System

Abstract

An object of a system according to an embodiment is to provide an appropriate service according to a state of a customer and a progress status of a meal.SOLUTION: A system according to an embodiment includes an observation unit, a speech generation unit, a progress status grasping unit, and a service providing unit. The observation unit observes a state of the customer. The conversation generation unit generates a conversation based on the state of the customer observed by the observation unit. The progress status grasping unit grasps the status of the meal of the customer. The service providing unit provides a service based on the status of the meal of the customer grasped by the progress status grasping unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has made it difficult for restaurants to provide appropriate service according to the customer's condition and the progress of their meal.

[0005] The system according to the embodiment aims to provide appropriate services according to the customer's condition and the progress of their meal. [Means for solving the problem]

[0006] The system according to the embodiment includes an observation unit, a conversation generation unit, a progress status grasping unit, and a service provision unit. The observation unit observes the state of a customer. The conversation generation unit generates a conversation based on the state of the customer observed by the observation unit. The progress status grasping unit grasps the state of the customer's meal. The service provision unit provides a service based on the state of the customer's meal grasped by the progress status grasping unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide appropriate services according to the customer's condition and the progress of their meal. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The customer service system according to an embodiment of the present invention utilizes tablets installed at customer tables in restaurants, and a generation AI monitors the customer's behavior and meal status while engaging in conversation, thereby improving customer satisfaction. This allows the customer service system to observe the customer's behavior and meal status, engage in conversation at the appropriate time, and provide service.

[0029] A customer service system according to an embodiment includes an observation unit, a conversation generation unit, a progress status assessment unit, and a service provision unit. The observation unit assesses the state of a customer. For example, the observation unit uses a camera or sensor mounted on a tablet to assess the customer's facial expressions and body movements. The observation unit can also analyze the tone and speed of the customer's voice. The conversation generation unit generates a conversation based on the state of the customer assessed by the observation unit. For example, the conversation generation unit uses a generation AI to generate a conversation based on the customer's facial expressions and body movements. The conversation generation unit can also generate a conversation based on the tone and speed of the customer's voice. The progress status assessment unit assesses the state of the customer's meal. For example, the progress status assessment unit analyzes the position and amount of dishes using a camera or sensor. The progress status assessment unit can also analyze the sound of dishes and the content of conversation using voice recognition technology. The service provision unit provides a service based on the state of the customer's meal assessed by the progress status assessment unit. For example, the service provision unit suggests dessert when the customer has finished eating. The service provision unit can also suggest an additional drink. As a result, the customer service system according to the embodiment can observe the customer's state and meal situation, and can engage in conversation and provide service at appropriate times.

[0030] The observation unit can refer to a customer's past visit history and conversation history to generate individually customized conversation content. For example, the observation unit retrieves the customer's past visit history from a database and references the conversation content from the previous visit. For example, the observation unit starts a conversation with a question like, "How was the pasta last time?" The observation unit also analyzes the customer's past conversation history to identify their preferences and interests. For example, for a customer who likes sports, the observation unit offers topics such as, "Have you seen the latest game?" The observation unit also proposes special services and discounts based on the customer's visit frequency and order history. For example, the conversation proceeds in a way that suggests, "Thank you for your continued patronage. We'll offer a free dessert as a special treat today." In this way, customer satisfaction can be improved by generating individually customized conversation content based on the customer's past visit history and conversation history.

[0031] The progress status grasping unit analyzes the progress of a customer's meal using a camera, estimates the progress of the meal based on the position and amount of dishes, and can provide service at the appropriate time. The progress status grasping unit, for example, uses a camera to analyze the position and amount of dishes in real time and estimates the progress of the meal. For example, if the dishes are empty, it may suggest, "Would you like dessert?" The progress status grasping unit also analyzes the movement of the dishes to grasp the progress of the meal. For example, if the dishes are moving frequently, it may determine that the customer is still eating and refrain from serving the meal. The progress status grasping unit also analyzes the amount of dishes and estimates the progress of the meal. For example, if the amount of dishes is decreasing, it may suggest, "Would you like another drink?" In this way, customer satisfaction can be improved by analyzing the progress of a customer's meal using a camera and providing service at the appropriate time.

[0032] The progress status grasping unit can analyze the progress of a customer's meal using voice recognition technology and estimate the degree of progress of the meal from the sound of dishes being scraped and the content of conversation. The progress status grasping unit, for example, uses voice recognition technology to analyze the sound of dishes being scraped and estimate the progress of the meal. For example, if dishes are clattering, it determines that the customer is still eating. The progress status grasping unit also analyzes the content of the customer's conversation to estimate the progress of the meal. For example, if it hears a conversation such as "I'm full," it determines that the customer has finished eating. The progress status grasping unit also analyzes a combination of the sound of dishes being scraped and the content of conversation to comprehensively determine the progress of the meal. For example, if the sound of dishes being scraped becomes quieter and the conversation increases, it determines that the customer is nearing the end of the meal. In this way, customer satisfaction can be improved by analyzing the progress of a customer's meal using voice recognition technology and providing service at the appropriate time.

[0033] The progress status grasping unit can monitor the movement of dishes in real time using a sensor installed on the table to grasp the progress of the meal. The progress status grasping unit monitors the movement of dishes in real time using, for example, a sensor installed on the table. For example, if the dishes are moving frequently, it determines that the meal is still being eaten. The progress status grasping unit also analyzes the position of the dishes using the sensor to grasp the progress of the meal. For example, if the dishes are placed at the edge of the table, it determines that the meal is finished. The progress status grasping unit also builds a system that displays the progress of the meal in real time based on data obtained from the sensor. For example, it displays the progress of the meal in a graph so that staff can check it. In this way, by monitoring the movement of dishes in real time using a sensor installed on the table, it is possible to accurately grasp the progress of the meal and provide appropriate service.

[0034] The progress grasping unit can link with the customer's smartphone to grasp the meal progress, allowing the meal progress to be checked on the app. The progress grasping unit, for example, links with the customer's smartphone to make the meal progress checkable on the app. For example, the meal progress may be displayed on the app so that the customer can check it. The progress grasping unit also grasps the meal progress using the smartphone's sensors. For example, it may analyze the movement of dishes using the smartphone's acceleration sensor. The progress grasping unit also links with the smartphone to provide services according to the meal progress. For example, when the meal is finished, the app may notify the customer, "Would you like dessert?" In this way, linking with the customer's smartphone and allowing the customer to check the meal progress on the app makes it easier for the customer to grasp the progress themselves.

[0035] The service provision unit manages customer preferences and allergy information and can suggest appropriate menus. For example, the service provision unit retrieves a customer's past order history from a database and analyzes preference trends. For example, it identifies frequently ordered menu items and a tendency to prefer specific ingredients. The service provision unit also uses the customer's order history to suggest a personalized menu for the next visit. For example, it might suggest, "How about the steak you had last time?" The service provision unit also learns customer preference trends and suggests new menu items. For example, it might suggest, "Would you like to add a new sauce to your favorite pasta?" In this way, managing customer preferences and allergy information and suggesting appropriate menu items improves customer satisfaction.

[0036] The service provision department updates customer allergy information in real time, and can respond immediately when new allergy information is added. The service provision department, for example, builds a system that updates a database of customer allergy information in real time. For example, when new allergy information is added, the database is updated immediately. The service provision department also immediately suggests a corresponding menu item when a customer enters new allergy information. For example, it suggests, "Based on your new allergy information, we recommend this menu item." The service provision department also builds a system that updates allergy information in real time and notifies staff. For example, when new allergy information is added, an alert is sent to staff. In this way, customer allergy information can be updated in real time, and when new allergy information is added, a response can be made immediately, thereby improving customer safety and satisfaction.

[0037] The service providing unit can share customer preference and allergy information with other restaurants, enabling consistent service to be provided at any store. The service providing unit, for example, builds a system for sharing customer preference and allergy information with other restaurants. For example, a consistent service can be provided even when a customer visits different stores. The service providing unit also stores customer preference and allergy information in the cloud, making it accessible at any store. For example, when a customer visits a new store, service can be provided based on past information. The service providing unit also shares information with other restaurants and provides personalized service based on the customer preference and allergy information. For example, a consistent menu can be suggested even when a customer visits different chain stores. In this way, customer preference and allergy information can be shared with other restaurants, enabling consistent service to be provided at any store, thereby improving customer satisfaction.

[0038] The service provision unit can propose seasonal menus and new menus based on customer preferences and allergy information. The service provision unit proposes seasonal menus based on customer preferences and allergy information, for example, by suggesting, "How about this salad for our new spring menu?" The service provision unit also analyzes customer preferences and allergy information to propose new menus. For example, it may suggest, "Would you like to try our newly added pasta menu?" The service provision unit also takes into consideration customer preferences and allergy information when proposing seasonal menus and new menus. For example, it may suggest, "We have prepared a new menu that does not include ingredients that you are allergic to." In this way, by proposing seasonal menus and new menus based on customer preferences and allergy information, customer satisfaction can be improved.

[0039] The feedback collection unit can collect customer feedback using speech recognition technology and analyze it using natural language processing technology to extract specific areas for improvement. The feedback collection unit, for example, uses speech recognition technology to collect customer feedback. For example, it asks, "How was our service today?" and records the customer's response by voice. The feedback collection unit also uses natural language processing technology to analyze the collected feedback and extract specific areas for improvement. For example, it extracts requests such as, "I would like more dessert varieties." The feedback collection unit also combines speech recognition technology and natural language processing technology to analyze customer feedback in real time and instantly identify areas for improvement. For example, it makes a suggestion in the form of, "Many customers would like more dessert varieties." In this way, collecting customer feedback using speech recognition technology and analyzing it using natural language processing technology to extract specific areas for improvement helps improve service.

[0040] The feedback collection unit can analyze customer feedback in real time and propose countermeasures on the spot. The feedback collection unit, for example, builds a system that analyzes customer feedback in real time and proposes countermeasures on the spot. For example, it asks, "Were you satisfied with our service today?" and immediately proposes a countermeasure. The feedback collection unit also builds a system that analyzes customer feedback in real time and notifies staff. For example, it notifies staff in the form of, "Many customers would like us to offer more dessert varieties." The feedback collection unit also analyzes customer feedback in real time and immediately proposes countermeasures. For example, in response to feedback saying, "We would like more dessert varieties," it proposes, "We have added a new dessert menu item." In this way, by analyzing customer feedback in real time and proposing countermeasures on the spot, it becomes possible to quickly improve service.

[0041] The feedback collection unit can improve the quality of feedback by sharing customer feedback with other customers and eliciting sympathy. The feedback collection unit, for example, builds a system for sharing customer feedback with other customers. For example, positive feedback is displayed on an in-store display. The feedback collection unit also improves the quality of feedback by sharing feedback and eliciting sympathy from other customers. For example, sharing in the form of "Many customers would like to see more dessert varieties." The feedback collection unit also builds a system for sharing customer feedback and encouraging additional feedback from other customers. For example, displaying a question such as "Do you empathize with this feedback?" to collect additional feedback. In this way, customer feedback can be shared with other customers and elicit sympathy, improving the quality of feedback.

[0042] The feedback collection unit can periodically create reports summarizing service improvements based on customer feedback and share them with staff. The feedback collection unit, for example, builds a system that periodically creates reports summarizing service improvements based on customer feedback. For example, it compiles feedback as a monthly report. The feedback collection unit also shares the created reports with staff to share service improvements. For example, it could share information such as, "Many customers would like to see more dessert varieties." The feedback collection unit also shares the reports created based on feedback with staff to suggest improvement measures. For example, it could suggest, "Let's add a new menu item to increase the variety of desserts." In this way, by periodically creating reports summarizing service improvements based on customer feedback and sharing them with staff, the quality of service is improved.

[0043] The entertainment providing unit can learn the customer's preferences and provide personalized entertainment content. For example, the entertainment providing unit analyzes the customer's past entertainment history and learns their preferences. For example, it identifies the types of quizzes and games that the customer has enjoyed in the past and suggests new content based on that. The entertainment providing unit also provides personalized music and videos based on the customer's entertainment history. For example, it may suggest, "We'll play the sequel to the music you enjoyed last time." The entertainment providing unit also learns the customer's preferences and suggests new entertainment content. For example, it may suggest, "You can enjoy a new quiz based on your favorite genre." In this way, the entertainment providing unit learns the customer's preferences and provides personalized entertainment content, thereby improving customer satisfaction.

[0044] The entertainment providing unit can analyze customer reactions in real time and dynamically change the entertainment content. The entertainment providing unit, for example, analyzes the customer's facial expressions and body movements in real time and dynamically changes the entertainment content. For example, if the customer is smiling and enjoying themselves, it continues to provide content of the same genre. The entertainment providing unit also analyzes the tone and speed of the customer's voice and dynamically changes the entertainment content. For example, if the customer's voice is high-pitched and fast, it determines that the customer is excited and provides more stimulating content. The entertainment providing unit also builds a system that analyzes customer reactions in real time and dynamically changes the entertainment content. For example, if the customer is not interested, it switches to different content. In this way, by analyzing customer reactions in real time and dynamically changing the entertainment content, customer satisfaction is improved.

[0045] The entertainment provider can promote communication by sharing entertainment content with other customers and providing common topics of conversation. The entertainment provider, for example, builds a system for sharing entertainment content with other customers. For example, it allows multiple customers to enjoy the same quiz or game at the same time. The entertainment provider also promotes communication between customers by providing common topics of conversation. For example, it introduces the quiz by saying, "This quiz is popular at other tables too." The entertainment provider also holds events that share entertainment content and encourage interaction between customers. For example, it suggests, "We're holding a quiz competition. Let's have participants compete against each other." In this way, entertainment content can be shared with other customers and communication can be promoted by providing common topics of conversation.

[0046] The entertainment providing unit can customize entertainment content to suit seasons and events, thereby providing a special experience. For example, the entertainment providing unit customizes entertainment content to suit seasons and events. For example, at Christmas, it provides Christmas-related quizzes and games. The entertainment providing unit also suggests seasonal entertainment content to provide a special experience. For example, it suggests, "You can enjoy a quiz related to cherry blossom viewing in the spring." The entertainment providing unit also customizes entertainment content to suit events, thereby providing a special experience to the customer. For example, it suggests, "You can enjoy a Halloween-related game at Halloween." In this way, the entertainment content can be customized to suit seasons and events, providing a special experience, and improving customer satisfaction.

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

[0048] The customer service system can further include a health management unit that monitors the health condition of the customer. The health management unit, for example, measures the customer's heart rate and blood pressure and monitors the health condition in real time. For example, if the heart rate is high, it provides advice on how to relax. The health management unit can also make meal suggestions based on the customer's health data. For example, it can suggest low-salt menus to customers with high blood pressure. The health management unit can also provide advice on exercise and stretching depending on the customer's health condition. In this way, customer satisfaction can be improved by monitoring the customer's health condition and providing appropriate advice and services.

[0049] The customer service system may further include a preference learning unit that learns customer preferences. The preference learning unit may analyze a customer's past order history and feedback to learn customer preferences. For example, it may identify frequently ordered menu items and a tendency to prefer specific ingredients. The preference learning unit may also suggest new menu items based on the customer's preferences. For example, it may suggest, "Would you like to add a new sauce to your favorite pasta?" The preference learning unit may also learn customer preferences and provide personalized services. This makes it possible to improve customer satisfaction by learning customer preferences and suggesting appropriate menu items and services.

[0050] The customer service system can further include a behavior prediction unit that predicts customer behavior. The behavior prediction unit, for example, analyzes past behavioral data of customers and predicts their next behavior. For example, it predicts the next visit time and order content based on past visit times and order patterns. The behavior prediction unit can also predict customer behavior and provide appropriate services. For example, it can provide special services based on the predicted visit time. The behavior prediction unit can also predict customer behavior and suggest personalized menus. This makes it possible to predict customer behavior and provide appropriate services and menus, thereby improving customer satisfaction.

[0051] The customer service system can further include a nutrition management unit that manages the nutritional balance of a customer's meals. The nutrition management unit, for example, analyzes the customer's order and evaluates the nutritional balance. For example, it calculates the intake of calories, vitamins, and minerals. The nutrition management unit can also suggest an appropriate menu based on the customer's nutritional balance. For example, it can suggest, "You're lacking in vitamin C, so I recommend this salad." The nutrition management unit can also manage the customer's nutritional balance and suggest healthy meals. In this way, by managing the customer's nutritional balance and suggesting appropriate menus, it is possible to improve the customer's health and satisfaction.

[0052] The customer service system can further include an allergy management unit that manages customer allergy information. The allergy management unit, for example, stores customer allergy information in a database and takes the allergy information into consideration when ordering. For example, it automatically suggests menu items that do not contain ingredients that the customer is allergic to. The allergy management unit can also update customer allergy information in real time and respond immediately when new allergy information is added. For example, it can suggest, "Based on the new allergy information, we recommend this menu item." The allergy management unit can also notify staff of the allergy information and encourage them to take appropriate action. In this way, customer safety and satisfaction can be improved by managing customer allergy information and suggesting appropriate menu items.

[0053] The customer service system may further include a feedback collection unit that collects customer feedback. The feedback collection unit may use, for example, speech recognition technology to collect customer feedback. For example, it may ask, "How was our service today?" and record the customer's voice response. The feedback collection unit may also use natural language processing technology to analyze the collected feedback and extract specific areas for improvement. For example, it may extract requests such as, "Please increase the variety of desserts." The feedback collection unit may also combine speech recognition technology and natural language processing technology to analyze customer feedback in real time and instantly identify areas for improvement. In this way, collecting customer feedback and extracting specific areas for improvement can be used to improve service.

[0054] The customer service system may further include an entertainment provider that provides entertainment to customers. The entertainment provider, for example, analyzes the customer's past entertainment history and learns their preferences. For example, it identifies the types of quizzes and games that the customer has enjoyed in the past and suggests new content based on that. The entertainment provider can also provide personalized music and videos based on the customer's entertainment history. For example, it can suggest, "We'll play the sequel to the music you enjoyed last time." The entertainment provider can also learn the customer's preferences and suggest new entertainment content. This makes it possible to improve customer satisfaction by learning the customer's preferences and providing personalized entertainment content.

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

[0056] Step 1: The observation department observes the customer's behavior. For example, the observation department uses a camera and sensors installed on the tablet to observe the customer's facial expressions and body movements. The observation department can also analyze the tone and speed of the customer's voice. Step 2: The conversation generation unit generates a conversation based on the customer's behavior observed by the observation unit. For example, the conversation generation unit uses a generation AI to generate a conversation based on the customer's facial expressions and body movements. The conversation generation unit can also generate a conversation based on the tone and speed of the customer's voice. Step 3: The progress status monitoring unit monitors the customer's meal status. For example, the progress status monitoring unit may use a camera or sensor to analyze the position and amount of dishes. The progress status monitoring unit may also use voice recognition technology to analyze the sound of dishes and the content of conversations. Step 4: The service providing unit provides service based on the customer's meal status ascertained by the progress status ascertaining unit. For example, the service providing unit may suggest dessert if the customer has finished eating. The service providing unit may also suggest an additional drink.

[0057] (Example 2) The customer service system according to an embodiment of the present invention utilizes tablets installed at customer tables in restaurants, and a generation AI monitors the customer's behavior and meal status while engaging in conversation, thereby improving customer satisfaction. This allows the customer service system to observe the customer's behavior and meal status, engage in conversation at the appropriate time, and provide service.

[0058] A customer service system according to an embodiment includes an observation unit, a conversation generation unit, a progress status assessment unit, and a service provision unit. The observation unit assesses the state of a customer. For example, the observation unit uses a camera or sensor mounted on a tablet to assess the customer's facial expressions and body movements. The observation unit can also analyze the tone and speed of the customer's voice. The conversation generation unit generates a conversation based on the state of the customer assessed by the observation unit. For example, the conversation generation unit uses a generation AI to generate a conversation based on the customer's facial expressions and body movements. The conversation generation unit can also generate a conversation based on the tone and speed of the customer's voice. The progress status assessment unit assesses the state of the customer's meal. For example, the progress status assessment unit analyzes the position and amount of dishes using a camera or sensor. The progress status assessment unit can also analyze the sound of dishes and the content of conversation using voice recognition technology. The service provision unit provides a service based on the state of the customer's meal assessed by the progress status assessment unit. For example, the service provision unit suggests dessert when the customer has finished eating. The service provision unit can also suggest an additional drink. As a result, the customer service system according to the embodiment can observe the customer's state and meal situation, and can engage in conversation and provide service at appropriate times.

[0059] The observation unit can analyze the customer's facial expressions and body movements in real time, infer the customer's emotions using an emotion estimation function, and generate conversations according to those emotions. For example, the observation unit captures the customer's facial expressions with a camera and analyzes them in real time. For example, it detects facial expressions such as smiling or furrowing the brow, and infers the customer's emotions using an emotion estimation algorithm. The observation unit also detects the customer's body movements with a sensor and analyzes their movement patterns. For example, it determines whether the customer is relaxed or nervous, and adjusts the tone of the conversation based on the results. The observation unit also analyzes the tone and speed of the customer's voice to infer stress and satisfaction. For example, if the voice is high-pitched and fast, it determines that the customer is excited, and continues the conversation in a calm tone. This allows for the provision of more personalized service by generating conversations according to the customer's emotions.

[0060] The observation unit can refer to a customer's past visit history and conversation history to generate individually customized conversation content. For example, the observation unit retrieves the customer's past visit history from a database and references the conversation content from the previous visit. For example, the observation unit starts a conversation with a question like, "How was the pasta last time?" The observation unit also analyzes the customer's past conversation history to identify their preferences and interests. For example, for a customer who likes sports, the observation unit offers topics such as, "Have you seen the latest game?" The observation unit also proposes special services and discounts based on the customer's visit frequency and order history. For example, the conversation proceeds in a way that suggests, "Thank you for your continued patronage. We'll offer a free dessert as a special treat today." In this way, customer satisfaction can be improved by generating individually customized conversation content based on the customer's past visit history and conversation history.

[0061] The observation unit can analyze the tone and speed of a customer's voice to estimate stress and satisfaction levels and adjust the tone of the conversation based on that. The observation unit, for example, analyzes the tone of a customer's voice in real time to estimate their stress level. For example, if the voice is high and fast, it is determined that stress is high and the conversation proceeds in a calm tone. The observation unit also analyzes the speed of the customer's voice to estimate their satisfaction level. For example, if the voice is slow and relaxed, it offers relaxing topics. The observation unit also analyzes the combination of the tone and speed of the customer's voice to estimate their overall emotional state. For example, if the voice is low and slow, it is determined that the customer is relaxed and offers relaxed conversation. In this way, by analyzing the tone and speed of a customer's voice and estimating their stress and satisfaction levels, it is possible to provide a more appropriate conversation.

[0062] The progress status grasping unit analyzes the progress of a customer's meal using a camera, estimates the progress of the meal based on the position and amount of dishes, and can provide service at the appropriate time. The progress status grasping unit, for example, uses a camera to analyze the position and amount of dishes in real time and estimates the progress of the meal. For example, if the dishes are empty, it may suggest, "Would you like dessert?" The progress status grasping unit also analyzes the movement of the dishes to grasp the progress of the meal. For example, if the dishes are moving frequently, it may determine that the customer is still eating and refrain from serving the meal. The progress status grasping unit also analyzes the amount of dishes and estimates the progress of the meal. For example, if the amount of dishes is decreasing, it may suggest, "Would you like another drink?" In this way, customer satisfaction can be improved by analyzing the progress of a customer's meal using a camera and providing service at the appropriate time.

[0063] The progress status grasping unit can analyze the progress of a customer's meal using voice recognition technology and estimate the degree of progress of the meal from the sound of dishes being scraped and the content of conversation. The progress status grasping unit, for example, uses voice recognition technology to analyze the sound of dishes being scraped and estimate the progress of the meal. For example, if dishes are clattering, it determines that the customer is still eating. The progress status grasping unit also analyzes the content of the customer's conversation to estimate the progress of the meal. For example, if it hears a conversation such as "I'm full," it determines that the customer has finished eating. The progress status grasping unit also analyzes a combination of the sound of dishes being scraped and the content of conversation to comprehensively determine the progress of the meal. For example, if the sound of dishes being scraped becomes quieter and the conversation increases, it determines that the customer is nearing the end of the meal. In this way, customer satisfaction can be improved by analyzing the progress of a customer's meal using voice recognition technology and providing service at the appropriate time.

[0064] The progress status grasping unit analyzes the progress of a customer's meal using an emotion estimation function, estimates their level of satisfaction or dissatisfaction during the meal, and can adjust service accordingly. The progress status grasping unit, for example, analyzes the customer's facial expressions to estimate their level of satisfaction during the meal. For example, if the customer smiles frequently, it determines that the customer is satisfied and refrains from serving them. The progress status grasping unit also analyzes the tone and speed of the customer's voice to estimate their level of dissatisfaction during the meal. For example, if the customer speaks low and fast, it determines that the customer is dissatisfied and provides service accordingly. The progress status grasping unit also analyzes the customer's body movements to estimate their level of satisfaction or dissatisfaction during the meal. For example, if the customer is moving their body frequently, it determines that the customer is dissatisfied and adjusts service accordingly. In this way, customer satisfaction is improved by analyzing the customer's level of satisfaction or dissatisfaction during the meal using the emotion estimation function and providing appropriate service.

[0065] The progress status grasping unit can monitor the movement of dishes in real time using a sensor installed on the table to grasp the progress of the meal. The progress status grasping unit monitors the movement of dishes in real time using, for example, a sensor installed on the table. For example, if the dishes are moving frequently, it determines that the meal is still being eaten. The progress status grasping unit also analyzes the position of the dishes using the sensor to grasp the progress of the meal. For example, if the dishes are placed at the edge of the table, it determines that the meal is finished. The progress status grasping unit also builds a system that displays the progress of the meal in real time based on data obtained from the sensor. For example, it displays the progress of the meal in a graph so that staff can check it. In this way, by monitoring the movement of dishes in real time using a sensor installed on the table, it is possible to accurately grasp the progress of the meal and provide appropriate service.

[0066] The progress grasping unit can link with the customer's smartphone to grasp the meal progress, allowing the meal progress to be checked on the app. The progress grasping unit, for example, links with the customer's smartphone to make the meal progress checkable on the app. For example, the meal progress may be displayed on the app so that the customer can check it. The progress grasping unit also grasps the meal progress using the smartphone's sensors. For example, it may analyze the movement of dishes using the smartphone's acceleration sensor. The progress grasping unit also links with the smartphone to provide services according to the meal progress. For example, when the meal is finished, the app may notify the customer, "Would you like dessert?" In this way, linking with the customer's smartphone and allowing the customer to check the meal progress on the app makes it easier for the customer to grasp the progress themselves.

[0067] The progress status grasping unit can use the emotion estimation function to determine whether a customer is enjoying their meal, and if so, offer an additional service. The progress status grasping unit, for example, analyzes the customer's facial expressions to determine whether they are enjoying their meal. For example, if they smile a lot, it is determined that they are enjoying their meal, and an additional service is offered. The progress status grasping unit also analyzes the tone and speed of the customer's voice to determine whether they are enjoying their meal. For example, if they speak high and fast, it is determined that they are enjoying their meal, and an additional service is offered. The progress status grasping unit also analyzes the customer's body movements to determine whether they are enjoying their meal. For example, if they appear relaxed, it is determined that they are enjoying their meal, and an additional service is offered. In this way, customer satisfaction can be further improved by using the emotion estimation function to determine whether a customer is enjoying their meal, and offering an additional service if they are enjoying their meal.

[0068] The service provision unit manages customer preferences and allergy information and can suggest appropriate menus. For example, the service provision unit retrieves a customer's past order history from a database and analyzes preference trends. For example, it identifies frequently ordered menu items and a tendency to prefer specific ingredients. The service provision unit also uses the customer's order history to suggest a personalized menu for the next visit. For example, it might suggest, "How about the steak you had last time?" The service provision unit also learns customer preference trends and suggests new menu items. For example, it might suggest, "Would you like to add a new sauce to your favorite pasta?" In this way, managing customer preferences and allergy information and suggesting appropriate menu items improves customer satisfaction.

[0069] The service provision department updates customer allergy information in real time, and can respond immediately when new allergy information is added. The service provision department, for example, builds a system that updates a database of customer allergy information in real time. For example, when new allergy information is added, the database is updated immediately. The service provision department also immediately suggests a corresponding menu item when a customer enters new allergy information. For example, it suggests, "Based on your new allergy information, we recommend this menu item." The service provision department also builds a system that updates allergy information in real time and notifies staff. For example, when new allergy information is added, an alert is sent to staff. In this way, customer allergy information can be updated in real time, and when new allergy information is added, a response can be made immediately, thereby improving customer safety and satisfaction.

[0070] The service providing unit can analyze a customer's preferences and allergy information using the emotion estimation function and suggest an optimal menu based on the customer's emotional reactions during past meals. The service providing unit, for example, analyzes a customer's emotional reactions during past meals and suggests an optimal menu based on the customer's preferences and allergy information. For example, it prioritizes suggesting menus that have proven highly satisfying in the past. The service providing unit also uses the emotion estimation function to analyze a customer's preferences and allergy information and suggest a personalized menu. For example, it may suggest, "We will suggest again the menu that proved highly satisfying during your last meal." The service providing unit also suggests an optimal menu that takes allergy information into consideration based on the customer's emotional reaction data. For example, it may suggest, "We will suggest a menu that does not include ingredients that the customer is allergic to and that has proven highly satisfying in the past." In this way, customer satisfaction is improved by analyzing a customer's preferences and allergy information using the emotion estimation function and suggesting an optimal menu based on the customer's emotional reactions during past meals.

[0071] The service providing unit can share customer preference and allergy information with other restaurants, enabling consistent service to be provided at any store. The service providing unit, for example, builds a system for sharing customer preference and allergy information with other restaurants. For example, a consistent service can be provided even when a customer visits different stores. The service providing unit also stores customer preference and allergy information in the cloud, making it accessible at any store. For example, when a customer visits a new store, service can be provided based on past information. The service providing unit also shares information with other restaurants and provides personalized service based on the customer preference and allergy information. For example, a consistent menu can be suggested even when a customer visits different chain stores. In this way, customer preference and allergy information can be shared with other restaurants, enabling consistent service to be provided at any store, thereby improving customer satisfaction.

[0072] The service provision unit can propose seasonal menus and new menus based on customer preferences and allergy information. The service provision unit proposes seasonal menus based on customer preferences and allergy information, for example, by suggesting, "How about this salad for our new spring menu?" The service provision unit also analyzes customer preferences and allergy information to propose new menus. For example, it may suggest, "Would you like to try our newly added pasta menu?" The service provision unit also takes into consideration customer preferences and allergy information when proposing seasonal menus and new menus. For example, it may suggest, "We have prepared a new menu that does not include ingredients that you are allergic to." In this way, by proposing seasonal menus and new menus based on customer preferences and allergy information, customer satisfaction can be improved.

[0073] The service providing unit can use the emotion estimation function to determine whether a customer is interested in a new menu item, and if so, suggest a sample. The service providing unit, for example, analyzes the customer's facial expression to determine whether the customer is interested in a new menu item. For example, if the customer is interested, it may suggest, "Would you like to try a sample of our new menu item?" The service providing unit also analyzes the tone and speed of the customer's voice to determine whether the customer is interested in the new menu item. For example, if the customer's voice is high-pitched and fast, it may determine that the customer is interested and suggest a sample. The service providing unit also analyzes the customer's body movements to determine whether the customer is interested in the new menu item. For example, if the customer is relaxed, it may determine that the customer is interested and suggest a sample. In this way, the emotion estimation function can determine whether the customer is interested in a new menu item, and if the customer is interested, it may suggest a sample, thereby improving customer satisfaction.

[0074] The feedback collection unit can collect customer feedback using speech recognition technology and analyze it using natural language processing technology to extract specific areas for improvement. The feedback collection unit, for example, uses speech recognition technology to collect customer feedback. For example, it asks, "How was our service today?" and records the customer's response by voice. The feedback collection unit also uses natural language processing technology to analyze the collected feedback and extract specific areas for improvement. For example, it extracts requests such as, "I would like more dessert varieties." The feedback collection unit also combines speech recognition technology and natural language processing technology to analyze customer feedback in real time and instantly identify areas for improvement. For example, it makes a suggestion in the form of, "Many customers would like more dessert varieties." In this way, collecting customer feedback using speech recognition technology and analyzing it using natural language processing technology to extract specific areas for improvement helps improve service.

[0075] The feedback collection unit can analyze customer feedback in real time and propose countermeasures on the spot. The feedback collection unit, for example, builds a system that analyzes customer feedback in real time and proposes countermeasures on the spot. For example, it asks, "Were you satisfied with our service today?" and immediately proposes a countermeasure. The feedback collection unit also builds a system that analyzes customer feedback in real time and notifies staff. For example, it notifies staff in the form of, "Many customers would like us to offer more dessert varieties." The feedback collection unit also analyzes customer feedback in real time and immediately proposes countermeasures. For example, in response to feedback saying, "We would like more dessert varieties," it proposes, "We have added a new dessert menu item." In this way, by analyzing customer feedback in real time and proposing countermeasures on the spot, it becomes possible to quickly improve service.

[0076] The feedback collection unit can analyze customer feedback using an emotion estimation function, classify the feedback into positive feedback and negative feedback, and respond accordingly. For example, the feedback collection unit analyzes customer feedback using the emotion estimation function and classifies the feedback into positive feedback and negative feedback. For example, feedback with a smile is determined to be positive, and feedback with a frown is determined to be negative. The feedback collection unit also automatically generates a message expressing gratitude in response to positive feedback. For example, it sends a message such as, "We're glad you were satisfied. We look forward to your next visit." The feedback collection unit also automatically generates a message suggesting improvement measures in response to negative feedback. For example, it sends a message such as, "We apologize for the inconvenience. We hope to offer more dessert varieties next time." In this way, the quality of service is improved by analyzing customer feedback using the emotion estimation function, classifying the feedback into positive feedback and negative feedback, and responding accordingly.

[0077] The feedback collection unit can improve the quality of feedback by sharing customer feedback with other customers and eliciting sympathy. The feedback collection unit, for example, builds a system for sharing customer feedback with other customers. For example, positive feedback is displayed on an in-store display. The feedback collection unit also improves the quality of feedback by sharing feedback and eliciting sympathy from other customers. For example, sharing in the form of "Many customers would like to see more dessert varieties." The feedback collection unit also builds a system for sharing customer feedback and encouraging additional feedback from other customers. For example, displaying a question such as "Do you empathize with this feedback?" to collect additional feedback. In this way, customer feedback can be shared with other customers and elicit sympathy, improving the quality of feedback.

[0078] The feedback collection unit can periodically create reports summarizing service improvements based on customer feedback and share them with staff. The feedback collection unit, for example, builds a system that periodically creates reports summarizing service improvements based on customer feedback. For example, it compiles feedback as a monthly report. The feedback collection unit also shares the created reports with staff to share service improvements. For example, it could share information such as, "Many customers would like to see more dessert varieties." The feedback collection unit also shares the reports created based on feedback with staff to suggest improvement measures. For example, it could suggest, "Let's add a new menu item to increase the variety of desserts." In this way, by periodically creating reports summarizing service improvements based on customer feedback and sharing them with staff, the quality of service is improved.

[0079] The feedback collection unit can use the emotion estimation function to analyze the emotion of the customer when providing feedback and evaluate the reliability of the feedback. The feedback collection unit, for example, uses the emotion estimation function to analyze the emotion of the customer when providing feedback. For example, it determines that feedback given with a smile is highly reliable. The feedback collection unit also analyzes the emotion of the customer and builds a system to evaluate the reliability of the feedback. For example, it evaluates feedback given with a positive emotion as highly reliable. The feedback collection unit also evaluates the reliability of the feedback and prioritizes analysis of highly reliable feedback. For example, it identifies areas for improvement in the service based on the highly reliable feedback. In this way, by analyzing the emotion of the customer when providing feedback and evaluating the reliability of the feedback, more accurate service improvements are possible.

[0080] The entertainment providing unit can learn the customer's preferences and provide personalized entertainment content. For example, the entertainment providing unit analyzes the customer's past entertainment history and learns their preferences. For example, it identifies the types of quizzes and games that the customer has enjoyed in the past and suggests new content based on that. The entertainment providing unit also provides personalized music and videos based on the customer's entertainment history. For example, it may suggest, "We'll play the sequel to the music you enjoyed last time." The entertainment providing unit also learns the customer's preferences and suggests new entertainment content. For example, it may suggest, "You can enjoy a new quiz based on your favorite genre." In this way, the entertainment providing unit learns the customer's preferences and provides personalized entertainment content, thereby improving customer satisfaction.

[0081] The entertainment providing unit can analyze customer reactions in real time and dynamically change the entertainment content. The entertainment providing unit, for example, analyzes the customer's facial expressions and body movements in real time and dynamically changes the entertainment content. For example, if the customer is smiling and enjoying themselves, it continues to provide content of the same genre. The entertainment providing unit also analyzes the tone and speed of the customer's voice and dynamically changes the entertainment content. For example, if the customer's voice is high-pitched and fast, it determines that the customer is excited and provides more stimulating content. The entertainment providing unit also builds a system that analyzes customer reactions in real time and dynamically changes the entertainment content. For example, if the customer is not interested, it switches to different content. In this way, by analyzing customer reactions in real time and dynamically changing the entertainment content, customer satisfaction is improved.

[0082] The entertainment providing unit can use the emotion estimation function to evaluate the effectiveness of entertainment and provide optimal content. The entertainment providing unit, for example, analyzes the customer's facial expressions to evaluate the effectiveness of the entertainment. For example, if the customer smiles a lot, it determines that the content is effective and provides content of the same genre. The entertainment providing unit also analyzes the tone and speed of the customer's voice to evaluate the effectiveness of the entertainment. For example, if the customer's voice is high-pitched and fast, it determines that the content is effective and provides content of the same genre. The entertainment providing unit also analyzes the customer's body movements to evaluate the effectiveness of the entertainment. For example, if the customer appears relaxed, it determines that the content is effective and provides content of the same genre. In this way, customer satisfaction is improved by evaluating the effectiveness of entertainment and providing optimal content.

[0083] The entertainment provider can promote communication by sharing entertainment content with other customers and providing common topics of conversation. The entertainment provider, for example, builds a system for sharing entertainment content with other customers. For example, it allows multiple customers to enjoy the same quiz or game at the same time. The entertainment provider also promotes communication between customers by providing common topics of conversation. For example, it introduces the quiz by saying, "This quiz is popular at other tables too." The entertainment provider also holds events that share entertainment content and encourage interaction between customers. For example, it suggests, "We're holding a quiz competition. Let's have participants compete against each other." In this way, entertainment content can be shared with other customers and communication can be promoted by providing common topics of conversation.

[0084] The entertainment providing unit can customize entertainment content to suit seasons and events, thereby providing a special experience. For example, the entertainment providing unit customizes entertainment content to suit seasons and events. For example, at Christmas, it provides Christmas-related quizzes and games. The entertainment providing unit also suggests seasonal entertainment content to provide a special experience. For example, it suggests, "You can enjoy a quiz related to cherry blossom viewing in the spring." The entertainment providing unit also customizes entertainment content to suit events, thereby providing a special experience to the customer. For example, it suggests, "You can enjoy a Halloween-related game at Halloween." In this way, the entertainment content can be customized to suit seasons and events, providing a special experience, and improving customer satisfaction.

[0085] The entertainment providing unit can use the emotion estimation function to identify the entertainment that the customer enjoys most and provide that content preferentially. The entertainment providing unit, for example, analyzes the customer's facial expressions to identify the entertainment that the customer enjoys most. For example, if the customer smiles a lot, that content is provided preferentially. The entertainment providing unit can also analyze the tone and speed of the customer's voice to identify the entertainment that the customer enjoys most. For example, if the customer's voice is high-pitched and fast, that content is provided preferentially. The entertainment providing unit can also analyze the customer's body movements to identify the entertainment that the customer enjoys most. For example, if the customer appears relaxed, that content is provided preferentially. In this way, customer satisfaction can be improved by identifying the entertainment that the customer enjoys most and providing that content preferentially.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The customer service system can further include a health management unit that monitors the health condition of the customer. The health management unit, for example, measures the customer's heart rate and blood pressure and monitors the health condition in real time. For example, if the heart rate is high, it provides advice on how to relax. The health management unit can also make meal suggestions based on the customer's health data. For example, it can suggest low-salt menus to customers with high blood pressure. The health management unit can also provide advice on exercise and stretching depending on the customer's health condition. In this way, customer satisfaction can be improved by monitoring the customer's health condition and providing appropriate advice and services.

[0088] The customer service system may further include a preference learning unit that learns customer preferences. The preference learning unit may analyze a customer's past order history and feedback to learn customer preferences. For example, it may identify frequently ordered menu items and a tendency to prefer specific ingredients. The preference learning unit may also suggest new menu items based on the customer's preferences. For example, it may suggest, "Would you like to add a new sauce to your favorite pasta?" The preference learning unit may also learn customer preferences and provide personalized services. This makes it possible to improve customer satisfaction by learning customer preferences and suggesting appropriate menu items and services.

[0089] The customer service system can further include a behavior prediction unit that predicts customer behavior. The behavior prediction unit, for example, analyzes past behavioral data of customers and predicts their next behavior. For example, it predicts the next visit time and order content based on past visit times and order patterns. The behavior prediction unit can also predict customer behavior and provide appropriate services. For example, it can provide special services based on the predicted visit time. The behavior prediction unit can also predict customer behavior and suggest personalized menus. This makes it possible to predict customer behavior and provide appropriate services and menus, thereby improving customer satisfaction.

[0090] The customer service system may further include a stress management unit that monitors the stress level of a customer. The stress management unit may, for example, analyze the customer's facial expression or tone of voice to estimate the stress level. For example, if the customer has a furrowed brow or speaks in a high-pitched, rapid voice, it may determine that the customer is under high stress. The stress management unit may also provide relaxation advice based on the customer's stress level. For example, it may suggest deep breathing or stretching techniques. The stress management unit may also monitor the customer's stress level and provide appropriate services. This allows the system to monitor the customer's stress level and provide appropriate advice and services, thereby improving customer satisfaction.

[0091] The customer service system can further include a nutrition management unit that manages the nutritional balance of a customer's meals. The nutrition management unit, for example, analyzes the customer's order and evaluates the nutritional balance. For example, it calculates the intake of calories, vitamins, and minerals. The nutrition management unit can also suggest an appropriate menu based on the customer's nutritional balance. For example, it can suggest, "You're lacking in vitamin C, so I recommend this salad." The nutrition management unit can also manage the customer's nutritional balance and suggest healthy meals. In this way, by managing the customer's nutritional balance and suggesting appropriate menus, it is possible to improve the customer's health and satisfaction.

[0092] The customer service system can further include an allergy management unit that manages customer allergy information. The allergy management unit, for example, stores customer allergy information in a database and takes the allergy information into consideration when ordering. For example, it automatically suggests menu items that do not contain ingredients that the customer is allergic to. The allergy management unit can also update customer allergy information in real time and respond immediately when new allergy information is added. For example, it can suggest, "Based on the new allergy information, we recommend this menu item." The allergy management unit can also notify staff of the allergy information and encourage them to take appropriate action. In this way, customer safety and satisfaction can be improved by managing customer allergy information and suggesting appropriate menu items.

[0093] The customer service system may further include a feedback collection unit that collects customer feedback. The feedback collection unit may use, for example, speech recognition technology to collect customer feedback. For example, it may ask, "How was our service today?" and record the customer's voice response. The feedback collection unit may also use natural language processing technology to analyze the collected feedback and extract specific areas for improvement. For example, it may extract requests such as, "Please increase the variety of desserts." The feedback collection unit may also combine speech recognition technology and natural language processing technology to analyze customer feedback in real time and instantly identify areas for improvement. In this way, collecting customer feedback and extracting specific areas for improvement can be used to improve service.

[0094] The customer service system can further analyze customer feedback using an emotion estimation function to classify feedback into positive and negative. The feedback collection unit, for example, analyzes the customer's facial expressions and classifies feedback into positive and negative. For example, feedback with a smile is determined to be positive, and feedback with a frown is determined to be negative. The feedback collection unit can automatically generate a message expressing gratitude in response to positive feedback. For example, it can send a message such as, "We're glad you were satisfied. We look forward to your next visit." The feedback collection unit can automatically generate a message suggesting improvement measures in response to negative feedback. For example, it can send a message such as, "We apologize for the inconvenience. We hope to offer more dessert varieties next time." In this way, the quality of service can be improved by analyzing customer feedback using the emotion estimation function, classifying feedback into positive and negative, and responding accordingly.

[0095] The customer service system may further include an entertainment provider that provides entertainment to customers. The entertainment provider, for example, analyzes the customer's past entertainment history and learns their preferences. For example, it identifies the types of quizzes and games that the customer has enjoyed in the past and suggests new content based on that. The entertainment provider can also provide personalized music and videos based on the customer's entertainment history. For example, it can suggest, "We'll play the sequel to the music you enjoyed last time." The entertainment provider can also learn the customer's preferences and suggest new entertainment content. This makes it possible to improve customer satisfaction by learning the customer's preferences and providing personalized entertainment content.

[0096] The customer service system may further include an entertainment evaluation unit that evaluates the effectiveness of entertainment for a customer. The entertainment evaluation unit may, for example, analyze the customer's facial expressions to evaluate the effectiveness of the entertainment. For example, if the customer smiles frequently, it may determine that the content is effective and provide content of the same genre. The entertainment evaluation unit may also analyze the tone and speed of the customer's voice to evaluate the effectiveness of the entertainment. For example, if the customer's voice is high-pitched and fast, it may determine that the content is effective and provide content of the same genre. The entertainment evaluation unit may also analyze the customer's body movements to evaluate the effectiveness of the entertainment. For example, if the customer appears relaxed, it may determine that the content is effective and provide content of the same genre. In this way, customer satisfaction can be improved by evaluating the effectiveness of entertainment and providing optimal content.

[0097] The processing flow of the second embodiment will be briefly explained below.

[0098] Step 1: The observation department observes the customer's behavior. For example, the observation department uses a camera and sensors installed on the tablet to observe the customer's facial expressions and body movements. The observation department can also analyze the tone and speed of the customer's voice. Step 2: The conversation generation unit generates a conversation based on the customer's behavior observed by the observation unit. For example, the conversation generation unit uses a generation AI to generate a conversation based on the customer's facial expressions and body movements. The conversation generation unit can also generate a conversation based on the tone and speed of the customer's voice. Step 3: The progress status monitoring unit monitors the customer's meal status. For example, the progress status monitoring unit may use a camera or sensor to analyze the position and amount of dishes. The progress status monitoring unit may also use voice recognition technology to analyze the sound of dishes and the content of conversations. Step 4: The service providing unit provides service based on the customer's meal status ascertained by the progress status ascertaining unit. For example, the service providing unit may suggest dessert if the customer has finished eating. The service providing unit may also suggest an additional drink.

[0099] 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.

[0100] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0101] 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.

[0102] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0103] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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).

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] 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.

[0117] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

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

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

[0127] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0129] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0131] The data processing system 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.

[0132] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0133] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[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 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.

[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 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).

[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] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0144] 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.

[0145] 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.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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."

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0166] 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. an observation department that observes the customer's condition; a conversation generation unit that generates a conversation based on the state of the customer observed by the observation unit; a progress status monitoring unit that monitors the customer's meal status; a service providing unit that provides a service based on the meal status of the customer grasped by the progress status grasping unit. A system characterized by:

2. The observation unit is Analyzing the customer's facial expressions and body movements in real time, estimating the customer's emotions, and generating a conversation according to those emotions.

2. The system of claim 1.

3. The observation unit is Refer to the customer's past visit history and conversation history to generate individually customized conversation content 2. The system of claim 1.

4. The observation unit is Analyzing the tone and speed of the customer's voice to estimate the customer's stress and satisfaction level and adjust the tone of the conversation accordingly 2. The system of claim 1.

5. The progress status grasping unit The camera analyzes the customer's meal progress, estimates the progress of the meal based on the position and amount of dishes, and provides service at the appropriate time.

2. The system of claim 1.

Images