system

Abstract

The system according to the embodiment aims to propose the best cocktail based on the customer's wishes. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, a generation unit, a proposal unit, and a feedback unit. The reception unit receives a customer's request. The analysis unit analyzes the request received by the reception unit. The generation unit generates a cocktail based on the request analyzed by the analysis unit. The proposal unit proposes the cocktail generated by the generation unit. The feedback unit receives feedback on the cocktail proposed by the proposal unit.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to propose original cocktails based on customer requests, and the process relied on the bartender's creativity.

[0005] The system according to the embodiment aims to propose the best cocktail based on the customer's wishes. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, a proposal unit, and a feedback unit. The reception unit receives a customer's request. The analysis unit analyzes the request received by the reception unit. The generation unit generates a cocktail based on the request analyzed by the analysis unit. The proposal unit proposes the cocktail generated by the generation unit. The feedback unit receives feedback on the cocktail proposed by the proposal unit. [Effects of the Invention]

[0007] The system according to the embodiment can suggest the best cocktail based on the customer's wishes. [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 cocktail recommendation system according to an embodiment of the present invention generates and recommends cocktails based on customer preferences and receives feedback. This cocktail recommendation system uses a generative AI to suggest cocktails based on customer preferences. Specifically, a customer's preferences are first input. For example, a customer may input a preference such as "I want a fruity and sweet cocktail." This information is then input into the generative AI. The generative AI then analyzes the input preference and generates an optimal cocktail from a vast database. The generative AI then suggests a cocktail recipe, appearance, and name. For example, it proposes a cocktail called "Mango Passion" as a "fruity and sweet cocktail" and outputs an image of the cocktail's recipe and appearance. Furthermore, the generative AI model is fine-tuned based on feedback from bartenders and customers. As a result, the more the system is used, the more unique cocktails it can suggest, reflecting the bartender's characteristics and customer preferences. For example, if a customer provides feedback such as "I'd like it a little less sweet," the system can suggest a new cocktail that reflects that preference. This system solves the problem of bartenders being unable to come up with original cocktails and allows them to provide cocktails that satisfy customers. This allows the cocktail suggestion system to generate and suggest cocktails based on customer preferences and receive feedback.

[0029] A cocktail recommendation system according to an embodiment includes a reception unit, an analysis unit, a generation unit, a recommendation unit, and a feedback unit. The reception unit receives customer requests. Customer requests may include, but are not limited to, taste preferences, allergy information, and the presence or absence of specific ingredients. The reception unit may receive the requests via, for example, text input, voice input, or image input. The analysis unit analyzes the requests received by the reception unit. The analysis may be performed via, for example, text analysis, sentiment analysis, or pattern recognition, but is not limited to, the methods. The analysis unit may analyze the customer requests using, for example, a text analysis algorithm. The analysis unit may also analyze the customer's sentiment using a sentiment analysis algorithm. The analysis unit may also analyze patterns of the customer's requests using a pattern recognition algorithm. The generation unit generates a cocktail based on the requests analyzed by the analysis unit. The generation may include, for example, generating a cocktail recipe, an image of the appearance, and a name, but is not limited to, the methods. The generation unit may generate the cocktail recipe using, for example, a generation AI. The generation unit may also generate an image of the appearance of the cocktail using an image generation algorithm. Furthermore, the generation unit can generate a name for the cocktail using a name generation algorithm. The suggestion unit suggests the cocktail generated by the generation unit. The suggestion may be in text format, image format, audio format, or the like, but is not limited to these examples. The suggestion unit may, for example, suggest a recipe for the generated cocktail in text format. The suggestion unit may also suggest an image of the appearance of the generated cocktail in image format. The suggestion unit may also suggest a name for the generated cocktail in audio format. The feedback unit receives feedback on the cocktail suggested by the suggestion unit. The feedback may be in text format, audio format, image format, or the like, but is not limited to these examples. The feedback unit receives feedback from the bartender or customer in text format, for example. The feedback unit may also receive feedback in audio format. The feedback unit may also receive feedback in image format.This allows the cocktail recommendation system according to the embodiment to create and recommend cocktails based on the customer's preferences and receive feedback.

[0030] The generation unit can generate a cocktail recipe. The generation unit generates the cocktail recipe using, for example, a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the generation unit can input a prompt such as "Please generate a recipe for a fruity and sweet cocktail" to the generation AI, causing the generation AI to generate a cocktail recipe based on the prompt. The generation unit can also input a prompt such as "Please generate a recipe for a spicy cocktail" to the generation AI, causing the generation AI to generate a cocktail recipe based on the prompt. Furthermore, the generation unit can input a prompt such as "Please generate a recipe for a classic cocktail" to the generation AI, causing the generation AI to generate a cocktail recipe based on the prompt. In this way, the generation unit can generate a cocktail recipe. Some or all of the above-described processing in the generation unit may be performed using, or without, an AI. For example, the generation unit can input a prompt to the generation AI, causing the generation AI to generate a cocktail recipe.

[0031] The generation unit can generate an image of the appearance of a cocktail. The generation unit generates an image of the appearance of a cocktail using, for example, an image generation algorithm. The image generation algorithm is, for example, a generative adversarial network (GAN) or a variational autoencoder (VAE), but is not limited to these examples. The generation unit generates an image of the appearance of a cocktail using, for example, a GAN. The generation unit can also generate an image of the appearance of a cocktail using a VAE. Furthermore, the generation unit can also generate an image of the appearance of a cocktail using an image generation algorithm. For example, the generation unit can generate an image of the appearance of a "fruity and sweet cocktail" using a GAN. The generation unit can also generate an image of the appearance of a "spicy cocktail" using a VAE. Furthermore, the generation unit can generate an image of the appearance of a "classic cocktail" using an image generation algorithm. In this way, the generation unit can generate an image of the appearance of a cocktail. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate an image of the appearance of a cocktail using an image generation algorithm.

[0032] The generation unit can generate the name of the cocktail. The generation unit generates the name of the cocktail using, for example, a name generation algorithm. The name generation algorithm is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. The generation unit generates the name of the cocktail using, for example, a text generation AI. The generation unit can also generate the name of the cocktail using a multimodal generation AI. Furthermore, the generation unit can also generate the name of the cocktail using a name generation algorithm. For example, the generation unit can generate the name of a "fruity and sweet cocktail" using a text generation AI. The generation unit can also generate the name of a "spicy cocktail" using a multimodal generation AI. Furthermore, the generation unit can generate the name of a "classic cocktail" using a name generation algorithm. In this way, the generation unit can generate the name of the cocktail. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate the name of the cocktail using a name generation algorithm.

[0033] The feedback unit can receive feedback from the bartender or the customer and fine-tune the generative AI model. The feedback unit receives the feedback from the bartender or the customer in text format, for example. The feedback may be, for example, about the taste, appearance, or name of the cocktail, but is not limited to these examples. For example, the feedback unit receives feedback in text format, such as "I wish it was a little less sweet." The feedback unit can also receive feedback in audio format, such as "I wish it looked more vibrant." The feedback unit can also receive feedback in image format, such as "I like the look of this cocktail." The feedback unit fine-tunes the generative AI model based on the received feedback. Fine-tuning is performed, for example, by adjusting the parameters of the generative AI, but is not limited to these examples. For example, the feedback unit adjusts the parameters of the generative AI based on the received feedback. The feedback unit can also update the learning data of the generative AI based on the received feedback. The feedback unit can also improve the generative AI's algorithm based on the received feedback. This allows the feedback unit to fine-tune the generative AI model based on the feedback. Some or all of the above-described processing in the feedback unit may be performed using AI or without AI, for example, the feedback unit may fine-tune the model of the generative AI based on the received feedback.

[0034] The reception unit can analyze the customer's past preference history and select the optimal reception method. For example, the reception unit retrieves the customer's past preference history from a database and selects the optimal reception method using an analysis algorithm. The analysis algorithm can be, for example, a machine learning algorithm or a data mining algorithm, but is not limited to these examples. For example, the reception unit analyzes the customer's past preference history using a machine learning algorithm. The reception unit can also analyze the customer's past preference history using a data mining algorithm. Furthermore, the reception unit can analyze the customer's past preference history using an analysis algorithm. The reception unit selects the optimal reception method based on the analysis results. For example, the reception unit can automatically display preferences entered by the customer in the past as candidates. The reception unit can also prioritize input methods (such as voice and text) that the customer has used in the past. Furthermore, the reception unit can predict and suggest preferences to be used during a specific time period based on the customer's past preference history. This allows the reception unit to select the optimal reception method based on the customer's past preference history. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input past preference history data into the generation AI and have the generation AI select the optimal reception method.

[0035] When receiving a request, the reception unit can prioritize relevant requests based on the customer's geographical location information. The reception unit, for example, acquires the customer's geographical location information using location information acquisition technology such as GPS or Wi-Fi, and filters the requests using a filtering algorithm. Examples of the filtering algorithm include, but are not limited to, a machine learning algorithm or a rule-based algorithm. The reception unit filters the customer's geographical location information using, for example, a machine learning algorithm. The reception unit can also filter the customer's geographical location information using a rule-based algorithm. The reception unit can also filter the customer's geographical location information using a filtering algorithm. The reception unit receives the request based on the filtering results. For example, if the customer is at the beach, a request for a tropical cocktail can be prioritized. If the customer is in a cold region, a request for a warm cocktail can be prioritized. If the customer is in an urban area, a request for a trendy cocktail can be prioritized. This allows the reception unit to filter the requests based on the customer's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception department can input the customer's geographical location information obtained via GPS, Wi-Fi, etc. into the generation AI and have the generation AI perform filtering.

[0036] The reception unit may analyze the customer's social media activity when receiving the request and receive related requests. For example, the reception unit may obtain the customer's social media activity through an API and receive related requests using an analysis algorithm. Examples of the analysis algorithm include, but are not limited to, a text analysis algorithm and a sentiment analysis algorithm. For example, the reception unit may analyze the customer's social media activity using a text analysis algorithm. The reception unit may also analyze the customer's social media activity using a sentiment analysis algorithm. The reception unit may also analyze the customer's social media activity using an analysis algorithm. The reception unit may receive related requests based on the analysis results. For example, the reception unit may prioritize requests for similar cocktails based on photos of cocktails shared by the customer on social media. The reception unit may also prioritize related requests based on trends in cocktail bars that the customer follows on social media. The reception unit may also prioritize requests based on information about cocktails that the customer has "liked" on social media. In this way, the reception unit can receive requests based on the customer's social media activity. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception department can input customer social media data obtained through the API into the generation AI and have the generation AI perform analysis.

[0037] The analysis unit can adjust the level of detail of the analysis based on the desired importance during analysis. The analysis unit adjusts the level of detail of the analysis using, for example, an algorithm for evaluating the desired importance. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The analysis unit can evaluate the desired importance using, for example, a machine learning algorithm. The analysis unit can also evaluate the desired importance using a rule-based algorithm. The analysis unit can also evaluate the desired importance using an evaluation algorithm. The analysis unit adjusts the level of detail of the analysis based on the evaluation results. For example, if the desire has high importance, a detailed analysis can be performed. If the desire has medium importance, an analysis with moderate detail can be performed. If the desire has low importance, a brief analysis can be performed. This allows the analysis unit to adjust the level of detail of the analysis based on the desired importance. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the desired importance data to the generation AI and cause the generation AI to adjust the level of detail.

[0038] The analysis unit can apply different analysis algorithms depending on the desired category during analysis. The analysis unit selects the analysis algorithm using, for example, an algorithm that classifies the desired category. The classification algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The analysis unit classifies the desired category using, for example, a machine learning algorithm. The analysis unit can also classify the desired category using a rule-based algorithm. Furthermore, the analysis unit can classify the desired category using a classification algorithm. The analysis unit selects the analysis algorithm based on the classification result. For example, if a fruity cocktail is desired, an algorithm that analyzes fruit combinations can be applied. If a spicy cocktail is desired, an algorithm that analyzes the balance of spices can be applied. If a classic cocktail is desired, an algorithm that analyzes traditional recipes can be applied. This allows the analysis unit to apply different analysis algorithms depending on the desired category. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input desired category data into the generation AI and have the generation AI select an analysis algorithm.

[0039] The analysis unit can determine the analysis priority based on the desired submission time during analysis. The analysis unit determines the analysis priority using, for example, an algorithm that evaluates the desired submission time. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The analysis unit can evaluate the desired submission time using, for example, a machine learning algorithm. The analysis unit can also evaluate the desired submission time using a rule-based algorithm. The analysis unit can also evaluate the desired submission time using an evaluation algorithm. The analysis unit determines the analysis priority based on the evaluation results. For example, if the request is submitted urgently, the analysis can be performed with priority. If the request is submitted at a normal time, the analysis can be performed with normal priority. If the request is submitted late, the analysis can be performed at a later date. This allows the analysis unit to determine the analysis priority based on the desired submission time. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the desired submission time data into the generation AI and have the generation AI determine the priority.

[0040] The analysis unit can adjust the order of analysis based on the desired relevance during analysis. The analysis unit adjusts the order of analysis using, for example, an algorithm that evaluates the desired relevance. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The analysis unit can evaluate the desired relevance using, for example, a machine learning algorithm. The analysis unit can also evaluate the desired relevance using a rule-based algorithm. Furthermore, the analysis unit can evaluate the desired relevance using an evaluation algorithm. The analysis unit adjusts the order of analysis based on the evaluation results. For example, if a desire is highly relevant to other desires, analysis can be performed with priority. Furthermore, if a desire is moderately relevant to other desires, analysis can be performed with moderate priority. Furthermore, if a desire is lowly relevant to other desires, analysis can be postponed. This allows the analysis unit to adjust the order of analysis based on the desired relevance. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the desired relevance data to the generation AI and have the generation AI adjust the order.

[0041] The generation unit can adjust the level of detail of the generation based on the ingredients of the cocktail during generation. The generation unit adjusts the level of detail of the generation, for example, using an algorithm that evaluates the ingredients of the cocktail. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The generation unit can evaluate the ingredients of the cocktail using, for example, a machine learning algorithm. The generation unit can also evaluate the ingredients of the cocktail using a rule-based algorithm. Furthermore, the generation unit can evaluate the ingredients of the cocktail using an evaluation algorithm. The generation unit adjusts the level of detail of the generation based on the evaluation results. For example, if the number of ingredients is large, a detailed recipe can be generated. Also, if the number of ingredients is medium, a recipe with moderate level of detail can be generated. Furthermore, if the number of ingredients is small, a concise recipe can be generated. In this way, the generation unit can adjust the level of detail of the generation based on the ingredients of the cocktail. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input cocktail ingredient data into the generation AI and cause the generation AI to adjust the level of detail.

[0042] The generation unit can apply different generation algorithms depending on the cocktail category during generation. The generation unit selects the generation algorithm, for example, using an algorithm that classifies cocktail categories. The classification algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The generation unit classifies cocktail categories using, for example, a machine learning algorithm. The generation unit can also classify cocktail categories using a rule-based algorithm. The generation unit can also classify cocktail categories using a classification algorithm. The generation unit selects the generation algorithm based on the classification results. For example, an algorithm that generates a fruit combination can be applied to a fruity cocktail. An algorithm that generates a spice balance can be applied to a spicy cocktail. Furthermore, an algorithm that generates a traditional recipe can be applied to a classic cocktail. This allows the generation unit to apply different generation algorithms depending on the cocktail category. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input cocktail category data to the generation AI and cause the generation AI to select a generation algorithm.

[0043] The generation unit can determine the generation priority based on the time of cocktail submission during generation. The generation unit determines the generation priority using, for example, an algorithm that evaluates the time of cocktail submission. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The generation unit can evaluate the time of cocktail submission using, for example, a machine learning algorithm. The generation unit can also evaluate the time of cocktail submission using a rule-based algorithm. The generation unit can also evaluate the time of cocktail submission using an evaluation algorithm. The generation unit determines the generation priority based on the evaluation results. For example, if a cocktail request is submitted urgently, the cocktail can be generated with priority. Also, if the cocktail request is submitted at a normal time, the cocktail can be generated with normal priority. Furthermore, if the cocktail request is submitted late, the cocktail can be generated at a later date. In this way, the generation unit can determine the generation priority based on the time of cocktail submission. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input cocktail submission time data into the generation AI and cause the generation AI to determine the priority.

[0044] The generation unit can adjust the order of cocktail generation based on the relevance of the cocktails during generation. The generation unit adjusts the order of cocktail generation, for example, using an algorithm that evaluates the relevance of the cocktails. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The generation unit can evaluate the relevance of the cocktails using, for example, a machine learning algorithm. The generation unit can also evaluate the relevance of the cocktails using a rule-based algorithm. The generation unit can also evaluate the relevance of the cocktails using an evaluation algorithm. The generation unit adjusts the order of cocktail generation based on the evaluation results. For example, if a desired cocktail is highly relevant to other desires, it can be generated with priority. Also, if a desired cocktail is moderately relevant to other desires, it can be generated with moderate priority. Furthermore, if a desired cocktail is lowly relevant to other desires, it can be generated later. In this way, the generation unit can adjust the order of cocktail generation based on the relevance of the cocktails. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input cocktail relevance data into the generation AI and cause the generation AI to adjust the order.

[0045] The suggestion unit can adjust the level of detail of the suggestion based on the importance of the cocktail when suggesting the cocktail. The suggestion unit adjusts the level of detail of the suggestion using, for example, an algorithm for evaluating the importance of the cocktail. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The suggestion unit can evaluate the importance of the cocktail using, for example, a machine learning algorithm. The suggestion unit can also evaluate the importance of the cocktail using a rule-based algorithm. Furthermore, the suggestion unit can evaluate the importance of the cocktail using an evaluation algorithm. The suggestion unit adjusts the level of detail of the suggestion based on the evaluation result. For example, for a cocktail with high importance, a detailed suggestion can be made. For a cocktail with medium importance, a suggestion with moderate detail can be made. For a cocktail with low importance, a concise suggestion can be made. In this way, the suggestion unit can adjust the level of detail of the suggestion based on the importance of the cocktail. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input cocktail importance data to a generation AI and cause the generation AI to adjust the level of detail.

[0046] The suggestion unit can apply different suggestion algorithms depending on the cocktail category when making a suggestion. The suggestion unit selects the suggestion algorithm, for example, using an algorithm for classifying cocktail categories. The classification algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The suggestion unit can classify cocktail categories using, for example, a machine learning algorithm. The suggestion unit can also classify cocktail categories using a rule-based algorithm. The suggestion unit can also classify cocktail categories using a classification algorithm. The suggestion unit selects the suggestion algorithm based on the classification results. For example, an algorithm that suggests fruit combinations can be applied to fruity cocktails. An algorithm that suggests a balance of spices can be applied to spicy cocktails. Furthermore, an algorithm that suggests traditional recipes can be applied to classic cocktails. This allows the suggestion unit to apply different suggestion algorithms depending on the cocktail category. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input cocktail category data to a generation AI and cause the generation AI to select a suggestion algorithm.

[0047] The suggestion unit can determine the priority of the suggestions based on the time of cocktail submission when making suggestions. The suggestion unit determines the priority of the suggestions using, for example, an algorithm that evaluates the time of cocktail submission. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The suggestion unit can evaluate the time of cocktail submission using, for example, a machine learning algorithm. The suggestion unit can also evaluate the time of cocktail submission using a rule-based algorithm. The suggestion unit can also evaluate the time of cocktail submission using an evaluation algorithm. The suggestion unit determines the priority of the suggestions based on the evaluation results. For example, if a cocktail request is submitted urgently, the suggestion unit can be prioritized. Also, if a cocktail request is submitted at a normal time, the suggestion unit can be proposed with normal priority. Furthermore, if a cocktail request is submitted late, the suggestion unit can be proposed at a later time. In this way, the suggestion unit can determine the priority of the suggestions based on the time of cocktail submission. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input cocktail submission time data to a generation AI and cause the generation AI to determine the priority.

[0048] The suggestion unit can adjust the order of suggestions based on the relevance of the cocktails when suggesting them. The suggestion unit adjusts the order of suggestions using, for example, an algorithm that evaluates the relevance of the cocktails. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The suggestion unit can evaluate the relevance of the cocktails using, for example, a machine learning algorithm. The suggestion unit can also evaluate the relevance of the cocktails using a rule-based algorithm. Furthermore, the suggestion unit can evaluate the relevance of the cocktails using an evaluation algorithm. The suggestion unit adjusts the order of suggestions based on the evaluation results. For example, if a desired cocktail is highly relevant to other preferences, it can be suggested with priority. Also, if a desired cocktail is moderately relevant to other preferences, it can be suggested with moderate priority. Furthermore, if a desired cocktail is lowly relevant to other preferences, it can be suggested later. In this way, the suggestion unit can adjust the order of suggestions based on the relevance of the cocktails. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or without AI. For example, the suggestion unit can input cocktail relevance data to a generation AI and cause the generation AI to adjust the order.

[0049] The feedback unit can adjust the level of detail of the feedback by referring to past feedback data when providing feedback. The feedback unit, for example, retrieves past feedback data from a database and adjusts the level of detail of the feedback using an analysis algorithm. The analysis algorithm is, for example, a machine learning algorithm or a data mining algorithm, but is not limited to these examples. The feedback unit, for example, analyzes the past feedback data using a machine learning algorithm. The feedback unit can also analyze the past feedback data using a data mining algorithm. The feedback unit can also analyze the past feedback data using an analysis algorithm. The feedback unit adjusts the level of detail of the feedback based on the analysis results. For example, a customer who provided detailed feedback in the past can be asked to provide more detailed feedback. A customer who provided brief feedback in the past can be asked to provide brief feedback. Furthermore, the feedback unit can suggest an appropriate level of detail of the feedback based on the past feedback data. In this way, the feedback unit can adjust the level of detail of the feedback based on the past feedback data. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input past feedback data to a generation AI and cause the generation AI to adjust the level of detail.

[0050] The feedback unit can apply different feedback algorithms depending on the category of the feedback when providing feedback. The feedback unit selects the feedback algorithm using, for example, an algorithm that classifies the category of the feedback. The classification algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The feedback unit classifies the category of the feedback using, for example, a machine learning algorithm. The feedback unit can also classify the category of the feedback using a rule-based algorithm. Furthermore, the feedback unit can classify the category of the feedback using a classification algorithm. The feedback unit selects the feedback algorithm based on the classification result. For example, an algorithm that evaluates the balance of the flavor can be applied to feedback regarding taste. Furthermore, an algorithm that performs visual evaluation can be applied to feedback regarding appearance. Furthermore, an algorithm that evaluates naming can be applied to feedback regarding the name. This allows the feedback unit to apply different feedback algorithms depending on the category of the feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input feedback category data to a generation AI and cause the generation AI to select a feedback algorithm.

[0051] The feedback unit can determine the priority of feedback based on the timing of feedback submission at the time of feedback. The feedback unit determines the priority of feedback, for example, using an algorithm that evaluates the timing of feedback submission. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The feedback unit evaluates the timing of feedback submission using, for example, a machine learning algorithm. The feedback unit can also evaluate the timing of feedback submission using a rule-based algorithm. Furthermore, the feedback unit can evaluate the timing of feedback submission using an evaluation algorithm. The feedback unit determines the priority of feedback based on the evaluation result. For example, if feedback is submitted promptly, it can be accepted with priority. If feedback is normally submitted, it can be accepted with normal priority. Furthermore, if feedback is submitted late, it can be accepted at a later date. In this way, the feedback unit can determine the priority of feedback based on the timing of feedback submission. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input feedback submission timing data to a generation AI and cause the generation AI to determine the priority.

[0052] The feedback unit can adjust the order of feedback based on the relevance of the feedback at the time of feedback. The feedback unit adjusts the order of feedback, for example, using an algorithm that evaluates the relevance of the feedback. The evaluation algorithm is, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The feedback unit evaluates the relevance of feedback, for example, using a machine learning algorithm. The feedback unit can also evaluate the relevance of feedback using a rule-based algorithm. The feedback unit can also evaluate the relevance of feedback using an evaluation algorithm. The feedback unit adjusts the order of feedback based on the evaluation result. For example, if feedback is highly relevant to other feedback, it can be accepted with priority. Also, if feedback is moderately relevant to other feedback, it can be accepted with moderate priority. Furthermore, if feedback is lowly relevant to other feedback, it can be accepted later. In this way, the feedback unit can adjust the order of feedback based on the relevance of the feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input feedback relevance data to a generation AI and cause the generation AI to adjust the order.

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

[0054] When accepting a customer's request, the reception unit can refer to the customer's past order history to make more personalized suggestions. For example, for a customer who has previously ordered fruity cocktails, similar fruity cocktails can be preferentially suggested. Also, for a customer who has previously avoided a particular ingredient, cocktails that do not contain that ingredient can be suggested. Furthermore, the reception unit can analyze the customer's preference trends from the customer's past order history and reflect them in suggesting new cocktails. This allows the reception unit to make more accurate cocktail suggestions based on the customer's past order history.

[0055] When generating cocktail recipes, the generation unit can suggest special recipes according to the season or event. For example, it can suggest a refreshing fruit cocktail in the summer and a warm spice cocktail in the winter. It can also generate themed cocktails for special events such as Christmas or Halloween. Furthermore, the generation unit can suggest cocktail recipes using local specialties. This allows the generation unit to generate a variety of cocktail recipes according to the season or event.

[0056] When generating an image of a cocktail's appearance, the generation unit can provide customization options according to the user's preferences. For example, the generation unit can allow the user to select the color and decoration of the cocktail and reflect this in the generated image. The generation unit can also generate an image of a cocktail that matches a specific theme or style. Furthermore, the generation unit can customize the appearance of the cocktail based on an image uploaded by the user. This allows the generation unit to generate an image of a cocktail's appearance that is customized according to the user's preferences.

[0057] When generating a cocktail name, the generator can suggest names based on keywords entered by the user. For example, if the user enters "summer" as a keyword, the generator can generate names such as "Summer Sunset" or "Tropical Breeze." The generator can also suggest names that match specific themes or events. Furthermore, the generator can generate original cocktail names that incorporate the user's name or nickname. This allows the generator to generate unique cocktail names based on the user's input.

[0058] When receiving feedback from bartenders and customers, the feedback department automatically classifies the content of the feedback and can efficiently fine-tune the generative AI model. For example, it can classify feedback about taste, feedback about appearance, and feedback about the name separately. It can also distinguish between positive and negative feedback to clarify areas for improvement in the generative AI. Furthermore, it can select feedback to be reflected as a priority based on the frequency and importance of the feedback. This allows the feedback department to efficiently and effectively fine-tune the generative AI model.

[0059] The reception department can analyze the customer's past preference history and select the optimal reception method. For example, preferences that the customer has previously input can be automatically displayed as candidates. It can also prioritize input methods (voice, text, etc.) that the customer has used in the past. Furthermore, it can predict and suggest preferences for use during specific time periods based on the customer's past preference history. This allows the reception department to select the optimal reception method based on the customer's past preference history.

[0060] When receiving a request, the reception department can prioritize relevant requests based on the customer's geographic location information. For example, if the customer is at the beach, the reception department can prioritize requests for tropical cocktails. If the customer is in a cold climate, the reception department can prioritize requests for hot cocktails. Furthermore, if the customer is in an urban area, the reception department can prioritize requests for trendy cocktails. This allows the reception department to filter requests based on the customer's geographic location information.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The reception unit receives the customer's requests. The customer's requests may include, but are not limited to, taste preferences, allergy information, and the presence or absence of specific ingredients. The reception unit may receive the requests by, for example, text input, voice input, image input, or the like. Step 2: The analysis unit analyzes the requests received by the reception unit. The analysis is performed by, for example, text analysis, sentiment analysis, pattern recognition, or other methods, but is not limited to these examples. The analysis unit analyzes the customer's requests using, for example, a text analysis algorithm. The analysis unit can also analyze the customer's sentiment using a sentiment analysis algorithm. Furthermore, the analysis unit can analyze the patterns of the customer's requests using a pattern recognition algorithm. Step 3: The generation unit generates a cocktail based on the desires analyzed by the analysis unit. The generation may, for example, generate a cocktail recipe, an image of the appearance, and a name, but is not limited to these examples. The generation unit may, for example, generate a cocktail recipe using a generation AI. The generation unit may also generate an image of the appearance of the cocktail using an image generation algorithm. Furthermore, the generation unit may also generate a name for the cocktail using a name generation algorithm. Step 4: The suggestion unit suggests the cocktail generated by the generation unit. The suggestion may be in, for example, text format, image format, or audio format, but is not limited to these examples. For example, the suggestion unit suggests the recipe of the generated cocktail in text format. The suggestion unit can also suggest an image of the appearance of the generated cocktail in image format. Furthermore, the suggestion unit can also suggest the name of the generated cocktail in audio format. Step 5: The feedback unit receives feedback on the cocktail suggested by the suggestion unit. The feedback may be received in, for example, text format, audio format, or image format, but is not limited to these examples. For example, the feedback unit receives feedback from the bartender or customer in text format. The feedback unit may also receive feedback in audio format. The feedback unit may also receive feedback in image format.

[0063] (Example 2) A cocktail recommendation system according to an embodiment of the present invention generates and recommends cocktails based on customer preferences and receives feedback. This cocktail recommendation system uses a generative AI to suggest cocktails based on customer preferences. Specifically, a customer's preferences are first input. For example, a customer may input a preference such as "I want a fruity and sweet cocktail." This information is then input into the generative AI. The generative AI then analyzes the input preference and generates an optimal cocktail from a vast database. The generative AI then suggests a cocktail recipe, appearance, and name. For example, it proposes a cocktail called "Mango Passion" as a "fruity and sweet cocktail" and outputs an image of the cocktail's recipe and appearance. Furthermore, the generative AI model is fine-tuned based on feedback from bartenders and customers. As a result, the more the system is used, the more unique cocktails it can suggest, reflecting the bartender's characteristics and customer preferences. For example, if a customer provides feedback such as "I'd like it a little less sweet," the system can suggest a new cocktail that reflects that preference. This system solves the problem of bartenders being unable to come up with original cocktails and allows them to provide cocktails that satisfy customers. This allows the cocktail suggestion system to generate and suggest cocktails based on customer preferences and receive feedback.

[0064] A cocktail recommendation system according to an embodiment includes a reception unit, an analysis unit, a generation unit, a recommendation unit, and a feedback unit. The reception unit receives customer requests. Customer requests may include, but are not limited to, taste preferences, allergy information, and the presence or absence of specific ingredients. The reception unit may receive the requests via, for example, text input, voice input, or image input. The analysis unit analyzes the requests received by the reception unit. The analysis may be performed via, for example, text analysis, sentiment analysis, or pattern recognition, but is not limited to, the methods. The analysis unit may analyze the customer requests using, for example, a text analysis algorithm. The analysis unit may also analyze the customer's sentiment using a sentiment analysis algorithm. The analysis unit may also analyze patterns of the customer's requests using a pattern recognition algorithm. The generation unit generates a cocktail based on the requests analyzed by the analysis unit. The generation may include, for example, generating a cocktail recipe, an image of the appearance, and a name, but is not limited to, the methods. The generation unit may generate the cocktail recipe using, for example, a generation AI. The generation unit may also generate an image of the appearance of the cocktail using an image generation algorithm. Furthermore, the generation unit can generate a name for the cocktail using a name generation algorithm. The suggestion unit suggests the cocktail generated by the generation unit. The suggestion may be in text format, image format, audio format, or the like, but is not limited to these examples. The suggestion unit may, for example, suggest a recipe for the generated cocktail in text format. The suggestion unit may also suggest an image of the appearance of the generated cocktail in image format. The suggestion unit may also suggest a name for the generated cocktail in audio format. The feedback unit receives feedback on the cocktail suggested by the suggestion unit. The feedback may be in text format, audio format, image format, or the like, but is not limited to these examples. The feedback unit receives feedback from the bartender or customer in text format, for example. The feedback unit may also receive feedback in audio format. The feedback unit may also receive feedback in image format.This allows the cocktail recommendation system according to the embodiment to create and recommend cocktails based on the customer's preferences and receive feedback.

[0065] The generation unit can generate a cocktail recipe. The generation unit generates the cocktail recipe using, for example, a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the generation unit can input a prompt such as "Please generate a recipe for a fruity and sweet cocktail" to the generation AI, causing the generation AI to generate a cocktail recipe based on the prompt. The generation unit can also input a prompt such as "Please generate a recipe for a spicy cocktail" to the generation AI, causing the generation AI to generate a cocktail recipe based on the prompt. Furthermore, the generation unit can input a prompt such as "Please generate a recipe for a classic cocktail" to the generation AI, causing the generation AI to generate a cocktail recipe based on the prompt. In this way, the generation unit can generate a cocktail recipe. Some or all of the above-described processing in the generation unit may be performed using, or without, an AI. For example, the generation unit can input a prompt to the generation AI, causing the generation AI to generate a cocktail recipe.

[0066] The generation unit can generate an image of the appearance of a cocktail. The generation unit generates an image of the appearance of a cocktail using, for example, an image generation algorithm. The image generation algorithm is, for example, a generative adversarial network (GAN) or a variational autoencoder (VAE), but is not limited to these examples. The generation unit generates an image of the appearance of a cocktail using, for example, a GAN. The generation unit can also generate an image of the appearance of a cocktail using a VAE. Furthermore, the generation unit can also generate an image of the appearance of a cocktail using an image generation algorithm. For example, the generation unit can generate an image of the appearance of a "fruity and sweet cocktail" using a GAN. The generation unit can also generate an image of the appearance of a "spicy cocktail" using a VAE. Furthermore, the generation unit can generate an image of the appearance of a "classic cocktail" using an image generation algorithm. In this way, the generation unit can generate an image of the appearance of a cocktail. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate an image of the appearance of a cocktail using an image generation algorithm.

[0067] The generation unit can generate the name of the cocktail. The generation unit generates the name of the cocktail using, for example, a name generation algorithm. The name generation algorithm is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. The generation unit generates the name of the cocktail using, for example, a text generation AI. The generation unit can also generate the name of the cocktail using a multimodal generation AI. Furthermore, the generation unit can also generate the name of the cocktail using a name generation algorithm. For example, the generation unit can generate the name of a "fruity and sweet cocktail" using a text generation AI. The generation unit can also generate the name of a "spicy cocktail" using a multimodal generation AI. Furthermore, the generation unit can generate the name of a "classic cocktail" using a name generation algorithm. In this way, the generation unit can generate the name of the cocktail. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate the name of the cocktail using a name generation algorithm.

[0068] The feedback unit can receive feedback from the bartender or the customer and fine-tune the generative AI model. The feedback unit receives the feedback from the bartender or the customer in text format, for example. The feedback may be, for example, about the taste, appearance, or name of the cocktail, but is not limited to these examples. For example, the feedback unit receives feedback in text format, such as "I wish it was a little less sweet." The feedback unit can also receive feedback in audio format, such as "I wish it looked more vibrant." The feedback unit can also receive feedback in image format, such as "I like the look of this cocktail." The feedback unit fine-tunes the generative AI model based on the received feedback. Fine-tuning is performed, for example, by adjusting the parameters of the generative AI, but is not limited to these examples. For example, the feedback unit adjusts the parameters of the generative AI based on the received feedback. The feedback unit can also update the learning data of the generative AI based on the received feedback. The feedback unit can also improve the generative AI's algorithm based on the received feedback. This allows the feedback unit to fine-tune the generative AI model based on the feedback. Some or all of the above-described processing in the feedback unit may be performed using AI or without AI, for example, the feedback unit may fine-tune the model of the generative AI based on the received feedback.

[0069] The reception unit can estimate the customer's emotions and adjust the desired reception method based on the estimated customer emotions. For example, the reception unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Examples of emotion estimation algorithms include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the reception unit estimates the customer's emotions using a facial expression recognition algorithm. The reception unit can also estimate the customer's emotions using a voice analysis algorithm. Furthermore, the reception unit can estimate the customer's emotions using a text analysis algorithm. The reception unit adjusts the desired reception method based on the estimated customer emotions. For example, if the customer is relaxed, an interface can be provided that allows the customer to enter detailed preferences. Alternatively, if the customer is in a hurry, only simple options can be displayed, allowing the customer to quickly enter preferences. Furthermore, if the customer is using the service for the first time, a guided interface can be provided to support the customer in entering preferences. This allows the reception unit to adjust the desired reception method based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit may input image data of a customer captured by a camera into the generation AI and cause the generation AI to estimate the customer's emotions.

[0070] The reception unit can analyze the customer's past preference history and select the optimal reception method. For example, the reception unit retrieves the customer's past preference history from a database and selects the optimal reception method using an analysis algorithm. The analysis algorithm can be, for example, a machine learning algorithm or a data mining algorithm, but is not limited to these examples. For example, the reception unit analyzes the customer's past preference history using a machine learning algorithm. The reception unit can also analyze the customer's past preference history using a data mining algorithm. Furthermore, the reception unit can analyze the customer's past preference history using an analysis algorithm. The reception unit selects the optimal reception method based on the analysis results. For example, the reception unit can automatically display preferences entered by the customer in the past as candidates. The reception unit can also prioritize input methods (such as voice and text) that the customer has used in the past. Furthermore, the reception unit can predict and suggest preferences to be used during a specific time period based on the customer's past preference history. This allows the reception unit to select the optimal reception method based on the customer's past preference history. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input past preference history data into the generation AI and have the generation AI select the optimal reception method.

[0071] The reception unit can filter the requests based on the customer's current mood or physical condition when accepting the requests. For example, the reception unit measures the customer's current mood or physical condition using a sensor and filters the requests using a filtering algorithm. The filtering algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. For example, the reception unit filters the customer's mood or physical condition using a machine learning algorithm. The reception unit can also filter the customer's mood or physical condition using a rule-based algorithm. Furthermore, the reception unit can filter the customer's mood or physical condition using a filtering algorithm. The reception unit accepts the requests based on the filtering results. For example, if the customer is tired, the reception unit can prioritize accepting requests for refreshing cocktails. Furthermore, if the customer is energetic, the reception unit can prioritize accepting requests for energetic cocktails. Furthermore, if the customer wants to relax, the reception unit can prioritize accepting requests for cocktails with a relaxing effect. In this way, the reception unit can filter the requests based on the customer's mood or physical condition. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the customer's mood and physical condition measured by a sensor into the generation AI and have the generation AI perform filtering.

[0072] The reception unit can estimate a customer's emotions and prioritize the requests to be received based on the estimated customer's emotions. For example, the reception unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm can be, for example, facial expression recognition, voice analysis, text analysis, etc., but is not limited to these examples. For example, the reception unit estimates the customer's emotions using a facial expression recognition algorithm. The reception unit can also estimate the customer's emotions using a voice analysis algorithm. Furthermore, the reception unit can estimate the customer's emotions using a text analysis algorithm. The reception unit prioritizes the requests based on the estimated customer's emotions. For example, if a customer is feeling stressed, a request for a relaxing cocktail can be prioritized. Alternatively, if a customer is enjoying themselves, a request for a cocktail with a high level of entertainment can be prioritized. Furthermore, if a customer is in a hurry, a request for a cocktail that can be served quickly can be prioritized. This allows the reception unit to prioritize the requests based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit may input image data of a customer captured by a camera into the generation AI and cause the generation AI to estimate the customer's emotions.

[0073] When receiving a request, the reception unit can prioritize relevant requests based on the customer's geographical location information. The reception unit, for example, acquires the customer's geographical location information using location information acquisition technology such as GPS or Wi-Fi, and filters the requests using a filtering algorithm. Examples of the filtering algorithm include, but are not limited to, a machine learning algorithm or a rule-based algorithm. The reception unit filters the customer's geographical location information using, for example, a machine learning algorithm. The reception unit can also filter the customer's geographical location information using a rule-based algorithm. The reception unit can also filter the customer's geographical location information using a filtering algorithm. The reception unit receives the request based on the filtering results. For example, if the customer is at the beach, a request for a tropical cocktail can be prioritized. If the customer is in a cold region, a request for a warm cocktail can be prioritized. If the customer is in an urban area, a request for a trendy cocktail can be prioritized. This allows the reception unit to filter the requests based on the customer's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception department can input the customer's geographical location information obtained via GPS, Wi-Fi, etc. into the generation AI and have the generation AI perform filtering.

[0074] The reception unit may analyze the customer's social media activity when receiving the request and receive related requests. For example, the reception unit may obtain the customer's social media activity through an API and receive related requests using an analysis algorithm. Examples of the analysis algorithm include, but are not limited to, a text analysis algorithm and a sentiment analysis algorithm. For example, the reception unit may analyze the customer's social media activity using a text analysis algorithm. The reception unit may also analyze the customer's social media activity using a sentiment analysis algorithm. The reception unit may also analyze the customer's social media activity using an analysis algorithm. The reception unit may receive related requests based on the analysis results. For example, the reception unit may prioritize requests for similar cocktails based on photos of cocktails shared by the customer on social media. The reception unit may also prioritize related requests based on trends in cocktail bars that the customer follows on social media. The reception unit may also prioritize requests based on information about cocktails that the customer has "liked" on social media. In this way, the reception unit can receive requests based on the customer's social media activity. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception department can input customer social media data obtained through the API into the generation AI and have the generation AI perform analysis.

[0075] The analysis unit can estimate the customer's emotions and adjust the presentation method of the analysis based on the estimated customer's emotions. For example, the analysis unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Examples of emotion estimation algorithms include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the analysis unit estimates the customer's emotions using a facial expression recognition algorithm. The analysis unit can also estimate the customer's emotions using a voice analysis algorithm. Furthermore, the analysis unit can estimate the customer's emotions using a text analysis algorithm. The analysis unit adjusts the presentation method of the analysis based on the estimated customer's emotions. For example, if the customer is relaxed, a detailed analysis result can be provided. If the customer is in a hurry, a concise analysis result can be provided. Furthermore, if the customer is excited, a visually appealing analysis result can be provided. This allows the analysis unit to adjust the presentation method of the analysis based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input image data of a customer taken with a camera into the generation AI and cause the generation AI to estimate the customer's emotions.

[0076] The analysis unit can adjust the level of detail of the analysis based on the desired importance during analysis. The analysis unit adjusts the level of detail of the analysis using, for example, an algorithm for evaluating the desired importance. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The analysis unit can evaluate the desired importance using, for example, a machine learning algorithm. The analysis unit can also evaluate the desired importance using a rule-based algorithm. The analysis unit can also evaluate the desired importance using an evaluation algorithm. The analysis unit adjusts the level of detail of the analysis based on the evaluation results. For example, if the desire has high importance, a detailed analysis can be performed. If the desire has medium importance, an analysis with moderate detail can be performed. If the desire has low importance, a brief analysis can be performed. This allows the analysis unit to adjust the level of detail of the analysis based on the desired importance. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the desired importance data to the generation AI and cause the generation AI to adjust the level of detail.

[0077] The analysis unit can apply different analysis algorithms depending on the desired category during analysis. The analysis unit selects the analysis algorithm using, for example, an algorithm that classifies the desired category. The classification algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The analysis unit classifies the desired category using, for example, a machine learning algorithm. The analysis unit can also classify the desired category using a rule-based algorithm. Furthermore, the analysis unit can classify the desired category using a classification algorithm. The analysis unit selects the analysis algorithm based on the classification result. For example, if a fruity cocktail is desired, an algorithm that analyzes fruit combinations can be applied. If a spicy cocktail is desired, an algorithm that analyzes the balance of spices can be applied. If a classic cocktail is desired, an algorithm that analyzes traditional recipes can be applied. This allows the analysis unit to apply different analysis algorithms depending on the desired category. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input desired category data into the generation AI and have the generation AI select an analysis algorithm.

[0078] The analysis unit can estimate the customer's emotion and adjust the length of the analysis based on the estimated customer's emotion. For example, the analysis unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm can be, for example, facial expression recognition, voice analysis, text analysis, etc., but is not limited to these examples. For example, the analysis unit can estimate the customer's emotion using a facial expression recognition algorithm. The analysis unit can also estimate the customer's emotion using a voice analysis algorithm. Furthermore, the analysis unit can estimate the customer's emotion using a text analysis algorithm. The analysis unit adjusts the length of the analysis based on the estimated customer's emotion. For example, if the customer is relaxed, a detailed analysis can be provided. If the customer is in a hurry, a concise analysis can be provided. Furthermore, if the customer is excited, a visually appealing analysis can be provided. Thus, the analysis unit can adjust the length of the analysis based on the customer's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input image data of a customer taken with a camera into the generation AI and cause the generation AI to estimate the customer's emotions.

[0079] The analysis unit can determine the analysis priority based on the desired submission time during analysis. The analysis unit determines the analysis priority using, for example, an algorithm that evaluates the desired submission time. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The analysis unit can evaluate the desired submission time using, for example, a machine learning algorithm. The analysis unit can also evaluate the desired submission time using a rule-based algorithm. The analysis unit can also evaluate the desired submission time using an evaluation algorithm. The analysis unit determines the analysis priority based on the evaluation results. For example, if the request is submitted urgently, the analysis can be performed with priority. If the request is submitted at a normal time, the analysis can be performed with normal priority. If the request is submitted late, the analysis can be performed at a later date. This allows the analysis unit to determine the analysis priority based on the desired submission time. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the desired submission time data into the generation AI and have the generation AI determine the priority.

[0080] The analysis unit can adjust the order of analysis based on the desired relevance during analysis. The analysis unit adjusts the order of analysis using, for example, an algorithm that evaluates the desired relevance. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The analysis unit can evaluate the desired relevance using, for example, a machine learning algorithm. The analysis unit can also evaluate the desired relevance using a rule-based algorithm. Furthermore, the analysis unit can evaluate the desired relevance using an evaluation algorithm. The analysis unit adjusts the order of analysis based on the evaluation results. For example, if a desire is highly relevant to other desires, analysis can be performed with priority. Furthermore, if a desire is moderately relevant to other desires, analysis can be performed with moderate priority. Furthermore, if a desire is lowly relevant to other desires, analysis can be postponed. This allows the analysis unit to adjust the order of analysis based on the desired relevance. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the desired relevance data to the generation AI and have the generation AI adjust the order.

[0081] The generation unit can estimate the customer's emotions and adjust the type of cocktail to be generated based on the estimated customer's emotions. For example, the generation unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm can be, for example, facial expression recognition, voice analysis, text analysis, etc., but is not limited to these examples. For example, the generation unit estimates the customer's emotions using a facial expression recognition algorithm. The generation unit can also estimate the customer's emotions using a voice analysis algorithm. Furthermore, the generation unit can estimate the customer's emotions using a text analysis algorithm. The generation unit adjusts the type of cocktail to be generated based on the estimated customer's emotions. For example, if the customer is relaxed, the generation unit generates a cocktail with a relaxing effect. If the customer is in a hurry, the generation unit can generate a cocktail that can be served quickly. Furthermore, if the customer is excited, the generation unit can generate a visually appealing cocktail. This allows the generation unit to adjust the type of cocktail to be generated based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may input image data of a customer taken with a camera into the generation AI and cause the generation AI to estimate the customer's emotions.

[0082] The generation unit can adjust the level of detail of the generation based on the ingredients of the cocktail during generation. The generation unit adjusts the level of detail of the generation, for example, using an algorithm that evaluates the ingredients of the cocktail. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The generation unit can evaluate the ingredients of the cocktail using, for example, a machine learning algorithm. The generation unit can also evaluate the ingredients of the cocktail using a rule-based algorithm. Furthermore, the generation unit can evaluate the ingredients of the cocktail using an evaluation algorithm. The generation unit adjusts the level of detail of the generation based on the evaluation results. For example, if the number of ingredients is large, a detailed recipe can be generated. Also, if the number of ingredients is medium, a recipe with moderate level of detail can be generated. Furthermore, if the number of ingredients is small, a concise recipe can be generated. In this way, the generation unit can adjust the level of detail of the generation based on the ingredients of the cocktail. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input cocktail ingredient data into the generation AI and cause the generation AI to adjust the level of detail.

[0083] The generation unit can apply different generation algorithms depending on the cocktail category during generation. The generation unit selects the generation algorithm, for example, using an algorithm that classifies cocktail categories. The classification algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The generation unit classifies cocktail categories using, for example, a machine learning algorithm. The generation unit can also classify cocktail categories using a rule-based algorithm. The generation unit can also classify cocktail categories using a classification algorithm. The generation unit selects the generation algorithm based on the classification results. For example, an algorithm that generates a fruit combination can be applied to a fruity cocktail. An algorithm that generates a spice balance can be applied to a spicy cocktail. Furthermore, an algorithm that generates a traditional recipe can be applied to a classic cocktail. This allows the generation unit to apply different generation algorithms depending on the cocktail category. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input cocktail category data to the generation AI and cause the generation AI to select a generation algorithm.

[0084] The generation unit can estimate the customer's emotions and prioritize cocktails to be generated based on the estimated customer's emotions. For example, the generation unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm can be, for example, facial expression recognition, voice analysis, text analysis, etc., but is not limited to these examples. For example, the generation unit estimates the customer's emotions using a facial expression recognition algorithm. The generation unit can also estimate the customer's emotions using a voice analysis algorithm. Furthermore, the generation unit can estimate the customer's emotions using a text analysis algorithm. The generation unit prioritizes cocktails to be generated based on the estimated customer's emotions. For example, if the customer is relaxed, the generation unit prioritizes cocktails that have a relaxing effect. If the customer is in a hurry, the generation unit can prioritize cocktails that can be served quickly. Furthermore, if the customer is excited, the generation unit can prioritize cocktails that are visually appealing. This allows the generation unit to prioritize cocktails to be generated based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit may input image data of a customer captured by a camera into the generation AI and cause the generation AI to estimate the customer's emotions.

[0085] The generation unit can determine the generation priority based on the time of cocktail submission during generation. The generation unit determines the generation priority using, for example, an algorithm that evaluates the time of cocktail submission. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The generation unit can evaluate the time of cocktail submission using, for example, a machine learning algorithm. The generation unit can also evaluate the time of cocktail submission using a rule-based algorithm. The generation unit can also evaluate the time of cocktail submission using an evaluation algorithm. The generation unit determines the generation priority based on the evaluation results. For example, if a cocktail request is submitted urgently, the cocktail can be generated with priority. Also, if the cocktail request is submitted at a normal time, the cocktail can be generated with normal priority. Furthermore, if the cocktail request is submitted late, the cocktail can be generated at a later date. In this way, the generation unit can determine the generation priority based on the time of cocktail submission. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input cocktail submission time data into the generation AI and cause the generation AI to determine the priority.

[0086] The generation unit can adjust the order of cocktail generation based on the relevance of the cocktails during generation. The generation unit adjusts the order of cocktail generation, for example, using an algorithm that evaluates the relevance of the cocktails. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The generation unit can evaluate the relevance of the cocktails using, for example, a machine learning algorithm. The generation unit can also evaluate the relevance of the cocktails using a rule-based algorithm. The generation unit can also evaluate the relevance of the cocktails using an evaluation algorithm. The generation unit adjusts the order of cocktail generation based on the evaluation results. For example, if a desired cocktail is highly relevant to other desires, it can be generated with priority. Also, if a desired cocktail is moderately relevant to other desires, it can be generated with moderate priority. Furthermore, if a desired cocktail is lowly relevant to other desires, it can be generated later. In this way, the generation unit can adjust the order of cocktail generation based on the relevance of the cocktails. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input cocktail relevance data into the generation AI and cause the generation AI to adjust the order.

[0087] The suggestion unit can estimate the customer's emotion and adjust the way the suggestion is presented based on the estimated emotion. For example, the suggestion unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Examples of emotion estimation algorithms include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the suggestion unit estimates the customer's emotion using a facial expression recognition algorithm. The suggestion unit can also estimate the customer's emotion using a voice analysis algorithm. Furthermore, the suggestion unit can estimate the customer's emotion using a text analysis algorithm. The suggestion unit adjusts the way the suggestion is presented based on the estimated emotion. For example, if the customer is relaxed, a detailed suggestion can be presented. If the customer is in a hurry, a concise suggestion can be presented. Furthermore, if the customer is excited, a visually appealing suggestion can be presented. This allows the suggestion unit to adjust the way the suggestion is presented based on the customer's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input image data of a customer taken with a camera to the generation AI and cause the generation AI to estimate the customer's emotions.

[0088] The suggestion unit can adjust the level of detail of the suggestion based on the importance of the cocktail when suggesting the cocktail. The suggestion unit adjusts the level of detail of the suggestion using, for example, an algorithm for evaluating the importance of the cocktail. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The suggestion unit can evaluate the importance of the cocktail using, for example, a machine learning algorithm. The suggestion unit can also evaluate the importance of the cocktail using a rule-based algorithm. Furthermore, the suggestion unit can evaluate the importance of the cocktail using an evaluation algorithm. The suggestion unit adjusts the level of detail of the suggestion based on the evaluation result. For example, for a cocktail with high importance, a detailed suggestion can be made. For a cocktail with medium importance, a suggestion with moderate detail can be made. For a cocktail with low importance, a concise suggestion can be made. In this way, the suggestion unit can adjust the level of detail of the suggestion based on the importance of the cocktail. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input cocktail importance data to a generation AI and cause the generation AI to adjust the level of detail.

[0089] The suggestion unit can apply different suggestion algorithms depending on the cocktail category when making a suggestion. The suggestion unit selects the suggestion algorithm, for example, using an algorithm for classifying cocktail categories. The classification algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The suggestion unit can classify cocktail categories using, for example, a machine learning algorithm. The suggestion unit can also classify cocktail categories using a rule-based algorithm. The suggestion unit can also classify cocktail categories using a classification algorithm. The suggestion unit selects the suggestion algorithm based on the classification results. For example, an algorithm that suggests fruit combinations can be applied to fruity cocktails. An algorithm that suggests a balance of spices can be applied to spicy cocktails. Furthermore, an algorithm that suggests traditional recipes can be applied to classic cocktails. This allows the suggestion unit to apply different suggestion algorithms depending on the cocktail category. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input cocktail category data to a generation AI and cause the generation AI to select a suggestion algorithm.

[0090] The suggestion unit can estimate the customer's emotion and adjust the length of the suggestion based on the estimated emotion. For example, the suggestion unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm can be, for example, facial expression recognition, voice analysis, text analysis, etc., but is not limited to these examples. For example, the suggestion unit can estimate the customer's emotion using a facial expression recognition algorithm. The suggestion unit can also estimate the customer's emotion using a voice analysis algorithm. Furthermore, the suggestion unit can estimate the customer's emotion using a text analysis algorithm. The suggestion unit adjusts the length of the suggestion based on the estimated emotion of the customer. For example, if the customer is relaxed, a detailed suggestion can be made. If the customer is in a hurry, a concise suggestion can be made. Furthermore, if the customer is excited, a visually appealing suggestion can be made. Thus, the suggestion unit can adjust the length of the suggestion based on the customer's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input image data of a customer taken with a camera to the generation AI and cause the generation AI to estimate the customer's emotions.

[0091] The suggestion unit can determine the priority of the suggestions based on the time of cocktail submission when making suggestions. The suggestion unit determines the priority of the suggestions using, for example, an algorithm that evaluates the time of cocktail submission. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The suggestion unit can evaluate the time of cocktail submission using, for example, a machine learning algorithm. The suggestion unit can also evaluate the time of cocktail submission using a rule-based algorithm. The suggestion unit can also evaluate the time of cocktail submission using an evaluation algorithm. The suggestion unit determines the priority of the suggestions based on the evaluation results. For example, if a cocktail request is submitted urgently, the suggestion unit can be prioritized. Also, if a cocktail request is submitted at a normal time, the suggestion unit can be proposed with normal priority. Furthermore, if a cocktail request is submitted late, the suggestion unit can be proposed at a later time. In this way, the suggestion unit can determine the priority of the suggestions based on the time of cocktail submission. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input cocktail submission time data to a generation AI and cause the generation AI to determine the priority.

[0092] The suggestion unit can adjust the order of suggestions based on the relevance of the cocktails when suggesting them. The suggestion unit adjusts the order of suggestions using, for example, an algorithm that evaluates the relevance of the cocktails. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The suggestion unit can evaluate the relevance of the cocktails using, for example, a machine learning algorithm. The suggestion unit can also evaluate the relevance of the cocktails using a rule-based algorithm. Furthermore, the suggestion unit can evaluate the relevance of the cocktails using an evaluation algorithm. The suggestion unit adjusts the order of suggestions based on the evaluation results. For example, if a desired cocktail is highly relevant to other preferences, it can be suggested with priority. Also, if a desired cocktail is moderately relevant to other preferences, it can be suggested with moderate priority. Furthermore, if a desired cocktail is lowly relevant to other preferences, it can be suggested later. In this way, the suggestion unit can adjust the order of suggestions based on the relevance of the cocktails. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or without AI. For example, the suggestion unit can input cocktail relevance data to a generation AI and cause the generation AI to adjust the order.

[0093] The feedback unit can estimate the customer's emotion and adjust the feedback acceptance method based on the estimated customer's emotion. For example, the feedback unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm can be, for example, facial expression recognition, voice analysis, text analysis, etc., but is not limited to these examples. For example, the feedback unit can estimate the customer's emotion using a facial expression recognition algorithm. The feedback unit can also estimate the customer's emotion using a voice analysis algorithm. Furthermore, the feedback unit can estimate the customer's emotion using a text analysis algorithm. The feedback unit adjusts the feedback acceptance method based on the estimated customer's emotion. For example, if the customer is relaxed, detailed feedback can be requested. If the customer is in a hurry, brief feedback can be requested. Furthermore, if the customer is excited, a visually appealing feedback form can be provided. This allows the feedback unit to adjust the feedback acceptance method based on the customer's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input image data of a customer taken with a camera into the generation AI and cause the generation AI to estimate the customer's emotions.

[0094] The feedback unit can adjust the level of detail of the feedback by referring to past feedback data when providing feedback. The feedback unit, for example, retrieves past feedback data from a database and adjusts the level of detail of the feedback using an analysis algorithm. The analysis algorithm is, for example, a machine learning algorithm or a data mining algorithm, but is not limited to these examples. The feedback unit, for example, analyzes the past feedback data using a machine learning algorithm. The feedback unit can also analyze the past feedback data using a data mining algorithm. The feedback unit can also analyze the past feedback data using an analysis algorithm. The feedback unit adjusts the level of detail of the feedback based on the analysis results. For example, a customer who provided detailed feedback in the past can be asked to provide more detailed feedback. A customer who provided brief feedback in the past can be asked to provide brief feedback. Furthermore, the feedback unit can suggest an appropriate level of detail of the feedback based on the past feedback data. In this way, the feedback unit can adjust the level of detail of the feedback based on the past feedback data. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input past feedback data to a generation AI and cause the generation AI to adjust the level of detail.

[0095] The feedback unit can apply different feedback algorithms depending on the category of the feedback when providing feedback. The feedback unit selects the feedback algorithm using, for example, an algorithm that classifies the category of the feedback. The classification algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The feedback unit classifies the category of the feedback using, for example, a machine learning algorithm. The feedback unit can also classify the category of the feedback using a rule-based algorithm. Furthermore, the feedback unit can classify the category of the feedback using a classification algorithm. The feedback unit selects the feedback algorithm based on the classification result. For example, an algorithm that evaluates the balance of the flavor can be applied to feedback regarding taste. Furthermore, an algorithm that performs visual evaluation can be applied to feedback regarding appearance. Furthermore, an algorithm that evaluates naming can be applied to feedback regarding the name. This allows the feedback unit to apply different feedback algorithms depending on the category of the feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input feedback category data to a generation AI and cause the generation AI to select a feedback algorithm.

[0096] The feedback unit can estimate the customer's emotions and prioritize feedback based on the estimated customer's emotions. For example, the feedback unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Examples of emotion estimation algorithms include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the feedback unit estimates the customer's emotions using a facial expression recognition algorithm. The feedback unit can also estimate the customer's emotions using a voice analysis algorithm. Furthermore, the feedback unit can estimate the customer's emotions using a text analysis algorithm. The feedback unit prioritizes feedback based on the estimated customer's emotions. For example, if the customer is relaxed, detailed feedback can be given priority. If the customer is in a hurry, brief feedback can be given priority. If the customer is excited, visually appealing feedback can be given priority. This allows the feedback unit to prioritize feedback based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit may be performed using AI, or may be performed without using AI. For example, the feedback unit may input image data of a customer captured by a camera into the generation AI and cause the generation AI to estimate the customer's emotions.

[0097] The feedback unit can determine the priority of feedback based on the timing of feedback submission at the time of feedback. The feedback unit determines the priority of feedback, for example, using an algorithm that evaluates the timing of feedback submission. The evaluation algorithm can be, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The feedback unit evaluates the timing of feedback submission using, for example, a machine learning algorithm. The feedback unit can also evaluate the timing of feedback submission using a rule-based algorithm. Furthermore, the feedback unit can evaluate the timing of feedback submission using an evaluation algorithm. The feedback unit determines the priority of feedback based on the evaluation result. For example, if feedback is submitted promptly, it can be accepted with priority. If feedback is normally submitted, it can be accepted with normal priority. Furthermore, if feedback is submitted late, it can be accepted at a later date. In this way, the feedback unit can determine the priority of feedback based on the timing of feedback submission. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input feedback submission timing data to a generation AI and cause the generation AI to determine the priority.

[0098] The feedback unit can adjust the order of feedback based on the relevance of the feedback at the time of feedback. The feedback unit adjusts the order of feedback, for example, using an algorithm that evaluates the relevance of the feedback. The evaluation algorithm is, for example, a machine learning algorithm or a rule-based algorithm, but is not limited to these examples. The feedback unit evaluates the relevance of feedback, for example, using a machine learning algorithm. The feedback unit can also evaluate the relevance of feedback using a rule-based algorithm. The feedback unit can also evaluate the relevance of feedback using an evaluation algorithm. The feedback unit adjusts the order of feedback based on the evaluation result. For example, if feedback is highly relevant to other feedback, it can be accepted with priority. Also, if feedback is moderately relevant to other feedback, it can be accepted with moderate priority. Furthermore, if feedback is lowly relevant to other feedback, it can be accepted later. In this way, the feedback unit can adjust the order of feedback based on the relevance of the feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input feedback relevance data to a generation AI and cause the generation AI to adjust the order. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, suggestion unit, and feedback unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14 and accepts text input and voice input. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and performs text analysis and sentiment analysis. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates cocktail recipes and images of their appearance using a generative AI. The suggestion unit is realized by the output device 40 of the smart device 14 and displays the generated cocktail recipes and images. The feedback unit is realized by the reception device 38 of the smart device 14 and receives feedback from the bartender and customers. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, suggestion unit, and feedback unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the smart glasses 214 and accepts voice input. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and performs text analysis and sentiment analysis. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates cocktail recipes and images of their appearance using a generation AI. The suggestion unit is realized by the speaker 240 of the smart glasses 214 and suggests the recipes and names of the generated cocktails by voice. The feedback unit is realized by the microphone 238 of the smart glasses 214 and receives feedback from the bartender and customers. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, suggestion unit, and feedback unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the headset-type terminal 314 and receives voice input. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and performs text analysis and sentiment analysis. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates cocktail recipes and images of their appearance using a generation AI. The suggestion unit is realized by the display 343 of the headset-type terminal 314 and displays the generated cocktail recipes and images. The feedback unit is realized by the microphone 238 of the headset-type terminal 314 and receives feedback from the bartender and customers. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, suggestion unit, and feedback unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the robot 414 and accepts voice input. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and performs text analysis and sentiment analysis. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates cocktail recipes and images of their appearance using a generative AI. The suggestion unit is realized by the speaker 240 of the robot 414 and suggests the recipes and names of the generated cocktails by voice. The feedback unit is realized by the microphone 238 of the robot 414 and receives feedback from the bartender and customers.

[0099] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0100] When accepting a customer's request, the reception unit can refer to the customer's past order history to make more personalized suggestions. For example, for a customer who has previously ordered fruity cocktails, similar fruity cocktails can be preferentially suggested. Also, for a customer who has previously avoided a particular ingredient, cocktails that do not contain that ingredient can be suggested. Furthermore, the reception unit can analyze the customer's preference trends from the customer's past order history and reflect them in suggesting new cocktails. This allows the reception unit to make more accurate cocktail suggestions based on the customer's past order history.

[0101] When generating cocktail recipes, the generation unit can suggest special recipes according to the season or event. For example, it can suggest a refreshing fruit cocktail in the summer and a warm spice cocktail in the winter. It can also generate themed cocktails for special events such as Christmas or Halloween. Furthermore, the generation unit can suggest cocktail recipes using local specialties. This allows the generation unit to generate a variety of cocktail recipes according to the season or event.

[0102] When generating an image of a cocktail's appearance, the generation unit can provide customization options according to the user's preferences. For example, the generation unit can allow the user to select the color and decoration of the cocktail and reflect this in the generated image. The generation unit can also generate an image of a cocktail that matches a specific theme or style. Furthermore, the generation unit can customize the appearance of the cocktail based on an image uploaded by the user. This allows the generation unit to generate an image of a cocktail's appearance that is customized according to the user's preferences.

[0103] When generating a cocktail name, the generator can suggest names based on keywords entered by the user. For example, if the user enters "summer" as a keyword, the generator can generate names such as "Summer Sunset" or "Tropical Breeze." The generator can also suggest names that match specific themes or events. Furthermore, the generator can generate original cocktail names that incorporate the user's name or nickname. This allows the generator to generate unique cocktail names based on the user's input.

[0104] When receiving feedback from bartenders and customers, the feedback department automatically classifies the content of the feedback and can efficiently fine-tune the generative AI model. For example, it can classify feedback about taste, feedback about appearance, and feedback about the name separately. It can also distinguish between positive and negative feedback to clarify areas for improvement in the generative AI. Furthermore, it can select feedback to be reflected as a priority based on the frequency and importance of the feedback. This allows the feedback department to efficiently and effectively fine-tune the generative AI model.

[0105] The reception unit can estimate the customer's emotions and personalize cocktail suggestions based on the estimated customer's emotions. For example, if the customer is feeling stressed, a cocktail with a relaxing effect can be suggested. If the customer is having fun, a cocktail with a high level of entertainment can be suggested. Furthermore, if the customer is tired, a cocktail that will replenish energy can be suggested. This allows the reception unit to make more appropriate cocktail suggestions based on the customer's emotions.

[0106] The reception department can analyze the customer's past preference history and select the optimal reception method. For example, preferences that the customer has previously input can be automatically displayed as candidates. It can also prioritize input methods (voice, text, etc.) that the customer has used in the past. Furthermore, it can predict and suggest preferences for use during specific time periods based on the customer's past preference history. This allows the reception department to select the optimal reception method based on the customer's past preference history.

[0107] The reception unit can filter requests based on the customer's current mood and physical condition when accepting requests. For example, if the customer is tired, a request for a refreshing cocktail can be given priority. If the customer is energetic, a request for an energetic cocktail can be given priority. Furthermore, if the customer wants to relax, a request for a cocktail with a relaxing effect can be given priority. In this way, the reception unit can filter requests based on the customer's mood and physical condition.

[0108] The reception unit can estimate the emotions of the customer and prioritize the requests to be received based on the estimated emotions of the customer. For example, if the customer is feeling stressed, priority can be given to a request for a cocktail with a relaxing effect. Also, if the customer is having fun, priority can be given to a request for a cocktail with a high entertainment value. Furthermore, if the customer is in a hurry, priority can be given to a request for a cocktail that can be served quickly. In this way, the reception unit can prioritize requests based on the emotions of the customer.

[0109] When receiving a request, the reception department can prioritize relevant requests based on the customer's geographic location information. For example, if the customer is at the beach, the reception department can prioritize requests for tropical cocktails. If the customer is in a cold climate, the reception department can prioritize requests for hot cocktails. Furthermore, if the customer is in an urban area, the reception department can prioritize requests for trendy cocktails. This allows the reception department to filter requests based on the customer's geographic location information.

[0110] The processing flow of the second embodiment will be briefly explained below.

[0111] Step 1: The reception unit receives the customer's requests. The customer's requests may include, but are not limited to, taste preferences, allergy information, and the presence or absence of specific ingredients. The reception unit may receive the requests by, for example, text input, voice input, image input, or the like. Step 2: The analysis unit analyzes the requests received by the reception unit. The analysis is performed by, for example, text analysis, sentiment analysis, pattern recognition, or other methods, but is not limited to these examples. The analysis unit analyzes the customer's requests using, for example, a text analysis algorithm. The analysis unit can also analyze the customer's sentiment using a sentiment analysis algorithm. Furthermore, the analysis unit can analyze the patterns of the customer's requests using a pattern recognition algorithm. Step 3: The generation unit generates a cocktail based on the desires analyzed by the analysis unit. The generation may, for example, generate a cocktail recipe, an image of the appearance, and a name, but is not limited to these examples. The generation unit may, for example, generate a cocktail recipe using a generation AI. The generation unit may also generate an image of the appearance of the cocktail using an image generation algorithm. Furthermore, the generation unit may also generate a name for the cocktail using a name generation algorithm. Step 4: The suggestion unit suggests the cocktail generated by the generation unit. The suggestion may be in, for example, text format, image format, or audio format, but is not limited to these examples. For example, the suggestion unit suggests the recipe of the generated cocktail in text format. The suggestion unit can also suggest an image of the appearance of the generated cocktail in image format. Furthermore, the suggestion unit can also suggest the name of the generated cocktail in audio format. Step 5: The feedback unit receives feedback on the cocktail suggested by the suggestion unit. The feedback may be received in, for example, text format, audio format, or image format, but is not limited to these examples. For example, the feedback unit receives feedback from the bartender or customer in text format. The feedback unit may also receive feedback in audio format. The feedback unit may also receive feedback in image format.

[0112] 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.

[0113] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0114] 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.

[0115] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0116] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0117] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0119] The 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.

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

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (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).

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

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0130] 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.

[0131] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0132] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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 identification processing unit 290 using these models.

[0143] 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.

[0144] 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.

[0145] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0146] 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.

[0147] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0148] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0149] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0160] 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.

[0161] 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.

[0162] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0163] 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.

[0164] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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).

[0169] 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.

[0170] 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."

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] [Explanation of symbols]

[0184] 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 reception desk that accepts customer requests, an analysis unit that analyzes the request received by the reception unit; a cocktail preparation unit that prepares cocktails based on the desires analyzed by the analysis unit; a suggestion unit that suggests cocktails generated by the generation unit; a feedback unit that receives feedback on the cocktail suggested by the suggestion unit. A system characterized by:

2. The generation unit Generate cocktail recipes 2. The system of claim 1.

3. The generation unit Generate an image of what the cocktail looks like 2. The system of claim 1.

4. The generation unit Generate cocktail names 2. The system of claim 1.

5. The feedback unit Receive feedback from bartenders or customers to fine-tune the generative AI model 2. The system of claim 1.

6. The reception unit Infer customer sentiment and adjust preferred reception method based on estimated customer sentiment 2. The system of claim 1.

7. The reception unit Analyze the customer's past request history and select the appropriate reception method 2. The system of claim 1.

8. The reception unit Filter your desired reception based on your current mood and physical condition 2. The system of claim 1.

9. The reception unit Estimate customer emotions and prioritize requests based on the estimated emotions 2. The system of claim 1.

10. The reception unit When receiving your preferences, we use your geographic location to prioritize the most relevant preferences.

2. The system of claim 1.

Images