system

Abstract

We provide the system. [Solution] A data collection method for collecting customer characteristic information, A time prediction means that analyzes information obtained by a data collection means to predict the customer's table stay time, A notification means that provides customers with seat availability information based on prediction information obtained from a time prediction means, A seating guidance system that provides optimal seating and guides customers to their seats, A scheduling management system that receives and shares visit plans and personal information with the store before the customer arrives. A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional restaurant operations, the waiting time for customers is often long, accompanied by problems such as loss of sales opportunities and decline in customer satisfaction. Also, due to inefficient seat guidance, the utilization of seats in the store is not optimized, and there are problems such as increased workload.

Means for Solving the Problems

[0005] The present invention provides a system that effectively utilizes waiting time by predicting customer dwell time and providing customers with information on available seats. Specifically, the system includes a data collection means for collecting customer characteristic information, a time prediction means for analyzing the collected information to predict dwell time, a notification means for notifying customers of available seats based on the prediction information, and a seating guidance means for achieving efficient customer service by providing optimal seating guidance.

[0006] "Customer characteristic information" refers to data that shows basic attributes and behavioral patterns of customers.

[0007] "Data collection means" refers to devices and technologies used to acquire customer characteristic information, and specifically includes sensors that capture video and audio data.

[0008] "Time prediction methods" refer to techniques that analyze customer data to estimate how often customers will use a given time schedule.

[0009] A "reinforcement learning algorithm" is a machine learning technique that learns the optimal action based on feedback from the environment.

[0010] "Notification means" refers to the technologies and methods used to communicate specific information to customers.

[0011] "Seat guidance methods" refer to methods and techniques for efficiently and optimally moving customers to their seats.

[0012] A "system" is a whole mechanism in which multiple components or technologies work together to achieve a specific purpose. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a system for reducing customer waiting times and efficiently utilizing seating in restaurants. This system streamlines the customer process from entry to exit, optimizing restaurant operations.

[0035] The server uses cameras and sensors installed in the store to monitor customer movements in real time. This allows for the collection of data regarding customer arrival times and the progress of their meals. The collected data is sent to the server and used for analysis.

[0036] The data is sent to a terminal, where image recognition and voice analysis models are used to extract customer characteristics. Based on these analysis results, the terminal predicts how long customers will spend at the table. In particular, it estimates when customers will finish their meals and makes a reasonable estimate of their stay.

[0037] The server applies a reinforcement learning algorithm to further refine the collected data and prediction results. This algorithm enables highly accurate predictions of dwell time based on past customer behavior data.

[0038] Customers receive real-time notifications about available seats via their smartphones. These notifications include information such as the customer's estimated waiting time and the location of available tables. Furthermore, in-store staff can quickly and efficiently guide customers based on the optimal seating arrangement information displayed on the terminals.

[0039] This reduces waiting times, improves customer satisfaction, increases the efficiency of seating utilization in the restaurant, and maximizes restaurant sales. This invention is a groundbreaking system that enhances convenience for both customers and restaurants and enables smooth operations.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server collects video and audio data in real time from cameras and sensors placed throughout the store. This data includes customer movements and table status.

[0043] Step 2:

[0044] The terminal feeds the data received from the server into image recognition and speech analysis models. Here, customer actions and conversation content are analyzed to determine the progress of the meal and the customer's stay duration.

[0045] Step 3:

[0046] Based on the analyzed data, the server uses past visitor data and a reinforcement learning algorithm to predict the customer's table dwell time. The prediction is continuously updated.

[0047] Step 4:

[0048] Users receive information about predicted seating availability and optimal seating options from the server via their smartphone app. This allows users to enter the store efficiently.

[0049] Step 5:

[0050] The terminal displays optimal seating plans to store staff. This includes information on seating arrangements based on each customer's needs and the current occupancy rate of the store.

[0051] Step 6:

[0052] The server continuously monitors the store's situation in real time and makes adjustments to optimize seating arrangements based on predictions. This minimizes customer waiting times and improves the efficiency of store operations.

[0053] (Example 1)

[0054] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0055] In restaurants and other establishments where customers wait, the challenge is to maximize seating efficiency while minimizing customer waiting times. In particular, accurately predicting customer dwell times and providing appropriate seating guidance is essential. Providing customers with real-time information on seat availability is also crucial to increasing customer satisfaction.

[0056] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0057] In this invention, the server includes an information gathering means for collecting characteristic information of visitors, a time prediction means for analyzing the data obtained by the information gathering means and predicting the visitor's stay time, and an information provision means for providing visitors with information on seat availability based on the prediction information obtained by the time prediction means. This makes it possible to reduce the waiting time of visitors and maximize the efficiency of seat utilization.

[0058] "Information gathering means" refers to methods and technologies used to acquire characteristic information about visitors, enabling the acquisition of diverse information, including video and audio data.

[0059] "Time prediction methods" refer to techniques and technologies that analyze collected data to predict the length of time visitors will stay based on past behavioral patterns and current circumstances.

[0060] "Information provision means" refers to methods and technologies for providing visitors with information on seat availability and waiting times based on predictive information obtained through time prediction means.

[0061] "Seat allocation means" refers to methods and technologies for arranging visitors in appropriate seats based on specific conditions or predictions.

[0062] "Monitoring methods" refer to techniques and technologies used to monitor visitors' activities in real time and understand the situation.

[0063] "Analysis means" refers to methods and techniques for processing collected data and analyzing the progress of meals, etc., using image analysis models.

[0064] A "learning algorithm" refers to computational methods or mathematical models used to improve prediction accuracy based on past data.

[0065] A description of embodiments for carrying out this invention will be given.

[0066] The server uses cameras and sensors installed within the restaurant to monitor customer movements in real time. Specifically, the server collects data including customers' arrival times and the progress of their meals, and records it in a database. This data is used to reduce customer waiting times and optimize seating arrangements.

[0067] The terminal receives data transmitted from the server and extracts visitor characteristics using image recognition and speech analysis models. These models utilize Python libraries such as OpenCV and TENSORFLOW®. The terminal also predicts customer dwell time based on the extracted information and applies reinforcement learning algorithms to improve prediction accuracy. This enables highly accurate predictions based on past visitor data.

[0068] Visitors, as users, receive real-time notifications about seat availability and waiting times via their mobile devices. This notification feature allows visitors to choose the optimal time to visit based on the store's congestion. For example, a customer might receive a notification via the app stating, "The current waiting time is 15 minutes. A window table will be available in 10 minutes."

[0069] An example of a prompt for a generative AI model might be: "Please describe the details of a system that accurately predicts customer dwell time in a restaurant and optimizes store operations."

[0070] In this way, the invention improves customer satisfaction and maximizes the operational efficiency of the store.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The server automatically detects visitors entering the store using cameras and sensors installed inside. Inputs include video data from the cameras and motion detection data from the sensors. The server analyzes this data to produce output that records the number of visitors and their arrival times. Specifically, when a visitor enters the store, the camera captures video and the sensor detects their movement.

[0074] Step 2:

[0075] The server continuously monitors the progress of the guests' meals. This input data consists of video from cameras and audio from microphones. The server uses an image recognition model to determine the progress of the meal and obtains output that analyzes which stage the meal is in. For example, it can determine whether a guest has finished their main course and is preparing dessert.

[0076] Step 3:

[0077] The terminal receives visitor characteristic information transmitted from the server and performs further detailed analysis. This input consists of analytical information about the visitor's actions and conversations. Using a speech analysis model, the terminal analyzes the length and content of the visitor's conversation and obtains an output that predicts the length of stay. Specifically, if a visitor says something like, "Shall we head home now?", an early departure is predicted.

[0078] Step 4:

[0079] The server uses time prediction tools and reinforcement learning algorithms to more accurately predict visitor dwell times. The input consists of past visitor data and current feature information. The server processes this data comprehensively, updating the prediction model to obtain an output that derives a more accurate dwell time. This enables future behavior prediction based on past behavior.

[0080] Step 5:

[0081] Visitors, as users, receive current waiting times and seat availability information via their mobile devices. This input is predictive information from the device. Users receive output via notifications to determine the optimal time to visit. Specifically, the app receives a notification stating, "A window seat will become available in 10 minutes."

[0082] Step 6:

[0083] The server determines the optimal seating arrangement based on information from the terminals and sends instructions to the store staff. This includes input data such as the expected arrival time of visitors and seat availability. The server processes this data to produce an output that proposes a seating arrangement plan. As a result, staff can quickly guide visitors to appropriate seats.

[0084] (Application Example 1)

[0085] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0086] Restaurants and other commercial establishments are required to reduce customer waiting times and efficiently utilize seating. However, traditional methods make it difficult to accurately understand customer behavior, posing challenges to seating arrangements and optimizing store operations. Furthermore, it is difficult to understand customer needs and preferences before their visit, potentially leading to decreased customer satisfaction.

[0087] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0088] In this invention, the server includes data collection means for collecting customer characteristic information, time prediction means for analyzing the information obtained by the data collection means and predicting the customer's table stay time, notification means for providing customers with seat availability information based on the prediction information obtained by the time prediction means, and schedule management means for receiving visit schedules and personal information before the visit and linking them to the store. This makes it possible to reduce customer waiting times and improve the operational efficiency of the store.

[0089] "Customer characteristic information" refers to individual data related to customers, such as video and audio, and includes information such as age group, gender, and preferences.

[0090] "Data collection means" refers to devices and methods that acquire information from external sources using sensors and cameras, and are responsible for collecting characteristic information about customers.

[0091] "Time prediction means" refers to algorithms and devices that analyze customer behavior based on collected data and estimate, in particular, the time spent at a table.

[0092] "Notification methods" refer to methods and technologies for informing customers or staff based on analysis results and predictive information, and include functions such as providing information on available seats and waiting times.

[0093] "Seat guidance methods" refer to systems and processes for guiding customers to appropriate seats, contributing to the efficiency of store operations.

[0094] "Schedule management means" refers to methods and devices for registering visit schedules and individual requests received from customers in advance into a system, and using that information when they visit the store.

[0095] The system of this invention is configured to efficiently collect customer characteristic information and optimize store operations. It mainly consists of the following components:

[0096] First, the server collects video and audio data using multiple cameras and sensors installed in the store. This data is processed through image recognition libraries such as OpenCV to extract customer characteristics. This provides the basic information necessary to predict customer dwell time.

[0097] Next, the collected data is analyzed using a time prediction tool designed with Python. Based on past customer data, a reinforcement learning algorithm is applied to predict dwell time with high accuracy. This prediction takes into account planned visits and individual customer preferences.

[0098] On the other hand, users use their smartphones to input personal information such as visit schedules and allergy information into the application. This information is transmitted to a server via Bluetooth or Wi-Fi and functions as a schedule management tool.

[0099] Furthermore, the server notifies customers of available seats and optimal arrival times based on predicted dwell time and current store congestion. Users can receive this information in real time through the application, and store staff can also obtain the information via terminals to guide customers to the best seats.

[0100] For example, when a customer enters their scheduled visit into the app, the in-store system prepares a table according to their expected arrival time. Furthermore, if a customer is accompanied by children, the system can issue instructions to the terminal to set up appropriate equipment (such as a child seat) based on specific requests.

[0101] Examples of prompts for the generating AI model include: "We are visiting the restaurant with our family. We have requests regarding seating arrangements and child-friendly facilities. Please tell us how we can ensure a smooth experience upon arrival." This allows for the provision of more flexible and customer-satisfying services.

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The server receives video and audio data from cameras and sensors. The input is real-time video and audio from inside the store. The server analyzes this data using the OpenCV library to extract customer characteristic information. The output is data on customer attributes and behavioral characteristics.

[0105] Step 2:

[0106] The server uses the customer characteristic information obtained in Step 1 to perform analysis using a time prediction method. The input is customer characteristic information. Using a reinforcement learning algorithm, it compares this with past data to predict the length of stay. The output is the customer's predicted length of stay.

[0107] Step 3:

[0108] Users enter their visit schedule and personal information into the application using their smartphones. This input includes the planned date and time of visit and any special requests. The device transmits this information to the server via Bluetooth or Wi-Fi. The reservation information is then registered on the server as output.

[0109] Step 4:

[0110] The server combines the predicted dwell time and visit schedule information from step 2 to assess the congestion level at the site. The inputs are the predicted dwell time and reservation information. It calculates the optimal availability information for the customer and determines what information should be notified. The output is appropriate availability information.

[0111] Step 5:

[0112] The server notifies users in real time based on the vacancy information generated in step 4. The input is vacancy information. The server provides users with information such as estimated waiting times and optimal arrival times through a smartphone application. The output is notification information.

[0113] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0114] This invention is a system that enhances the customer experience by incorporating an emotion engine that recognizes user emotions, in addition to conventional customer management systems. This system aims to improve the operational efficiency of restaurants and increase customer satisfaction by understanding the emotional state of customers.

[0115] The server uses multiple sensors (such as cameras and microphones) installed in the store to collect customer image and audio data in real time. The collected data is analyzed by an emotion engine within the server to evaluate the customer's facial expressions and tone of voice and infer their current emotional state.

[0116] The terminal utilizes emotional data analyzed by an emotion engine to improve the accuracy of predicting customer dwell time. This can be applied, for example, by shortening the predicted dwell time if the customer appears restless. Furthermore, by suggesting personalized service based on the customer's emotional state, it provides a more comfortable dining experience.

[0117] Customers, as users, benefit from services that are dynamically delivered based on their own emotions. For example, if a customer expresses dissatisfaction or frustration, instructions for quick follow-up are provided to staff from their device. This allows staff to respond appropriately and reduce customer stress.

[0118] Overall, this system aims to improve seating efficiency and enhance customer satisfaction by combining real-time sentiment analysis with dwell time prediction. Using this embodiment of the invention, restaurants can provide services that take customer emotions into account, resulting in a higher level of customer experience.

[0119] The following describes the processing flow.

[0120] Step 1:

[0121] The server collects video and audio data in real time from cameras and microphones installed in the store. This data includes features that indicate customers' emotions, such as their facial expressions and tone of voice.

[0122] Step 2:

[0123] The device analyzes the data received by its emotion engine to evaluate the customer's emotional state. Specifically, it uses image recognition to detect facial expressions such as smiles and anger, and evaluates voice tone and speaking style through voice analysis.

[0124] Step 3:

[0125] The server performs time predictions to forecast the customer's table stay based on the results of sentiment analysis. Prediction accuracy is improved by considering the impact of emotional state on customer behavior.

[0126] Step 4:

[0127] Users receive real-time notifications through a smartphone app, based on their emotional state and seat availability. For example, if they are in a relaxed state, they may receive specific suggestions such as being recommended a slower service.

[0128] Step 5:

[0129] The terminal instructs staff to assign the most appropriate seating based on the customer's emotional state. If the customer expresses dissatisfaction, it promptly issues instructions to provide service.

[0130] Step 6:

[0131] The server integrates and monitors all data, including store conditions, in real time, and makes adjustments as needed to optimize seating efficiency. This aims to maximize customer satisfaction.

[0132] (Example 2)

[0133] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0134] In today's service industry, meticulous attention to each customer's individual circumstances and needs is required to improve customer satisfaction. However, previous customer management systems lacked the ability to analyze customers' emotional states in real time and link that analysis to service delivery, making it difficult to maximize the customer experience.

[0135] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0136] In this invention, the server includes a data acquisition means for collecting biometric information, an emotion analysis means for analyzing the biometric information obtained by the data acquisition means and inferring the customer's emotional state, and a dwell time prediction means for predicting the customer's table dwell time based on the emotion data obtained by the emotion analysis means. This makes it possible to provide personalized services based on the customer's emotional state.

[0137] "Biometric information" refers to data about a customer's physical condition, specifically including information such as facial expressions and tone of voice.

[0138] "Data acquisition means" refers to the process of using sensors and devices installed to collect biometric information from customers.

[0139] "Emotional analysis means" refers to the processing and algorithms used to infer and evaluate a customer's emotional state based on acquired biometric information.

[0140] A "stay-time prediction method" is a technique that uses data obtained through sentiment analysis to predict how long customers will stay at a service facility.

[0141] A "personalized service system" is a system that adjusts and provides service content in order to deliver services tailored to the emotional state of each individual customer.

[0142] To implement this invention, the server first collects customer biometric information using hardware such as multiple sensor devices installed in the store, including high-resolution cameras and highly sensitive microphones. The server then inputs this data into a software engine for emotion analysis and performs the analysis. This analysis combines image processing algorithms and voice analysis algorithms to evaluate the customer's facial expressions and tone of voice in real time and estimate their emotional state.

[0143] The terminal, once it infers the customer's emotional state, runs a model that predicts the length of stay based on that data. This model applies machine learning algorithms based on past data to recognize customer behavior patterns and improve prediction accuracy. The terminal also provides customized services to the customer based on the predicted length of stay and emotional state. This includes menu suggestions tailored to the specific customer's emotional state and instructions for staff.

[0144] Users, or customers, can benefit from personalized services tailored to their emotions. For example, if a customer's emotions are "dissatisfied" or "frustrated," the system will send a prompt follow-up instruction to the staff. In this way, customers can enjoy a more comfortable service experience with less stress.

[0145] For example, once a customer enters a restaurant and takes their seat, a server analyzes their emotions based on data collected by a camera and microphone. If the customer is relaxed, a typical length of stay is predicted, and appropriate dishes are suggested. On the other hand, if the customer is clearly showing signs of irritation, staff are instructed to speak to them immediately.

[0146] An example of a specific prompt for a generative AI model would be: "Explain what kind of service a restaurant customer will receive based on sentiment analysis using data collected through cameras and microphones."

[0147] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0148] Step 1:

[0149] The server collects customer image and audio data using sensors such as cameras and microphones installed within the store. In this collection process, cameras capture the customer's face and microphones record their speech. The input is images and audio obtained from biosensors, and the output is raw data that can be analyzed.

[0150] Step 2:

[0151] The server inputs the collected image and audio data into the emotion analysis engine. There, it uses image processing technology to analyze facial expressions and infer which emotion category the expression belongs to. Simultaneously, it uses audio signal processing technology to analyze the tone and pitch of the voice to infer the customer's emotional state in more detail. The input is the raw data obtained in step 1, and the output is the inferred emotional state information.

[0152] Step 3:

[0153] The terminal executes an algorithm that predicts dwell time based on emotional state information received from the server. This process utilizes historical data and machine learning models to predict how long customers will spend in the store. The input is emotional state information, and the output is the predicted dwell time.

[0154] Step 4:

[0155] The terminal provides customized services to customers based on inferred emotional state information and predicted length of stay. For example, if a customer is relaxed, standard service is provided, along with menu suggestions as needed. On the other hand, if a customer is dissatisfied, prompt staff intervention is instructed. The input is the information obtained in steps 2 and 3, and the output is specific service instructions.

[0156] Step 5:

[0157] Users receive the services provided, and their satisfaction improves throughout the overall customer experience. For users, the optimization of the service according to their individual circumstances provides greater convenience and comfort. The input is the service provided from the device, and the output is the improved customer experience and satisfaction.

[0158] (Application Example 2)

[0159] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0160] The challenge lies in achieving efficient store operations and a high level of customer satisfaction by considering the emotional state of customers. Traditional customer management systems struggle to accurately reflect customer emotions in their service delivery, potentially leading to decreased customer satisfaction. Furthermore, accurately predicting customer dwell time is necessary to optimize resource allocation within the store, but this too does not take emotions into account.

[0161] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0162] In this invention, the server includes data collection means for collecting customer characteristic information, emotion analysis means for analyzing video and audio data acquired by the data collection means to recognize the customer's emotional state, and time prediction means for predicting the customer's table stay time based on the emotion information obtained by the emotion analysis means. This enables efficient store operations that reflect the customer's emotional state in real time and the provision of personalized services.

[0163] "Customer characteristic information" refers to data such as a customer's gender, age, facial expression, and tone of voice, which is used to identify individual customers and infer their emotional state.

[0164] "Data collection means" refers to a system that includes sensors such as cameras and microphones for acquiring characteristic information about customers.

[0165] "Emotion analysis means" refers to means that analyze video and audio data collected by data collection means and perform processing to recognize the customer's emotional state.

[0166] A "time prediction method" is a method that uses machine learning algorithms to predict the time a customer will spend at a table, based on their emotional state.

[0167] A "notification means" is an interface for providing relevant information to customers based on predictive information obtained by a time prediction means.

[0168] A "seat guidance system" is a method that utilizes predictive information to guide customers to the most suitable seats.

[0169] To implement this invention, it is necessary to build a system in which a server and a terminal work together. The server collects data in real time from cameras and microphones installed in the store. This uses the OpenCV image processing library and the Librosa audio processing library. The cameras capture the customer's facial expressions, and the microphones capture the tone of their voices. This data is sent to the server, where a machine learning model using TensorFlow as an emotion analysis tool infers the customer's emotional state from their facial expressions and voice tone.

[0170] The terminal receives sentiment information transmitted from the server and uses it to perform a time prediction system that predicts the customer's table dwell time. This information is processed by a Python®-based program and communicated to staff via a notification system. The notification is displayed as a smartphone application, creating an environment where staff can respond quickly to customers.

[0171] Store staff, as users, can improve the customer experience by checking the emotional state and recommended actions presented by the device and providing appropriate service that is attentive to the customer's emotions.

[0172] For example, if a customer is frustrated after waiting for a long time, the application can recommend that staff offer a free dessert. This recommendation is based on the results of an emotion analysis model, and an example of a prompt used by the generative AI model might be, "Please tell us what actions would be effective in alleviating the customer's frustration."

[0173] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0174] Step 1:

[0175] The server collects customer video and audio data in real time from cameras and microphones installed in the store. The input is data from the cameras and microphones, which is acquired to form the initial dataset. The video data is temporarily stored in memory for future processing.

[0176] Step 2:

[0177] The server analyzes the collected video data using OpenCV to extract customer facial features. The input is the image data acquired in step 1, which is processed by an image processing algorithm to obtain facial landmarks and facial feature vectors as output. These facial features are used in subsequent emotion analysis.

[0178] Step 3:

[0179] The server analyzes the audio data using Librosa and extracts features from the customer's voice tone. The input is the audio data acquired in step 1, and it outputs audio feature vectors such as pitch and volume level from the audio signal. These audio features are also used for sentiment analysis.

[0180] Step 4:

[0181] The server uses TensorFlow to integrate the extracted facial and vocal features and apply them to an emotion analysis model. The input is the feature vector obtained in steps 2 and 3, which is then input into the emotion analysis model, and the output is an estimate of the customer's current emotional state.

[0182] Step 5:

[0183] The terminal receives emotional state information sent from the server and executes a time prediction algorithm to predict the customer's table stay time. The input is emotional state information provided by the server, and the output is the calculation of the predicted stay time. This provides time management information useful for store operations.

[0184] Step 6:

[0185] The store staff, acting as users, decide on actions to provide appropriate service based on the emotional state and predicted dwell time presented by the terminal. Using prompts output by the generative AI model, quick and appropriate responses become possible.

[0186] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0187] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0188] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0189] [Second Embodiment]

[0190] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0191] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0192] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0193] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0194] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0195] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0196] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0197] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0198] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0199] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0200] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0201] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0202] This invention is a system for reducing customer waiting times and efficiently utilizing seating in restaurants. This system streamlines the customer process from entry to exit, optimizing restaurant operations.

[0203] The server uses cameras and sensors installed in the store to monitor customer movements in real time. This allows for the collection of data regarding customer arrival times and the progress of their meals. The collected data is sent to the server and used for analysis.

[0204] The data is sent to a terminal, where image recognition and voice analysis models are used to extract customer characteristics. Based on these analysis results, the terminal predicts how long customers will spend at the table. In particular, it estimates when customers will finish their meals and makes a reasonable estimate of their stay.

[0205] The server applies a reinforcement learning algorithm to further refine the collected data and prediction results. This algorithm enables highly accurate predictions of dwell time based on past customer behavior data.

[0206] Customers receive real-time notifications about available seats via their smartphones. These notifications include information such as the customer's estimated waiting time and the location of available tables. Furthermore, in-store staff can quickly and efficiently guide customers based on the optimal seating arrangement information displayed on the terminals.

[0207] This reduces waiting times, improves customer satisfaction, increases the efficiency of seating utilization in the restaurant, and maximizes restaurant sales. This invention is a groundbreaking system that enhances convenience for both customers and restaurants and enables smooth operations.

[0208] The following describes the processing flow.

[0209] Step 1:

[0210] The server collects video and audio data in real time from cameras and sensors placed throughout the store. This data includes customer movements and table status.

[0211] Step 2:

[0212] The terminal feeds the data received from the server into image recognition and speech analysis models. Here, customer actions and conversation content are analyzed to determine the progress of the meal and the customer's stay duration.

[0213] Step 3:

[0214] Based on the analyzed data, the server uses past visitor data and a reinforcement learning algorithm to predict the customer's table dwell time. The prediction is continuously updated.

[0215] Step 4:

[0216] Users receive information about predicted seating availability and optimal seating options from the server via their smartphone app. This allows users to enter the store efficiently.

[0217] Step 5:

[0218] The terminal displays optimal seating plans to store staff. This includes information on seating arrangements based on each customer's needs and the current occupancy rate of the store.

[0219] Step 6:

[0220] The server continuously monitors the store's situation in real time and makes adjustments to optimize seating arrangements based on predictions. This minimizes customer waiting times and improves the efficiency of store operations.

[0221] (Example 1)

[0222] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0223] In restaurants and other establishments where customers wait, the challenge is to maximize seating efficiency while minimizing customer waiting times. In particular, accurately predicting customer dwell times and providing appropriate seating guidance is essential. Providing customers with real-time information on seat availability is also crucial to increasing customer satisfaction.

[0224] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0225] In this invention, the server includes an information gathering means for collecting characteristic information of visitors, a time prediction means for analyzing the data obtained by the information gathering means and predicting the visitor's stay time, and an information provision means for providing visitors with information on seat availability based on the prediction information obtained by the time prediction means. This makes it possible to reduce the waiting time of visitors and maximize the efficiency of seat utilization.

[0226] "Information gathering means" refers to methods and technologies used to acquire characteristic information about visitors, enabling the acquisition of diverse information, including video and audio data.

[0227] "Time prediction methods" refer to techniques and technologies that analyze collected data to predict the length of time visitors will stay based on past behavioral patterns and current circumstances.

[0228] "Information provision means" refers to methods and technologies for providing visitors with information on seat availability and waiting times based on predictive information obtained through time prediction means.

[0229] "Seat allocation means" refers to methods and technologies for arranging visitors in appropriate seats based on specific conditions or predictions.

[0230] "Monitoring methods" refer to techniques and technologies used to monitor visitors' activities in real time and understand the situation.

[0231] "Analysis means" refers to methods and techniques for processing collected data and analyzing the progress of meals, etc., using image analysis models.

[0232] A "learning algorithm" refers to computational methods or mathematical models used to improve prediction accuracy based on past data.

[0233] A description of embodiments for carrying out this invention will be given.

[0234] The server uses cameras and sensors installed within the restaurant to monitor customer movements in real time. Specifically, the server collects data including customers' arrival times and the progress of their meals, and records it in a database. This data is used to reduce customer waiting times and optimize seating arrangements.

[0235] The terminal receives data sent from the server and extracts visitor characteristics using image recognition and speech analysis models. These models utilize Python libraries such as OpenCV and TensorFlow. The terminal also predicts customer dwell time based on the extracted information and applies reinforcement learning algorithms to improve prediction accuracy. This enables highly accurate predictions based on past visitor data.

[0236] Visitors, as users, receive real-time notifications about seat availability and waiting times via their mobile devices. This notification feature allows visitors to choose the optimal time to visit based on the store's congestion. For example, a customer might receive a notification via the app stating, "The current waiting time is 15 minutes. A window table will be available in 10 minutes."

[0237] An example of a prompt for a generative AI model might be: "Please describe the details of a system that accurately predicts customer dwell time in a restaurant and optimizes store operations."

[0238] In this way, the invention improves customer satisfaction and maximizes the operational efficiency of the store.

[0239] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0240] Step 1:

[0241] The server automatically detects visitors entering the store using cameras and sensors installed inside. Inputs include video data from the cameras and motion detection data from the sensors. The server analyzes this data to produce output that records the number of visitors and their arrival times. Specifically, when a visitor enters the store, the camera captures video and the sensor detects their movement.

[0242] Step 2:

[0243] The server continuously monitors the progress of the guests' meals. This input data consists of video from cameras and audio from microphones. The server uses an image recognition model to determine the progress of the meal and obtains output that analyzes which stage the meal is in. For example, it can determine whether a guest has finished their main course and is preparing dessert.

[0244] Step 3:

[0245] The terminal receives visitor characteristic information transmitted from the server and performs further detailed analysis. This input consists of analytical information about the visitor's actions and conversations. Using a speech analysis model, the terminal analyzes the length and content of the visitor's conversation and obtains an output that predicts the length of stay. Specifically, if a visitor says something like, "Shall we head home now?", an early departure is predicted.

[0246] Step 4:

[0247] The server uses time prediction tools and reinforcement learning algorithms to more accurately predict visitor dwell times. The input consists of past visitor data and current feature information. The server processes this data comprehensively, updating the prediction model to obtain an output that derives a more accurate dwell time. This enables future behavior prediction based on past behavior.

[0248] Step 5:

[0249] Visitors, as users, receive current waiting times and seat availability information via their mobile devices. This input is predictive information from the device. Users receive output via notifications to determine the optimal time to visit. Specifically, the app receives a notification stating, "A window seat will become available in 10 minutes."

[0250] Step 6:

[0251] The server determines the optimal seating arrangement based on information from the terminals and sends instructions to the store staff. This includes input data such as the expected arrival time of visitors and seat availability. The server processes this data to produce an output that proposes a seating arrangement plan. As a result, staff can quickly guide visitors to appropriate seats.

[0252] (Application Example 1)

[0253] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0254] Restaurants and other commercial establishments are required to reduce customer waiting times and efficiently utilize seating. However, traditional methods make it difficult to accurately understand customer behavior, posing challenges to seating arrangements and optimizing store operations. Furthermore, it is difficult to understand customer needs and preferences before their visit, potentially leading to decreased customer satisfaction.

[0255] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0256] In this invention, the server includes data collection means for collecting customer characteristic information, time prediction means for analyzing the information obtained by the data collection means and predicting the customer's table stay time, notification means for providing customers with seat availability information based on the prediction information obtained by the time prediction means, and schedule management means for receiving visit schedules and personal information before the visit and linking them to the store. This makes it possible to reduce customer waiting times and improve the operational efficiency of the store.

[0257] "Customer characteristic information" refers to individual data related to customers, such as video and audio, and includes information such as age group, gender, and preferences.

[0258] "Data collection means" refers to devices and methods that acquire information from external sources using sensors and cameras, and are responsible for collecting characteristic information about customers.

[0259] "Time prediction means" refers to algorithms and devices that analyze customer behavior based on collected data and estimate, in particular, the time spent at a table.

[0260] "Notification methods" refer to methods and technologies for informing customers or staff based on analysis results and predictive information, and include functions such as providing information on available seats and waiting times.

[0261] "Seat guidance methods" refer to systems and processes for guiding customers to appropriate seats, contributing to the efficiency of store operations.

[0262] "Schedule management means" refers to methods and devices for registering visit schedules and individual requests received from customers in advance into a system, and using that information when they visit the store.

[0263] The system of this invention is configured to efficiently collect customer characteristic information and optimize store operations. It mainly consists of the following components:

[0264] First, the server collects video and audio data using multiple cameras and sensors installed in the store. This data is processed through image recognition libraries such as OpenCV to extract customer characteristics. This provides the basic information necessary to predict customer dwell time.

[0265] Next, the collected data is analyzed using a time prediction tool designed with Python. Based on past customer data, a reinforcement learning algorithm is applied to predict dwell time with high accuracy. This prediction takes into account planned visits and individual customer preferences.

[0266] On the other hand, users use their smartphones to input personal information such as visit schedules and allergy information into the application. This information is transmitted to a server via Bluetooth or Wi-Fi and functions as a schedule management tool.

[0267] Furthermore, the server notifies customers of available seats and optimal arrival times based on predicted dwell time and current store congestion. Users can receive this information in real time through the application, and store staff can also obtain the information via terminals to guide customers to the best seats.

[0268] For example, when a customer enters their scheduled visit into the app, the in-store system prepares a table according to their expected arrival time. Furthermore, if a customer is accompanied by children, the system can issue instructions to the terminal to set up appropriate equipment (such as a child seat) based on specific requests.

[0269] Examples of prompts for the generating AI model include: "We are visiting the restaurant with our family. We have requests regarding seating arrangements and child-friendly facilities. Please tell us how we can ensure a smooth experience upon arrival." This allows for the provision of more flexible and customer-satisfying services.

[0270] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0271] Step 1:

[0272] The server receives video and audio data from cameras and sensors. The input is real-time video and audio from inside the store. The server analyzes this data using the OpenCV library to extract customer characteristic information. The output is data on customer attributes and behavioral characteristics.

[0273] Step 2:

[0274] The server uses the customer characteristic information obtained in Step 1 to perform analysis using a time prediction method. The input is customer characteristic information. Using a reinforcement learning algorithm, it compares this with past data to predict the length of stay. The output is the customer's predicted length of stay.

[0275] Step 3:

[0276] Users enter their visit schedule and personal information into the application using their smartphones. This input includes the planned date and time of visit and any special requests. The device transmits this information to the server via Bluetooth or Wi-Fi. The reservation information is then registered on the server as output.

[0277] Step 4:

[0278] The server combines the predicted dwell time and visit schedule information from step 2 to assess the congestion level at the site. The inputs are the predicted dwell time and reservation information. It calculates the optimal availability information for the customer and determines what information should be notified. The output is appropriate availability information.

[0279] Step 5:

[0280] Based on the vacancy information generated in step 4, the server notifies the user in real time. There is vacancy information as input. Through the smartphone application, information such as the estimated waiting time and the optimal arrival time is provided to the user. Notification information is transmitted as output.

[0281] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion specific model 59 and perform specific processing using the user's emotion.

[0282] In addition to the conventional customer management system, the present invention is a system that further improves the customer experience by incorporating an emotion engine that recognizes the user's emotion. This system grasps the emotional state of the customer and aims to improve the operational efficiency of the restaurant and customer satisfaction.

[0283] The server uses a plurality of sensors (such as cameras and microphones) installed in the store to collect customer images and audio data in real time. The collected data is analyzed by the emotion engine in the server to evaluate the customer's expression and voice tone and infer the current emotional state.

[0284] The terminal utilizes the emotion data analyzed by the emotion engine to improve the prediction accuracy of the customer's staying time. This is applied, for example, in the form of shortening the predicted staying time if the customer appears restless. Also, by proposing personalized hospitality according to the customer's emotional state, a more comfortable dining experience is provided.

[0285] The customer, who is the user, benefits from the services dynamically provided based on their own emotions. For example, when the customer shows dissatisfaction or impatience, an instruction for prompt follow-up is presented from the terminal to the staff. As a result, the staff can take appropriate actions and reduce the customer's stress.

[0286] As a whole, this system aims to improve the seat utilization efficiency in the store and enhance customer satisfaction by combining real-time sentiment analysis and stay time prediction. By using the form of this invention, restaurants can provide services considering customers' emotions and achieve a higher-dimensional customer experience.

[0287] The processing flow will be described below.

[0288] Step 1:

[0289] The server collects video and audio data in real time from cameras and microphones installed in the store. This data contains features indicating emotions such as customers' expressions and vocal tones.

[0290] Step 2:

[0291] The terminal analyzes the data received by the emotion engine and evaluates the customer's emotional state. Specifically, it uses image recognition to detect expressions such as smiles and anger, and evaluates vocal tones and speaking styles through voice analysis.

[0292] Step 3:

[0293] The server performs time prediction to predict the customer's table stay time based on the result of sentiment analysis. By considering the influence of the emotional state on the customer's behavior, the prediction accuracy is improved.

[0294] Step 4:

[0295] The user receives real-time notifications based on their own emotional state and vacant seat information through the smartphone app. For example, when in a relaxed state, specific suggestions such as a slow-paced service are recommended.

[0296] Step 5:

[0297] The terminal instructs staff to assign the most appropriate seating based on the customer's emotional state. If the customer expresses dissatisfaction, it promptly issues instructions to provide service.

[0298] Step 6:

[0299] The server integrates and monitors all data, including store conditions, in real time, and makes adjustments as needed to optimize seating efficiency. This aims to maximize customer satisfaction.

[0300] (Example 2)

[0301] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0302] In today's service industry, meticulous attention to each customer's individual circumstances and needs is required to improve customer satisfaction. However, previous customer management systems lacked the ability to analyze customers' emotional states in real time and link that analysis to service delivery, making it difficult to maximize the customer experience.

[0303] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0304] In this invention, the server includes a data acquisition means for collecting biometric information, an emotion analysis means for analyzing the biometric information obtained by the data acquisition means and inferring the customer's emotional state, and a dwell time prediction means for predicting the customer's table dwell time based on the emotion data obtained by the emotion analysis means. This makes it possible to provide personalized services based on the customer's emotional state.

[0305] "Biometric information" refers to data about a customer's physical condition, specifically including information such as facial expressions and tone of voice.

[0306] The "data acquisition means" is a process that uses sensors and devices installed to collect biometric information from customers.

[0307] The "emotion analysis means" is a process and algorithm for inferring and evaluating the emotional state of a customer based on the acquired biometric information.

[0308] The "stay time prediction means" is a method that uses data obtained by emotion analysis to predict the time a customer stays at a service facility.

[0309] The "personal service means" is a system that adjusts and provides service content in order to provide services according to the emotional state of individual customers.

[0310] To implement this invention, first, the server uses a plurality of sensor devices installed in the store, such as high-resolution cameras and sensitive microphones, to collect biometric information of customers. The server inputs this data into a software engine for emotion analysis and performs the analysis. In this analysis, image processing algorithms and voice analysis algorithms are combined to evaluate the customer's expression and voice tone in real time and infer the emotional state.

[0311] When the emotional state of the customer is inferred, the terminal executes a model that predicts the stay time based on that data. This model applies machine learning algorithms based on past data to recognize the customer's behavior pattern and improve the prediction accuracy. The terminal also provides customized services to the customer based on the predicted stay time and emotional state. This includes menu suggestions according to the emotional state of a specific customer and instructions to the staff.

[0312] Users, or customers, can benefit from personalized services tailored to their emotions. For example, if a customer's emotions are "dissatisfied" or "frustrated," the system will send a prompt follow-up instruction to the staff. In this way, customers can enjoy a more comfortable service experience with less stress.

[0313] For example, once a customer enters a restaurant and takes their seat, a server analyzes their emotions based on data collected by a camera and microphone. If the customer is relaxed, a typical length of stay is predicted, and appropriate dishes are suggested. On the other hand, if the customer is clearly showing signs of irritation, staff are instructed to speak to them immediately.

[0314] An example of a specific prompt for a generative AI model would be: "Explain what kind of service a restaurant customer will receive based on sentiment analysis using data collected through cameras and microphones."

[0315] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0316] Step 1:

[0317] The server collects customer image and audio data using sensors such as cameras and microphones installed within the store. In this collection process, cameras capture the customer's face and microphones record their speech. The input is images and audio obtained from biosensors, and the output is raw data that can be analyzed.

[0318] Step 2:

[0319] The server inputs the collected image and audio data into the emotion analysis engine. There, it uses image processing technology to analyze facial expressions and infer which emotion category the expression belongs to. Simultaneously, it uses audio signal processing technology to analyze the tone and pitch of the voice to infer the customer's emotional state in more detail. The input is the raw data obtained in step 1, and the output is the inferred emotional state information.

[0320] Step 3:

[0321] The terminal executes an algorithm that predicts the length of stay based on emotional state information received from the server. This process utilizes historical data and machine learning models to predict how long customers will spend in the store. The input is emotional state information, and the output is the predicted length of stay.

[0322] Step 4:

[0323] The terminal provides customized services to customers based on inferred emotional state information and predicted length of stay. For example, if a customer is relaxed, standard service is provided, along with menu suggestions as needed. On the other hand, if a customer is dissatisfied, prompt staff intervention is instructed. The input is the information obtained in steps 2 and 3, and the output is specific service instructions.

[0324] Step 5:

[0325] Users receive the services provided, and their satisfaction improves throughout the overall customer experience. For users, the optimization of the service according to their individual circumstances provides greater convenience and comfort. The input is the service provided from the device, and the output is the improved customer experience and satisfaction.

[0326] (Application Example 2)

[0327] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0328] The challenge lies in achieving efficient store operations and a high level of customer satisfaction by considering the emotional state of customers. Traditional customer management systems struggle to accurately reflect customer emotions in their service delivery, potentially leading to decreased customer satisfaction. Furthermore, accurately predicting customer dwell time is necessary to optimize resource allocation within the store, but this too does not take emotions into account.

[0329] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0330] In this invention, the server includes data collection means for collecting customer characteristic information, emotion analysis means for analyzing video and audio data acquired by the data collection means to recognize the customer's emotional state, and time prediction means for predicting the customer's table stay time based on the emotion information obtained by the emotion analysis means. This enables efficient store operations that reflect the customer's emotional state in real time and the provision of personalized services.

[0331] "Customer characteristic information" refers to data such as a customer's gender, age, facial expression, and tone of voice, which is used to identify individual customers and infer their emotional state.

[0332] "Data collection means" refers to a system that includes sensors such as cameras and microphones for acquiring characteristic information about customers.

[0333] "Emotion analysis means" refers to means that analyze video and audio data collected by data collection means and perform processing to recognize the emotional state of the customer.

[0334] A "time prediction method" is a method that uses machine learning algorithms to predict the time a customer will spend at a table, based on their emotional state.

[0335] A "notification means" is an interface for providing relevant information to customers based on predictive information obtained by a time prediction means.

[0336] A "seat guidance system" is a method that utilizes predictive information to guide customers to the most suitable seats.

[0337] To implement this invention, it is necessary to build a system in which a server and a terminal work together. The server collects data in real time from cameras and microphones installed in the store. This uses the OpenCV image processing library and the Librosa audio processing library. The cameras capture the customer's facial expressions, and the microphones capture the tone of their voices. This data is sent to the server, where a machine learning model using TensorFlow as an emotion analysis tool infers the customer's emotional state from their facial expressions and voice tone.

[0338] The terminal receives sentiment information transmitted from the server and uses it to perform a time prediction system that predicts the customer's table stay time. This information is processed by a Python-based program and communicated to staff via a notification system. The notification is displayed as a smartphone application, creating an environment where staff can respond quickly to customers.

[0339] Store staff, as users, can improve the customer experience by checking the emotional state and recommended actions presented by the device and providing appropriate service that is attentive to the customer's emotions.

[0340] For example, if a customer is frustrated after waiting for a long time, the application can recommend that staff offer a free dessert. This recommendation is based on the results of an emotion analysis model, and an example of a prompt used by the generative AI model might be, "Please tell us what actions would be effective in alleviating the customer's frustration."

[0341] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0342] Step 1:

[0343] The server collects customer video and audio data in real time from cameras and microphones installed in the store. The input is data from the cameras and microphones, which is acquired to form the initial dataset. The video data is temporarily stored in memory for future processing.

[0344] Step 2:

[0345] The server analyzes the collected video data using OpenCV to extract customer facial features. The input is the image data acquired in step 1, which is processed by an image processing algorithm to obtain facial landmarks and facial feature vectors as output. These facial features are used in subsequent emotion analysis.

[0346] Step 3:

[0347] The server analyzes the audio data using Librosa and extracts features from the customer's voice tone. The input is the audio data acquired in step 1, and it outputs audio feature vectors such as pitch and volume level from the audio signal. These audio features are also used for sentiment analysis.

[0348] Step 4:

[0349] The server uses TensorFlow to integrate the extracted facial and vocal features and apply them to an emotion analysis model. The input is the feature vector obtained in steps 2 and 3, which is then input into the emotion analysis model, and the output is an estimate of the customer's current emotional state.

[0350] Step 5:

[0351] The terminal receives emotional state information sent from the server and executes a time prediction algorithm to predict the customer's table stay time. The input is emotional state information provided by the server, and the output is the calculation of the predicted stay time. This provides time management information useful for store operations.

[0352] Step 6:

[0353] The store staff, acting as users, decide on actions to provide appropriate service based on the emotional state and predicted dwell time presented by the terminal. Using prompts output by the generative AI model, quick and appropriate responses become possible.

[0354] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0355] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0356] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0357] [Third Embodiment]

[0358] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0359] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0360] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0361] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0362] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0363] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0364] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0365] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0366] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0367] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0368] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0369] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0370] This invention is a system for reducing customer waiting times and efficiently utilizing seating in restaurants. This system streamlines the customer process from entry to exit, optimizing restaurant operations.

[0371] The server uses cameras and sensors installed in the store to monitor customer movements in real time. This allows for the collection of data regarding customer arrival times and the progress of their meals. The collected data is sent to the server and used for analysis.

[0372] The data is sent to a terminal, where image recognition and voice analysis models are used to extract customer characteristics. Based on these analysis results, the terminal predicts how long customers will spend at the table. In particular, it estimates when customers will finish their meals and makes a reasonable estimate of their stay.

[0373] The server applies a reinforcement learning algorithm to further refine the collected data and prediction results. This algorithm enables highly accurate predictions of dwell time based on past customer behavior data.

[0374] Customers receive real-time notifications about available seats via their smartphones. These notifications include information such as the customer's estimated waiting time and the location of available tables. Furthermore, in-store staff can quickly and efficiently guide customers based on the optimal seating arrangement information displayed on the terminals.

[0375] This reduces waiting times, improves customer satisfaction, increases the efficiency of seating utilization in the restaurant, and maximizes restaurant sales. This invention is a groundbreaking system that enhances convenience for both customers and restaurants and enables smooth operations.

[0376] The following describes the processing flow.

[0377] Step 1:

[0378] The server collects video and audio data in real time from cameras and sensors placed throughout the store. This data includes customer movements and table status.

[0379] Step 2:

[0380] The terminal feeds the data received from the server into image recognition and speech analysis models. Here, customer actions and conversation content are analyzed to determine the progress of the meal and the customer's stay duration.

[0381] Step 3:

[0382] Based on the analyzed data, the server uses past visitor data and a reinforcement learning algorithm to predict the customer's table dwell time. The prediction is continuously updated.

[0383] Step 4:

[0384] Users receive information about predicted seating availability and optimal seating options from the server via their smartphone app. This allows users to enter the store efficiently.

[0385] Step 5:

[0386] The terminal displays optimal seating plans to store staff. This includes information on seating arrangements based on each customer's needs and the current occupancy rate of the store.

[0387] Step 6:

[0388] The server continuously monitors the store's situation in real time and makes adjustments to optimize seating arrangements based on predictions. This minimizes customer waiting times and improves the efficiency of store operations.

[0389] (Example 1)

[0390] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0391] In restaurants and other establishments where customers wait, the challenge is to maximize seating efficiency while minimizing customer waiting times. In particular, accurately predicting customer dwell times and providing appropriate seating guidance is essential. Providing customers with real-time information on seat availability is also crucial to increasing customer satisfaction.

[0392] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0393] In this invention, the server includes an information gathering means for collecting characteristic information of visitors, a time prediction means for analyzing the data obtained by the information gathering means and predicting the visitor's stay time, and an information provision means for providing visitors with information on seat availability based on the prediction information obtained by the time prediction means. This makes it possible to reduce the waiting time of visitors and maximize the efficiency of seat utilization.

[0394] "Information gathering means" refers to methods and technologies used to acquire characteristic information about visitors, enabling the acquisition of diverse information, including video and audio data.

[0395] "Time prediction methods" refer to techniques and technologies that analyze collected data to predict the length of time visitors will stay based on past behavioral patterns and current circumstances.

[0396] "Information provision means" refers to methods and technologies for providing visitors with information on seat availability and waiting times based on predictive information obtained through time prediction means.

[0397] "Seat allocation means" refers to methods and technologies for arranging visitors in appropriate seats based on specific conditions or predictions.

[0398] "Monitoring methods" refer to techniques and technologies used to monitor visitors' activities in real time and understand the situation.

[0399] "Analysis means" refers to methods and techniques for processing collected data and analyzing the progress of meals, etc., using image analysis models.

[0400] A "learning algorithm" refers to computational methods or mathematical models used to improve prediction accuracy based on past data.

[0401] A description of embodiments for carrying out this invention will be given.

[0402] The server uses cameras and sensors installed within the restaurant to monitor customer movements in real time. Specifically, the server collects data including customers' arrival times and the progress of their meals, and records it in a database. This data is used to reduce customer waiting times and optimize seating arrangements.

[0403] The terminal receives data sent from the server and extracts visitor characteristics using image recognition and speech analysis models. These models utilize Python libraries such as OpenCV and TensorFlow. The terminal also predicts customer dwell time based on the extracted information and applies reinforcement learning algorithms to improve prediction accuracy. This enables highly accurate predictions based on past visitor data.

[0404] Visitors, as users, receive real-time notifications about seat availability and waiting times via their mobile devices. This notification feature allows visitors to choose the optimal time to visit based on the store's congestion. For example, a customer might receive a notification via the app stating, "The current waiting time is 15 minutes. A window table will be available in 10 minutes."

[0405] An example of a prompt for a generative AI model might be: "Please describe the details of a system that accurately predicts customer dwell time in a restaurant and optimizes store operations."

[0406] In this way, the invention improves customer satisfaction and maximizes the operational efficiency of the store.

[0407] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0408] Step 1:

[0409] The server automatically detects visitors entering the store using cameras and sensors installed inside. Inputs include video data from the cameras and motion detection data from the sensors. The server analyzes this data to produce output that records the number of visitors and their arrival times. Specifically, when a visitor enters the store, the camera captures video and the sensor detects their movement.

[0410] Step 2:

[0411] The server continuously monitors the progress of the guests' meals. This input data consists of video from cameras and audio from microphones. The server uses an image recognition model to determine the progress of the meal and obtains output that analyzes which stage the meal is in. For example, it can determine whether a guest has finished their main course and is preparing dessert.

[0412] Step 3:

[0413] The terminal receives visitor characteristic information transmitted from the server and performs further detailed analysis. This input consists of analytical information about the visitor's actions and conversations. Using a speech analysis model, the terminal analyzes the length and content of the visitor's conversation and obtains an output that predicts the length of stay. Specifically, if a visitor says something like, "Shall we head home now?", an early departure is predicted.

[0414] Step 4:

[0415] The server uses time prediction tools and reinforcement learning algorithms to more accurately predict visitor dwell times. The input consists of past visitor data and current feature information. The server processes this data comprehensively, updating the prediction model to obtain an output that derives a more accurate dwell time. This enables future behavior prediction based on past behavior.

[0416] Step 5:

[0417] Visitors, as users, receive current waiting times and seat availability information via their mobile devices. This input is predictive information from the device. Users receive output via notifications to determine the optimal time to visit. Specifically, the app receives a notification stating, "A window seat will become available in 10 minutes."

[0418] Step 6:

[0419] The server determines the optimal seating arrangement based on information from the terminals and sends instructions to the store staff. This includes input data such as the expected arrival time of visitors and seat availability. The server processes this data to produce an output that proposes a seating arrangement plan. As a result, staff can quickly guide visitors to appropriate seats.

[0420] (Application Example 1)

[0421] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0422] Restaurants and other commercial establishments are required to reduce customer waiting times and efficiently utilize seating. However, traditional methods make it difficult to accurately understand customer behavior, posing challenges to seating arrangements and optimizing store operations. Furthermore, it is difficult to understand customer needs and preferences before their visit, potentially leading to decreased customer satisfaction.

[0423] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0424] In this invention, the server includes data collection means for collecting customer characteristic information, time prediction means for analyzing the information obtained by the data collection means and predicting the customer's table stay time, notification means for providing customers with seat availability information based on the prediction information obtained by the time prediction means, and schedule management means for receiving visit schedules and personal information before the visit and linking them to the store. This makes it possible to reduce customer waiting times and improve the operational efficiency of the store.

[0425] "Customer characteristic information" refers to individual data related to customers, such as video and audio, and includes information such as age group, gender, and preferences.

[0426] "Data collection means" refers to devices and methods that acquire information from external sources using sensors and cameras, and are responsible for collecting characteristic information about customers.

[0427] "Time prediction means" refers to algorithms and devices that analyze customer behavior based on collected data and estimate, in particular, the time spent at a table.

[0428] "Notification methods" refer to methods and technologies for informing customers or staff based on analysis results and predictive information, and include functions such as providing information on available seats and waiting times.

[0429] "Seat guidance methods" refer to systems and processes for guiding customers to appropriate seats, contributing to the efficiency of store operations.

[0430] "Schedule management means" refers to methods and devices for registering visit schedules and individual requests received from customers in advance into a system, and using that information when they visit the store.

[0431] The system of this invention is configured to efficiently collect customer characteristic information and optimize store operations. It mainly consists of the following components:

[0432] First, the server collects video and audio data using multiple cameras and sensors installed in the store. This data is processed through image recognition libraries such as OpenCV to extract customer characteristics. This provides the basic information necessary to predict customer dwell time.

[0433] Next, the collected data is analyzed using a time prediction tool designed with Python. Based on past customer data, a reinforcement learning algorithm is applied to predict dwell time with high accuracy. This prediction takes into account planned visits and individual customer preferences.

[0434] On the other hand, users use their smartphones to input personal information such as visit schedules and allergy information into the application. This information is transmitted to a server via Bluetooth or Wi-Fi and functions as a schedule management tool.

[0435] Furthermore, the server notifies customers of available seats and optimal arrival times based on predicted dwell time and current store congestion. Users can receive this information in real time through the application, and store staff can also obtain the information via terminals to guide customers to the best seats.

[0436] For example, when a customer enters their scheduled visit into the app, the in-store system prepares a table according to their expected arrival time. Furthermore, if a customer is accompanied by children, the system can issue instructions to the terminal to set up appropriate equipment (such as a child seat) based on specific requests.

[0437] Examples of prompts for the generating AI model include: "We are visiting the restaurant with our family. We have requests regarding seating arrangements and child-friendly facilities. Please tell us how we can ensure a smooth experience upon arrival." This allows for the provision of more flexible and customer-satisfying services.

[0438] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0439] Step 1:

[0440] The server receives video and audio data from cameras and sensors. The input is real-time video and audio from inside the store. The server analyzes this data using the OpenCV library to extract customer characteristic information. The output is data on customer attributes and behavioral characteristics.

[0441] Step 2:

[0442] The server uses the customer characteristic information obtained in Step 1 to perform analysis using a time prediction method. The input is customer characteristic information. Using a reinforcement learning algorithm, it compares this with past data to predict the length of stay. The output is the customer's predicted length of stay.

[0443] Step 3:

[0444] Users enter their visit schedule and personal information into the application using their smartphones. This input includes the planned date and time of visit and any special requests. The device transmits this information to the server via Bluetooth or Wi-Fi. The reservation information is then registered on the server as output.

[0445] Step 4:

[0446] The server combines the predicted dwell time and visit schedule information from step 2 to assess the congestion level at the site. The inputs are the predicted dwell time and reservation information. It calculates the optimal availability information for the customer and determines what information should be notified. The output is appropriate availability information.

[0447] Step 5:

[0448] The server notifies users in real time based on the vacancy information generated in step 4. The input is vacancy information. The server provides users with information such as estimated waiting times and optimal arrival times through a smartphone application. The output is notification information.

[0449] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0450] This invention is a system that enhances the customer experience by incorporating an emotion engine that recognizes user emotions, in addition to conventional customer management systems. This system aims to improve the operational efficiency of restaurants and increase customer satisfaction by understanding the emotional state of customers.

[0451] The server uses multiple sensors (such as cameras and microphones) installed in the store to collect customer image and audio data in real time. The collected data is analyzed by an emotion engine within the server to evaluate the customer's facial expressions and tone of voice and infer their current emotional state.

[0452] The terminal utilizes emotional data analyzed by an emotion engine to improve the accuracy of predicting customer dwell time. This can be applied, for example, by shortening the predicted dwell time if the customer appears restless. Furthermore, by suggesting personalized service based on the customer's emotional state, it provides a more comfortable dining experience.

[0453] Customers, as users, benefit from services that are dynamically delivered based on their own emotions. For example, if a customer expresses dissatisfaction or frustration, instructions for quick follow-up are provided to staff from their device. This allows staff to respond appropriately and reduce customer stress.

[0454] Overall, this system aims to improve seating efficiency and enhance customer satisfaction by combining real-time sentiment analysis with dwell time prediction. Using this embodiment of the invention, restaurants can provide services that take customer emotions into account, resulting in a higher level of customer experience.

[0455] The following describes the processing flow.

[0456] Step 1:

[0457] The server collects video and audio data in real time from cameras and microphones installed in the store. This data includes features that indicate customers' emotions, such as their facial expressions and tone of voice.

[0458] Step 2:

[0459] The device analyzes the data received by its emotion engine to evaluate the customer's emotional state. Specifically, it uses image recognition to detect facial expressions such as smiles and anger, and evaluates voice tone and speaking style through voice analysis.

[0460] Step 3:

[0461] The server performs time predictions to forecast the customer's table stay based on the results of sentiment analysis. Prediction accuracy is improved by considering the impact of emotional state on customer behavior.

[0462] Step 4:

[0463] Users receive real-time notifications through a smartphone app, based on their emotional state and seat availability. For example, if they are in a relaxed state, they may receive specific suggestions such as being recommended a slower service.

[0464] Step 5:

[0465] The terminal instructs staff to assign the most appropriate seating based on the customer's emotional state. If the customer expresses dissatisfaction, it promptly issues instructions to provide service.

[0466] Step 6:

[0467] The server integrates and monitors all data, including store conditions, in real time, and makes adjustments as needed to optimize seating efficiency. This aims to maximize customer satisfaction.

[0468] (Example 2)

[0469] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0470] In today's service industry, meticulous attention to each customer's individual circumstances and needs is required to improve customer satisfaction. However, previous customer management systems lacked the ability to analyze customers' emotional states in real time and link that analysis to service delivery, making it difficult to maximize the customer experience.

[0471] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0472] In this invention, the server includes a data acquisition means for collecting biometric information, an emotion analysis means for analyzing the biometric information obtained by the data acquisition means and inferring the customer's emotional state, and a dwell time prediction means for predicting the customer's table dwell time based on the emotion data obtained by the emotion analysis means. This makes it possible to provide personalized services based on the customer's emotional state.

[0473] "Biometric information" refers to data about a customer's physical condition, specifically including information such as facial expressions and tone of voice.

[0474] "Data acquisition means" refers to the process of using sensors and devices installed to collect biometric information from customers.

[0475] "Emotional analysis means" refers to the processing and algorithms used to infer and evaluate a customer's emotional state based on acquired biometric information.

[0476] A "stay-time prediction method" is a technique that uses data obtained through sentiment analysis to predict how long customers will stay at a service facility.

[0477] A "personalized service system" is a system that adjusts and provides service content in order to deliver services tailored to the emotional state of each individual customer.

[0478] To implement this invention, the server first collects customer biometric information using hardware such as multiple sensor devices installed in the store, including high-resolution cameras and highly sensitive microphones. The server then inputs this data into a software engine for emotion analysis and performs the analysis. This analysis combines image processing algorithms and voice analysis algorithms to evaluate the customer's facial expressions and tone of voice in real time and estimate their emotional state.

[0479] The terminal, once it infers the customer's emotional state, runs a model that predicts the length of stay based on that data. This model applies machine learning algorithms based on past data to recognize customer behavior patterns and improve prediction accuracy. The terminal also provides customized services to the customer based on the predicted length of stay and emotional state. This includes menu suggestions tailored to the specific customer's emotional state and instructions for staff.

[0480] Users, or customers, can benefit from personalized services tailored to their emotions. For example, if a customer's emotions are "dissatisfied" or "frustrated," the system will send a prompt follow-up instruction to the staff. In this way, customers can enjoy a more comfortable service experience with less stress.

[0481] For example, once a customer enters a restaurant and takes their seat, a server analyzes their emotions based on data collected by a camera and microphone. If the customer is relaxed, a typical length of stay is predicted, and appropriate dishes are suggested. On the other hand, if the customer is clearly showing signs of irritation, staff are instructed to speak to them immediately.

[0482] An example of a specific prompt for a generative AI model would be: "Explain what kind of service a restaurant customer will receive based on sentiment analysis using data collected through cameras and microphones."

[0483] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0484] Step 1:

[0485] The server collects customer image and audio data using sensors such as cameras and microphones installed within the store. In this collection process, cameras capture the customer's face and microphones record their speech. The input is images and audio obtained from biosensors, and the output is raw data that can be analyzed.

[0486] Step 2:

[0487] The server inputs the collected image and audio data into the emotion analysis engine. There, it uses image processing technology to analyze facial expressions and infer which emotion category the expression belongs to. Simultaneously, it uses audio signal processing technology to analyze the tone and pitch of the voice to infer the customer's emotional state in more detail. The input is the raw data obtained in step 1, and the output is the inferred emotional state information.

[0488] Step 3:

[0489] The terminal executes an algorithm that predicts dwell time based on emotional state information received from the server. This process utilizes historical data and machine learning models to predict how long customers will spend in the store. The input is emotional state information, and the output is the predicted dwell time.

[0490] Step 4:

[0491] The terminal provides customized services to customers based on inferred emotional state information and predicted length of stay. For example, if a customer is relaxed, standard service is provided, along with menu suggestions as needed. On the other hand, if a customer is dissatisfied, prompt staff intervention is instructed. The input is the information obtained in steps 2 and 3, and the output is specific service instructions.

[0492] Step 5:

[0493] Users receive the services provided, and their satisfaction improves throughout the overall customer experience. For users, the optimization of the service according to their individual circumstances provides greater convenience and comfort. The input is the service provided from the device, and the output is the improved customer experience and satisfaction.

[0494] (Application Example 2)

[0495] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0496] The challenge lies in achieving efficient store operations and a high level of customer satisfaction by considering the emotional state of customers. Traditional customer management systems struggle to accurately reflect customer emotions in their service delivery, potentially leading to decreased customer satisfaction. Furthermore, accurately predicting customer dwell time is necessary to optimize resource allocation within the store, but this too does not take emotions into account.

[0497] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0498] In this invention, the server includes data collection means for collecting customer characteristic information, emotion analysis means for analyzing video and audio data acquired by the data collection means to recognize the customer's emotional state, and time prediction means for predicting the customer's table stay time based on the emotion information obtained by the emotion analysis means. This enables efficient store operations that reflect the customer's emotional state in real time and the provision of personalized services.

[0499] "Customer characteristic information" refers to data such as a customer's gender, age, facial expression, and tone of voice, which is used to identify individual customers and infer their emotional state.

[0500] "Data collection means" refers to a system that includes sensors such as cameras and microphones for acquiring characteristic information about customers.

[0501] "Emotion analysis means" refers to means that analyze video and audio data collected by data collection means and perform processing to recognize the customer's emotional state.

[0502] A "time prediction method" is a method that uses machine learning algorithms to predict the time spent at a table based on the customer's emotional state.

[0503] A "notification means" is an interface for providing relevant information to customers based on predictive information obtained by a time prediction means.

[0504] A "seat guidance system" is a method that utilizes predictive information to guide customers to the most suitable seats.

[0505] To implement this invention, it is necessary to build a system in which a server and a terminal work together. The server collects data in real time from cameras and microphones installed in the store. This uses the OpenCV image processing library and the Librosa audio processing library. The cameras capture the customer's facial expressions, and the microphones capture the tone of their voices. This data is sent to the server, where a machine learning model using TensorFlow as an emotion analysis tool infers the customer's emotional state from their facial expressions and voice tone.

[0506] The terminal receives sentiment information transmitted from the server and uses it to perform a time prediction system that predicts the customer's table stay time. This information is processed by a Python-based program and communicated to staff via a notification system. The notification is displayed as a smartphone application, creating an environment where staff can respond quickly to customers.

[0507] Store staff, as users, can improve the customer experience by checking the emotional state and recommended actions presented by the device and providing appropriate service that is attentive to the customer's emotions.

[0508] For example, if a customer is frustrated after waiting for a long time, the application can recommend that staff offer a free dessert. This recommendation is based on the results of an emotion analysis model, and an example of a prompt used by the generative AI model might be, "Please tell us what actions would be effective in alleviating the customer's frustration."

[0509] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0510] Step 1:

[0511] The server collects customer video and audio data in real time from cameras and microphones installed in the store. The input is data from the cameras and microphones, which is acquired to form the initial dataset. The video data is temporarily stored in memory for future processing.

[0512] Step 2:

[0513] The server analyzes the collected video data using OpenCV to extract customer facial features. The input is the image data acquired in step 1, which is processed by an image processing algorithm to obtain facial landmarks and facial feature vectors as output. These facial features are used in subsequent emotion analysis.

[0514] Step 3:

[0515] The server analyzes the audio data using Librosa and extracts features from the customer's voice tone. The input is the audio data acquired in step 1, and it outputs audio feature vectors such as pitch and volume level from the audio signal. These audio features are also used for sentiment analysis.

[0516] Step 4:

[0517] The server uses TensorFlow to integrate the extracted facial and vocal features and apply them to an emotion analysis model. The input is the feature vector obtained in steps 2 and 3, which is then input into the emotion analysis model, and the output is an estimate of the customer's current emotional state.

[0518] Step 5:

[0519] The terminal receives emotional state information sent from the server and executes a time prediction algorithm to predict the customer's table stay time. The input is emotional state information provided by the server, and the output is the calculation of the predicted stay time. This provides time management information useful for store operations.

[0520] Step 6:

[0521] The store staff, acting as users, decide on actions to provide appropriate service based on the emotional state and predicted dwell time presented by the terminal. Using prompts output by the generative AI model, quick and appropriate responses become possible.

[0522] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0523] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0524] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0525] [Fourth Embodiment]

[0526] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0527] As shown in Figure 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.

[0528] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0529] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0530] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0531] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0532] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0533] The controlled 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0534] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0535] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0536] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0537] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0538] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0539] This invention is a system for reducing customer waiting times and efficiently utilizing seating in restaurants. This system streamlines the customer process from entry to exit, optimizing restaurant operations.

[0540] The server uses cameras and sensors installed in the store to monitor customer movements in real time. This allows for the collection of data regarding customer arrival times and the progress of their meals. The collected data is sent to the server and used for analysis.

[0541] The data is sent to a terminal, where image recognition and voice analysis models are used to extract customer characteristics. Based on these analysis results, the terminal predicts how long customers will spend at the table. In particular, it estimates when customers will finish their meals and makes a reasonable estimate of their stay.

[0542] The server applies a reinforcement learning algorithm to further refine the collected data and prediction results. This algorithm enables highly accurate predictions of dwell time based on past customer behavior data.

[0543] Customers receive real-time notifications about available seats via their smartphones. These notifications include information such as the customer's estimated waiting time and the location of available tables. Furthermore, in-store staff can quickly and efficiently guide customers based on the optimal seating arrangement information displayed on the terminals.

[0544] This reduces waiting times, improves customer satisfaction, increases the efficiency of seating utilization in the restaurant, and maximizes restaurant sales. This invention is a groundbreaking system that enhances convenience for both customers and restaurants and enables smooth operations.

[0545] The following describes the processing flow.

[0546] Step 1:

[0547] The server collects video and audio data in real time from cameras and sensors placed throughout the store. This data includes customer movements and table status.

[0548] Step 2:

[0549] The terminal feeds the data received from the server into image recognition and speech analysis models. Here, customer actions and conversation content are analyzed to determine the progress of the meal and the customer's stay duration.

[0550] Step 3:

[0551] Based on the analyzed data, the server uses past visitor data and a reinforcement learning algorithm to predict the customer's table dwell time. The prediction is continuously updated.

[0552] Step 4:

[0553] Users receive information about predicted seating availability and optimal seating options from the server via their smartphone app. This allows users to enter the store efficiently.

[0554] Step 5:

[0555] The terminal displays optimal seating plans to store staff. This includes information on seating arrangements based on each customer's needs and the current occupancy rate of the store.

[0556] Step 6:

[0557] The server continuously monitors the store's situation in real time and makes adjustments to optimize seating arrangements based on predictions. This minimizes customer waiting times and improves the efficiency of store operations.

[0558] (Example 1)

[0559] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0560] In restaurants and other establishments where customers wait, the challenge is to maximize seating efficiency while minimizing customer waiting times. In particular, accurately predicting customer dwell times and providing appropriate seating guidance is essential. Providing customers with real-time information on seat availability is also crucial to increasing customer satisfaction.

[0561] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0562] In this invention, the server includes an information gathering means for collecting characteristic information of visitors, a time prediction means for analyzing the data obtained by the information gathering means and predicting the visitor's stay time, and an information provision means for providing visitors with information on seat availability based on the prediction information obtained by the time prediction means. This makes it possible to reduce the waiting time of visitors and maximize the efficiency of seat utilization.

[0563] "Information gathering means" refers to methods and technologies used to acquire characteristic information about visitors, enabling the acquisition of diverse information, including video and audio data.

[0564] "Time prediction methods" refer to techniques and technologies that analyze collected data and predict the length of time visitors will stay based on past behavioral patterns and current circumstances.

[0565] "Information provision means" refers to methods and technologies for providing visitors with information on seat availability and waiting times based on predictive information obtained through time prediction means.

[0566] "Seat allocation means" refers to methods and technologies for arranging visitors in appropriate seats based on specific conditions or predictions.

[0567] "Monitoring methods" refer to techniques and technologies used to monitor visitors' activities in real time and understand the situation.

[0568] "Analysis means" refers to methods and techniques for processing collected data and analyzing the progress of meals, etc., using image analysis models.

[0569] A "learning algorithm" refers to computational methods or mathematical models used to improve prediction accuracy based on past data.

[0570] A description of embodiments for carrying out this invention will be given.

[0571] The server uses cameras and sensors installed within the restaurant to monitor customer movements in real time. Specifically, the server collects data including customers' arrival times and the progress of their meals, and records it in a database. This data is used to reduce customer waiting times and optimize seating arrangements.

[0572] The terminal receives data sent from the server and extracts visitor characteristics using image recognition and speech analysis models. These models utilize Python libraries such as OpenCV and TensorFlow. The terminal also predicts customer dwell time based on the extracted information and applies reinforcement learning algorithms to improve prediction accuracy. This enables highly accurate predictions based on past visitor data.

[0573] Visitors, as users, receive real-time notifications about seat availability and waiting times via their mobile devices. This notification feature allows visitors to choose the optimal time to visit based on the store's congestion. For example, a customer might receive a notification via the app stating, "The current waiting time is 15 minutes. A window table will be available in 10 minutes."

[0574] An example of a prompt for a generative AI model might be: "Please describe the details of a system that accurately predicts customer dwell time in a restaurant and optimizes store operations."

[0575] In this way, the invention improves customer satisfaction and maximizes the operational efficiency of the store.

[0576] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0577] Step 1:

[0578] The server automatically detects visitors entering the store using cameras and sensors installed inside. Inputs include video data from the cameras and motion detection data from the sensors. The server analyzes this data to produce output that records the number of visitors and their arrival times. Specifically, when a visitor enters the store, the camera captures video and the sensor detects their movement.

[0579] Step 2:

[0580] The server continuously monitors the progress of the guests' meals. This input data consists of video from cameras and audio from microphones. The server uses an image recognition model to determine the progress of the meal and obtains output that analyzes which stage the meal is in. For example, it can determine whether a guest has finished their main course and is preparing dessert.

[0581] Step 3:

[0582] The terminal receives visitor characteristic information transmitted from the server and performs further detailed analysis. This input consists of analytical information about the visitor's actions and conversations. Using a speech analysis model, the terminal analyzes the length and content of the visitor's conversation and obtains an output that predicts the length of stay. Specifically, if a visitor says something like, "Shall we head home now?", an early departure is predicted.

[0583] Step 4:

[0584] The server uses time prediction tools and reinforcement learning algorithms to more accurately predict visitor dwell times. The input consists of past visitor data and current feature information. The server processes this data comprehensively, updating the prediction model to obtain an output that derives a more accurate dwell time. This enables future behavior prediction based on past behavior.

[0585] Step 5:

[0586] Visitors, as users, receive current waiting times and seat availability information via their mobile devices. This input is predictive information from the device. Users receive output via notifications to determine the optimal time to visit. Specifically, the app receives a notification stating, "A window seat will become available in 10 minutes."

[0587] Step 6:

[0588] The server determines the optimal seating arrangement based on information from the terminals and sends instructions to the store staff. This includes input data such as the expected arrival time of visitors and seat availability. The server processes this data to produce an output that proposes a seating arrangement plan. As a result, staff can quickly guide visitors to appropriate seats.

[0589] (Application Example 1)

[0590] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0591] Restaurants and other commercial establishments are required to reduce customer waiting times and efficiently utilize seating. However, traditional methods make it difficult to accurately understand customer behavior, posing challenges to seating arrangements and optimizing store operations. Furthermore, it is difficult to understand customer needs and preferences before their visit, potentially leading to decreased customer satisfaction.

[0592] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0593] In this invention, the server includes data collection means for collecting customer characteristic information, time prediction means for analyzing the information obtained by the data collection means and predicting the customer's table stay time, notification means for providing customers with seat availability information based on the prediction information obtained by the time prediction means, and schedule management means for receiving visit schedules and personal information before the visit and linking them to the store. This makes it possible to reduce customer waiting times and improve the operational efficiency of the store.

[0594] "Customer characteristic information" refers to individual data related to customers, such as video and audio, and includes information such as age group, gender, and preferences.

[0595] "Data collection means" refers to devices and methods that acquire information from external sources using sensors and cameras, and are responsible for collecting characteristic information about customers.

[0596] "Time prediction means" refers to algorithms and devices that analyze customer behavior based on collected data and estimate, in particular, the time spent at a table.

[0597] "Notification methods" refer to methods and technologies for informing customers or staff based on analysis results and predictive information, and include functions such as providing information on available seats and waiting times.

[0598] "Seat guidance methods" refer to systems and processes for guiding customers to appropriate seats, contributing to the efficiency of store operations.

[0599] "Schedule management means" refers to methods and devices for registering visit schedules and individual requests received from customers in advance into a system, and using that information when they visit the store.

[0600] The system of this invention is configured to efficiently collect customer characteristic information and optimize store operations. It mainly consists of the following components:

[0601] First, the server collects video and audio data using multiple cameras and sensors installed in the store. This data is processed through image recognition libraries such as OpenCV to extract customer characteristics. This provides the basic information necessary to predict customer dwell time.

[0602] Next, the collected data is analyzed using a time prediction tool designed with Python. Based on past customer data, a reinforcement learning algorithm is applied to predict dwell time with high accuracy. This prediction takes into account planned visits and individual customer preferences.

[0603] On the other hand, users use their smartphones to input personal information such as visit schedules and allergy information into the application. This information is transmitted to a server via Bluetooth or Wi-Fi and functions as a schedule management tool.

[0604] Furthermore, the server notifies customers of available seats and optimal arrival times based on predicted dwell time and current store congestion. Users can receive this information in real time through the application, and store staff can also obtain the information via terminals to guide customers to the best seats.

[0605] For example, when a customer enters their scheduled visit into the app, the in-store system prepares a table according to their expected arrival time. Furthermore, if a customer is accompanied by children, the system can send instructions to the terminal to set up appropriate equipment (such as a child seat) based on specific requests.

[0606] Examples of prompts for the generating AI model include: "We are visiting the restaurant with our family. We have requests regarding seating arrangements and child-friendly facilities. Please tell us how we can ensure a smooth experience upon arrival." This allows for the provision of more flexible and customer-satisfying services.

[0607] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0608] Step 1:

[0609] The server receives video and audio data from cameras and sensors. The input is real-time video and audio from inside the store. The server analyzes this data using the OpenCV library to extract customer characteristic information. The output is data on customer attributes and behavioral characteristics.

[0610] Step 2:

[0611] The server uses the customer characteristic information obtained in Step 1 to perform analysis using a time prediction method. The input is customer characteristic information. Using a reinforcement learning algorithm, it compares this with past data to predict the length of stay. The output is the customer's predicted length of stay.

[0612] Step 3:

[0613] Users enter their visit schedule and personal information into the application using their smartphones. This input includes the planned date and time of visit and any special requests. The device transmits this information to the server via Bluetooth or Wi-Fi. The reservation information is then registered on the server as output.

[0614] Step 4:

[0615] The server combines the predicted dwell time and visit schedule information from step 2 to assess the congestion level at the site. The inputs are the predicted dwell time and reservation information. It calculates the optimal availability information for the customer and determines what information should be notified. The output is appropriate availability information.

[0616] Step 5:

[0617] The server notifies users in real time based on the vacancy information generated in step 4. The input is vacancy information. The server provides users with information such as estimated waiting times and optimal arrival times through a smartphone application. The output is notification information.

[0618] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0619] This invention is a system that enhances the customer experience by incorporating an emotion engine that recognizes user emotions, in addition to conventional customer management systems. This system aims to improve the operational efficiency of restaurants and increase customer satisfaction by understanding the emotional state of customers.

[0620] The server uses multiple sensors (such as cameras and microphones) installed in the store to collect customer image and audio data in real time. The collected data is analyzed by an emotion engine within the server to evaluate the customer's facial expressions and tone of voice and infer their current emotional state.

[0621] The terminal utilizes emotional data analyzed by an emotion engine to improve the accuracy of predicting customer dwell time. This can be applied, for example, by shortening the predicted dwell time if the customer appears restless. Furthermore, by suggesting personalized service based on the customer's emotional state, it provides a more comfortable dining experience.

[0622] Customers, as users, benefit from services that are dynamically delivered based on their own emotions. For example, if a customer expresses dissatisfaction or frustration, instructions for quick follow-up are provided to staff from their device. This allows staff to respond appropriately and reduce customer stress.

[0623] Overall, this system aims to improve seating efficiency and enhance customer satisfaction by combining real-time sentiment analysis with dwell time prediction. Using this embodiment of the invention, restaurants can provide services that take customer emotions into account, resulting in a higher level of customer experience.

[0624] The following describes the processing flow.

[0625] Step 1:

[0626] The server collects video and audio data in real time from cameras and microphones installed in the store. This data includes features that indicate customers' emotions, such as their facial expressions and tone of voice.

[0627] Step 2:

[0628] The device analyzes the data received by its emotion engine to evaluate the customer's emotional state. Specifically, it uses image recognition to detect facial expressions such as smiles and anger, and evaluates voice tone and speaking style through voice analysis.

[0629] Step 3:

[0630] The server performs time predictions to forecast the customer's table stay based on the results of sentiment analysis. Prediction accuracy is improved by considering the impact of emotional state on customer behavior.

[0631] Step 4:

[0632] Users receive real-time notifications through a smartphone app, based on their emotional state and seat availability. For example, if they are in a relaxed state, they may receive specific suggestions such as being recommended a slower service.

[0633] Step 5:

[0634] The terminal instructs staff to assign the most appropriate seating based on the customer's emotional state. If the customer expresses dissatisfaction, it promptly issues instructions to provide service.

[0635] Step 6:

[0636] The server integrates and monitors all data, including store conditions, in real time, and makes adjustments as needed to optimize seating efficiency. This aims to maximize customer satisfaction.

[0637] (Example 2)

[0638] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0639] In today's service industry, meticulous attention to each customer's individual circumstances and needs is required to improve customer satisfaction. However, previous customer management systems lacked the ability to analyze customers' emotional states in real time and link that analysis to service delivery, making it difficult to maximize the customer experience.

[0640] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0641] In this invention, the server includes a data acquisition means for collecting biometric information, an emotion analysis means for analyzing the biometric information obtained by the data acquisition means and inferring the customer's emotional state, and a dwell time prediction means for predicting the customer's table dwell time based on the emotion data obtained by the emotion analysis means. This makes it possible to provide personalized services based on the customer's emotional state.

[0642] "Biometric information" refers to data about a customer's physical condition, specifically including information such as facial expressions and tone of voice.

[0643] "Data acquisition means" refers to the process of using sensors and devices installed to collect biometric information from customers.

[0644] "Emotional analysis means" refers to the processing and algorithms used to infer and evaluate a customer's emotional state based on acquired biometric information.

[0645] A "stay-time prediction method" is a technique that uses data obtained through sentiment analysis to predict how long customers will stay at a service facility.

[0646] A "personalized service system" is a system that adjusts and provides service content in order to deliver services tailored to the emotional state of each individual customer.

[0647] To implement this invention, the server first collects customer biometric information using hardware such as multiple sensor devices installed in the store, including high-resolution cameras and highly sensitive microphones. The server then inputs this data into a software engine for emotion analysis and performs the analysis. This analysis combines image processing algorithms and voice analysis algorithms to evaluate the customer's facial expressions and tone of voice in real time and estimate their emotional state.

[0648] The terminal, once it infers the customer's emotional state, runs a model that predicts the length of stay based on that data. This model applies machine learning algorithms based on past data to recognize customer behavior patterns and improve prediction accuracy. The terminal also provides customized services to the customer based on the predicted length of stay and emotional state. This includes menu suggestions tailored to the specific customer's emotional state and instructions for staff.

[0649] Users, or customers, can benefit from personalized services tailored to their emotions. For example, if a customer's emotions are "dissatisfied" or "frustrated," the system will send a prompt follow-up instruction to the staff. In this way, customers can enjoy a more comfortable service experience with less stress.

[0650] For example, once a customer enters a restaurant and takes their seat, a server analyzes their emotions based on data collected by a camera and microphone. If the customer is relaxed, a typical length of stay is predicted, and appropriate dishes are suggested. On the other hand, if the customer is clearly showing signs of irritation, staff are instructed to speak to them immediately.

[0651] An example of a specific prompt for a generative AI model would be: "Explain what kind of service a restaurant customer will receive based on sentiment analysis using data collected through cameras and microphones."

[0652] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0653] Step 1:

[0654] The server collects customer image and audio data using sensors such as cameras and microphones installed within the store. In this collection process, cameras capture the customer's face and microphones record their speech. The input is images and audio obtained from biosensors, and the output is raw data that can be analyzed.

[0655] Step 2:

[0656] The server inputs the collected image and audio data into the emotion analysis engine. There, it uses image processing technology to analyze facial expressions and infer which emotion category the expression belongs to. Simultaneously, it uses audio signal processing technology to analyze the tone and pitch of the voice to infer the customer's emotional state in more detail. The input is the raw data obtained in step 1, and the output is the inferred emotional state information.

[0657] Step 3:

[0658] The terminal executes an algorithm that predicts dwell time based on emotional state information received from the server. This process utilizes historical data and machine learning models to predict how long customers will spend in the store. The input is emotional state information, and the output is the predicted dwell time.

[0659] Step 4:

[0660] The terminal provides customized services to customers based on inferred emotional state information and predicted length of stay. For example, if a customer is relaxed, standard service is provided, along with menu suggestions as needed. On the other hand, if a customer is dissatisfied, prompt staff intervention is instructed. The input is the information obtained in steps 2 and 3, and the output is specific service instructions.

[0661] Step 5:

[0662] Users receive the services provided, and their satisfaction improves throughout the overall customer experience. For users, the optimization of the service according to their individual circumstances provides greater convenience and comfort. The input is the service provided from the device, and the output is the improved customer experience and satisfaction.

[0663] (Application Example 2)

[0664] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0665] The challenge lies in achieving efficient store operations and a high level of customer satisfaction by considering the emotional state of customers. Traditional customer management systems struggle to accurately reflect customer emotions in their service delivery, potentially leading to decreased customer satisfaction. Furthermore, accurately predicting customer dwell time is necessary to optimize resource allocation within the store, but this too does not take emotions into account.

[0666] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0667] In this invention, the server includes data collection means for collecting customer characteristic information, emotion analysis means for analyzing video and audio data acquired by the data collection means to recognize the customer's emotional state, and time prediction means for predicting the customer's table stay time based on the emotion information obtained by the emotion analysis means. This enables efficient store operations that reflect the customer's emotional state in real time and the provision of personalized services.

[0668] "Customer characteristic information" refers to data such as a customer's gender, age, facial expression, and tone of voice, which is used to identify individual customers and infer their emotional state.

[0669] "Data collection means" refers to a system that includes sensors such as cameras and microphones for acquiring characteristic information about customers.

[0670] "Emotion analysis means" refers to means that analyze video and audio data collected by data collection means and perform processing to recognize the customer's emotional state.

[0671] A "time prediction method" is a method that uses machine learning algorithms to predict the time spent at a table based on the customer's emotional state.

[0672] A "notification means" is an interface for providing relevant information to customers based on predictive information obtained by a time prediction means.

[0673] A "seat guidance system" is a method that utilizes predictive information to guide customers to the most suitable seats.

[0674] To implement this invention, it is necessary to build a system in which a server and a terminal work together. The server collects data in real time from cameras and microphones installed in the store. This uses the OpenCV image processing library and the Librosa audio processing library. The cameras capture the customer's facial expressions, and the microphones capture the tone of their voices. This data is sent to the server, where a machine learning model using TensorFlow as an emotion analysis tool infers the customer's emotional state from their facial expressions and voice tone.

[0675] The terminal receives sentiment information transmitted from the server and uses it to perform a time prediction system that predicts the customer's table stay time. This information is processed by a Python-based program and communicated to staff via a notification system. The notification is displayed as a smartphone application, creating an environment where staff can respond quickly to customers.

[0676] Store staff, as users, can improve the customer experience by checking the emotional state and recommended actions presented by the device and providing appropriate service that is attentive to the customer's emotions.

[0677] For example, if a customer is frustrated after waiting for a long time, the application can recommend that staff offer a free dessert. This recommendation is based on the results of an emotion analysis model, and an example of a prompt used by the generative AI model might be, "Please tell us what actions would be effective in alleviating the customer's frustration."

[0678] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0679] Step 1:

[0680] The server collects customer video and audio data in real time from cameras and microphones installed in the store. The input is data from the cameras and microphones, which is acquired to form the initial dataset. The video data is temporarily stored in memory for future processing.

[0681] Step 2:

[0682] The server analyzes the collected video data using OpenCV to extract customer facial features. The input is the image data acquired in step 1, which is processed by an image processing algorithm to obtain facial landmarks and facial feature vectors as output. These facial features are used in subsequent emotion analysis.

[0683] Step 3:

[0684] The server analyzes the audio data using Librosa and extracts features from the customer's voice tone. The input is the audio data acquired in step 1, and it outputs audio feature vectors such as pitch and volume level from the audio signal. These audio features are also used for sentiment analysis.

[0685] Step 4:

[0686] The server uses TensorFlow to integrate the extracted facial and vocal features and apply them to an emotion analysis model. The input is the feature vector obtained in steps 2 and 3, which is then input into the emotion analysis model, and the output is an estimate of the customer's current emotional state.

[0687] Step 5:

[0688] The terminal receives emotional state information sent from the server and executes a time prediction algorithm to predict the customer's table stay time. The input is emotional state information provided by the server, and the output is the calculation of the predicted stay time. This provides time management information useful for store operations.

[0689] Step 6:

[0690] The store staff, acting as users, decide on actions to provide appropriate service based on the emotional state and predicted dwell time presented by the terminal. Using prompts output by the generative AI model, quick and appropriate responses become possible.

[0691] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0692] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0693] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0694] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0695] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0696] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0697] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0698] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0699] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0700] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0701] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0702] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0703] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0704] 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.

[0705] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0706] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0707] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0708] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0709] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0710] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0711] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0712] The following is further disclosed regarding the embodiments described above.

[0713] (Claim 1)

[0714] A data collection method for collecting customer characteristic information,

[0715] A time prediction means that analyzes information obtained by a data collection means to predict the customer's table stay time,

[0716] A notification means that provides customers with seat availability information based on prediction information obtained from a time prediction means,

[0717] A seating guidance system that provides optimal seating and guides customers to their seats,

[0718] A system that includes this.

[0719] (Claim 2)

[0720] The system according to claim 1, wherein the data acquisition means includes a sensor for capturing video and audio data.

[0721] (Claim 3)

[0722] The time prediction means predicts the length of stay using a reinforcement learning algorithm based on past customer data, according to claim 1.

[0723] "Example 1"

[0724] (Claim 1)

[0725] Information gathering methods for collecting visitor characteristics information,

[0726] A time prediction means that analyzes data obtained by information gathering means to predict the length of stay of visitors,

[0727] An information provision means that provides visitors with information on seat availability based on the prediction information obtained by the time prediction means,

[0728] A seating arrangement method that guides visitors to specific seats and appropriately positions them,

[0729] A monitoring system that monitors the activity status of visitors in real time,

[0730] An analytical means that processes the progress of eating using an image analysis model based on activity data,

[0731] A system that includes this.

[0732] (Claim 2)

[0733] The information gathering means includes a sensor that acquires video and audio data, according to claim 1.

[0734] (Claim 3)

[0735] The time prediction means predicts the length of stay using a learning algorithm based on past visitor data, according to claim 1.

[0736] "Application Example 1"

[0737] (Claim 1)

[0738] A data collection method for collecting customer characteristic information,

[0739] A time prediction means that analyzes information obtained by a data collection means to predict the customer's table stay time,

[0740] A notification means that provides customers with seat availability information based on prediction information obtained from a time prediction means,

[0741] A seating guidance system that provides optimal seating and guides customers to their seats,

[0742] A scheduling management system that receives and shares visit plans and personal information with the store before the customer arrives.

[0743] A system that includes this.

[0744] (Claim 2)

[0745] The system according to claim 1, wherein the data collection means includes a sensor that acquires video and audio data.

[0746] (Claim 3)

[0747] The time prediction means is a system according to claim 1 that uses past customer data and a learning algorithm to predict the length of stay.

[0748] "Example 2 of combining an emotion engine"

[0749] (Claim 1)

[0750] A data acquisition method for collecting biometric information,

[0751] An emotion analysis means that analyzes biometric information obtained by data acquisition means to infer the emotional state of the customer,

[0752] A dwell time prediction method that predicts the customer's table dwell time based on emotional data obtained from an emotional analysis method,

[0753] A personal service means that provides customized services tailored to the customer based on information obtained from a means of predicting the length of stay,

[0754] A system that includes this.

[0755] (Claim 2)

[0756] The data acquisition means includes a detector for capturing video and audio data, according to claim 1.

[0757] (Claim 3)

[0758] The system according to claim 1, wherein the emotion analysis means performs a process to analyze the customer's emotions in real time using multiple biometric data.

[0759] "Application example 2 when combining with an emotional engine"

[0760] (Claim 1)

[0761] A data collection method for collecting customer characteristic information,

[0762] An emotion analysis means that analyzes video and audio data acquired by data collection means to recognize the customer's emotional state,

[0763] A time prediction method that predicts the customer's table stay time based on emotional information obtained by an emotional analysis method,

[0764] A notification means that provides customers with seat availability information based on prediction information obtained from a time prediction means,

[0765] A seating guidance system that provides optimal seating and guides customers to their seats,

[0766] A system that includes this.

[0767] (Claim 2)

[0768] The system according to claim 1, wherein the data acquisition means includes a sensor for capturing video and audio data.

[0769] (Claim 3)

[0770] The emotion analysis means is the system according to claim 1, which uses a machine learning algorithm to infer the customer's emotional state from their facial expressions and tone of voice. [Explanation of Symbols]

[0771] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection method for collecting customer characteristic information, A time prediction means that analyzes information obtained by a data collection means to predict the customer's table stay time, A notification means that provides customers with seat availability information based on prediction information obtained from a time prediction means, A seating guidance system that provides optimal seating and guides customers to their seats, A scheduling management system that receives and shares visit plans and personal information with the store before the customer arrives. A system that includes this.

2. The system according to claim 1, wherein the data collection means includes a sensor that acquires video and audio data.

3. The time prediction means is a system according to claim 1 that predicts the length of stay using a learning algorithm that utilizes past customer data.

Images