System

Abstract

An object of a system according to an embodiment is to brew coffee according to a user's preference.SOLUTION: A system includes an interaction unit, a proposal unit, and a learning unit. The dialogue unit receives a question or an instruction from the user. The suggestion unit suggests the type and brewing method of coffee based on the user's question or instruction received by the interaction unit. The learning unit learns the user's preferences and reflects the preferences in the next and subsequent coffee brewing.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] Conventional techniques make it difficult to brew coffee that suits a user's preferences, and there is room for improvement to accommodate individual preferences.

[0005] The system according to the embodiment aims to brew coffee that suits the user's preferences. [Means for solving the problem]

[0006] The system according to the embodiment includes a dialogue unit, a suggestion unit, and a learning unit. The dialogue unit receives questions and instructions from a user. The suggestion unit suggests types of coffee and brewing methods based on the user's questions and instructions received by the dialogue unit. The learning unit learns the user's preferences and reflects them in the way coffee is brewed from the next time onwards. [Effects of the Invention]

[0007] The system according to the embodiment can brew coffee according to the user's preferences. [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) A coffee maker according to an embodiment of the present invention is a system that uses a generative AI to brew coffee tailored to the user's preferences. This system allows the user to ask the generative AI questions and brew coffee that suits their mood, physical condition, and situation. Furthermore, the generative AI learns the user's preferences each time the coffee is brewed, allowing the user to explore the ultimate personalized coffee. This allows the coffee maker to provide coffee tailored to the user's preferences.

[0029] A coffee maker according to an embodiment includes a dialogue unit, a suggestion unit, and a learning unit. The dialogue unit receives questions and instructions from a user. For example, if the user issues an instruction such as, "I'm a little tired today, so I'd like a refreshing coffee," the dialogue unit receives the instruction. The dialogue unit can also receive specific user instructions such as, "I want a coffee with a strong acidity." The suggestion unit suggests a type of coffee and a brewing method based on the user's questions and instructions received by the dialogue unit. For example, if the user receives an instruction such as, "I want to relax today, so a latte would be good," the suggestion unit suggests a latte based on the instruction. If the user says, "I want a coffee with a strong bitterness," the suggestion unit can suggest a coffee with a strong bitterness. The learning unit learns the user's preferences and reflects them in the coffee brewing method from the next time onwards. For example, if the user provides feedback such as, "This coffee is a little too bitter," the learning unit records the information and reflects it in the coffee brewing method from the next time onwards. If the user provides feedback such as, "This temperature is just right," the learning unit records the information and adjusts the coffee temperature from the next time onwards. This allows the coffee maker according to the embodiment to provide coffee that matches the preferences of the user.

[0030] The dialogue unit can analyze the user's past dialogue history and generate a personalized dialogue style. For example, if the user has previously said, "I like coffee with a strong acidity," the dialogue unit records that information and preferentially suggests coffee with a strong acidity in future dialogues. For example, it selects coffee beans from Ethiopia. Also, if the user says, "I like black coffee in the morning," the dialogue unit uses that information to suggest black coffee in the morning dialogue. For example, it uses dark roasted coffee beans to create a strong flavor. Also, if the user says, "I like decaffeinated coffee in the evening," the dialogue unit records that information and suggests decaffeinated coffee in the evening dialogue. For example, it selects decaffeinated coffee beans to enhance the relaxing effect. This makes it possible to provide a dialogue style tailored to the user.

[0031] The dialogue unit analyzes not only the text entered by the user, but also image and voice data, enabling more accurate coffee recommendations. For example, if a user uploads an image of coffee beans, the dialogue unit analyzes the image, identifies the type of beans and the degree of roasting, and suggests the optimal brewing method. For example, a French press may be recommended for lightly roasted beans. Also, if a user says, "It's cold today," the dialogue unit analyzes the voice data and suggests hot coffee. For example, selecting a hot latte or cappuccino enhances the warming effect. Also, if a user uploads an image of a cafe menu, the dialogue unit analyzes the image and suggests coffee based on the menu. For example, it may reproduce a specific flavor on the menu. This allows for more accurate coffee recommendations by analyzing text, image, and voice data.

[0032] The dialogue unit supports dialogue in different languages ​​and can accommodate international users. For example, if a user says, "I want a strong coffee" in English, the dialogue unit analyzes the instruction and suggests a strong-tasting coffee. For example, it can select an espresso or a double shot of coffee. If a user says, "Je veux un cafe doux" in French, the dialogue unit analyzes the instruction and suggests a soft-tasting coffee. For example, it can select a latte or cappuccino with milk. If a user says, "I want a cup of sour? of coffee?" in Chinese, the dialogue unit analyzes the instruction and suggests a strong-tasting coffee. For example, it can select coffee beans from Ethiopia and brew them lightly roasted. This allows the dialogue unit to accommodate international users by supporting dialogue in different languages.

[0033] The learning unit can analyze user feedback in real time and immediately reflect it in the learning results. For example, if a user says, "This coffee is a little too bitter," the learning unit analyzes that feedback in real time and adjusts the bitterness of the coffee from the next time onwards. For example, it selects beans with less bitterness. Also, if a user says, "I want it a little more sour," the learning unit analyzes that feedback in real time and adjusts the acidity of the coffee from the next time onwards. For example, it selects beans with a stronger sourness. Also, if a user says, "This temperature is just right," the learning unit analyzes that feedback in real time and maintains the temperature of the coffee from the next time onwards. For example, it uses the same temperature setting. In this way, by reflecting user feedback in real time, it is possible to more quickly respond to user preferences.

[0034] The learning unit can also take into account external factors such as season and time of day when learning a user's preferences. For example, if a user says, "I like iced coffee in the summer," the learning unit will preferentially suggest iced coffee in the summer based on that information. For example, it will select a cold iced latte or Frappuccino. Also, if a user says, "I like black coffee in the morning," the learning unit will suggest black coffee in the morning based on that information. For example, it will use dark roasted coffee beans to create a strong flavor. Also, if a user says, "I like decaffeinated coffee in the evening," the learning unit will suggest decaffeinated coffee in the evening based on that information. For example, it will select decaffeinated coffee beans to enhance the relaxing effect. This makes it possible to suggest more appropriate coffee by taking into account external factors such as season and time of day.

[0035] When learning a user's preferences, the learning unit can compare the user's preferences with those of other users and find common patterns. For example, if a user says, "I like coffee with a strong acidity," the learning unit compares the user's preferences with those of other users and finds a common pattern among users who like coffee with a strong acidity. For example, the learning unit selects coffee beans from Ethiopia. If a user says, "I like black coffee in the morning," the learning unit compares the user's preferences with those of other users and finds a common pattern among users who like black coffee in the morning. For example, the learning unit uses dark roasted coffee beans to create a strong flavor. If a user says, "I like decaffeinated coffee in the evening," the learning unit compares the user's preferences with those of other users and finds a common pattern among users who like decaffeinated coffee in the evening. For example, the learning unit selects decaffeinated coffee beans to enhance the relaxing effect. This allows the learning unit to find common patterns by comparing the user's preferences with those of other users and recommend more appropriate coffees.

[0036] When learning a user's preferences, the learning unit can also simultaneously learn preferences for different beverages (e.g., tea and juice). For example, if the user says, "I also like tea," the learning unit will learn tea preferences based on that information and suggest both coffee and tea. For example, it will select Earl Grey or Darjeeling. Also, if the user says, "I also drink juice," the learning unit will learn juice preferences based on that information and suggest both coffee and juice. For example, it will select orange juice or apple juice. Also, if the user says, "I also like herbal tea," the learning unit will learn herbal tea preferences based on that information and suggest both coffee and herbal tea. For example, it will select chamomile tea or peppermint tea. This allows the learning unit to learn preferences for different beverages, making it possible to make a wider variety of suggestions.

[0037] The suggestion unit can suggest a new type of coffee to try next based on the user's past selection history. For example, if the user has previously selected "acidic coffee," the suggestion unit will suggest a more acidic coffee to try next based on that history. For example, it will select coffee beans from Kenya. Also, if the user has previously selected "latte with milk," the suggestion unit will suggest a coffee with milk to try next based on that history. For example, it will select cafe au lait or cappuccino. Also, if the user has previously selected "espresso," the suggestion unit will suggest an espresso-based coffee to try next based on that history. For example, it will select ristretto or macchiato. In this way, it is possible to suggest new types of coffee based on the user's past selection history.

[0038] The suggestion unit can suggest the most suitable type of coffee taking into consideration the user's health condition. For example, if the user says, "I want to cut down on caffeine," the suggestion unit will suggest decaffeinated coffee based on that information. For example, decaffeinated coffee beans will be selected to enhance the relaxing effect. Also, if the user says, "I have consumed too much caffeine," the suggestion unit will suggest coffee with a lower caffeine content based on that information. For example, lightly roasted coffee beans will be selected to reduce the caffeine content. Also, if the user says, "I am health-conscious," the suggestion unit will suggest coffee with health benefits based on that information. For example, coffee beans with antioxidant properties will be selected to enhance the health benefits. In this way, the most suitable type of coffee can be suggested taking into consideration the user's health condition.

[0039] The suggestion unit can suggest a type of coffee and a method of brewing it, taking into consideration the user's diet and lifestyle. For example, if the user says, "I eat bread for breakfast," the suggestion unit suggests a coffee that goes well with bread based on that information. For example, it selects coffee made with a French press or a light-flavored American coffee. Also, if the user says, "I eat salad for lunch," the suggestion unit suggests a coffee that goes well with salad based on that information. For example, it selects coffee with a sour taste or coffee with a fruity flavor. Also, if the user says, "I eat a light snack in the evening," the suggestion unit suggests a coffee that goes well with the snack based on that information. For example, it selects decaf coffee or a latte with milk. In this way, it is possible to suggest the optimal type of coffee and a method of brewing it, taking into consideration the user's diet and lifestyle.

[0040] The suggestion unit can also suggest types of beverages other than coffee and how to brew them. For example, if the user says, "I also like black tea," the suggestion unit suggests types of tea and how to brew them based on that information. For example, select Earl Grey or Darjeeling tea and brew it for an appropriate extraction time. Also, if the user says, "I also drink herbal tea," the suggestion unit suggests types of herbal tea and how to brew it based on that information. For example, select chamomile tea or peppermint tea and brew it at an appropriate temperature. Also, if the user says, "I also like fruit tea," the suggestion unit suggests types of fruit tea and how to brew it based on that information. For example, select lemon tea or peach tea and brew it using an appropriate extraction method. In this way, types of beverages other than coffee and how to brew them can be suggested.

[0041] The suggestion unit can suggest optimal coffee beans based on the user's past preference data. For example, if the user previously selected "strongly sour coffee," the suggestion unit can suggest strongly sour coffee beans to try next based on that preference data. For example, it can select coffee beans from Ethiopia. Also, if the user previously selected "strongly bitter coffee," the suggestion unit can suggest strongly bitter coffee beans to try next based on that preference data. For example, it can select coffee beans from Brazil. Also, if the user previously selected "coffee with a fruity flavor," the suggestion unit can suggest fruity coffee beans to try next based on that preference data. For example, it can select coffee beans from Kenya. In this way, it is possible to suggest optimal coffee beans based on the user's past preference data.

[0042] The suggestion unit can suggest coffee beans taking into consideration detailed information such as the bean's origin and harvest time. For example, if a user says, "I want to drink coffee from Brazil," the suggestion unit suggests coffee beans from Brazil based on that information. For example, it selects beans from Minas Gerais and selects the optimal beans taking into consideration the harvest time. Also, if a user says, "I want to drink coffee from Ethiopia," the suggestion unit suggests coffee beans from Ethiopia based on that information. For example, it selects beans from the Sidamo region and selects the optimal beans taking into consideration the harvest time. Also, if a user says, "I want to drink coffee from Colombia," the suggestion unit suggests coffee beans from Colombia based on that information. For example, it selects beans from the Antioquia region and selects the optimal beans taking into consideration the harvest time. In this way, it is possible to suggest optimal coffee beans taking into consideration detailed information such as the bean's origin and harvest time.

[0043] The suggestion unit can suggest coffee beans taking into consideration the user's diet and lifestyle. For example, if the user says, "I eat bread for breakfast," the suggestion unit suggests coffee beans that go well with bread based on that information. For example, it selects coffee made with a French press or a light-flavored American coffee. Also, if the user says, "I eat salad for lunch," the suggestion unit suggests coffee beans that go well with salad based on that information. For example, it selects coffee with a sour taste or coffee with a fruity flavor. Also, if the user says, "I eat a light snack in the evening," the suggestion unit suggests coffee beans that go well with the snack based on that information. For example, it selects decaf coffee or a latte with milk. In this way, the suggestion unit can suggest the optimal coffee beans taking into consideration the user's diet and lifestyle.

[0044] The suggestion unit can also suggest the selection of favorite items other than coffee beans. For example, if the user says, "I also like chocolate," the suggestion unit suggests the selection of chocolate based on that information. For example, select dark chocolate or milk chocolate and enjoy it with coffee. Furthermore, if the user says, "I also eat nuts," the suggestion unit suggests the selection of nuts based on that information. For example, select almonds or cashew nuts and enjoy them with coffee. Furthermore, if the user says, "I also like cookies," the suggestion unit suggests the selection of cookies based on that information. For example, select butter cookies or chocolate chip cookies and enjoy them with coffee. In this way, the suggestion unit can also suggest the selection of favorite items other than coffee beans.

[0045] The suggestion unit can suggest the optimal coffee grinding method and temperature based on the user's past preference data. For example, if the user has previously said, "I like espresso," the suggestion unit will brew coffee with a fine grind and at a high temperature suitable for espresso based on the preference data. For example, use an espresso machine. Also, if the user has previously said, "I like Americano," the suggestion unit will brew coffee with a coarse grind and at a low temperature suitable for Americano based on the preference data. For example, use a drip coffee maker. Also, if the user has previously said, "I like French press," the suggestion unit will brew coffee with a medium grind and at an appropriate temperature suitable for French press based on the preference data. For example, use a French press. In this way, the suggestion unit can suggest the optimal coffee grinding method and temperature based on the user's past preference data.

[0046] The suggestion unit can take into account the type of beans and the roasting level when optimizing the coffee grinding method and temperature. For example, if a user says, "I like light roast beans," the suggestion unit will suggest a grinding method and temperature suitable for light roast beans based on that information. For example, for light roast beans, medium grind coffee will be brewed at the appropriate temperature. Also, if a user says, "I like dark roast beans," the suggestion unit will suggest a grinding method and temperature suitable for dark roast beans based on that information. For example, for dark roast beans, fine grind coffee will be brewed at a high temperature. Also, if a user says, "I like medium roast beans," the suggestion unit will suggest a grinding method and temperature suitable for medium roast beans based on that information. For example, for medium roast beans, medium-fine grind coffee will be brewed at the appropriate temperature. In this way, the optimal grinding method and temperature can be suggested taking into account the type of beans and the roasting level.

[0047] The suggestion unit can suggest a coffee grinding method and temperature taking into account the user's dietary content and lifestyle. For example, if the user says, "I eat bread for breakfast," the suggestion unit suggests a grinding method and temperature that suits the bread based on that information. For example, the suggestion unit brews medium-ground coffee at an appropriate temperature in a French press. Also, if the user says, "I eat a salad for lunch," the suggestion unit suggests a grinding method and temperature that suits the salad based on that information. For example, the suggestion unit brews medium-fine ground coffee at an appropriate temperature in a drip coffee maker. Also, if the user says, "I eat a light meal in the evening," the suggestion unit suggests a grinding method and temperature that suits the light meal based on that information. For example, decaffeinated beans are coarsely ground at a low temperature. This makes it possible to suggest the optimal grinding method and temperature taking into account the user's dietary content and lifestyle.

[0048] The suggestion unit can also suggest optimal brewing methods for beverages other than coffee. For example, if the user says, "I also like black tea," the suggestion unit suggests the optimal brewing method for black tea based on that information. For example, it brews Earl Grey at the appropriate temperature and time. Also, if the user says, "I also drink herbal tea," the suggestion unit suggests the optimal brewing method for herbal tea based on that information. For example, it brews chamomile tea at the appropriate temperature and time. Also, if the user says, "I also like fruit tea," the suggestion unit suggests the optimal brewing method for fruit tea based on that information. For example, it brews lemon tea at the appropriate temperature and time. In this way, it is possible to suggest optimal brewing methods for beverages other than coffee.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The dialogue unit can analyze the user's past dialogue history and generate a personalized dialogue style. For example, if the user previously said, "I like coffee with a strong acidity," the dialogue unit records that information and preferentially suggests coffee with a strong acidity in future dialogues. For example, it selects coffee beans from Ethiopia. Also, if the user says, "I like black coffee in the morning," the dialogue unit uses that information to suggest black coffee in the morning dialogue. For example, it uses dark roasted coffee beans to create a strong flavor. Also, if the user says, "I like decaffeinated coffee in the evening," the dialogue unit records that information and suggests decaffeinated coffee in the evening dialogue. For example, it selects decaffeinated coffee beans to enhance the relaxing effect. This makes it possible to provide a dialogue style tailored to the user.

[0051] The dialogue unit analyzes not only the text entered by the user, but also image and voice data, enabling more accurate coffee recommendations. For example, if a user uploads an image of coffee beans, the image is analyzed to identify the type of beans and the degree of roasting and suggest the optimal brewing method. For example, a French press may be recommended for lightly roasted beans. Also, if the user says, "It's cold today," the dialogue unit analyzes the voice data and suggests hot coffee. For example, selecting a hot latte or cappuccino enhances the warming effect. Also, if a user uploads an image of a cafe menu, the dialogue unit analyzes the image and suggests coffee based on the menu. For example, it may reproduce a specific flavor on the menu. This allows for more accurate coffee recommendations by analyzing text, image, and voice data.

[0052] The dialogue unit supports dialogue in different languages ​​and can accommodate international users. For example, if a user says, "I want a strong coffee" in English, the dialogue unit analyzes the instruction and suggests a strong-tasting coffee. For example, it can select an espresso or a double shot of coffee. If a user says, "Je veux un cafe doux" in French, the dialogue unit analyzes the instruction and suggests a soft-tasting coffee. For example, it can select a latte or cappuccino with milk. If a user says, "I want a cup of sour? of coffee?" in Chinese, the dialogue unit analyzes the instruction and suggests a strong-tasting coffee. For example, it can select coffee beans from Ethiopia and brew them lightly roasted. This allows the system to accommodate international users by supporting dialogue in different languages.

[0053] The learning unit can analyze user feedback in real time and immediately reflect it in the learning results. For example, if a user says, "This coffee is a little too bitter," the learning unit analyzes that feedback in real time and adjusts the bitterness of the coffee from the next time onwards. For example, it selects beans with less bitterness. Also, if a user says, "I want it a little more sour," the learning unit analyzes that feedback in real time and adjusts the acidity of the coffee from the next time onwards. For example, it selects beans with a stronger sourness. Also, if a user says, "This temperature is just right," the learning unit analyzes that feedback in real time and maintains the temperature of the coffee from the next time onwards. For example, it uses the same temperature setting. This allows the user's feedback to be reflected in real time, making it possible to respond to user preferences more quickly.

[0054] When learning a user's preferences, the learning unit can also take into account external factors such as the season and time of day. For example, if a user says, "I like iced coffee in the summer," the learning unit will prioritize iced coffee in the summer based on that information. For example, it will select a cold iced latte or Frappuccino. Also, if a user says, "I like black coffee in the morning," the learning unit will recommend black coffee for the morning based on that information. For example, it will use dark roasted coffee beans to create a strong flavor. Also, if a user says, "I like decaffeinated coffee in the evening," the learning unit will recommend decaffeinated coffee for the evening based on that information. For example, it will select decaffeinated coffee beans to enhance the relaxing effect. This makes it possible to recommend more appropriate coffee by taking into account external factors such as the season and time of day.

[0055] When learning a user's preferences, the learning unit can compare the user's preferences with those of other users and find common patterns. For example, if a user says, "I like coffee with a strong acidity," the learning unit compares the user's preferences with those of other users to find a common pattern among users who like coffee with a strong acidity. For example, the learning unit selects coffee beans from Ethiopia. If a user says, "I like black coffee in the morning," the learning unit compares the user's preferences with those of other users to find a common pattern among users who like black coffee in the morning. For example, the learning unit uses dark roasted coffee beans to create a strong flavor. If a user says, "I like decaffeinated coffee in the evening," the learning unit compares the user's preferences with those of other users to find a common pattern among users who like decaffeinated coffee in the evening. For example, the learning unit selects decaffeinated coffee beans to enhance the relaxing effect. By comparing the user's preferences with those of other users, the learning unit can find common patterns and recommend more appropriate coffees.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The dialogue unit receives questions and instructions from the user. For example, the user may receive instructions such as "I'm feeling a little tired today, so I'd like a refreshing coffee" or specific instructions such as "I'd like a coffee with a strong acidity." Step 2: The suggestion unit suggests types of coffee and how to brew it based on the user's questions and instructions received by the dialogue unit. For example, if the user says, "I want to relax today, so a latte would be good," the suggestion unit suggests a latte based on that instruction. Also, if the user says, "I want a coffee with a strong bitter taste," the suggestion unit suggests a coffee with a strong bitter taste. Step 3: The learning unit learns the user's preferences and reflects them in the way the coffee is brewed from the next time onwards. For example, if the user gives feedback such as "This coffee is a little too bitter," the learning unit records that information and reflects it in the way the coffee is brewed from the next time onwards. Also, if the user gives feedback such as "This temperature is just right," the learning unit records that information and adjusts the temperature of the coffee from the next time onwards.

[0058] (Example 2) A coffee maker according to an embodiment of the present invention is a system that uses a generative AI to brew coffee tailored to the user's preferences. This system allows the user to ask the generative AI questions and brew coffee that suits their mood, physical condition, and situation. Furthermore, the generative AI learns the user's preferences each time the coffee is brewed, allowing the user to explore the ultimate personalized coffee. This allows the coffee maker to provide coffee tailored to the user's preferences.

[0059] A coffee maker according to an embodiment includes a dialogue unit, a suggestion unit, and a learning unit. The dialogue unit receives questions and instructions from a user. For example, if the user issues an instruction such as, "I'm a little tired today, so I'd like a refreshing coffee," the dialogue unit receives the instruction. The dialogue unit can also receive specific user instructions such as, "I want a coffee with a strong acidity." The suggestion unit suggests a type of coffee and a brewing method based on the user's questions and instructions received by the dialogue unit. For example, if the user receives an instruction such as, "I want to relax today, so a latte would be good," the suggestion unit suggests a latte based on the instruction. If the user says, "I want a coffee with a strong bitterness," the suggestion unit can suggest a coffee with a strong bitterness. The learning unit learns the user's preferences and reflects them in the coffee brewing method from the next time onwards. For example, if the user provides feedback such as, "This coffee is a little too bitter," the learning unit records the information and reflects it in the coffee brewing method from the next time onwards. If the user provides feedback such as, "This temperature is just right," the learning unit records the information and adjusts the coffee temperature from the next time onwards. This allows the coffee maker according to the embodiment to provide coffee that matches the preferences of the user.

[0060] The dialogue unit can analyze the tone and speed of the user's voice, estimate their emotional state, and reflect this in coffee recommendations. For example, if the user says, "I feel a little tired today," the dialogue unit analyzes the tone and speed of the voice and suggests coffee with a refreshing effect. For example, it can select coffee with a minty aroma or coffee with less caffeine. If the user says, "I want to relax," the dialogue unit analyzes whether the tone of the voice is calm and suggests a latte or cappuccino with a relaxing effect. For example, it can increase the amount of milk to create a creamy taste. If the user says, "I want to feel energized," the dialogue unit analyzes whether the voice speed is fast and suggests an espresso or double shot coffee that will replenish energy. For example, it can increase the amount of caffeine to enhance the awakening effect. This makes it possible to suggest coffee that suits the user's emotional state.

[0061] The dialogue unit can analyze the user's past dialogue history and generate a personalized dialogue style. For example, if the user has previously said, "I like coffee with a strong acidity," the dialogue unit records that information and preferentially suggests coffee with a strong acidity in future dialogues. For example, it selects coffee beans from Ethiopia. Also, if the user says, "I like black coffee in the morning," the dialogue unit uses that information to suggest black coffee in the morning dialogue. For example, it uses dark roasted coffee beans to create a strong flavor. Also, if the user says, "I like decaffeinated coffee in the evening," the dialogue unit records that information and suggests decaffeinated coffee in the evening dialogue. For example, it selects decaffeinated coffee beans to enhance the relaxing effect. This makes it possible to provide a dialogue style tailored to the user.

[0062] The dialogue unit can use the emotion estimation function to suggest coffee according to the user's emotions. For example, if the user says, "I'm happy today," the dialogue unit detects the positive emotion using the emotion estimation function and suggests a special coffee. For example, it selects a vanilla-flavored latte or a coffee that goes well with dessert. If the user says, "I'm sad today," the dialogue unit detects the negative emotion using the emotion estimation function and suggests a coffee that has a comforting effect. For example, it selects a chocolate-flavored cappuccino or a coffee with warm milk. If the user says, "I'm stressed today," the dialogue unit detects stress using the emotion estimation function and suggests a coffee that has a relaxing effect. For example, it selects a coffee blended with chamomile tea or a low-caffeine coffee. This makes it possible to suggest coffee according to the user's emotions.

[0063] The dialogue unit analyzes not only the text entered by the user, but also image and voice data, enabling more accurate coffee recommendations. For example, if a user uploads an image of coffee beans, the dialogue unit analyzes the image, identifies the type of beans and the degree of roasting, and suggests the optimal brewing method. For example, a French press may be recommended for lightly roasted beans. Also, if a user says, "It's cold today," the dialogue unit analyzes the voice data and suggests hot coffee. For example, selecting a hot latte or cappuccino enhances the warming effect. Also, if a user uploads an image of a cafe menu, the dialogue unit analyzes the image and suggests coffee based on the menu. For example, it may reproduce a specific flavor on the menu. This allows for more accurate coffee recommendations by analyzing text, image, and voice data.

[0064] The dialogue unit supports dialogue in different languages ​​and can accommodate international users. For example, if a user says, "I want a strong coffee" in English, the dialogue unit analyzes the instruction and suggests a strong-tasting coffee. For example, it can select an espresso or a double shot of coffee. If a user says, "Je veux un cafe doux" in French, the dialogue unit analyzes the instruction and suggests a soft-tasting coffee. For example, it can select a latte or cappuccino with milk. If a user says, "I want a cup of sour? of coffee?" in Chinese, the dialogue unit analyzes the instruction and suggests a strong-tasting coffee. For example, it can select coffee beans from Ethiopia and brew them lightly roasted. This allows the dialogue unit to accommodate international users by supporting dialogue in different languages.

[0065] The dialogue unit can use the emotion estimation function to suggest relaxation and refreshment methods according to the user's emotions. For example, if the user says, "I'm tired today," the dialogue unit detects the fatigue using the emotion estimation function and suggests a coffee with a refreshing effect. For example, it selects mint-flavored coffee or iced coffee. Also, if the user says, "I'm stressed today," the dialogue unit detects stress using the emotion estimation function and suggests a coffee with a relaxing effect. For example, it selects coffee blended with chamomile tea or low-caffeine coffee. Also, if the user says, "I'm happy today," the dialogue unit detects positive emotions using the emotion estimation function and suggests a special coffee. For example, it selects a vanilla-flavored latte or a coffee that can be enjoyed with dessert. In this way, it is possible to suggest relaxation and refreshment methods according to the user's emotions.

[0066] The learning unit can analyze user feedback in real time and immediately reflect it in the learning results. For example, if a user says, "This coffee is a little too bitter," the learning unit analyzes that feedback in real time and adjusts the bitterness of the coffee from the next time onwards. For example, it selects beans with less bitterness. Also, if a user says, "I want it a little more sour," the learning unit analyzes that feedback in real time and adjusts the acidity of the coffee from the next time onwards. For example, it selects beans with a stronger sourness. Also, if a user says, "This temperature is just right," the learning unit analyzes that feedback in real time and maintains the temperature of the coffee from the next time onwards. For example, it uses the same temperature setting. In this way, by reflecting user feedback in real time, it is possible to more quickly respond to user preferences.

[0067] The learning unit can also take into account external factors such as season and time of day when learning a user's preferences. For example, if a user says, "I like iced coffee in the summer," the learning unit will preferentially suggest iced coffee in the summer based on that information. For example, it will select a cold iced latte or Frappuccino. Also, if a user says, "I like black coffee in the morning," the learning unit will suggest black coffee in the morning based on that information. For example, it will use dark roasted coffee beans to create a strong flavor. Also, if a user says, "I like decaffeinated coffee in the evening," the learning unit will suggest decaffeinated coffee in the evening based on that information. For example, it will select decaffeinated coffee beans to enhance the relaxing effect. This makes it possible to suggest more appropriate coffee by taking into account external factors such as season and time of day.

[0068] The learning unit can use the emotion estimation function to learn changes in preferences based on the user's emotions. For example, if the user says, "I'm happy today," the learning unit detects positive emotions using the emotion estimation function and learns coffee preferences based on that emotion. For example, the learning unit selects a sweet-flavored coffee. Also, if the user says, "I'm sad today," the learning unit detects negative emotions using the emotion estimation function and learns coffee preferences based on that emotion. For example, the learning unit selects a chocolate-flavored cappuccino. Also, if the user says, "I'm stressed today," the learning unit detects stress using the emotion estimation function and learns coffee preferences based on that emotion. For example, the learning unit selects coffee blended with chamomile tea, which has a relaxing effect. This allows the learning unit to learn changes in preferences based on the user's emotions, making it possible to suggest more personalized coffees.

[0069] When learning a user's preferences, the learning unit can compare the user's preferences with those of other users and find common patterns. For example, if a user says, "I like coffee with a strong acidity," the learning unit compares the user's preferences with those of other users and finds a common pattern among users who like coffee with a strong acidity. For example, the learning unit selects coffee beans from Ethiopia. If a user says, "I like black coffee in the morning," the learning unit compares the user's preferences with those of other users and finds a common pattern among users who like black coffee in the morning. For example, the learning unit uses dark roasted coffee beans to create a strong flavor. If a user says, "I like decaffeinated coffee in the evening," the learning unit compares the user's preferences with those of other users and finds a common pattern among users who like decaffeinated coffee in the evening. For example, the learning unit selects decaffeinated coffee beans to enhance the relaxing effect. This allows the learning unit to find common patterns by comparing the user's preferences with those of other users and recommend more appropriate coffees.

[0070] When learning a user's preferences, the learning unit can also simultaneously learn preferences for different beverages (e.g., tea and juice). For example, if the user says, "I also like tea," the learning unit will learn tea preferences based on that information and suggest both coffee and tea. For example, it will select Earl Grey or Darjeeling. Also, if the user says, "I also drink juice," the learning unit will learn juice preferences based on that information and suggest both coffee and juice. For example, it will select orange juice or apple juice. Also, if the user says, "I also like herbal tea," the learning unit will learn herbal tea preferences based on that information and suggest both coffee and herbal tea. For example, it will select chamomile tea or peppermint tea. This allows the learning unit to learn preferences for different beverages, making it possible to make a wider variety of suggestions.

[0071] The learning unit can use the emotion estimation function to suggest other favorite items (e.g., sweets or snacks) based on the user's emotions. For example, if the user says, "I'm happy today," the learning unit detects the positive emotion using the emotion estimation function and suggests sweets based on that emotion. For example, it selects chocolate cake or cookies. Also, if the user says, "I'm sad today," the learning unit detects the negative emotion using the emotion estimation function and suggests snacks based on that emotion. For example, it selects hot soup or sandwiches. Also, if the user says, "I'm stressed today," the learning unit detects stress using the emotion estimation function and suggests favorite items with a relaxing effect based on that emotion. For example, it selects herbal tea or nuts. This makes it possible to suggest other favorite items based on the user's emotions.

[0072] The suggestion unit can suggest a new type of coffee to try next based on the user's past selection history. For example, if the user has previously selected "acidic coffee," the suggestion unit will suggest a more acidic coffee to try next based on that history. For example, it will select coffee beans from Kenya. Also, if the user has previously selected "latte with milk," the suggestion unit will suggest a coffee with milk to try next based on that history. For example, it will select cafe au lait or cappuccino. Also, if the user has previously selected "espresso," the suggestion unit will suggest an espresso-based coffee to try next based on that history. For example, it will select ristretto or macchiato. In this way, it is possible to suggest new types of coffee based on the user's past selection history.

[0073] The suggestion unit can suggest the most suitable type of coffee taking into consideration the user's health condition. For example, if the user says, "I want to cut down on caffeine," the suggestion unit will suggest decaffeinated coffee based on that information. For example, decaffeinated coffee beans will be selected to enhance the relaxing effect. Also, if the user says, "I have consumed too much caffeine," the suggestion unit will suggest coffee with a lower caffeine content based on that information. For example, lightly roasted coffee beans will be selected to reduce the caffeine content. Also, if the user says, "I am health-conscious," the suggestion unit will suggest coffee with health benefits based on that information. For example, coffee beans with antioxidant properties will be selected to enhance the health benefits. In this way, the most suitable type of coffee can be suggested taking into consideration the user's health condition.

[0074] The suggestion unit can use the emotion estimation function to suggest a type of coffee and a brewing method according to the user's emotion. For example, if the user says, "I'm happy today," the suggestion unit detects the user's positive emotion using the emotion estimation function and suggests a type of coffee based on that emotion. For example, the suggestion unit selects a vanilla-flavored latte or a coffee that goes well with dessert. If the user says, "I'm sad today," the suggestion unit detects the user's negative emotion using the emotion estimation function and suggests a type of coffee based on that emotion. For example, the suggestion unit selects a chocolate-flavored cappuccino or a coffee with warm milk. If the user says, "I'm stressed today," the suggestion unit detects stress using the emotion estimation function and suggests a type of coffee based on that emotion. For example, the suggestion unit selects a coffee blended with chamomile tea or a low-caffeine coffee. This makes it possible to suggest a type of coffee and a brewing method according to the user's emotion.

[0075] The suggestion unit can suggest a type of coffee and a method of brewing it, taking into consideration the user's diet and lifestyle. For example, if the user says, "I eat bread for breakfast," the suggestion unit suggests a coffee that goes well with bread based on that information. For example, it selects coffee made with a French press or a light-flavored American coffee. Also, if the user says, "I eat salad for lunch," the suggestion unit suggests a coffee that goes well with salad based on that information. For example, it selects coffee with a sour taste or coffee with a fruity flavor. Also, if the user says, "I eat a light snack in the evening," the suggestion unit suggests a coffee that goes well with the snack based on that information. For example, it selects decaf coffee or a latte with milk. In this way, it is possible to suggest the optimal type of coffee and a method of brewing it, taking into consideration the user's diet and lifestyle.

[0076] The suggestion unit can also suggest types of beverages other than coffee and how to brew them. For example, if the user says, "I also like black tea," the suggestion unit suggests types of tea and how to brew them based on that information. For example, select Earl Grey or Darjeeling tea and brew it for an appropriate extraction time. Also, if the user says, "I also drink herbal tea," the suggestion unit suggests types of herbal tea and how to brew it based on that information. For example, select chamomile tea or peppermint tea and brew it at an appropriate temperature. Also, if the user says, "I also like fruit tea," the suggestion unit suggests types of fruit tea and how to brew it based on that information. For example, select lemon tea or peach tea and brew it using an appropriate extraction method. In this way, types of beverages other than coffee and how to brew them can be suggested.

[0077] The suggestion unit can use the emotion estimation function to suggest a beverage with a relaxing effect according to the user's emotion. For example, if the user says, "I'm tired today," the suggestion unit detects the feeling of fatigue using the emotion estimation function and suggests a beverage with a refreshing effect. For example, the suggestion unit selects mint-flavored coffee or iced coffee. Also, if the user says, "I'm stressed today," the suggestion unit detects stress using the emotion estimation function and suggests a beverage with a relaxing effect. For example, the suggestion unit selects chamomile tea or low-caffeine coffee. Also, if the user says, "I'm happy today," the suggestion unit detects positive emotion using the emotion estimation function and suggests a special beverage based on that emotion. For example, the suggestion unit selects a vanilla-flavored latte or a coffee that can be enjoyed with dessert. In this way, it is possible to suggest a beverage with a relaxing effect according to the user's emotion.

[0078] The suggestion unit can suggest optimal coffee beans based on the user's past preference data. For example, if the user previously selected "strongly sour coffee," the suggestion unit can suggest strongly sour coffee beans to try next based on that preference data. For example, it can select coffee beans from Ethiopia. Also, if the user previously selected "strongly bitter coffee," the suggestion unit can suggest strongly bitter coffee beans to try next based on that preference data. For example, it can select coffee beans from Brazil. Also, if the user previously selected "coffee with a fruity flavor," the suggestion unit can suggest fruity coffee beans to try next based on that preference data. For example, it can select coffee beans from Kenya. In this way, it is possible to suggest optimal coffee beans based on the user's past preference data.

[0079] The suggestion unit can suggest coffee beans taking into consideration detailed information such as the bean's origin and harvest time. For example, if a user says, "I want to drink coffee from Brazil," the suggestion unit suggests coffee beans from Brazil based on that information. For example, it selects beans from Minas Gerais and selects the optimal beans taking into consideration the harvest time. Also, if a user says, "I want to drink coffee from Ethiopia," the suggestion unit suggests coffee beans from Ethiopia based on that information. For example, it selects beans from the Sidamo region and selects the optimal beans taking into consideration the harvest time. Also, if a user says, "I want to drink coffee from Colombia," the suggestion unit suggests coffee beans from Colombia based on that information. For example, it selects beans from the Antioquia region and selects the optimal beans taking into consideration the harvest time. In this way, it is possible to suggest optimal coffee beans taking into consideration detailed information such as the bean's origin and harvest time.

[0080] The suggestion unit can use the emotion estimation function to select coffee beans that correspond to the user's emotions. For example, if the user says, "I'm happy today," the suggestion unit detects the positive emotion using the emotion estimation function and selects coffee beans based on that emotion. For example, it selects beans from Ethiopia with a fruity flavor. Also, if the user says, "I'm sad today," the suggestion unit detects the negative emotion using the emotion estimation function and selects coffee beans based on that emotion. For example, it selects beans from Brazil with a chocolate flavor. Also, if the user says, "I'm stressed today," the suggestion unit detects stress using the emotion estimation function and selects coffee beans based on that emotion. For example, it selects coffee beans blended with chamomile tea, which has a relaxing effect. In this way, it is possible to select coffee beans that correspond to the user's emotions.

[0081] The suggestion unit can suggest coffee beans taking into consideration the user's diet and lifestyle. For example, if the user says, "I eat bread for breakfast," the suggestion unit suggests coffee beans that go well with bread based on that information. For example, it selects coffee made with a French press or a light-flavored American coffee. Also, if the user says, "I eat salad for lunch," the suggestion unit suggests coffee beans that go well with salad based on that information. For example, it selects coffee with a sour taste or coffee with a fruity flavor. Also, if the user says, "I eat a light snack in the evening," the suggestion unit suggests coffee beans that go well with the snack based on that information. For example, it selects decaf coffee or a latte with milk. In this way, the suggestion unit can suggest the optimal coffee beans taking into consideration the user's diet and lifestyle.

[0082] The suggestion unit can also suggest the selection of favorite items other than coffee beans. For example, if the user says, "I also like chocolate," the suggestion unit suggests the selection of chocolate based on that information. For example, select dark chocolate or milk chocolate and enjoy it with coffee. Furthermore, if the user says, "I also eat nuts," the suggestion unit suggests the selection of nuts based on that information. For example, select almonds or cashew nuts and enjoy them with coffee. Furthermore, if the user says, "I also like cookies," the suggestion unit suggests the selection of cookies based on that information. For example, select butter cookies or chocolate chip cookies and enjoy them with coffee. In this way, the suggestion unit can also suggest the selection of favorite items other than coffee beans.

[0083] The suggestion unit can use the emotion estimation function to select other favorite items according to the user's emotions. For example, if the user says, "I'm happy today," the suggestion unit detects a positive emotion using the emotion estimation function and suggests favorite items based on that emotion. For example, the suggestion unit selects a fruit tart or ice cream to enjoy with coffee. If the user says, "I'm sad today," the suggestion unit detects a negative emotion using the emotion estimation function and suggests favorite items based on that emotion. For example, the suggestion unit selects chocolate cake or hot soup to enjoy with coffee. If the user says, "I'm stressed today," the suggestion unit detects stress using the emotion estimation function and suggests favorite items based on that emotion. For example, the suggestion unit selects nuts or herbal tea to enjoy with coffee. In this way, other favorite items can be selected according to the user's emotions.

[0084] The suggestion unit can suggest the optimal coffee grinding method and temperature based on the user's past preference data. For example, if the user has previously said, "I like espresso," the suggestion unit will brew coffee with a fine grind and at a high temperature suitable for espresso based on the preference data. For example, use an espresso machine. Also, if the user has previously said, "I like Americano," the suggestion unit will brew coffee with a coarse grind and at a low temperature suitable for Americano based on the preference data. For example, use a drip coffee maker. Also, if the user has previously said, "I like French press," the suggestion unit will brew coffee with a medium grind and at an appropriate temperature suitable for French press based on the preference data. For example, use a French press. In this way, the suggestion unit can suggest the optimal coffee grinding method and temperature based on the user's past preference data.

[0085] The suggestion unit can take into account the type of beans and the roasting level when optimizing the coffee grinding method and temperature. For example, if a user says, "I like light roast beans," the suggestion unit will suggest a grinding method and temperature suitable for light roast beans based on that information. For example, for light roast beans, medium grind coffee will be brewed at the appropriate temperature. Also, if a user says, "I like dark roast beans," the suggestion unit will suggest a grinding method and temperature suitable for dark roast beans based on that information. For example, for dark roast beans, fine grind coffee will be brewed at a high temperature. Also, if a user says, "I like medium roast beans," the suggestion unit will suggest a grinding method and temperature suitable for medium roast beans based on that information. For example, for medium roast beans, medium-fine grind coffee will be brewed at the appropriate temperature. In this way, the optimal grinding method and temperature can be suggested taking into account the type of beans and the roasting level.

[0086] The suggestion unit can use the emotion estimation function to suggest a grinding method and temperature according to the user's emotions. For example, if the user says, "I'm happy today," the suggestion unit detects the positive emotion using the emotion estimation function and suggests a grinding method and temperature based on that emotion. For example, if the user says, "I'm sad today," the suggestion unit detects the negative ... stressed today," the suggestion unit detects stress using the emotion estimation function and suggests a grinding method and temperature based on that emotion. For example, if the user says, "I'm stressed today," the suggestion unit detects stress using the emotion estimation function and suggests a grinding method and temperature based on that emotion. For example, if the user says, "I'm stressed today," the suggestion unit coarsely grinds beans with a relaxing effect at a low temperature. In this way, it is possible to suggest a grinding method and temperature according to the user's emotions.

[0087] The suggestion unit can suggest a coffee grinding method and temperature taking into account the user's dietary content and lifestyle. For example, if the user says, "I eat bread for breakfast," the suggestion unit suggests a grinding method and temperature that suits the bread based on that information. For example, the suggestion unit brews medium-ground coffee at an appropriate temperature in a French press. Also, if the user says, "I eat a salad for lunch," the suggestion unit suggests a grinding method and temperature that suits the salad based on that information. For example, the suggestion unit brews medium-fine ground coffee at an appropriate temperature in a drip coffee maker. Also, if the user says, "I eat a light meal in the evening," the suggestion unit suggests a grinding method and temperature that suits the light meal based on that information. For example, decaffeinated beans are coarsely ground at a low temperature. This makes it possible to suggest the optimal grinding method and temperature taking into account the user's dietary content and lifestyle.

[0088] The suggestion unit can also suggest optimal brewing methods for beverages other than coffee. For example, if the user says, "I also like black tea," the suggestion unit suggests the optimal brewing method for black tea based on that information. For example, it brews Earl Grey at the appropriate temperature and time. Also, if the user says, "I also drink herbal tea," the suggestion unit suggests the optimal brewing method for herbal tea based on that information. For example, it brews chamomile tea at the appropriate temperature and time. Also, if the user says, "I also like fruit tea," the suggestion unit suggests the optimal brewing method for fruit tea based on that information. For example, it brews lemon tea at the appropriate temperature and time. In this way, it is possible to suggest optimal brewing methods for beverages other than coffee.

[0089] The suggestion unit can use the emotion estimation function to suggest an optimal brewing method for other beverages based on the user's emotions. For example, if the user says, "I'm happy today," the suggestion unit detects the positive emotion using the emotion estimation function and suggests an optimal brewing method for the beverage based on that emotion. For example, fruit tea is brewed at an appropriate temperature and time. Also, if the user says, "I'm sad today," the suggestion unit detects the negative emotion using the emotion estimation function and suggests an optimal brewing method for the beverage based on that emotion. For example, chocolate-flavored herbal tea is brewed at an appropriate temperature and time. Also, if the user says, "I'm stressed today," the suggestion unit detects stress using the emotion estimation function and suggests an optimal brewing method for the beverage based on that emotion. For example, chamomile tea, which has a relaxing effect, is brewed at an appropriate temperature and time. This makes it possible to suggest an optimal brewing method for other beverages based on the user's emotions.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The dialogue unit can analyze the tone and speed of the user's voice, infer their emotional state, and reflect this in the coffee recommendations. For example, if the user says, "I feel a little tired today," the dialogue unit can analyze the tone and speed of the voice and suggest a coffee with a refreshing effect. For example, it can select a coffee with a minty aroma or one with less caffeine. If the user says, "I want to relax," the dialogue unit can analyze whether the tone of the voice is calm and suggest a latte or cappuccino with a relaxing effect. For example, it can increase the amount of milk to create a creamy taste. If the user says, "I want to feel energized," the dialogue unit can analyze whether the voice speed is fast and suggest an espresso or double shot coffee that will replenish energy. For example, it can increase the amount of caffeine to enhance the awakening effect. This makes it possible to suggest coffee that suits the user's emotional state.

[0092] The dialogue unit can analyze the user's past dialogue history and generate a personalized dialogue style. For example, if the user previously said, "I like coffee with a strong acidity," the dialogue unit records that information and preferentially suggests coffee with a strong acidity in future dialogues. For example, it selects coffee beans from Ethiopia. Also, if the user says, "I like black coffee in the morning," the dialogue unit uses that information to suggest black coffee in the morning dialogue. For example, it uses dark roasted coffee beans to create a strong flavor. Also, if the user says, "I like decaffeinated coffee in the evening," the dialogue unit records that information and suggests decaffeinated coffee in the evening dialogue. For example, it selects decaffeinated coffee beans to enhance the relaxing effect. This makes it possible to provide a dialogue style tailored to the user.

[0093] The dialogue unit can use the emotion estimation function to suggest coffee according to the user's emotions. For example, if the user says, "I'm happy today," the emotion estimation function detects the positive emotion and suggests a special coffee. For example, it selects a vanilla-flavored latte or a coffee that goes well with dessert. If the user says, "I'm sad today," the dialogue unit detects the negative emotion using the emotion estimation function and suggests a coffee that has a comforting effect. For example, it selects a chocolate-flavored cappuccino or a coffee with warm milk. If the user says, "I'm stressed today," the dialogue unit detects stress using the emotion estimation function and suggests a coffee that has a relaxing effect. For example, it selects a coffee blended with chamomile tea or a low-caffeine coffee. This makes it possible to suggest coffee according to the user's emotions.

[0094] The dialogue unit analyzes not only the text entered by the user, but also image and voice data, enabling more accurate coffee recommendations. For example, if a user uploads an image of coffee beans, the image is analyzed to identify the type of beans and the degree of roasting and suggest the optimal brewing method. For example, a French press may be recommended for lightly roasted beans. Also, if the user says, "It's cold today," the dialogue unit analyzes the voice data and suggests hot coffee. For example, selecting a hot latte or cappuccino enhances the warming effect. Also, if a user uploads an image of a cafe menu, the dialogue unit analyzes the image and suggests coffee based on the menu. For example, it may reproduce a specific flavor on the menu. This allows for more accurate coffee recommendations by analyzing text, image, and voice data.

[0095] The dialogue unit supports dialogue in different languages ​​and can accommodate international users. For example, if a user says, "I want a strong coffee" in English, the dialogue unit analyzes the instruction and suggests a strong-tasting coffee. For example, it can select an espresso or a double shot of coffee. If a user says, "Je veux un cafe doux" in French, the dialogue unit analyzes the instruction and suggests a soft-tasting coffee. For example, it can select a latte or cappuccino with milk. If a user says, "I want a cup of sour? of coffee?" in Chinese, the dialogue unit analyzes the instruction and suggests a strong-tasting coffee. For example, it can select coffee beans from Ethiopia and brew them lightly roasted. This allows the system to accommodate international users by supporting dialogue in different languages.

[0096] The dialogue unit can use the emotion estimation function to suggest relaxation and refreshment methods according to the user's emotions. For example, if the user says, "I'm tired today," the emotion estimation function detects the fatigue and suggests a coffee with a refreshing effect. For example, it can select mint-flavored coffee or iced coffee. If the user says, "I'm stressed today," the dialogue unit can detect stress using the emotion estimation function and suggest a coffee with a relaxing effect. For example, it can select coffee blended with chamomile tea or low-caffeine coffee. If the user says, "I'm happy today," the dialogue unit can detect positive emotions using the emotion estimation function and suggest a special coffee. For example, it can select a vanilla-flavored latte or a coffee that can be enjoyed with dessert. This makes it possible to suggest relaxation and refreshment methods according to the user's emotions.

[0097] The learning unit can analyze user feedback in real time and immediately reflect it in the learning results. For example, if a user says, "This coffee is a little too bitter," the learning unit analyzes that feedback in real time and adjusts the bitterness of the coffee from the next time onwards. For example, it selects beans with less bitterness. Also, if a user says, "I want it a little more sour," the learning unit analyzes that feedback in real time and adjusts the acidity of the coffee from the next time onwards. For example, it selects beans with a stronger sourness. Also, if a user says, "This temperature is just right," the learning unit analyzes that feedback in real time and maintains the temperature of the coffee from the next time onwards. For example, it uses the same temperature setting. This allows the user's feedback to be reflected in real time, making it possible to respond to user preferences more quickly.

[0098] When learning a user's preferences, the learning unit can also take into account external factors such as the season and time of day. For example, if a user says, "I like iced coffee in the summer," the learning unit will prioritize iced coffee in the summer based on that information. For example, it will select a cold iced latte or Frappuccino. Also, if a user says, "I like black coffee in the morning," the learning unit will recommend black coffee for the morning based on that information. For example, it will use dark roasted coffee beans to create a strong flavor. Also, if a user says, "I like decaffeinated coffee in the evening," the learning unit will recommend decaffeinated coffee for the evening based on that information. For example, it will select decaffeinated coffee beans to enhance the relaxing effect. This makes it possible to recommend more appropriate coffee by taking into account external factors such as the season and time of day.

[0099] The learning unit can use the emotion estimation function to learn changes in preferences based on the user's emotions. For example, if the user says, "I'm happy today," the emotion estimation function detects the positive emotion and learns coffee preferences based on that emotion. For example, the learning unit selects a sweet-flavored coffee. If the user says, "I'm sad today," the learning unit detects the negative emotion and learns coffee preferences based on that emotion. For example, the learning unit selects a chocolate-flavored cappuccino. If the user says, "I'm stressed today," the learning unit detects stress using the emotion estimation function and learns coffee preferences based on that emotion. For example, the learning unit selects coffee blended with chamomile tea, which has a relaxing effect. This allows the system to learn changes in preferences based on the user's emotions, making it possible to suggest more personalized coffees.

[0100] When learning a user's preferences, the learning unit can compare the user's preferences with those of other users and find common patterns. For example, if a user says, "I like coffee with a strong acidity," the learning unit compares the user's preferences with those of other users to find a common pattern among users who like coffee with a strong acidity. For example, the learning unit selects coffee beans from Ethiopia. If a user says, "I like black coffee in the morning," the learning unit compares the user's preferences with those of other users to find a common pattern among users who like black coffee in the morning. For example, the learning unit uses dark roasted coffee beans to create a strong flavor. If a user says, "I like decaffeinated coffee in the evening," the learning unit compares the user's preferences with those of other users to find a common pattern among users who like decaffeinated coffee in the evening. For example, the learning unit selects decaffeinated coffee beans to enhance the relaxing effect. By comparing the user's preferences with those of other users, the learning unit can find common patterns and recommend more appropriate coffees.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The dialogue unit receives questions and instructions from the user. For example, the user may receive instructions such as "I'm feeling a little tired today, so I'd like a refreshing coffee" or specific instructions such as "I'd like a coffee with a strong acidity." Step 2: The suggestion unit suggests types of coffee and how to brew it based on the user's questions and instructions received by the dialogue unit. For example, if the user says, "I want to relax today, so a latte would be good," the suggestion unit suggests a latte based on that instruction. Also, if the user says, "I want a coffee with a strong bitter taste," the suggestion unit suggests a coffee with a strong bitter taste. Step 3: The learning unit learns the user's preferences and reflects them in the way the coffee is brewed from the next time onwards. For example, if the user gives feedback such as "This coffee is a little too bitter," the learning unit records that information and reflects it in the way the coffee is brewed from the next time onwards. Also, if the user gives feedback such as "This temperature is just right," the learning unit records that information and adjusts the temperature of the coffee from the next time onwards.

[0103] 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.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] 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.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0148] 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.

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A coffee maker that uses generative AI to make coffee tailored to the user's preferences, a dialogue unit that receives questions and instructions from a user; a suggestion unit that suggests types of coffee and brewing methods based on questions and instructions from the user received by the dialogue unit; A learning unit that learns the user's preferences and reflects them in the way coffee is made from the next time onwards. A system characterized by:

2. The dialogue unit Analyzing the tone and speed of the user's voice to estimate their emotional state and reflect that in the coffee recommendation.

2. The system of claim 1.

3. The dialogue unit Analyzing the user's past interaction history and generating a personalized interaction style 2. The system of claim 1.

4. The dialogue unit Proposing coffee according to the user's emotions 2. The system of claim 1.

5. The dialogue unit Analyzes not only the text entered by the user, but also images and voice data to make more accurate coffee recommendations.

2. The system of claim 1.

6. The dialogue unit Supports interaction in different languages ​​to cater to international users 2. The system of claim 1.

Images