AI can automatically translate and provide the voting results in different languages. The distribution unit, for example, uses the generation AI to make the results of the voting contest multilingual, and automatically translate and provide the voting results in different languages. For example, Japanese voting results are translated into English or Chinese and displayed. A system is also constructed that collects multilingual voting results and the generation AI performs automatic translation. For example, English voting results are translated into Japanese and displayed. The generation AI also translates voting results in different languages ​​in real time and provides them to users. For example, voting results in a foreign language are instantly translated and displayed. This makes it possible to provide voting results in multiple languages.

[0041] The distribution unit compares the results of the voting contest with past data, and the generation AI can analyze and provide long-term trends. The distribution unit, for example, uses the generation AI to compare the results of the voting contest with past data and analyze long-term trends. For example, it analyzes fluctuations in popularity based on voting results from the past few years. It also builds a system that compares the voting results with past data and the generation AI analyzes long-term trends. For example, it predicts this year's trends based on past voting trends. The generation AI also compares the results of the voting contest with past data and visualizes long-term trends. For example, it displays past voting results in a graph to show the trends. This makes it possible to analyze and provide long-term trends.

[0042] The crowdfunding department can use the generation AI to predict the success probability of a crowdfunding project and provide it to users. For example, the crowdfunding department uses the generation AI to analyze past data on crowdfunding projects and predict the success probability. For example, it calculates the success probability of a current project based on the characteristics of projects that have been successful in the past. In addition, to predict the success probability of a crowdfunding project, the generation AI analyzes the project content and backer data. For example, it predicts the success probability based on the number of backers and the amount of support. In addition, the generation AI predicts the success probability of a crowdfunding project in real time and provides it to users. For example, it updates the success probability based on the progress of the project. In this way, it is possible to predict and provide the success probability of a crowdfunding project.

[0043] The crowdfunding department can analyze the content of a video presentation and provide a summary of the project's appeal using a generation AI. For example, the crowdfunding department can use a generation AI to analyze a crowdfunding project's video presentation and provide a summary of the key points. For example, it can concisely summarize the project's objectives and features. It can also analyze the content of the video presentation and build a system where the generation AI summarizes the project's appeal. For example, it can extract and display the points emphasized in the video. The generation AI can also analyze the content of the video presentation and provide a summary of information important to the user. For example, it can summarize the project's progress and the voices of supporters. This allows it to provide a summary of the project's appeal.

[0044] The crowdfunding department can support crowdfunding projects in multiple languages, and the generation AI can automatically translate and provide project information in different languages. The crowdfunding department, for example, uses the generation AI to support crowdfunding projects in multiple languages, and automatically translates and provides project information in different languages. For example, Japanese project information is translated into English or Chinese and displayed. A system is also built to collect multilingual crowdfunding project information and the generation AI performs automatic translation. For example, English project information is translated into Japanese and displayed. The generation AI also translates crowdfunding project information in different languages ​​in real time and provides it to users. For example, project information in a foreign language is instantly translated and displayed. This makes it possible to provide multilingual crowdfunding project information.

[0045] The crowdfunding department can provide video presentations in an interactive format and add a function that allows users to ask questions directly. For example, the crowdfunding department can provide video presentations in an interactive format and add a function that allows users to ask questions directly. For example, a question button can be placed in the video, allowing users to submit questions in real time. The generation AI can also analyze users' questions and display the questions at the appropriate time in the video presentation. For example, if a user asks, "What are the characteristics of this sake?", the question can be answered in the video. The crowdfunding department can also provide video presentations in an interactive format and build a system that allows users to interact directly. For example, they can interact with project staff through live chat or video calls. This can provide an interactive format that allows users to ask questions directly.

[0046] The tasting event information department can use the generation AI to analyze past tasting event participant data and recommend tasting event information based on the participant's preferences. For example, the tasting event information department can use the generation AI to analyze past tasting event participant data and recommend tasting event information based on the participant's preferences. For example, for a participant who has previously preferred a particular brand, the department can recommend tasting events where that brand is offered. The tasting event participant data can also be analyzed, and a system can be built in which the generation AI provides tasting event information that matches the participant's preferences. For example, for a participant who prefers dry sake, the generation AI can recommend tasting events where many dry brands are offered. The generation AI can also predict the participant's preferences based on past tasting event participant data and recommend optimal tasting event information. For example, for a participant who prefers fruity sake, the generation AI can recommend tasting events where many fruity brands are offered. This makes it possible to recommend tasting event information based on the participant's preferences.

[0047] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0048] The sake recommendation system can further include a region specialization section. The region specialization section aggregates information about sake from a specific region and provides it in combination with information about the region's specialty products and tourist attractions. For example, the region specialization section provides information about Hokkaido sake along with information about Hokkaido's specialty products and tourist spots. The region specialization section can also introduce the characteristics and history of sake from each region, conveying the appeal of the region to the user. For example, it can provide a detailed introduction to the history and characteristics of Kyoto sake, conveying its appeal to the user. The region specialization section can also provide event information for each region, which the user can use as a reference when visiting that region. For example, it can provide information about local sake brewery tours and local festivals. This allows the user to enjoy the sake from a specific region together with the appeal of the region.

[0049] The recommendation unit can further use the health estimation function to recommend sake based on the user's health condition. For example, when a user inputs health checkup data, the recommendation unit can recommend healthy sake based on that data. For example, it can recommend low-alcohol sake or sake with low sugar content. The health estimation function can also monitor the user's health condition in real time and recommend sake that is considered healthy. For example, it can recommend sake that is suitable for the user to drink after exercise. The health estimation function can also recommend sake based on the user's health goals. For example, it can recommend low-calorie sake to a user who is on a diet. This allows the user to enjoy sake while being mindful of their health.

[0050] The data generation unit further collects environmental data, allowing the generation AI to recommend environmentally friendly sake. For example, it may recommend sake from breweries that use environmentally friendly production methods. The generation AI also provides information based on the environmental data to help users make environmentally friendly choices. For example, it may recommend sake with a low carbon footprint. The generation AI can also suggest ways to select environmentally friendly sake to users based on the environmental data. For example, it may recommend sake that uses recyclable packaging. The generation AI can also use the environmental data to introduce users to the environmentally friendly sake production process. For example, it may provide information on sake breweries that use renewable energy. This allows users to select sake while being mindful of the environment.

[0051] The data generation unit also collects data on alcoholic beverages other than sake, allowing the generation AI to analyze the correlation of preferences between different beverages and make recommendations. For example, for a user who likes the fruity aroma of wine, it will recommend sake with a similar aroma. The generation AI also finds correlations between different beverages based on the user's preferred alcoholic beverage data and makes recommendations. For example, for a user who likes the bitterness of beer, it will recommend sake with a similar bitterness. The generation AI also integrates data on different alcoholic beverages and analyzes the user's overall preferences. For example, it understands the user's overall preferences based on data on wine, beer, and sake and recommends the most suitable sake. This allows it to analyze the correlation of preferences between different alcoholic beverages and recommend the most suitable sake.

[0052] The recommendation unit digitizes sake pairing information, allowing the generation AI to recommend the optimal sake based on the user's meal details. For example, it can recommend a fruity sake for sushi and a dry sake for grilled meat. The generation AI also analyzes the meal details entered by the user and recommends sake that matches it. For example, if a user enters "fish dishes," it will recommend sake that goes well with fish dishes. Furthermore, based on the pairing information, the generation AI suggests new combinations of food and sake. For example, if a user enters "cheese," it will recommend sake that goes well with cheese. This allows the system to recommend the optimal sake based on the user's meal details.

[0053] The sharing unit can use the generation AI to evaluate the reliability of reviews and prioritize the display of highly reliable reviews. For example, the sharing unit uses the generation AI to analyze the content of the review and information about the poster to evaluate reliability. For example, if the poster has received many high ratings in the past, the review is judged to be highly reliable. In addition, to evaluate the reliability of the review, the generation AI analyzes the poster's past posting history and ratings. For example, reviews from users who have posted highly reliable reviews in the past are displayed preferentially. The generation AI also analyzes the content of the review and extracts highly reliable information. For example, reviews that include specific taste characteristics and detailed impressions are judged to be highly reliable. In this way, highly reliable reviews are displayed preferentially, allowing users to obtain reliable information.

[0054] The sharing section collects the voices of sake brewers not only in text format, but also in audio and video format, and the generation AI can analyze them and provide them to users. For example, the sharing section collects the voices of sake brewers in audio and video format, and the generation AI analyzes them and provides them to users. For example, a video presentation may be presented in which a sake brewer talks about the characteristics and production process of sake. The generation AI may also analyze audio and video data, extract important information, and provide it in text format. For example, a summary of key points from a video interview with a sake brewer may be displayed. The voices of sake brewers may also be collected in various formats, and the generation AI may integrate them and provide them to users. For example, text, audio, and video information may be combined to provide a comprehensive presentation of the voices of sake brewers. This allows the voices of sake brewers to be collected in various formats and provided to users.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The data collection department collects data on sake brands and flavors. For example, they collect information on sake brands from all over the country and register it in a database. They also analyze the flavor characteristics of each brand and register taste elements such as sweetness, sourness, and bitterness in the database. Step 2: The recommendation unit recommends sake that matches the user's preferences based on the data collected by the data conversion unit. For example, it analyzes the preference information entered by the user and recommends corresponding sake. It can also analyze the user's past drinking history and predict future changes in preferences to recommend sake. Step 3: The sharing unit shares the reviews and opinions of sake brewers about the sake recommended by the recommendation unit. For example, the user's impressions and reviews of sake they have tried are registered in a database and shared with other users. Interviews and comments from sake brewers are also collected and registered in the database. Step 4: The distribution department broadcasts the annual brand voting contest live online. For example, they hold a voting contest for sake brands from all over the country and broadcast the event live online. They can also analyze the voting results in real time and display them in ranking form. Step 5: The crowdfunding department provides crowdfunding information for new sake breweries. For example, they may post a list of crowdfunding applications for new sake breweries and provide video presentations for each brewery. They may also use generative AI to predict the success rate of crowdfunding projects and provide this information to users. Step 6: The tasting information department provides information about tasting events held in various locations. For example, it shares a list of information about sake tasting events held across the country. Generative AI can also be used to analyze past tasting event participant data and recommend tasting event information based on the participant's preferences.

[0057] (Example 2) The sake recommendation system according to an embodiment of the present invention is a system that digitizes local sake brands, flavors, and reviews from around the country, allowing users to select sake that suits their tastes from the AI ​​data. This allows users to easily find sake that suits their tastes, contributing to the spread and development of sake culture.

[0058] A sake recommendation system according to an embodiment includes a data conversion unit, a recommendation unit, a sharing unit, a distribution unit, a crowdfunding unit, and a tasting event information unit. The data conversion unit collects data on sake brands and flavors. For example, the data conversion unit collects information on sake brands from all over Japan and registers it in a database. The data conversion unit can also analyze the flavor characteristics of each brand and register it in the database. For example, the data conversion unit analyzes taste elements such as sweetness, sourness, and bitterness and registers them in the database. The recommendation unit recommends sake that matches the user's preferences based on the data collected by the data conversion unit. For example, the recommendation unit analyzes preference information entered by the user and recommends corresponding sake. The recommendation unit can also analyze the user's past drinking history and predict future changes in preferences before making recommendations. For example, the recommendation unit collects data on the brands and flavors of sake the user has drunk in the past and analyzes changes in preferences over time. The sharing unit shares word-of-mouth reviews and comments from sake brewers about the sake recommended by the recommendation unit. For example, the sharing section registers users' impressions and reviews of sake they have tried in a database and shares them with other users. The sharing section can also collect the opinions of sake brewers and provide them to users. For example, the sharing section collects interviews and comments from sake brewers and registers them in a database. The distribution section broadcasts an annual brand voting contest live online. For example, the distribution section holds a voting contest for sake brands from all over the country and broadcasts the event live online. The distribution section can also analyze the voting results in real time and display them in ranking form. The crowdfunding section provides information on crowdfunding campaigns for new sake breweries. For example, the crowdfunding section lists crowdfunding campaigns for new sake breweries and provides video presentations for each brewery. The crowdfunding section can also use generative AI to predict the success rate of crowdfunding projects and provide the results to users. The tasting event information section provides information on tasting events held in various locations. For example, the tasting event information section shares a list of information on sake tasting events held across the country. The tasting information department can also use generative AI to analyze past tasting participant data and recommend tasting information based on participants' preferences.As a result, the sake recommendation system according to the embodiment allows users to easily find sake that suits their tastes, thereby contributing to the spread and development of sake culture.

[0059] The recommendation unit analyzes the user's past drinking history and changes in preferences, and can predict and recommend future changes in preferences. For example, using a generation AI, the recommendation unit collects data on the brands and flavors of sake the user has drunk in the past and analyzes changes in preferences. For example, if a user previously preferred fruity sake but has recently started to prefer dry sake, the recommendation unit predicts future preferences based on this change. The recommendation unit also analyzes the user's drinking history and predicts changes in preferences based on seasons and events. For example, if a user tends to prefer refreshing sake in the summer and rich sake in the winter, the recommendation unit can make recommendations for each season based on this information. The recommendation unit also uses a generation AI to compare the user's drinking history with data from other users and predict future changes in preferences. For example, the recommendation unit recommends brands that other users with similar preferences are likely to prefer next. This allows the recommendation unit to predict future changes in the user's preferences and recommend the most suitable sake.

[0060] The data conversion unit collects sake component analysis data, and the generation AI analyzes the correlation between components and taste, enabling scientifically based recommendations. For example, the data conversion unit collects sake component analysis data, and the generation AI analyzes the correlation between components and taste. For example, it can find a correlation, such as sake with a high content of a specific component having a stronger fruity aroma, and make recommendations based on that information. The generation AI also scientifically recommends sake that suits the user's preferences based on the component analysis data. For example, if a user prefers a fruity aroma, it will recommend brands that contain a high content of components that bring out that aroma. The generation AI also uses the component analysis data to provide information that is useful for developing new sake. For example, if sake with a high content of a specific component is highly rated, a new brand can be developed by increasing that component. This makes it possible to recommend sake based on scientific evidence.

[0061] The recommendation unit uses the emotion estimation function to analyze the emotions felt by the user when drinking sake and can recommend brands based on those emotions. For example, the recommendation unit uses the emotion estimation function to analyze the emotions felt by the user when drinking sake in real time. For example, it analyzes the user's facial expressions and voice while drinking sake and calculates an emotion score. The generation AI also recommends brands based on the user's emotion data. For example, when the user wants to relax, it recommends brands that are known to have a high relaxing effect. It also uses the emotion estimation data to suggest sake pairings based on the user's emotions. For example, when the user is in a good mood, it recommends sake that is suitable for a party. This makes it possible to recommend the optimal sake based on the user's emotions.

[0062] The data generation unit also collects data on alcoholic beverages other than sake, allowing the generation AI to analyze the correlation of preferences between different beverages and make recommendations. The data generation unit, for example, collects data on alcoholic beverages other than sake (wine, beer, etc.), and the generation AI analyzes the correlation of preferences between different beverages. For example, for a user who likes the fruity aroma of wine, it recommends sake with a similar aroma. The generation AI also finds correlations between different beverages based on the user's preferred alcoholic beverage data and makes recommendations. For example, for a user who likes the bitterness of beer, it recommends sake with a similar bitterness. The generation AI also integrates data on different alcoholic beverages and analyzes the user's overall preferences. For example, it understands the user's overall preferences based on data on wine, beer, and sake and recommends the most suitable sake. This allows the correlation of preferences between different alcoholic beverages to be analyzed and the most suitable sake to be recommended.

[0063] The recommendation unit digitizes sake pairing information, allowing the generation AI to recommend the optimal sake based on the user's meal details. The recommendation unit, for example, digitizes sake pairing information, allowing the generation AI to recommend the optimal sake based on the user's meal details. For example, it may recommend a fruity sake for sushi and a dry sake for yakiniku. The generation AI also analyzes the meal details entered by the user and recommends sake that matches it. For example, if the user enters "fish dishes," it will recommend sake that goes well with fish dishes. Furthermore, based on the pairing information, the generation AI suggests new combinations of food and sake. For example, if the user enters "cheese," it will recommend sake that goes well with cheese. This makes it possible to recommend the optimal sake based on the user's meal details.

[0064] The recommendation unit can use the emotion estimation function to recommend sake that the user would like to drink for a specific event or situation. For example, the recommendation unit uses the emotion estimation function to recommend sake that the user would like to drink for a specific event or situation. For example, if the user inputs "party," the recommendation unit will recommend sake that is suitable for a party. The generation AI also recommends sake that suits a specific situation based on the user's emotion data. For example, if the user inputs "I want to relax," the recommendation unit will recommend sake that has a high relaxing effect. The emotion estimation data is also used to suggest sake that is best suited to the event or situation based on the user's emotion. For example, if the user inputs "date," the recommendation unit will recommend sake that is suitable for a date. This makes it possible to recommend sake that is best suited to a specific event or situation.

[0065] The sharing unit can use the generation AI to evaluate the reliability of reviews and prioritize the display of highly reliable reviews. For example, the sharing unit uses the generation AI to analyze the content of the review and information about the poster to evaluate reliability. For example, if the poster has received many high ratings in the past, the review is judged to be highly reliable. In addition, to evaluate the reliability of the review, the generation AI analyzes the poster's past posting history and ratings. For example, reviews from users who have posted highly reliable reviews in the past are displayed preferentially. The generation AI also analyzes the content of the review and extracts highly reliable information. For example, reviews that include specific taste characteristics and detailed impressions are judged to be highly reliable. In this way, highly reliable reviews are displayed preferentially, allowing users to obtain reliable information.

[0066] The sharing section collects the voices of sake brewers not only in text format, but also in audio and video format, and the generation AI can analyze them and provide them to users. For example, the sharing section collects the voices of sake brewers in audio and video format, and the generation AI analyzes them and provides them to users. For example, a video presentation may be presented in which a sake brewer talks about the characteristics and production process of sake. The generation AI may also analyze audio and video data, extract important information, and provide it in text format. For example, a summary of key points from a video interview with a sake brewer may be displayed. The voices of sake brewers may also be collected in various formats, and the generation AI may integrate them and provide them to users. For example, text, audio, and video information may be combined to provide a comprehensive presentation of the voices of sake brewers. This allows the voices of sake brewers to be collected in various formats and provided to users.

[0067] The sharing unit can use the emotion estimation function to analyze the emotions of the reviewer and filter reviews based on the emotions. For example, the sharing unit can use the emotion estimation function to analyze the emotions of the reviewer and prioritize displaying reviews with positive emotions. For example, reviews with a strong sense of joy or satisfaction can be prioritized. The generation AI also performs emotion-based filtering based on the reviewer's emotion data. For example, it can exclude reviews with negative emotions. The emotion estimation data can also be used to calculate an emotion score for the review and perform emotion-based filtering. For example, it can prioritize displaying reviews with a high emotion score. This makes it possible to filter reviews based on emotions.

[0068] The sharing unit supports multiple languages ​​for review data, and the generation AI can automatically translate and provide reviews in different languages. The sharing unit, for example, uses the generation AI to support multiple languages ​​for review data, and automatically translate and provide reviews in different languages. For example, Japanese reviews are translated into English or Chinese and displayed. A system is also built that collects multilingual review data and uses the generation AI to perform automatic translation. For example, English reviews are translated into Japanese and displayed. The generation AI also translates reviews in different languages ​​in real time and provides them to users. For example, reviews in foreign languages ​​are instantly translated and displayed. This makes it possible to provide multilingual review data.

[0069] The sharing section can provide the voices of sake brewers in an interactive format and add a function that allows users to ask questions directly. For example, the sharing section can provide the voices of sake brewers in an interactive format and add a function that allows users to ask questions directly. For example, questions can be sent to sake brewers in real time and answers can be obtained. The generation AI can also analyze users' questions and automatically generate appropriate questions for sake brewers. For example, if a user asks, "What are the characteristics of this sake?", the generation AI can send that question to the sake brewer. A system can also be built that provides the voices of sake brewers in an interactive format and allows users to interact directly. For example, interacting with sake brewers through live chat or video calls. This can provide an interactive format that allows users to ask sake brewers questions directly.

[0070] The sharing unit can use the emotion estimation function to classify reviews by emotion, allowing users to search for reviews based on specific emotions. For example, the sharing unit uses the emotion estimation function to classify reviews by emotion, allowing users to search for reviews based on specific emotions. For example, it searches for reviews with strong feelings of joy or satisfaction. The generation AI also analyzes the emotion data of reviews and builds a system to classify them by emotion. For example, it displays reviews with positive emotions separately from reviews with negative emotions. It also uses the emotion estimation data to allow users to search for reviews based on specific emotions. For example, it displays reviews with high emotion scores preferentially. This makes it possible to search for reviews based on emotions.

[0071] The distribution unit can use the generation AI to analyze the voter's past voting history and preferences and predict the voting results. For example, the distribution unit uses the generation AI to analyze the voter's past voting history and preferences and predict the voting results. For example, the distribution unit predicts this year's voting results based on data from users who have voted for a specific brand in the past. The generation AI also analyzes the voter's preferences and predicts the trend in the voting results. For example, if there are many voters who prefer dry sake, the voting results are predicted based on that trend. The generation AI also makes real-time predictions of the voting results based on the voter's past data. For example, as voting progresses, the final results are predicted based on current voting trends. This makes it possible to predict the voting results based on the voter's past voting history and preferences.

[0072] The distribution unit analyzes the results of the voting contest in real time, and the generation AI can visualize voting trends and changes in popularity. The distribution unit, for example, uses the generation AI to analyze the results of the voting contest in real time and visualize voting trends and changes in popularity. For example, it displays the increase or decrease in the number of votes in a graph. It also builds a system that analyzes the voting results in real time and the generation AI visualizes changes in popularity. For example, it shows changes in the number of votes using color or size. The generation AI also analyzes the results of the voting contest in real time and visualizes voting trends. For example, it highlights stocks with a large number of votes. This makes it possible to visualize voting trends and changes in popularity in real time.

[0073] The distribution unit can use the emotion estimation function to analyze the voter's emotions and provide feedback on the voting results based on those emotions. The distribution unit, for example, uses the emotion estimation function to analyze the voter's emotions and provide feedback on the voting results based on those emotions. For example, if the voter is feeling happy or satisfied, feedback reflecting that emotion is provided. The generation AI also provides feedback on the voting results based on the voter's emotion data. For example, opinions of voters with positive emotions are preferentially displayed. Furthermore, a system is constructed that uses the emotion estimation data to provide feedback on the voting results based on the voter's emotions. For example, opinions of voters with high emotion scores are highlighted. This makes it possible to provide feedback based on the voter's emotions.

[0074] The distribution unit can make the results of the voting contest multilingual, and the generation AI can automatically translate and provide the voting results in different languages. The distribution unit, for example, uses the generation AI to make the results of the voting contest multilingual, and automatically translate and provide the voting results in different languages. For example, Japanese voting results are translated into English or Chinese and displayed. A system is also constructed that collects multilingual voting results and the generation AI performs automatic translation. For example, English voting results are translated into Japanese and displayed. The generation AI also translates voting results in different languages ​​in real time and provides them to users. For example, voting results in a foreign language are instantly translated and displayed. This makes it possible to provide voting results in multiple languages.

[0075] The distribution unit compares the results of the voting contest with past data, and the generation AI can analyze and provide long-term trends. The distribution unit, for example, uses the generation AI to compare the results of the voting contest with past data and analyze long-term trends. For example, it analyzes fluctuations in popularity based on voting results from the past few years. It also builds a system that compares the voting results with past data and the generation AI analyzes long-term trends. For example, it predicts this year's trends based on past voting trends. The generation AI also compares the results of the voting contest with past data and visualizes long-term trends. For example, it displays past voting results in a graph to show the trends. This makes it possible to analyze and provide long-term trends.

[0076] The distribution unit can use the emotion estimation function to provide a ranking of voting results based on voter emotions. The distribution unit, for example, uses the emotion estimation function to provide a ranking of voting results based on voter emotions. For example, it displays a ranking that reflects the opinions of voters with positive emotions. The generation AI also ranks voting results based on emotions based on voter emotion data. For example, it preferentially displays opinions of voters with high emotion scores. Furthermore, it uses the emotion estimation data to build a system that provides a ranking of voting results based on voter emotions. For example, it highlights opinions of voters with positive emotions. This makes it possible to provide a ranking of voting results based on emotions.

[0077] The crowdfunding department can use the generation AI to predict the success probability of a crowdfunding project and provide it to users. For example, the crowdfunding department uses the generation AI to analyze past data on crowdfunding projects and predict the success probability. For example, it calculates the success probability of a current project based on the characteristics of projects that have been successful in the past. In addition, to predict the success probability of a crowdfunding project, the generation AI analyzes the project content and backer data. For example, it predicts the success probability based on the number of backers and the amount of support. In addition, the generation AI predicts the success probability of a crowdfunding project in real time and provides it to users. For example, it updates the success probability based on the progress of the project. In this way, it is possible to predict and provide the success probability of a crowdfunding project.

[0078] The crowdfunding department can analyze the content of a video presentation and provide a summary of the project's appeal using a generation AI. For example, the crowdfunding department can use a generation AI to analyze a crowdfunding project's video presentation and provide a summary of the key points. For example, it can concisely summarize the project's objectives and features. It can also analyze the content of the video presentation and build a system where the generation AI summarizes the project's appeal. For example, it can extract and display the points emphasized in the video. The generation AI can also analyze the content of the video presentation and provide a summary of information important to the user. For example, it can summarize the project's progress and the voices of supporters. This allows it to provide a summary of the project's appeal.

[0079] The crowdfunding unit can use the emotion estimation function to recommend crowdfunding projects based on the user's emotions. For example, the crowdfunding unit uses the emotion estimation function to recommend crowdfunding projects based on the user's emotions. For example, if the user is excited or excited, the crowdfunding unit recommends projects that match those emotions. The generation AI also recommends crowdfunding projects based on the user's emotion data. For example, projects with positive emotions are preferentially displayed. The emotion estimation data is also used to build a system that recommends crowdfunding projects based on the user's emotions. For example, projects with high emotion scores are highlighted. This makes it possible to recommend crowdfunding projects based on the user's emotions.

[0080] The crowdfunding department can support crowdfunding projects in multiple languages, and the generation AI can automatically translate and provide project information in different languages. The crowdfunding department, for example, uses the generation AI to support crowdfunding projects in multiple languages, and automatically translates and provides project information in different languages. For example, Japanese project information is translated into English or Chinese and displayed. A system is also built to collect multilingual crowdfunding project information and the generation AI performs automatic translation. For example, English project information is translated into Japanese and displayed. The generation AI also translates crowdfunding project information in different languages ​​in real time and provides it to users. For example, project information in a foreign language is instantly translated and displayed. This makes it possible to provide multilingual crowdfunding project information.

[0081] The crowdfunding department can provide video presentations in an interactive format and add a function that allows users to ask questions directly. For example, the crowdfunding department can provide video presentations in an interactive format and add a function that allows users to ask questions directly. For example, a question button can be placed in the video, allowing users to submit questions in real time. The generation AI can also analyze users' questions and display the questions at the appropriate time in the video presentation. For example, if a user asks, "What are the characteristics of this sake?", the question can be answered in the video. The crowdfunding department can also provide video presentations in an interactive format and build a system that allows users to interact directly. For example, they can interact with project staff through live chat or video calls. This can provide an interactive format that allows users to ask questions directly.

[0082] The crowdfunding department can use the emotion estimation function to provide project feedback based on the user's emotions. For example, the crowdfunding department uses the emotion estimation function to provide project feedback based on the user's emotions. For example, if the user is excited or feeling anticipation, feedback that matches that emotion is provided. The generation AI also provides emotion-based project feedback based on the user's emotion data. For example, opinions of users with positive emotions are preferentially displayed. The emotion estimation data is also used to build a system that provides project feedback based on the user's emotions. For example, opinions of users with high emotion scores are highlighted. This makes it possible to provide project feedback based on the user's emotions.

[0083] The tasting event information department can use the generation AI to analyze past tasting event participant data and recommend tasting event information based on the participant's preferences. For example, the tasting event information department can use the generation AI to analyze past tasting event participant data and recommend tasting event information based on the participant's preferences. For example, for a participant who has previously preferred a particular brand, the department can recommend tasting events where that brand is offered. The tasting event participant data can also be analyzed, and a system can be built in which the generation AI provides tasting event information that matches the participant's preferences. For example, for a participant who prefers dry sake, the generation AI can recommend tasting events where many dry brands are offered. The generation AI can also predict the participant's preferences based on past tasting event participant data and recommend optimal tasting event information. For example, for a participant who prefers fruity sake, the generation AI can recommend tasting events where many fruity brands are offered. This makes it possible to recommend tasting event information based on the participant's preferences.

[0084] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0085] The sake recommendation system can further include a region specialization section. The region specialization section aggregates information about sake from a specific region and provides it in combination with information about the region's specialty products and tourist attractions. For example, the region specialization section provides information about Hokkaido sake along with information about Hokkaido's specialty products and tourist spots. The region specialization section can also introduce the characteristics and history of sake from each region, conveying the appeal of the region to the user. For example, it can provide a detailed introduction to the history and characteristics of Kyoto sake, conveying its appeal to the user. The region specialization section can also provide event information for each region, which the user can use as a reference when visiting that region. For example, it can provide information about local sake brewery tours and local festivals. This allows the user to enjoy the sake from a specific region together with the appeal of the region.

[0086] The recommendation unit can further use the health estimation function to recommend sake based on the user's health condition. For example, when a user inputs health checkup data, the recommendation unit can recommend healthy sake based on that data. For example, it can recommend low-alcohol sake or sake with low sugar content. The health estimation function can also monitor the user's health condition in real time and recommend sake that is considered healthy. For example, it can recommend sake that is suitable for the user to drink after exercise. The health estimation function can also recommend sake based on the user's health goals. For example, it can recommend low-calorie sake to a user who is on a diet. This allows the user to enjoy sake while being mindful of their health.

[0087] The data generation unit further collects environmental data, allowing the generation AI to recommend environmentally friendly sake. For example, it may recommend sake from breweries that use environmentally friendly production methods. The generation AI also provides information based on the environmental data to help users make environmentally friendly choices. For example, it may recommend sake with a low carbon footprint. The generation AI can also suggest ways to select environmentally friendly sake to users based on the environmental data. For example, it may recommend sake that uses recyclable packaging. The generation AI can also use the environmental data to introduce users to the environmentally friendly sake production process. For example, it may provide information on sake breweries that use renewable energy. This allows users to select sake while being mindful of the environment.

[0088] The recommendation unit uses the emotion estimation function to analyze the emotions felt when the user drinks sake, and can recommend brands based on those emotions. For example, it can analyze the user's facial expressions and voice while drinking sake and calculate an emotion score. The generation AI then recommends brands based on the user's emotion data. For example, when a user wants to relax, it can recommend brands that are known to have a high relaxing effect. It also uses the emotion estimation data to suggest sake pairings that match the user's emotions. For example, when a user is in a good mood, it can recommend sake that is suitable for a party. This makes it possible to recommend the optimal sake based on the user's emotions.

[0089] The data generation unit also collects data on alcoholic beverages other than sake, allowing the generation AI to analyze the correlation of preferences between different beverages and make recommendations. For example, for a user who likes the fruity aroma of wine, it will recommend sake with a similar aroma. The generation AI also finds correlations between different beverages based on the user's preferred alcoholic beverage data and makes recommendations. For example, for a user who likes the bitterness of beer, it will recommend sake with a similar bitterness. The generation AI also integrates data on different alcoholic beverages and analyzes the user's overall preferences. For example, it understands the user's overall preferences based on data on wine, beer, and sake and recommends the most suitable sake. This allows it to analyze the correlation of preferences between different alcoholic beverages and recommend the most suitable sake.

[0090] The recommendation unit digitizes sake pairing information, allowing the generation AI to recommend the optimal sake based on the user's meal details. For example, it can recommend a fruity sake for sushi and a dry sake for grilled meat. The generation AI also analyzes the meal details entered by the user and recommends sake that matches it. For example, if a user enters "fish dishes," it will recommend sake that goes well with fish dishes. Furthermore, based on the pairing information, the generation AI suggests new combinations of food and sake. For example, if a user enters "cheese," it will recommend sake that goes well with cheese. This allows the system to recommend the optimal sake based on the user's meal details.

[0091] The recommendation unit uses the emotion estimation function to recommend sake that the user would like to drink for a specific event or situation. For example, if the user inputs "party," it will recommend sake suitable for a party. The generation AI also recommends sake that suits a specific situation based on the user's emotion data. For example, if the user inputs "I want to relax," it will recommend sake that has a high relaxing effect. It also uses emotion estimation data to suggest the best sake for an event or situation based on the user's emotion. For example, if the user inputs "date," it will recommend sake that is suitable for a date. This makes it possible to recommend the best sake for a specific event or situation.

[0092] The sharing unit can use the generation AI to evaluate the reliability of reviews and prioritize the display of highly reliable reviews. For example, the sharing unit uses the generation AI to analyze the content of the review and information about the poster to evaluate reliability. For example, if the poster has received many high ratings in the past, the review is judged to be highly reliable. In addition, to evaluate the reliability of the review, the generation AI analyzes the poster's past posting history and ratings. For example, reviews from users who have posted highly reliable reviews in the past are displayed preferentially. The generation AI also analyzes the content of the review and extracts highly reliable information. For example, reviews that include specific taste characteristics and detailed impressions are judged to be highly reliable. In this way, highly reliable reviews are displayed preferentially, allowing users to obtain reliable information.

[0093] The sharing section collects the voices of sake brewers not only in text format, but also in audio and video format, and the generation AI can analyze them and provide them to users. For example, the sharing section collects the voices of sake brewers in audio and video format, and the generation AI analyzes them and provides them to users. For example, a video presentation may be presented in which a sake brewer talks about the characteristics and production process of sake. The generation AI may also analyze audio and video data, extract important information, and provide it in text format. For example, a summary of key points from a video interview with a sake brewer may be displayed. The voices of sake brewers may also be collected in various formats, and the generation AI may integrate them and provide them to users. For example, text, audio, and video information may be combined to provide a comprehensive presentation of the voices of sake brewers. This allows the voices of sake brewers to be collected in various formats and provided to users.

[0094] The sharing unit can use the emotion estimation function to analyze the emotions of the reviewer and filter reviews based on the emotions. For example, the sharing unit can use the emotion estimation function to analyze the emotions of the reviewer and prioritize displaying reviews with positive emotions. For example, reviews with a strong sense of joy or satisfaction can be prioritized. The generation AI also performs emotion-based filtering based on the reviewer's emotion data. For example, it can exclude reviews with negative emotions. The emotion estimation data can also be used to calculate an emotion score for the review and perform emotion-based filtering. For example, it can prioritize displaying reviews with a high emotion score. This makes it possible to filter reviews based on emotions.

[0095] The processing flow of the second embodiment will be briefly explained below.

[0096] Step 1: The data collection department collects data on sake brands and flavors. For example, they collect information on sake brands from all over the country and register it in a database. They also analyze the flavor characteristics of each brand and register taste elements such as sweetness, sourness, and bitterness in the database. Step 2: The recommendation unit recommends sake that matches the user's preferences based on the data collected by the data conversion unit. For example, it analyzes the preference information entered by the user and recommends corresponding sake. It can also analyze the user's past drinking history and predict future changes in preferences to recommend sake. Step 3: The sharing unit shares the reviews and opinions of sake brewers about the sake recommended by the recommendation unit. For example, the user's impressions and reviews of sake they have tried are registered in a database and shared with other users. Interviews and comments from sake brewers are also collected and registered in the database. Step 4: The distribution department broadcasts the annual brand voting contest live online. For example, they hold a voting contest for sake brands from all over the country and broadcast the event live online. They can also analyze the voting results in real time and display them in ranking form. Step 5: The crowdfunding department provides crowdfunding information for new sake breweries. For example, they may post a list of crowdfunding applications for new sake breweries and provide video presentations for each brewery. They may also use generative AI to predict the success rate of crowdfunding projects and provide this information to users. Step 6: The tasting information department provides information about tasting events held in various locations. For example, it shares a list of information about sake tasting events held across the country. Generative AI can also be used to analyze past tasting event participant data and recommend tasting event information based on the participant's preferences.

[0097] 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.

[0098] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0099] 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.

[0100] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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).

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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 AI 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.

[0114] 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.

[0115] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0116] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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 AI 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.

[0129] 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.

[0130] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0131] 7, a 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0142] 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.

[0143] 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.

[0144] 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 AI 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0151] 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."

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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]

[0164] 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. The data collection department collects data on sake brands and flavors, a recommendation unit that recommends sake that matches the user's preferences based on the data collected by the data conversion unit; A sharing department that shares reviews and opinions of sake brewers about the sake recommended by the recommendation department; The distribution department broadcasts the annual brand voting contest live online, The crowdfunding department provides information on crowdfunding for new sake breweries, The tasting information department provides information on tasting events held in various locations. A system characterized by:

2. The recommendation unit Analyze the user's past drinking history and changes in preferences, predict future changes in preferences, and make recommendations 2. The system of claim 1.

3. The data conversion unit Collecting data on the ingredients of sake, the AI ​​analyzes the correlation between the ingredients and the taste, and makes recommendations based on scientific evidence.

2. The system of claim 1.

4. The recommendation unit Analyze the emotions of the user when drinking sake and recommend brands based on those emotions 2. The system of claim 1.

5. The data conversion unit Data on alcoholic beverages other than sake will also be collected, and the AI ​​will analyze the correlation between preferences among different beverages and make recommendations.

2. The system of claim 1.

6. The recommendation unit The sake pairing information is digitized, and the generation AI recommends the most suitable sake based on the user's dietary details.

2. The system of claim 1.

7. The recommendation unit Recommending the sake that the user wants to drink for a specific event or situation 2. The system of claim 1.

Images