System

Abstract

To allow hall staff in a restaurant to effectively grasp a meal situation of customers and detect abnormal behavior.SOLUTION: A system includes an acquisition part, an analysis part, a detection part, and a notification part. The acquisition part acquires image data from a monitor camera. The analysis part analyzes a meal situation of customers based on the image data acquired by the acquisition part. The detection part detects abnormal behavior of the customers based on the image data acquired by the acquisition part. The notification part notifies hall staff based on the information acquired by the analysis part and the detection part.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult for restaurant wait staff to efficiently grasp how customers were eating and detect any abnormal behavior.

[0005] The system according to the embodiment aims to enable wait staff at a restaurant to efficiently grasp the eating habits of customers and detect abnormal behavior. [Means for solving the problem]

[0006] The system according to the embodiment includes an acquisition unit, an analysis unit, a detection unit, and a notification unit. The acquisition unit acquires video data from a surveillance camera. The analysis unit analyzes the eating status of customers based on the video data acquired by the acquisition unit. The detection unit detects abnormal behavior of customers based on the video data acquired by the acquisition unit. The notification unit notifies the hall staff based on the information acquired by the analysis unit and the detection unit. Effect of the Invention

[0007] The system according to the embodiment enables wait staff at a restaurant to efficiently grasp the dining status of customers and detect abnormal behavior. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] 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.

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

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

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

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

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

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

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The AI-equipped surveillance camera system according to the embodiment of the present invention is a system that improves the efficiency of the work of the hall staff of a restaurant. In this system, surveillance cameras are installed, and AI analyzes the eating status of customers in real time. For example, AI determines whether the customer has finished their meal or whether the drink has run out. This allows the hall staff to clear away the dishes and refill the water at the appropriate time. Next, AI detects irregular behavior of the customer. For example, AI detects loud noises and other behaviors that cause trouble to other customers, and notifies the hall staff. This allows for a quick response and minimizes the inconvenience to other customers. This system consists of the following steps. 1. Surveillance cameras are installed, and AI analyzes the eating status of customers in real time. 2. AI grasps the eating status and notifies the hall staff. 3. AI detects irregular behavior and notifies the hall staff. This system improves the efficiency of the work of the hall staff and improves service to customers. It also makes it possible to monitor nuisance behavior, allowing customers to enjoy their meals with peace of mind. As a result, the AI-equipped surveillance camera system can improve the efficiency of the work of the hall staff and improve service to customers.

[0029] The AI-equipped surveillance camera system according to the embodiment includes an acquisition unit, an analysis unit, a detection unit, and a notification unit. The acquisition unit acquires video data from the surveillance camera. The surveillance camera is installed, for example, on the ceiling or wall of the restaurant, and can cover a wide area. The acquisition unit can acquire optimal video data, for example, by adjusting the resolution and frame rate of the camera. The analysis unit analyzes the customer's eating situation based on the video data acquired by the acquisition unit. The analysis unit, for example, uses AI to analyze the customer's movements and facial expressions to grasp the progress of the meal. For example, the analysis unit can determine whether the customer has finished the meal and whether the drink has run out. The detection unit detects irregular behavior of the customer based on the video data acquired by the acquisition unit. The detection unit, for example, uses AI to analyze the customer's movements and facial expressions to detect abnormal behavior. For example, the detection unit can detect loud noises, behaviors that cause inconvenience to other customers, and the like. The notification unit notifies the hall staff based on the information acquired by the analysis unit and the detection unit. The notification unit can convey information to the hall staff, for example, by using audio or visual notifications. For example, the notification unit can send notifications to the smartphones or tablets of the hall staff, which allows the AI-equipped surveillance camera system according to the embodiment to streamline the work of the hall staff and improve service to customers.

[0030] The acquisition unit acquires video data from the surveillance cameras. The surveillance cameras are installed, for example, on the ceiling or walls of the store and can cover a wide range. The acquisition unit can, for example, adjust the resolution and frame rate of the cameras to acquire optimal video data. Specifically, the surveillance cameras are equipped with high-resolution lenses and can clearly capture even the finest details in the store. Furthermore, the cameras are equipped with infrared sensors and high-sensitivity image sensors to provide high-quality images even in low-light environments. The acquisition unit acquires video data from these cameras in real time and transmits it to a central database. The video data is efficiently stored using compression technology so that the analysis unit and detection unit can access it as needed. In addition, the acquisition unit can remotely control the viewing angle and zoom function of the cameras and can focus on specific areas or objects. This allows the acquisition unit to grasp the situation in the store in detail and provide high-quality data to the analysis unit and detection unit. Furthermore, the acquisition unit can integrate video data from multiple cameras and centrally manage the overall situation. This allows the acquisition unit to efficiently and effectively collect data and improve the performance of the entire system.

[0031] The analysis unit analyzes the customer's eating situation based on the video data acquired by the acquisition unit. The analysis unit, for example, uses AI to analyze the customer's movements and facial expressions to grasp the progress of the meal. Specifically, the AI ​​uses deep learning technology to analyze the customer's movements and facial expressions with high accuracy. For example, the AI ​​detects the movement of the customer using a fork and knife to grasp the progress of the meal in real time. In addition, by analyzing the customer's facial expressions, it is possible to determine whether the customer is satisfied or dissatisfied. Furthermore, the AI ​​detects whether the contents of the drink glass are reduced and determines whether the drink needs to be refilled. This allows the analysis unit to grasp the customer's eating situation in detail and provide information to the hall staff to provide service at the appropriate time. The analysis unit can learn the meal progress pattern and the customer's behavior pattern by utilizing past data and statistical information, and perform more accurate analysis. For example, by analyzing the behavior pattern of the customer during a specific time period or day of the week and building a predictive model, it can be used to improve service in the future. This allows the analysis unit to contribute not only to grasping the situation in real time, but also to improving service in the long term.

[0032] The detection unit detects irregular customer behavior based on the video data acquired by the acquisition unit. The detection unit, for example, uses AI to analyze the customer's movements and facial expressions to detect abnormal behavior. Specifically, the AI ​​uses an anomaly detection algorithm to learn the customer's behavior patterns and detect unusual behavior in real time. For example, it can detect behavior such as shouting, causing trouble to other customers, suddenly standing up, and running around the store. In addition, the AI ​​can analyze the customer's facial expressions and detect emotions such as anger, dissatisfaction, and excitement. This allows the detection unit to quickly detect abnormal behavior and changes in emotion and issue a warning to the hall staff. The detection unit can learn patterns of abnormal behavior by utilizing past data and statistical information, and perform more accurate detection. For example, by analyzing the frequency of occurrence of abnormal behavior during specific times of the day or days of the week and building a predictive model, it can be used to help with future risk management. This allows the detection unit to not only detect abnormalities in real time, but also handle long-term risk management, improving the reliability and safety of the entire system.

[0033] The notification unit notifies the hall staff based on the information obtained by the analysis unit and the detection unit. The notification unit can convey information to the hall staff using, for example, audio or visual notifications. Specifically, the notification unit sends notifications to the hall staff's smartphones or tablets in real time to prompt them to take the necessary action. For example, when a customer has finished their meal or when a drink needs to be refilled, the hall staff is immediately notified of the information. In addition, when abnormal behavior is detected, a warning notification is issued to prompt a prompt response. The notification unit can reliably transmit information using multiple communication means. For example, important information can be reliably delivered by using not only smartphone notifications but also voice calls, SMS, emails, etc. in combination. Furthermore, the notification unit can collect feedback from the hall staff and continuously improve the accuracy and effectiveness of the notification content. For example, the timing and content of the notification can be reviewed based on feedback from the hall staff who received the notification, and more effective notification can be provided. As a result, the notification unit can quickly and reliably provide information to the hall staff, thereby improving work efficiency and service to customers.

[0034] The analysis unit may include a detailed analysis unit that performs detailed analysis of the eating situation. The detailed analysis unit performs detailed analysis of the eating situation of the customer using, for example, AI. For example, the detailed analysis unit can determine whether the customer has finished eating or whether the drink has run out. The detailed analysis unit can also grasp the progress of the customer's meal in real time and notify the hall staff. For example, the detailed analysis unit can notify the hall staff when the customer has finished eating, so that the tableware can be quickly cleared away. This enables detailed analysis of the eating situation.

[0035] The detection unit may include a behavior identification unit that detects specific behavior. The behavior identification unit detects specific behavior of customers by using, for example, AI. For example, the behavior identification unit can detect customers making loud noises or other behavior that causes a nuisance to other customers. The behavior identification unit can also analyze the movements and facial expressions of customers to detect abnormal behavior. For example, the behavior identification unit can detect behavior such as a customer suddenly standing up or abandoning their meal. This makes it possible to detect specific behavior in detail.

[0036] The notification unit may include a notification selection unit that selects the notification method. The notification selection unit may use, for example, AI to select the notification method for the hall staff. For example, the notification selection unit may select a method such as audio notification, visual notification, or vibration notification. The notification selection unit may also select the optimal notification method based on the work status and location information of the hall staff. For example, the notification selection unit may provide a brief notification when the hall staff is busy, and a detailed notification when the hall staff has time. This allows for flexible selection of the notification method.

[0037] The acquisition unit can acquire video data from a surveillance camera in real time. The acquisition unit acquires, for example, video data from a surveillance camera in real time. Specific definitions and standards of real time include, for example, delay time and data update frequency. The acquisition unit can adjust, for example, the resolution and frame rate of the camera to acquire optimal video data in real time. This makes it possible to acquire video data in real time.

[0038] The notification unit can notify the hall staff by voice or visually. The notification unit, for example, issues voice or visual notifications to the hall staff. A specific method of voice notification, for example, is to use a voice message. A specific method of visual notification, for example, is to use a visual alert. The notification unit can, for example, send a notification to the hall staff's smartphone or tablet. This makes it possible to notify the hall staff effectively.

[0039] The acquisition unit can change the acquisition method according to a specific time period or congestion when acquiring video data. The acquisition unit, for example, uses AI to change the acquisition method according to a specific time period or congestion when acquiring video data. Specific definitions and standards of a specific time period or congestion include, for example, peak times and congestion indicators. For example, the acquisition unit frequently acquires video data during busy times such as lunchtime, and quickly grasps the eating situation. In addition, the acquisition unit periodically acquires video data during quiet times such as just before closing time, and can efficiently check the eating situation. Furthermore, the acquisition unit can acquire video data in real time during specific events, allowing for immediate response. This makes it possible to acquire appropriate video data according to the time period and congestion.

[0040] The acquisition unit can focus on a specific area or table when acquiring video data. The acquisition unit, for example, uses AI to focus on a specific area or table when acquiring video data. Specific ranges and criteria for a specific area or table include, for example, seat numbers and area divisions. For example, the acquisition unit acquires video data focusing on areas where many customers gather, and grasps the eating situation. In addition, the acquisition unit can acquire video data focusing on a specific table, and check the individual eating situation. Furthermore, the acquisition unit acquires video data focusing on areas where problems are likely to occur, and can respond quickly. This makes it possible to acquire video data focusing on a specific area or table.

[0041] The acquisition unit can simultaneously acquire audio data when acquiring video data and use it for analysis. The acquisition unit, for example, uses AI to simultaneously acquire audio data when acquiring video data and use it for analysis. Specific types and formats of audio data include, for example, audio quality and recording method. For example, the acquisition unit acquires audio data simultaneously with the video data and analyzes the content of the customer's conversation. In addition, the acquisition unit can acquire audio data simultaneously with the video data and analyze the tone of the customer's voice. Furthermore, the acquisition unit can acquire audio data simultaneously with the video data and estimate emotions from the customer's voice. This makes it possible to simultaneously acquire video data and audio data and use them for analysis.

[0042] The acquisition unit can also acquire environmental data such as temperature or humidity when acquiring the video data, and use the data for analysis. The acquisition unit can, for example, use AI to acquire environmental data such as temperature and humidity when acquiring the video data, and use the data for analysis. Specific types and acquisition methods of environmental data include, for example, temperature sensors and humidity sensors. For example, the acquisition unit acquires temperature data simultaneously with the video data, and analyzes the comfort level of the customer. The acquisition unit can also acquire humidity data simultaneously with the video data, and analyze the comfort level of the customer. Furthermore, the acquisition unit can acquire environmental data simultaneously with the video data, and comprehensively analyze the comfort level of the customer. This makes it possible to acquire environmental data and use it for analysis.

[0043] The analysis unit can change the analysis algorithm according to the type and amount of food when analyzing the eating situation. The analysis unit can change the analysis algorithm according to the type and amount of food when analyzing the eating situation, for example, using AI. Specific definitions and standards for the type and amount of food include, for example, food categories and units of amount. For example, the analysis unit uses a simple analysis algorithm for a light meal. Also, the analysis unit can use a detailed analysis algorithm for a full course meal. Furthermore, the analysis unit can use a combination of multiple analysis algorithms for a meal with a large number of people. This makes it possible to perform an appropriate analysis according to the type and amount of food.

[0044] The analysis unit can improve the accuracy of the analysis when analyzing the eating situation by referring to past meal data. The analysis unit can improve the accuracy of the analysis by referring to past meal data when analyzing the eating situation, for example, using AI. Specific content and acquisition method of past meal data include, for example, the data storage period and the type of data. For example, the analysis unit can predict the progress of the meal by referring to the past meal data. Furthermore, the analysis unit can predict the type and amount of the meal by referring to the past meal data. Furthermore, the analysis unit can predict the timing of the end of the meal by referring to the past meal data. Thereby, the accuracy of the analysis is improved by referring to the past data.

[0045] The analysis unit can analyze the beverage consumption status at the same time as analyzing the meal status. The analysis unit, for example, uses AI to analyze the beverage consumption status at the same time as analyzing the meal status. Specific content and criteria of the beverage consumption status include, for example, the type of beverage and the amount consumed. For example, the analysis unit analyzes the beverage consumption status at the same time as the meal status and determines the timing for refilling the beverage. The analysis unit can also analyze the beverage consumption status at the same time as the meal status and determine the type of beverage. Furthermore, the analysis unit can analyze the beverage consumption status at the same time as the meal status and determine the amount of beverage consumed. This makes it possible to analyze the beverage consumption status at the same time.

[0046] The analysis unit can also analyze the cleanliness and arrangement of the table when analyzing the meal situation. The analysis unit, for example, uses AI to analyze the cleanliness and arrangement of the table when analyzing the meal situation. Specific standards and methods for the cleanliness and arrangement of the table include, for example, cleaning frequency and arrangement patterns. For example, the analysis unit analyzes the cleanliness of the table at the same time as the meal situation and grasps the need for cleaning. In addition, the analysis unit can analyze the arrangement of the table at the same time as the meal situation and propose the optimal arrangement. Furthermore, the analysis unit can analyze the cleanliness and arrangement of the table at the same time as the meal situation, and improve overall service. This makes it possible to simultaneously analyze the cleanliness and arrangement of the table.

[0047] The detection unit can change the detection algorithm according to the frequency or intensity of the behavior when detecting an irregular behavior. The detection unit, for example, changes the detection algorithm according to the frequency or intensity of the behavior when detecting an irregular behavior using AI. Specific standards and measurement methods for the frequency or intensity of a behavior include, for example, the number of times the behavior occurs and the intensity of the behavior. For example, the detection unit uses a strict detection algorithm when the frequency of the behavior is high. Furthermore, the detection unit can use a detailed detection algorithm when the intensity of the behavior is high. Furthermore, the detection unit can select an appropriate detection algorithm according to the frequency or intensity of the behavior. This makes it possible to use an appropriate detection algorithm according to the frequency or intensity of the behavior.

[0048] The detection unit can improve the accuracy of detection when detecting an irregular behavior by referring to past behavior data. The detection unit can improve the accuracy of detection by referring to past behavior data when detecting an irregular behavior, for example, using AI. Specific content and acquisition method of the past behavior data include, for example, a data storage period and a data type. For example, the detection unit refers to the past behavior data to grasp the pattern of the irregular behavior. Also, the detection unit can grasp the frequency of the irregular behavior by referring to the past behavior data. Furthermore, the detection unit can grasp the intensity of the irregular behavior by referring to the past behavior data. As a result, the accuracy of detection is improved by referring to the past behavior data.

[0049] The detection unit can simultaneously detect a change in voice or facial expression when detecting an irregular behavior. The detection unit, for example, uses AI to simultaneously detect a change in voice or facial expression when detecting an irregular behavior. Specific criteria and detection methods for changes in voice and facial expression include, for example, a change pattern in voice tone or facial expression. For example, the detection unit detects a change in voice at the same time as the irregular behavior and grasps the cause of the behavior. In addition, the detection unit can detect a change in facial expression at the same time as the irregular behavior and grasp the cause of the behavior. Furthermore, the detection unit can detect a change in voice or facial expression at the same time as the irregular behavior and analyze the behavior comprehensively. As a result, it is possible to grasp the cause of the behavior by simultaneously detecting changes in voice and facial expression.

[0050] The detection unit can simultaneously detect the reactions of other customers when it detects irregular behavior. The detection unit, for example, uses AI to simultaneously detect the reactions of other customers when it detects irregular behavior. Specific content and detection methods of other customers' reactions include, for example, changes in gaze direction and facial expressions. For example, the detection unit detects the reactions of other customers at the same time as the irregular behavior and grasps the impact of the behavior. In addition, the detection unit can detect the reactions of other customers at the same time as the irregular behavior and respond quickly. Furthermore, the detection unit can detect the reactions of other customers at the same time as the irregular behavior and analyze the behavior comprehensively. This makes it possible to grasp the impact of the behavior by simultaneously detecting the reactions of other customers.

[0051] The notification unit can select the optimal notification method in consideration of the current work status of the hall staff at the time of notification. The notification unit, for example, uses AI to select the optimal notification method in consideration of the current work status of the hall staff at the time of notification. Specific criteria and selection methods for the optimal notification method include, for example, the urgency of the notification and the status of the staff. For example, if the hall staff is busy, the notification unit provides a brief notification. Also, if the hall staff has time, the notification unit can provide a detailed notification. Furthermore, the notification unit can select an appropriate notification method according to the work status of the hall staff. This makes it possible to select an appropriate notification method according to the work status of the hall staff.

[0052] The notification unit can improve the accuracy of notifications by referring to past notification history at the time of notification. The notification unit can improve the accuracy of notifications by referring to past notification history at the time of notification, for example, using AI. Specific contents and acquisition methods of the past notification history include, for example, the type of notification and the frequency of notifications. For example, the notification unit can refer to the past notification history to grasp the appropriate timing of notification. Also, the notification unit can refer to the past notification history to grasp the appropriate notification content. Furthermore, the notification unit can improve the accuracy of notifications by referring to the past notification history. As a result, the accuracy of notifications is improved by referring to the past notification history.

[0053] The notification unit can use not only audio and visual but also other notification means such as vibration and light when notifying. The notification unit can use not only audio and visual but also other notification means such as vibration and light when notifying, for example, using AI. Specific types and usage methods of notification means such as vibration and light include, for example, the strength of vibration and the color and pattern of light. For example, the notification unit can issue a vibration notification at the same time as the audio notification to alert the hall staff. In addition, the notification unit can issue a light notification at the same time as the visual notification to alert the hall staff. Furthermore, the notification unit can use a combination of multiple notification means such as audio, visual, vibration, and light. As a result, it is possible to effectively notify the hall staff by using multiple notification means.

[0054] The notification unit can select the optimal notification method in consideration of the location information of the hall staff at the time of notification. The notification unit, for example, uses AI to select the optimal notification method in consideration of the location information of the hall staff at the time of notification. Specific methods of acquiring and using location information include, for example, GPS data and indoor location information systems. For example, the notification unit issues a voice notification when the hall staff is nearby. Also, the notification unit can issue a visual notification when the hall staff is far away. Furthermore, the notification unit can select an appropriate notification method according to the location information of the hall staff. This makes it possible to select an appropriate notification method according to the location information of the hall staff.

[0055] The detailed analysis unit can analyze the meal progress and the arrangement of tableware in detail during the detailed analysis. The detailed analysis unit, for example, uses AI to analyze the meal progress and the arrangement of tableware in detail during the detailed analysis. Specific criteria and analysis methods for the meal progress and the arrangement of tableware include, for example, the stage of meal progress and the arrangement pattern of tableware. For example, the detailed analysis unit analyzes the meal progress in detail to grasp the timing for clearing away the tableware. In addition, the detailed analysis unit can analyze the arrangement of tableware in detail and propose the optimal arrangement. Furthermore, the detailed analysis unit can analyze the meal progress and the arrangement of tableware in detail to improve overall service. This makes it possible to analyze the meal progress and the arrangement of tableware in detail.

[0056] The detailed analysis unit can improve the accuracy of the analysis by referring to past detailed analysis data during detailed analysis. The detailed analysis unit can improve the accuracy of the analysis by referring to past detailed analysis data during detailed analysis, for example, using AI. Specific content and acquisition method of past detailed analysis data include, for example, the data storage period and the type of data. For example, the detailed analysis unit can improve the accuracy of the analysis by referring to past detailed analysis data. Also, the detailed analysis unit can predict the progress of the meal by referring to past detailed analysis data. Furthermore, the detailed analysis unit can optimize the arrangement of tableware by referring to past detailed analysis data. Thereby, the accuracy of the analysis is improved by referring to past detailed analysis data.

[0057] The detailed analysis unit can simultaneously analyze the drink consumption status and the cleanliness of the table during the detailed analysis. The detailed analysis unit, for example, uses AI to simultaneously analyze the drink consumption status and the cleanliness of the table during the detailed analysis. Specific standards and analysis methods for the drink consumption status and the cleanliness of the table include, for example, a method of measuring the consumption amount and an evaluation standard for the cleanliness. For example, the detailed analysis unit analyzes the drink consumption status at the same time as the detailed analysis to grasp the timing of refilling the drink. In addition, the detailed analysis unit can analyze the cleanliness of the table at the same time as the detailed analysis to grasp the need for cleaning. Furthermore, the detailed analysis unit can analyze the drink consumption status and the cleanliness of the table at the same time as the detailed analysis to improve overall service. This makes it possible to simultaneously analyze the drink consumption status and the cleanliness of the table.

[0058] The detailed analysis unit can simultaneously analyze the eating status of other customers during the detailed analysis. The detailed analysis unit, for example, uses AI to simultaneously analyze the eating status of other customers during the detailed analysis. Specific content and analysis methods of the eating status of other customers include, for example, the progress of the meal and the type of meal. For example, the detailed analysis unit analyzes the eating status of other customers simultaneously with the detailed analysis to improve the overall service. In addition, the detailed analysis unit can analyze the eating status of other customers simultaneously with the detailed analysis to provide optimal service. Furthermore, the detailed analysis unit can analyze the eating status of other customers simultaneously with the detailed analysis to improve the overall service. As a result, it is possible to improve the overall service by simultaneously analyzing the eating status of other customers.

[0059] The behavior identification unit can change the identification algorithm according to the type and frequency of the behavior when identifying the behavior. The behavior identification unit changes the identification algorithm according to the type and frequency of the behavior when identifying the behavior, for example, using AI. Specific standards and measurement methods for the type and frequency of the behavior include, for example, behavior categories and frequency measurement methods. For example, the behavior identification unit uses a detailed identification algorithm when there are many types of behavior. Also, the behavior identification unit can use a strict identification algorithm when the frequency of the behavior is high. Furthermore, the behavior identification unit can select an appropriate identification algorithm according to the type and frequency of the behavior. This makes it possible to use an appropriate identification algorithm according to the type and frequency of the behavior.

[0060] The behavior identification unit can improve the accuracy of identification by referring to past behavior data when identifying a behavior. The behavior identification unit can improve the accuracy of identification by referring to past behavior data when identifying a behavior, for example, using AI. Specific content and acquisition method of past behavior data include, for example, a data storage period and a data type. For example, the behavior identification unit refers to past behavior data to grasp a pattern of a behavior. Also, the behavior identification unit can grasp the frequency of a behavior by referring to past behavior data. Furthermore, the behavior identification unit can grasp the intensity of a behavior by referring to past behavior data. As a result, the accuracy of identification is improved by referring to past behavior data.

[0061] The behavior identification unit can simultaneously identify changes in voice and facial expression when identifying the behavior. The behavior identification unit can simultaneously identify changes in voice and facial expression when identifying the behavior, for example, using AI. Specific criteria and detection methods for changes in voice and facial expression include, for example, change patterns in voice tone and facial expression. For example, the behavior identification unit can simultaneously identify changes in voice and facial expression and grasp the cause of the behavior. In addition, the behavior identification unit can simultaneously identify changes in facial expression and grasp the cause of the behavior. Furthermore, the behavior identification unit can simultaneously identify changes in voice and facial expression and analyze the behavior comprehensively. As a result, it is possible to grasp the cause of the behavior by simultaneously identifying changes in voice and facial expression.

[0062] The behavior identification unit can simultaneously identify the reactions of other customers when identifying a behavior. The behavior identification unit, for example, uses AI to simultaneously identify the reactions of other customers when identifying a behavior. Specific content and detection methods of other customers' reactions include, for example, changes in gaze direction and facial expressions. For example, the behavior identification unit identifies the reactions of other customers at the same time as identifying the behavior, and grasps the impact of the behavior. In addition, the behavior identification unit can identify the reactions of other customers at the same time as identifying the behavior, and respond quickly. Furthermore, the behavior identification unit can identify the reactions of other customers at the same time as identifying the behavior, and analyze the behavior comprehensively. This makes it possible to grasp the impact of the behavior by simultaneously identifying the reactions of other customers.

[0063] The notification selection unit can select the optimal notification method by considering the current work status of the hall staff when selecting the notification method. The notification selection unit, for example, uses AI to select the optimal notification method by considering the current work status of the hall staff when selecting the notification method. Specific criteria and selection methods for the optimal notification method include, for example, the urgency of the notification and the status of the staff. For example, when the hall staff is busy, the notification selection unit selects a simple notification method. In addition, when the hall staff has time, the notification selection unit can select a detailed notification method. Furthermore, the notification selection unit can select an appropriate notification method according to the work status of the hall staff. This makes it possible to select an appropriate notification method according to the work status of the hall staff.

[0064] The notification selection unit can improve the accuracy of notifications by referring to past notification history when selecting a notification method. The notification selection unit can improve the accuracy of notifications by referring to past notification history when selecting a notification method, for example, using AI. Specific content and acquisition method of the past notification history include, for example, the type of notification and the frequency of notifications. For example, the notification selection unit selects an appropriate notification method by referring to the past notification history. In addition, the notification selection unit can optimize the timing of notifications by referring to the past notification history. Furthermore, the notification selection unit can customize the notification content by referring to the past notification history. As a result, the accuracy of notifications is improved by referring to the past notification history.

[0065] The notification selection unit can use not only audio and visual but also other notification means such as vibration and light when notifying. The notification selection unit can use not only audio and visual but also other notification means such as vibration and light when notifying, for example, using AI. Specific types and usage methods of notification means such as vibration and light include, for example, the strength of vibration and the color and pattern of light. For example, the notification selection unit can issue a vibration notification at the same time as the audio notification to alert the hall staff. In addition, the notification selection unit can issue a light notification at the same time as the visual notification to alert the hall staff. Furthermore, the notification selection unit can use a combination of multiple notification means such as audio, visual, vibration, and light. This makes it possible to effectively notify the hall staff by using multiple notification means.

[0066] The notification selection unit can select the optimal notification method in consideration of the location information of the hall staff at the time of notification. The notification selection unit, for example, uses AI to select the optimal notification method in consideration of the location information of the hall staff at the time of notification. Specific methods of acquiring and using location information include, for example, GPS data and indoor location information systems. For example, the notification selection unit issues a voice notification when the hall staff is nearby. Also, the notification selection unit can issue a visual notification when the hall staff is far away. Furthermore, the notification selection unit can select an appropriate notification method according to the location information of the hall staff. This makes it possible to select an appropriate notification method according to the location information of the hall staff.

[0067] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0068] When analyzing the eating situation, the analysis unit can change the analysis algorithm according to the type and amount of food. For example, for a light meal, a simple analysis algorithm can be used. For a full course meal, a detailed analysis algorithm can be used. Furthermore, for a large group meal, multiple analysis algorithms can be used in combination. This makes it possible to perform an appropriate analysis according to the type and amount of food.

[0069] When detecting an irregular behavior, the detection unit can change the detection algorithm according to the frequency or intensity of the behavior. For example, if the frequency of the behavior is high, a strict detection algorithm can be used. Also, if the intensity of the behavior is high, a detailed detection algorithm can be used. Furthermore, an appropriate detection algorithm can be selected according to the frequency and intensity of the behavior. This makes it possible to use an appropriate detection algorithm according to the frequency and intensity of the behavior.

[0070] When acquiring video data, the acquisition unit can change the acquisition method depending on a specific time period or congestion level. For example, video data is acquired frequently during busy times such as lunchtime, to quickly grasp the eating situation. Also, video data is acquired periodically during quiet times such as just before closing time, to efficiently check the eating situation. Furthermore, video data can be acquired in real time during specific events, to enable immediate response. This makes it possible to acquire appropriate video data depending on the time period and congestion level.

[0071] The notification unit can use not only audio and visual notification, but also other notification means such as vibration and light when notifying. For example, a vibration notification can be issued simultaneously with an audio notification to alert the hall staff. Also, a light notification can be issued simultaneously with a visual notification to alert the hall staff. Furthermore, multiple notification means such as audio, visual, vibration, and light can be used in combination. This makes it possible to effectively notify the hall staff by using multiple notification means.

[0072] When analyzing the eating situation, the analysis unit can improve the accuracy of the analysis by referring to past meal data. For example, the analysis unit can predict the progress of the meal by referring to the past meal data. The analysis unit can also predict the type and amount of food by referring to the past meal data. Furthermore, the analysis unit can predict the end timing of the meal by referring to the past meal data. Thus, by referring to the past data, the analysis unit can improve the accuracy of the analysis. For example, the analysis unit can predict the progress of the meal by referring to the past meal data. Also, the analysis unit can predict the type and amount of food by referring to the past meal data. Furthermore, the analysis unit can predict the end timing of the meal by referring to the past meal data.

[0073] The process flow of the first embodiment will be briefly described below.

[0074] Step 1: The acquisition unit acquires video data from a surveillance camera. The surveillance camera is installed, for example, on the ceiling or wall of a store and can cover a wide area. The acquisition unit can adjust, for example, the resolution and frame rate of the camera to acquire optimal video data. Step 2: The analysis unit analyzes the customer's eating status based on the video data acquired by the acquisition unit. The analysis unit, for example, uses AI to analyze the customer's movements and facial expressions to grasp the progress of the meal. For example, the analysis unit can determine whether the customer has finished their meal or whether they have run out of drinks. Step 3: The detection unit detects irregular customer behavior based on the video data acquired by the acquisition unit. The detection unit, for example, uses AI to analyze the customer's movements and facial expressions to detect abnormal behavior. For example, the detection unit can detect loud noises or other behavior that causes a nuisance to other customers. Step 4: The notification unit notifies the hall staff based on the information obtained by the analysis unit and the detection unit. The notification unit can convey the information to the hall staff using, for example, an audio notification or a visual notification. For example, the notification unit can send a notification to the hall staff's smartphone or tablet.

[0075] (Example 2) The AI-equipped surveillance camera system according to the embodiment of the present invention is a system that improves the efficiency of the work of the hall staff of a restaurant. In this system, surveillance cameras are installed, and AI analyzes the eating status of customers in real time. For example, AI determines whether the customer has finished their meal or whether the drink has run out. This allows the hall staff to clear away the dishes and refill the water at the appropriate time. Next, AI detects irregular behavior of the customer. For example, AI detects loud noises and other behaviors that cause trouble to other customers, and notifies the hall staff. This allows for a quick response and minimizes the inconvenience to other customers. This system consists of the following steps. 1. Surveillance cameras are installed, and AI analyzes the eating status of customers in real time. 2. AI grasps the eating status and notifies the hall staff. 3. AI detects irregular behavior and notifies the hall staff. This system improves the efficiency of the work of the hall staff and improves service to customers. It also makes it possible to monitor nuisance behavior, allowing customers to enjoy their meals with peace of mind. As a result, the AI-equipped surveillance camera system can improve the efficiency of the work of the hall staff and improve service to customers.

[0076] The AI-equipped surveillance camera system according to the embodiment includes an acquisition unit, an analysis unit, a detection unit, and a notification unit. The acquisition unit acquires video data from the surveillance camera. The surveillance camera is installed, for example, on the ceiling or wall inside the restaurant, and can cover a wide area. The acquisition unit can, for example, adjust the resolution and frame rate of the camera to acquire optimal video data. The analysis unit analyzes the customer's eating situation based on the video data acquired by the acquisition unit. The analysis unit, for example, uses AI to analyze the customer's movements and facial expressions to grasp the progress of the meal. For example, the analysis unit can determine whether the customer has finished the meal and whether the drink has run out. The detection unit detects irregular behavior of the customer based on the video data acquired by the acquisition unit. The detection unit, for example, uses AI to analyze the customer's movements and facial expressions to detect abnormal behavior. For example, the detection unit can detect loud noises, behaviors that cause a nuisance to other customers, and the like. The notification unit notifies the hall staff based on the information acquired by the analysis unit and the detection unit. The notification unit can convey information to the hall staff using, for example, audio notifications or visual notifications. For example, the notification unit can send notifications to the smartphones or tablets of the hall staff, which allows the AI-equipped surveillance camera system according to the embodiment to streamline the work of the hall staff and improve service to customers.

[0077] The acquisition unit acquires video data from the surveillance cameras. The surveillance cameras are installed, for example, on the ceiling or walls of the store and can cover a wide range. The acquisition unit can, for example, adjust the resolution and frame rate of the cameras to acquire optimal video data. Specifically, the surveillance cameras are equipped with high-resolution lenses and can clearly capture even the finest details in the store. Furthermore, the cameras are equipped with infrared sensors and high-sensitivity image sensors to provide high-quality images even in low-light environments. The acquisition unit acquires video data from these cameras in real time and transmits it to a central database. The video data is efficiently stored using compression technology so that the analysis unit and detection unit can access it as needed. In addition, the acquisition unit can remotely control the viewing angle and zoom function of the cameras and can focus on specific areas or objects. This allows the acquisition unit to grasp the situation in the store in detail and provide high-quality data to the analysis unit and detection unit. Furthermore, the acquisition unit can integrate video data from multiple cameras and centrally manage the overall situation. This allows the acquisition unit to efficiently and effectively collect data and improve the performance of the entire system.

[0078] The analysis unit analyzes the customer's eating situation based on the video data acquired by the acquisition unit. The analysis unit, for example, uses AI to analyze the customer's movements and facial expressions to grasp the progress of the meal. Specifically, the AI ​​uses deep learning technology to analyze the customer's movements and facial expressions with high accuracy. For example, the AI ​​detects the movement of the customer using a fork and knife to grasp the progress of the meal in real time. In addition, by analyzing the customer's facial expressions, it is possible to determine whether the customer is satisfied or dissatisfied. Furthermore, the AI ​​detects whether the contents of the drink glass are reduced and determines whether the drink needs to be refilled. This allows the analysis unit to grasp the customer's eating situation in detail and provide information to the hall staff to provide service at the appropriate time. The analysis unit can learn the meal progress pattern and the customer's behavior pattern by utilizing past data and statistical information, and perform more accurate analysis. For example, by analyzing the behavior pattern of the customer during a specific time period or day of the week and building a predictive model, it can be used to improve service in the future. This allows the analysis unit to contribute not only to grasping the situation in real time, but also to long-term service improvement.

[0079] The detection unit detects irregular customer behavior based on the video data acquired by the acquisition unit. The detection unit, for example, uses AI to analyze the customer's movements and facial expressions to detect abnormal behavior. Specifically, the AI ​​uses an anomaly detection algorithm to learn the customer's behavior patterns and detect unusual behavior in real time. For example, it can detect behavior such as shouting, disturbing other customers, suddenly standing up, and running around the store. In addition, the AI ​​can analyze the customer's facial expressions and detect emotions such as anger, dissatisfaction, and excitement. This allows the detection unit to quickly detect abnormal behavior and changes in emotion and issue a warning to the hall staff. The detection unit can learn patterns of abnormal behavior by utilizing past data and statistical information, and perform more accurate detection. For example, by analyzing the frequency of occurrence of abnormal behavior during specific times of the day or days of the week and building a predictive model, it can be used to help with future risk management. This allows the detection unit to not only detect abnormalities in real time, but also handle long-term risk management, improving the reliability and safety of the entire system.

[0080] The notification unit notifies the hall staff based on the information obtained by the analysis unit and the detection unit. The notification unit can convey information to the hall staff using, for example, audio or visual notifications. Specifically, the notification unit sends notifications to the hall staff's smartphones or tablets in real time to prompt them to take the necessary action. For example, when a customer has finished their meal or when a drink needs to be refilled, the hall staff is immediately notified of the information. In addition, when abnormal behavior is detected, a warning notification is issued to prompt a prompt response. The notification unit can reliably transmit information using multiple communication means. For example, important information can be reliably delivered by using not only smartphone notifications but also voice calls, SMS, emails, etc. in combination. Furthermore, the notification unit can collect feedback from the hall staff and continuously improve the accuracy and effectiveness of the notification content. For example, the timing and content of the notification can be reviewed based on feedback from the hall staff who received the notification, and more effective notification can be provided. As a result, the notification unit can quickly and reliably provide information to the hall staff, thereby improving work efficiency and service to customers.

[0081] The analysis unit may include a detailed analysis unit that performs detailed analysis of the eating situation. The detailed analysis unit performs detailed analysis of the eating situation of the customer using, for example, AI. For example, the detailed analysis unit can determine whether the customer has finished eating or whether the drink has run out. The detailed analysis unit can also grasp the progress of the customer's meal in real time and notify the hall staff. For example, the detailed analysis unit can notify the hall staff when the customer has finished eating, so that the tableware can be quickly cleared away. This enables detailed analysis of the eating situation.

[0082] The detection unit may include a behavior identification unit that detects specific behavior. The behavior identification unit detects specific behavior of customers by using, for example, AI. For example, the behavior identification unit can detect customers making loud noises or other behavior that causes a nuisance to other customers. The behavior identification unit can also analyze the movements and facial expressions of customers to detect abnormal behavior. For example, the behavior identification unit can detect behavior such as a customer suddenly standing up or abandoning their meal. This makes it possible to detect specific behavior in detail.

[0083] The notification unit may include a notification selection unit that selects the notification method. The notification selection unit may use, for example, AI to select the notification method for the hall staff. For example, the notification selection unit may select a method such as audio notification, visual notification, or vibration notification. The notification selection unit may also select the optimal notification method based on the work status and location information of the hall staff. For example, the notification selection unit may provide a brief notification when the hall staff is busy, and a detailed notification when the hall staff has time. This allows for flexible selection of the notification method.

[0084] The acquisition unit can acquire video data from a surveillance camera in real time. The acquisition unit acquires, for example, video data from a surveillance camera in real time. Specific definitions and standards of real time include, for example, delay time and data update frequency. The acquisition unit can adjust, for example, the resolution and frame rate of the camera to acquire optimal video data in real time. This makes it possible to acquire video data in real time.

[0085] The notification unit can notify the hall staff by voice or visually. The notification unit, for example, issues voice or visual notifications to the hall staff. A specific method of voice notification, for example, is to use a voice message. A specific method of visual notification, for example, is to use a visual alert. The notification unit can, for example, send a notification to the hall staff's smartphone or tablet. This makes it possible to notify the hall staff effectively.

[0086] The acquisition unit can estimate the customer's emotions and adjust the timing of acquiring the video data based on the estimated customer's emotions. The acquisition unit can estimate the customer's emotions using, for example, AI, and adjust the timing of acquiring the video data based on the estimated emotions. The emotion estimation is performed using, for example, technologies such as facial expression recognition, voice analysis, and behavior analysis. For example, when the customer is relaxed, the acquisition unit periodically acquires video data and checks the meal situation. In addition, when the customer is in a hurry, the acquisition unit can frequently acquire video data and quickly grasp the meal situation. Furthermore, when the customer is dissatisfied, the acquisition unit can acquire video data in real time to enable immediate response. This makes it possible to acquire video data at an appropriate timing according to the customer's emotions.

[0087] The acquisition unit can change the acquisition method according to a specific time period or congestion when acquiring video data. The acquisition unit, for example, uses AI to change the acquisition method according to a specific time period or congestion when acquiring video data. Specific definitions and standards of a specific time period or congestion include, for example, peak times and congestion indicators. For example, the acquisition unit frequently acquires video data during busy times such as lunchtime, and quickly grasps the eating situation. In addition, the acquisition unit periodically acquires video data during quiet times such as just before closing time, and can efficiently check the eating situation. Furthermore, the acquisition unit can acquire video data in real time during specific events, allowing for immediate response. This makes it possible to acquire appropriate video data according to the time period and congestion.

[0088] The acquisition unit can focus on a specific area or table when acquiring video data. The acquisition unit, for example, uses AI to focus on a specific area or table when acquiring video data. Specific ranges and criteria for a specific area or table include, for example, seat numbers and area divisions. For example, the acquisition unit acquires video data focusing on areas where many customers gather, and grasps the eating situation. In addition, the acquisition unit can acquire video data focusing on a specific table, and check the individual eating situation. Furthermore, the acquisition unit acquires video data focusing on areas where problems are likely to occur, and can respond quickly. This makes it possible to acquire video data focusing on a specific area or table.

[0089] The acquisition unit can estimate the emotion of a customer and determine the priority of the video data to be acquired based on the estimated emotion of the customer. The acquisition unit can estimate the emotion of a customer using, for example, AI and determine the priority of the video data to be acquired based on the estimated emotion. The emotion estimation is performed using, for example, technologies such as facial expression recognition, voice analysis, and behavior analysis. For example, when a customer is dissatisfied, the acquisition unit can preferentially acquire the video data of the customer. Furthermore, when a customer is relaxed, the acquisition unit can preferentially acquire the video data of other customers. Furthermore, when a customer is in a hurry, the acquisition unit can preferentially acquire the video data of the customer. This makes it possible to acquire video data in a priority order according to the emotion of the customer.

[0090] The acquisition unit can simultaneously acquire audio data when acquiring video data and use it for analysis. The acquisition unit, for example, uses AI to simultaneously acquire audio data when acquiring video data and use it for analysis. Specific types and formats of audio data include, for example, audio quality and recording method. For example, the acquisition unit acquires audio data simultaneously with the video data and analyzes the content of the customer's conversation. In addition, the acquisition unit can acquire audio data simultaneously with the video data and analyze the tone of the customer's voice. Furthermore, the acquisition unit can acquire audio data simultaneously with the video data and estimate emotions from the customer's voice. This makes it possible to simultaneously acquire video data and audio data and use them for analysis.

[0091] The acquisition unit can also acquire environmental data such as temperature or humidity when acquiring the video data, and use the data for analysis. The acquisition unit can, for example, use AI to acquire environmental data such as temperature and humidity when acquiring the video data, and use the data for analysis. Specific types and acquisition methods of environmental data include, for example, temperature sensors and humidity sensors. For example, the acquisition unit acquires temperature data simultaneously with the video data, and analyzes the comfort level of the customer. The acquisition unit can also acquire humidity data simultaneously with the video data, and analyze the comfort level of the customer. Furthermore, the acquisition unit can acquire environmental data simultaneously with the video data, and comprehensively analyze the comfort level of the customer. This makes it possible to acquire environmental data and use it for analysis.

[0092] The analysis unit can estimate the customer's emotions and adjust the analysis method of the eating situation based on the estimated customer's emotions. The analysis unit can estimate the customer's emotions using, for example, AI, and adjust the analysis method of the eating situation based on the estimated emotions. The emotion estimation is performed using, for example, technologies such as facial expression recognition, voice analysis, and behavior analysis. For example, the analysis unit uses a normal analysis method when the customer is relaxed. Also, the analysis unit can use a method of quickly analyzing the eating situation when the customer is in a hurry. Furthermore, the analysis unit can use a method of analyzing the eating situation in detail when the customer is dissatisfied. This makes it possible to use an appropriate analysis method according to the customer's emotions.

[0093] The analysis unit can change the analysis algorithm according to the type and amount of food when analyzing the eating situation. The analysis unit can change the analysis algorithm according to the type and amount of food when analyzing the eating situation, for example, using AI. Specific definitions and standards for the type and amount of food include, for example, food categories and units of amount. For example, the analysis unit uses a simple analysis algorithm for a light meal. Also, the analysis unit can use a detailed analysis algorithm for a full course meal. Furthermore, the analysis unit can use a combination of multiple analysis algorithms for a meal with a large number of people. This makes it possible to perform an appropriate analysis according to the type and amount of food.

[0094] The analysis unit can improve the accuracy of the analysis when analyzing the eating situation by referring to past meal data. The analysis unit can improve the accuracy of the analysis by referring to past meal data when analyzing the eating situation, for example, using AI. Specific content and acquisition method of past meal data include, for example, the data storage period and the type of data. For example, the analysis unit can predict the progress of the meal by referring to the past meal data. Furthermore, the analysis unit can predict the type and amount of the meal by referring to the past meal data. Furthermore, the analysis unit can predict the timing of the end of the meal by referring to the past meal data. Thereby, the accuracy of the analysis is improved by referring to the past data.

[0095] The analysis unit can estimate the customer's emotions and adjust the display method of the analysis results based on the estimated customer's emotions. The analysis unit can estimate the customer's emotions using, for example, AI, and adjust the display method of the analysis results based on the estimated emotions. The emotion estimation is performed using, for example, technologies such as facial expression recognition, voice analysis, and behavior analysis. For example, the analysis unit can display detailed analysis results when the customer is relaxed. Furthermore, the analysis unit can display concise analysis results when the customer is in a hurry. Furthermore, the analysis unit can display detailed analysis results when the customer is dissatisfied. This makes it possible to use an appropriate display method according to the customer's emotions.

[0096] The analysis unit can analyze the beverage consumption status at the same time as analyzing the meal status. The analysis unit, for example, uses AI to analyze the beverage consumption status at the same time as analyzing the meal status. Specific content and criteria of the beverage consumption status include, for example, the type of beverage and the amount consumed. For example, the analysis unit analyzes the beverage consumption status at the same time as the meal status and determines the timing for refilling the beverage. The analysis unit can also analyze the beverage consumption status at the same time as the meal status and determine the type of beverage. Furthermore, the analysis unit can analyze the beverage consumption status at the same time as the meal status and determine the amount of beverage consumed. This makes it possible to analyze the beverage consumption status at the same time.

[0097] The analysis unit can also analyze the cleanliness and arrangement of the table when analyzing the meal situation. The analysis unit, for example, uses AI to analyze the cleanliness and arrangement of the table when analyzing the meal situation. Specific standards and methods for the cleanliness and arrangement of the table include, for example, cleaning frequency and arrangement patterns. For example, the analysis unit analyzes the cleanliness of the table at the same time as the meal situation and grasps the need for cleaning. In addition, the analysis unit can analyze the arrangement of the table at the same time as the meal situation and propose the optimal arrangement. Furthermore, the analysis unit can analyze the cleanliness and arrangement of the table at the same time as the meal situation, and improve overall service. This makes it possible to simultaneously analyze the cleanliness and arrangement of the table.

[0098] The detection unit can estimate the customer's emotions and adjust the detection criteria for irregular behavior based on the estimated customer's emotions. The detection unit can estimate the customer's emotions using, for example, AI, and adjust the detection criteria for irregular behavior based on the estimated emotions. The emotion estimation is performed using, for example, technologies such as facial expression recognition, voice analysis, and behavior analysis. For example, the detection unit can set strict detection criteria when the customer is dissatisfied. Furthermore, the detection unit can set normal detection criteria when the customer is relaxed. Furthermore, the detection unit can set lenient detection criteria when the customer is excited. This makes it possible to set appropriate detection criteria according to the customer's emotions.

[0099] The detection unit can change the detection algorithm according to the frequency or intensity of the behavior when detecting an irregular behavior. The detection unit, for example, changes the detection algorithm according to the frequency or intensity of the behavior when detecting an irregular behavior using AI. Specific standards and measurement methods for the frequency or intensity of a behavior include, for example, the number of times the behavior occurs and the intensity of the behavior. For example, the detection unit uses a strict detection algorithm when the frequency of the behavior is high. Furthermore, the detection unit can use a detailed detection algorithm when the intensity of the behavior is high. Furthermore, the detection unit can select an appropriate detection algorithm according to the frequency or intensity of the behavior. This makes it possible to use an appropriate detection algorithm according to the frequency or intensity of the behavior.

[0100] The detection unit can improve the accuracy of detection when detecting an irregular behavior by referring to past behavior data. The detection unit can improve the accuracy of detection by referring to past behavior data when detecting an irregular behavior, for example, using AI. Specific content and acquisition method of the past behavior data include, for example, a data storage period and a data type. For example, the detection unit refers to the past behavior data to grasp the pattern of the irregular behavior. Also, the detection unit can grasp the frequency of the irregular behavior by referring to the past behavior data. Furthermore, the detection unit can grasp the intensity of the irregular behavior by referring to the past behavior data. As a result, the accuracy of detection is improved by referring to the past behavior data.

[0101] The detection unit can estimate the customer's emotion and adjust the display method of the detection result based on the estimated emotion of the customer. The detection unit can estimate the customer's emotion using, for example, AI, and adjust the display method of the detection result based on the estimated emotion. The emotion estimation is performed using, for example, technologies such as facial expression recognition, voice analysis, and behavior analysis. For example, the detection unit can display a detailed detection result when the customer is dissatisfied. Furthermore, the detection unit can display a concise detection result when the customer is relaxed. Furthermore, the detection unit can display a visually easy-to-understand detection result when the customer is excited. This makes it possible to use an appropriate display method according to the customer's emotion.

[0102] The detection unit can simultaneously detect a change in voice or facial expression when detecting an irregular behavior. The detection unit, for example, uses AI to simultaneously detect a change in voice or facial expression when detecting an irregular behavior. Specific criteria and detection methods for changes in voice and facial expression include, for example, a change pattern in voice tone or facial expression. For example, the detection unit detects a change in voice at the same time as the irregular behavior and grasps the cause of the behavior. In addition, the detection unit can detect a change in facial expression at the same time as the irregular behavior and grasp the cause of the behavior. Furthermore, the detection unit can detect a change in voice or facial expression at the same time as the irregular behavior and analyze the behavior comprehensively. As a result, it is possible to grasp the cause of the behavior by simultaneously detecting changes in voice and facial expression.

[0103] The detection unit can simultaneously detect the reactions of other customers when it detects irregular behavior. The detection unit, for example, uses AI to simultaneously detect the reactions of other customers when it detects irregular behavior. Specific content and detection methods of other customers' reactions include, for example, changes in gaze direction and facial expressions. For example, the detection unit detects the reactions of other customers at the same time as the irregular behavior and grasps the impact of the behavior. In addition, the detection unit can detect the reactions of other customers at the same time as the irregular behavior and respond quickly. Furthermore, the detection unit can detect the reactions of other customers at the same time as the irregular behavior and analyze the behavior comprehensively. This makes it possible to grasp the impact of the behavior by simultaneously detecting the reactions of other customers.

[0104] The notification unit can estimate the customer's emotions and adjust the timing of the notification based on the estimated customer's emotions. The notification unit can estimate the customer's emotions using, for example, AI, and adjust the timing of the notification based on the estimated emotions. The emotion estimation is performed using, for example, technologies such as facial expression recognition, voice analysis, and behavior analysis. For example, the notification unit can immediately notify the customer when the customer is dissatisfied. Furthermore, the notification unit can notify the customer at an appropriate time when the customer is relaxed. Furthermore, the notification unit can quickly notify the customer when the customer is in a hurry. This makes it possible to notify the customer at an appropriate time according to the customer's emotions.

[0105] The notification unit can select the optimal notification method in consideration of the current work status of the hall staff at the time of notification. The notification unit, for example, uses AI to select the optimal notification method in consideration of the current work status of the hall staff at the time of notification. Specific criteria and selection methods for the optimal notification method include, for example, the urgency of the notification and the status of the staff. For example, if the hall staff is busy, the notification unit provides a brief notification. Also, if the hall staff has time, the notification unit can provide a detailed notification. Furthermore, the notification unit can select an appropriate notification method according to the work status of the hall staff. This makes it possible to select an appropriate notification method according to the work status of the hall staff.

[0106] The notification unit can improve the accuracy of notifications by referring to past notification history at the time of notification. The notification unit can improve the accuracy of notifications by referring to past notification history at the time of notification, for example, using AI. Specific contents and acquisition methods of the past notification history include, for example, the type of notification and the frequency of notifications. For example, the notification unit can refer to the past notification history to grasp the appropriate timing of notification. Also, the notification unit can refer to the past notification history to grasp the appropriate notification content. Furthermore, the notification unit can improve the accuracy of notifications by referring to the past notification history. As a result, the accuracy of notifications is improved by referring to the past notification history.

[0107] The notification unit can estimate the customer's emotions and customize the notification content based on the estimated customer's emotions. The notification unit can estimate the customer's emotions using, for example, AI, and customize the notification content based on the estimated emotions. Emotion estimation is performed using, for example, technologies such as facial expression recognition, voice analysis, and behavior analysis. For example, when the customer is dissatisfied, the notification unit can provide notification content that encourages a quick response. Furthermore, when the customer is relaxed, the notification unit can provide notification content that includes detailed information. Furthermore, when the customer is in a hurry, the notification unit can provide notification content that is concise. This makes it possible to provide appropriate notification content according to the customer's emotions.

[0108] The notification unit can use not only audio and visual but also other notification means such as vibration and light when notifying. The notification unit can use not only audio and visual but also other notification means such as vibration and light when notifying, for example, using AI. Specific types and usage methods of notification means such as vibration and light include, for example, the strength of vibration and the color and pattern of light. For example, the notification unit can issue a vibration notification at the same time as the audio notification to alert the hall staff. In addition, the notification unit can issue a light notification at the same time as the visual notification to alert the hall staff. Furthermore, the notification unit can use a combination of multiple notification means such as audio, visual, vibration, and light. As a result, it is possible to effectively notify the hall staff by using multiple notification means.

[0109] The notification unit can select the optimal notification method in consideration of the location information of the hall staff at the time of notification. The notification unit, for example, uses AI to select the optimal notification method in consideration of the location information of the hall staff at the time of notification. Specific methods of acquiring and using location information include, for example, GPS data and indoor location information systems. For example, the notification unit issues a voice notification when the hall staff is nearby. Also, the notification unit can issue a visual notification when the hall staff is far away. Furthermore, the notification unit can select an appropriate notification method according to the location information of the hall staff. This makes it possible to select an appropriate notification method according to the location information of the hall staff.

[0110] The detailed analysis unit can estimate the customer's emotions and adjust the method of detailed analysis based on the estimated customer's emotions. The detailed analysis unit can estimate the customer's emotions using, for example, AI, and adjust the method of detailed analysis based on the estimated emotions. Emotion estimation is performed using, for example, techniques such as facial expression recognition, voice analysis, and behavior analysis. For example, the detailed analysis unit uses a normal detailed analysis method when the customer is relaxed. Also, the detailed analysis unit can use a method of performing a quick detailed analysis when the customer is in a hurry. Furthermore, the detailed analysis unit can use a method of performing a detailed analysis when the customer is dissatisfied. This makes it possible to use an appropriate detailed analysis method according to the customer's emotions.

[0111] The detailed analysis unit can analyze the meal progress and the arrangement of tableware in detail during the detailed analysis. The detailed analysis unit, for example, uses AI to analyze the meal progress and the arrangement of tableware in detail during the detailed analysis. Specific criteria and analysis methods for the meal progress and the arrangement of tableware include, for example, the stage of meal progress and the arrangement pattern of tableware. For example, the detailed analysis unit analyzes the meal progress in detail to grasp the timing for clearing away the tableware. In addition, the detailed analysis unit can analyze the arrangement of tableware in detail and propose the optimal arrangement. Furthermore, the detailed analysis unit can analyze the meal progress and the arrangement of tableware in detail to improve overall service. This makes it possible to analyze the meal progress and the arrangement of tableware in detail.

[0112] The detailed analysis unit can improve the accuracy of the analysis by referring to past detailed analysis data during detailed analysis. The detailed analysis unit can improve the accuracy of the analysis by referring to past detailed analysis data during detailed analysis, for example, using AI. Specific content and acquisition method of past detailed analysis data include, for example, the data storage period and the type of data. For example, the detailed analysis unit can improve the accuracy of the analysis by referring to past detailed analysis data. Also, the detailed analysis unit can predict the progress of the meal by referring to past detailed analysis data. Furthermore, the detailed analysis unit can optimize the arrangement of tableware by referring to past detailed analysis data. Thereby, the accuracy of the analysis is improved by referring to past detailed analysis data.

[0113] The detailed analysis unit can estimate the customer's emotions and adjust the display method of the detailed analysis results based on the estimated customer's emotions. The detailed analysis unit can estimate the customer's emotions using, for example, AI, and adjust the display method of the detailed analysis results based on the estimated emotions. The emotion estimation is performed using, for example, technologies such as facial expression recognition, voice analysis, and behavior analysis. For example, the detailed analysis unit can display detailed analysis results when the customer is relaxed. Furthermore, the detailed analysis unit can display concise analysis results when the customer is in a hurry. Furthermore, the detailed analysis unit can display detailed analysis results when the customer is dissatisfied. This makes it possible to use an appropriate display method according to the customer's emotions.

[0114] The detailed analysis unit can simultaneously analyze the drink consumption status and the cleanliness of the table during the detailed analysis. The detailed analysis unit, for example, uses AI to simultaneously analyze the drink consumption status and the cleanliness of the table during the detailed analysis. Specific standards and analysis methods for the drink consumption status and the cleanliness of the table include, for example, a method of measuring the consumption amount and an evaluation standard for the cleanliness. For example, the detailed analysis unit analyzes the drink consumption status at the same time as the detailed analysis to grasp the timing of refilling the drink. In addition, the detailed analysis unit can analyze the cleanliness of the table at the same time as the detailed analysis to grasp the need for cleaning. Furthermore, the detailed analysis unit can analyze the drink consumption status and the cleanliness of the table at the same time as the detailed analysis to improve overall service. This makes it possible to simultaneously analyze the drink consumption status and the cleanliness of the table.

[0115] The detailed analysis unit can simultaneously analyze the eating status of other customers during the detailed analysis. The detailed analysis unit, for example, uses AI to simultaneously analyze the eating status of other customers during the detailed analysis. Specific content and analysis methods of the eating status of other customers include, for example, the progress of the meal and the type of meal. For example, the detailed analysis unit analyzes the eating status of other customers simultaneously with the detailed analysis to improve the overall service. In addition, the detailed analysis unit can analyze the eating status of other customers simultaneously with the detailed analysis to provide optimal service. Furthermore, the detailed analysis unit can analyze the eating status of other customers simultaneously with the detailed analysis to improve the overall service. As a result, it is possible to improve the overall service by simultaneously analyzing the eating status of other customers.

[0116] The behavior identification unit can estimate the customer's emotions and adjust the behavior identification criteria based on the estimated customer's emotions. The behavior identification unit can estimate the customer's emotions using, for example, AI, and adjust the behavior identification criteria based on the estimated emotions. The emotion estimation is performed using, for example, techniques such as facial expression recognition, voice analysis, and behavior analysis. For example, the behavior identification unit can set strict behavior identification criteria when the customer is dissatisfied. Furthermore, the behavior identification unit can set normal behavior identification criteria when the customer is relaxed. Furthermore, the behavior identification unit can set lenient behavior identification criteria when the customer is excited. This makes it possible to set appropriate behavior identification criteria according to the customer's emotions.

[0117] The behavior identification unit can change the identification algorithm according to the type and frequency of the behavior when identifying the behavior. The behavior identification unit changes the identification algorithm according to the type and frequency of the behavior when identifying the behavior, for example, using AI. Specific standards and measurement methods for the type and frequency of the behavior include, for example, behavior categories and frequency measurement methods. For example, the behavior identification unit uses a detailed identification algorithm when there are many types of behavior. Also, the behavior identification unit can use a strict identification algorithm when the frequency of the behavior is high. Furthermore, the behavior identification unit can select an appropriate identification algorithm according to the type and frequency of the behavior. This makes it possible to use an appropriate identification algorithm according to the type and frequency of the behavior.

[0118] The behavior identification unit can improve the accuracy of identification by referring to past behavior data when identifying a behavior. The behavior identification unit can improve the accuracy of identification by referring to past behavior data when identifying a behavior, for example, using AI. Specific content and acquisition method of past behavior data include, for example, a data storage period and a data type. For example, the behavior identification unit refers to past behavior data to grasp a pattern of a behavior. Also, the behavior identification unit can grasp the frequency of a behavior by referring to past behavior data. Furthermore, the behavior identification unit can grasp the intensity of a behavior by referring to past behavior data. As a result, the accuracy of identification is improved by referring to past behavior data.

[0119] The behavior identification unit can estimate the customer's emotion and adjust the display method of the behavior identification result based on the estimated emotion of the customer. The behavior identification unit can estimate the customer's emotion using, for example, AI, and adjust the display method of the behavior identification result based on the estimated emotion. The emotion estimation is performed using, for example, technologies such as facial expression recognition, voice analysis, and behavior analysis. For example, when the customer is dissatisfied, the behavior identification unit can display a detailed behavior identification result. Furthermore, when the customer is relaxed, the behavior identification unit can display a simple behavior identification result. Furthermore, when the customer is excited, the behavior identification unit can display a visually easy-to-understand behavior identification result. This makes it possible to use an appropriate display method according to the customer's emotion.

[0120] The behavior identification unit can simultaneously identify changes in voice and facial expression when identifying the behavior. The behavior identification unit can simultaneously identify changes in voice and facial expression when identifying the behavior, for example, using AI. Specific criteria and detection methods for changes in voice and facial expression include, for example, change patterns in voice tone and facial expression. For example, the behavior identification unit can simultaneously identify changes in voice and facial expression and grasp the cause of the behavior. In addition, the behavior identification unit can simultaneously identify changes in facial expression and grasp the cause of the behavior. Furthermore, the behavior identification unit can simultaneously identify changes in voice and facial expression and analyze the behavior comprehensively. As a result, it is possible to grasp the cause of the behavior by simultaneously identifying changes in voice and facial expression.

[0121] The behavior identification unit can simultaneously identify the reactions of other customers when identifying a behavior. The behavior identification unit, for example, uses AI to simultaneously identify the reactions of other customers when identifying a behavior. Specific content and detection methods of other customers' reactions include, for example, changes in gaze direction and facial expressions. For example, the behavior identification unit identifies the reactions of other customers at the same time as identifying the behavior, and grasps the impact of the behavior. In addition, the behavior identification unit can identify the reactions of other customers at the same time as identifying the behavior, and respond quickly. Furthermore, the behavior identification unit can identify the reactions of other customers at the same time as identifying the behavior, and analyze the behavior comprehensively. This makes it possible to grasp the impact of the behavior by simultaneously identifying the reactions of other customers.

[0122] The notification selection unit can estimate the customer's emotions and select a notification method based on the estimated customer's emotions. The notification selection unit can estimate the customer's emotions using, for example, AI, and select a notification method based on the estimated emotions. Emotion estimation is performed using, for example, technologies such as facial expression recognition, voice analysis, and behavior analysis. For example, when a customer is dissatisfied, the notification selection unit selects a notification method that encourages a quick response. Furthermore, when a customer is relaxed, the notification selection unit can select a notification method that includes detailed information. Furthermore, when a customer is in a hurry, the notification selection unit can select a concise notification method. This makes it possible to select an appropriate notification method according to the customer's emotions.

[0123] The notification selection unit can select the optimal notification method by considering the current work status of the hall staff when selecting the notification method. The notification selection unit, for example, uses AI to select the optimal notification method by considering the current work status of the hall staff when selecting the notification method. Specific criteria and selection methods for the optimal notification method include, for example, the urgency of the notification and the status of the staff. For example, when the hall staff is busy, the notification selection unit selects a simple notification method. In addition, when the hall staff has time, the notification selection unit can select a detailed notification method. Furthermore, the notification selection unit can select an appropriate notification method according to the work status of the hall staff. This makes it possible to select an appropriate notification method according to the work status of the hall staff.

[0124] The notification selection unit can improve the accuracy of notifications by referring to past notification history when selecting a notification method. The notification selection unit can improve the accuracy of notifications by referring to past notification history when selecting a notification method, for example, using AI. Specific content and acquisition method of the past notification history include, for example, the type of notification and the frequency of notifications. For example, the notification selection unit selects an appropriate notification method by referring to the past notification history. In addition, the notification selection unit can optimize the timing of notifications by referring to the past notification history. Furthermore, the notification selection unit can customize the notification content by referring to the past notification history. As a result, the accuracy of notifications is improved by referring to the past notification history.

[0125] The notification selection unit can estimate the customer's emotions and customize the notification content based on the estimated customer's emotions. The notification selection unit can estimate the customer's emotions using, for example, AI, and customize the notification content based on the estimated emotions. The emotion estimation is performed using, for example, technologies such as facial expression recognition, voice analysis, and behavior analysis. For example, when the customer is dissatisfied, the notification selection unit sets the notification content to encourage a quick response. Furthermore, when the customer is relaxed, the notification selection unit can set the notification content to include detailed information. Furthermore, when the customer is in a hurry, the notification selection unit can set the notification content to be concise. This makes it possible to provide appropriate notification content according to the customer's emotions.

[0126] The notification selection unit can use not only audio and visual but also other notification means such as vibration and light when notifying. The notification selection unit can use not only audio and visual but also other notification means such as vibration and light when notifying, for example, using AI. Specific types and usage methods of notification means such as vibration and light include, for example, the strength of vibration and the color and pattern of light. For example, the notification selection unit can issue a vibration notification at the same time as the audio notification to alert the hall staff. In addition, the notification selection unit can issue a light notification at the same time as the visual notification to alert the hall staff. Furthermore, the notification selection unit can use a combination of multiple notification means such as audio, visual, vibration, and light. This makes it possible to effectively notify the hall staff by using multiple notification means.

[0127] The notification selection unit can select the optimal notification method in consideration of the location information of the hall staff at the time of notification. The notification selection unit, for example, uses AI to select the optimal notification method in consideration of the location information of the hall staff at the time of notification. Specific methods of acquiring and using location information include, for example, GPS data and indoor location information systems. For example, the notification selection unit issues a voice notification when the hall staff is nearby. Also, the notification selection unit can issue a visual notification when the hall staff is far away. Furthermore, the notification selection unit can select an appropriate notification method according to the location information of the hall staff. This makes it possible to select an appropriate notification method according to the location information of the hall staff.

[0128] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0129] When analyzing the eating situation, the analysis unit can change the analysis algorithm according to the type and amount of food. For example, for a light meal, a simple analysis algorithm can be used. For a full course meal, a detailed analysis algorithm can be used. Furthermore, for a large group meal, multiple analysis algorithms can be used in combination. This makes it possible to perform an appropriate analysis according to the type and amount of food.

[0130] When detecting an irregular behavior, the detection unit can change the detection algorithm according to the frequency or intensity of the behavior. For example, if the frequency of the behavior is high, a strict detection algorithm can be used. Also, if the intensity of the behavior is high, a detailed detection algorithm can be used. Furthermore, an appropriate detection algorithm can be selected according to the frequency and intensity of the behavior. This makes it possible to use an appropriate detection algorithm according to the frequency and intensity of the behavior.

[0131] When acquiring video data, the acquisition unit can change the acquisition method depending on a specific time period or congestion level. For example, video data is acquired frequently during busy times such as lunchtime, to quickly grasp the eating situation. Also, video data is acquired periodically during quiet times such as just before closing time, to efficiently check the eating situation. Furthermore, video data can be acquired in real time during specific events, to enable immediate response. This makes it possible to acquire appropriate video data depending on the time period and congestion level.

[0132] The notification unit can use not only audio and visual notification, but also other notification means such as vibration and light when notifying. For example, a vibration notification can be issued simultaneously with an audio notification to alert the hall staff. Also, a light notification can be issued simultaneously with a visual notification to alert the hall staff. Furthermore, multiple notification means such as audio, visual, vibration, and light can be used in combination. This makes it possible to effectively notify the hall staff by using multiple notification means.

[0133] When analyzing the eating situation, the analysis unit can improve the accuracy of the analysis by referring to past meal data. For example, the analysis unit can predict the progress of the meal by referring to the past meal data. The analysis unit can also predict the type and amount of food by referring to the past meal data. Furthermore, the analysis unit can predict the end timing of the meal by referring to the past meal data. Thus, by referring to the past data, the analysis unit can improve the accuracy of the analysis. For example, the analysis unit can predict the progress of the meal by referring to the past meal data. Also, the analysis unit can predict the type and amount of food by referring to the past meal data. Furthermore, the analysis unit can predict the end timing of the meal by referring to the past meal data.

[0134] The acquisition unit can estimate the customer's emotions and adjust the timing of acquiring the video data based on the estimated customer's emotions. For example, if the customer is relaxed, video data can be acquired periodically to check the eating situation. If the customer is in a hurry, video data can be acquired frequently to quickly grasp the eating situation. Furthermore, if the customer is dissatisfied, video data can be acquired in real time to enable immediate response. This makes it possible to acquire video data at an appropriate timing according to the customer's emotions.

[0135] The analysis unit can estimate the customer's emotions and adjust the method of analyzing the eating situation based on the estimated customer's emotions. For example, if the customer is relaxed, a normal analysis method can be used. If the customer is in a hurry, a method of quickly analyzing the eating situation can be used. Furthermore, if the customer is dissatisfied, a method of analyzing the eating situation in detail can be used. This makes it possible to use an appropriate analysis method according to the customer's emotions.

[0136] The detection unit can estimate the customer's emotions and adjust the detection criteria for irregular behavior based on the estimated customer's emotions. For example, if the customer is dissatisfied, strict detection criteria can be set. If the customer is relaxed, normal detection criteria can be set. Furthermore, if the customer is excited, lenient detection criteria can be set. This makes it possible to set appropriate detection criteria according to the customer's emotions.

[0137] The notification unit can estimate the customer's emotions and adjust the timing of the notification based on the estimated customer's emotions. For example, if the customer is dissatisfied, the notification can be made immediately. If the customer is relaxed, the notification can be made at an appropriate time. If the customer is in a hurry, the notification can be made quickly. This makes it possible to make notifications at appropriate times according to the customer's emotions.

[0138] The notification unit can estimate the customer's emotions and customize the notification content based on the estimated customer's emotions. For example, if the customer is dissatisfied, the notification content can be set to encourage a quick response. If the customer is relaxed, the notification content can include detailed information. If the customer is in a hurry, the notification content can be simple. This makes it possible to provide appropriate notification content according to the customer's emotions.

[0139] The process flow of the second embodiment will be briefly described below.

[0140] Step 1: The acquisition unit acquires video data from a surveillance camera. The surveillance camera is installed, for example, on the ceiling or wall of a store and can cover a wide area. The acquisition unit can adjust, for example, the resolution and frame rate of the camera to acquire optimal video data. Step 2: The analysis unit analyzes the customer's eating status based on the video data acquired by the acquisition unit. The analysis unit, for example, uses AI to analyze the customer's movements and facial expressions to grasp the progress of the meal. For example, the analysis unit can determine whether the customer has finished their meal or whether they have run out of drinks. Step 3: The detection unit detects irregular customer behavior based on the video data acquired by the acquisition unit. The detection unit, for example, uses AI to analyze the customer's movements and facial expressions to detect abnormal behavior. For example, the detection unit can detect loud noises or other behavior that causes a nuisance to other customers. Step 4: The notification unit notifies the hall staff based on the information obtained by the analysis unit and the detection unit. The notification unit can convey the information to the hall staff using, for example, an audio notification or a visual notification. For example, the notification unit can send a notification to the hall staff's smartphone or tablet.

[0141] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0142] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0143] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0144] For example, the acquisition unit is realized by the camera 42 of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the customer's actions and facial expressions using AI. For example, the detection unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the notification unit is realized by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12, and transmits notifications to the smartphones or tablets of the wait staff. The correspondence between each unit and the devices or control units is not limited to the above-mentioned examples, and various changes are possible.

[0145] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0146] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0147] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0148] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0149] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0151] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0152] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0153] 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.

[0154] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0155] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0156] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0157] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0158] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0159] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0160] For example, the acquisition unit is realized by the camera 42 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the customer's actions and facial expressions using AI. For example, the detection unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the notification unit is realized by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and transmits a notification to the smartphone or tablet of the waiter. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0161] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0162] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0163] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0164] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0165] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0167] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0168] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0169] 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.

[0170] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0171] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0172] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0173] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0174] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0175] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0176] For example, the acquisition unit is realized by the camera 42 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the customer's actions and facial expressions using AI. For example, the detection unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the notification unit is realized by the speaker 240 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and transmits notifications to the smartphones or tablets of the wait staff. The correspondence between each unit and the devices or control units is not limited to the above-mentioned examples, and various changes are possible.

[0177] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0178] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0179] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0180] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0181] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0182] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0183] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0184] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0185] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0186] 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.

[0187] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0188] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0189] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0190] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0191] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0192] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0193] For example, the acquisition unit is realized by the camera 42 of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the customer's movements and facial expressions using AI. For example, the detection unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the notification unit is realized by the speaker 240 of the robot 414 or the specific processing unit 290 of the data processing device 12, and transmits notifications to the smartphones or tablets of the hall staff. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0194] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0195] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0196] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0197] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0198] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0199] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0200] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0201] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0202] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0203] In addition, 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 upon request from the data processing device 12.

[0204] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0205] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0206] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0207] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0208] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0209] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0210] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0211] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0212] (Appendix 1) An acquisition unit that acquires video data from a surveillance camera; an analysis unit that analyzes the eating habits of customers based on the video data acquired by the acquisition unit; A detection unit that detects abnormal behavior of a customer based on the video data acquired by the acquisition unit; a notification unit that notifies a hall staff member based on the information obtained by the analysis unit and the detection unit. A system characterized by: (Appendix 2) The analysis unit is Equipped with a detailed analysis section that analyzes eating habits in detail 2. The system of claim 1, (Appendix 3) The detection unit is Equipped with a behavior identification unit that detects specific behaviors 2. The system of claim 1, (Appendix 4) The notification unit is Equipped with a notification selection section for selecting the notification method 2. The system of claim 1, (Appendix 5) The acquisition unit is Acquire video data from surveillance cameras in real time 2. The system of claim 1, (Appendix 6) The notification unit is Provide audio or visual notifications to hall staff 2. The system of claim 1, (Appendix 7) The acquisition unit is Estimate customer emotions and adjust the timing of video data acquisition based on the estimated customer emotions 2. The system of claim 1, (Appendix 8) The acquisition unit is When acquiring video data, change the acquisition method according to specific time periods or congestion situations. 2. The system of claim 1, (Appendix 9) The acquisition unit is Focus on a specific area or table when capturing video data 2. The system of claim 1, (Appendix 10) The acquisition unit is Estimate customer emotions and prioritize video data to be acquired based on the estimated customer emotions 2. The system of claim 1, (Appendix 11) The acquisition unit is When acquiring video data, audio data is also acquired at the same time and used for analysis. 2. The system of claim 1, (Appendix 12) The acquisition unit is When acquiring video data, environmental data such as temperature and humidity are also acquired and used for analysis. 2. The system of claim 1, (Appendix 13) The analysis unit is Infer customer emotions and adjust meal analysis methods based on the inferred customer emotions 2. The system of claim 1, (Appendix 14) The analysis unit is When analyzing meal status, the analysis algorithm is changed according to the type and amount of food 2. The system of claim 1, (Appendix 15) The analysis unit is When analyzing dietary habits, past dietary data is referenced to improve the accuracy of the analysis. 2. The system of claim 1, (Appendix 16) The analysis unit is Infer customer sentiment and adjust how analytics results are displayed based on the inferred customer sentiment 2. The system of claim 1, (Appendix 17) The analysis unit is When analyzing meal habits, beverage consumption is also analyzed at the same time. 2. The system of claim 1, (Appendix 18) The analysis unit is When analyzing dining status, the cleanliness and arrangement of tables are also analyzed. 2. The system of claim 1, (Appendix 19) The detection unit is Infer customer sentiment and adjust irregular behavior detection criteria based on the inferred customer sentiment 2. The system of claim 1, (Appendix 20) The detection unit is When detecting irregular behavior, the detection algorithm changes depending on the frequency or intensity of the behavior. 2. The system of claim 1, (Appendix 21) The detection unit is When detecting irregular behavior, improve detection accuracy by referencing past behavior data. 2. The system of claim 1, (Appendix 22) The detection unit is Infer customer sentiment and adjust how detection results are displayed based on the inferred customer sentiment 2. The system of claim 1, (Appendix 23) The detection unit is When detecting irregular behavior, changes in voice or facial expression are also detected at the same time. 2. The system of claim 1, (Appendix 24) The detection unit is When detecting irregular behavior, the reactions of other customers are also detected at the same time. 2. The system of claim 1, (Appendix 25) The notification unit is Infer customer sentiment and adjust notification timing based on estimated customer sentiment 2. The system of claim 1, (Appendix 26) The notification unit is When notifying customers, the most appropriate notification method is selected taking into account the current work situation of the hall staff. 2. The system of claim 1, (Appendix 27) The notification unit is When receiving a notification, refer to the notification history to improve the accuracy of the notification. 2. The system of claim 1, (Appendix 28) The notification unit is Infer customer sentiment and customize notifications based on the inferred sentiment 2. The system of claim 1, (Appendix 29) The notification unit is When notifying users, use not only audio and visual notifications but also other means such as vibration and light. 2. The system of claim 1, (Appendix 30) The notification unit is When notifying customers, the optimal notification method is selected taking into account the location information of the hall staff. 2. The system of claim 1, (Appendix 31) The detailed analysis unit is Infer customer sentiment and adjust detailed analysis methods based on the inferred customer sentiment 3. The system of claim 2, (Appendix 32) The detailed analysis unit is During detailed analysis, the meal progress and tableware arrangement are analyzed in detail. 3. The system of claim 2, (Appendix 33) The detailed analysis unit is When conducting detailed analysis, improve the accuracy of the analysis by referring to past detailed analysis data. 3. The system of claim 2, (Appendix 34) The detailed analysis unit is Infer customer sentiment and adjust the way detailed analysis results are displayed based on the inferred customer sentiment 3. The system of claim 2, (Appendix 35) The detailed analysis unit is During detailed analysis, beverage consumption and table cleanliness are also analyzed at the same time. 3. The system of claim 2, (Appendix 36) The detailed analysis unit is When performing detailed analysis, the eating habits of other customers are also analyzed at the same time 3. The system of claim 2, (Appendix 37) The behavior identification unit is Infer customer sentiment and adjust action-specific criteria based on the inferred sentiment 4. The system of claim 3. (Appendix 38) The behavior identification unit is When identifying behavior, the identification algorithm is changed depending on the type and frequency of the behavior. 4. The system of claim 3. (Appendix 39) The behavior identification unit is When identifying behavior, refer to past behavior data to improve the accuracy of identification. 4. The system of claim 3. (Appendix 40) The behavior identification unit is Infer customer sentiment and adjust how behavioral results are displayed based on the inferred customer sentiment 4. The system of claim 3. (Appendix 41) The behavior identification unit is When identifying behavior, changes in voice and facial expressions are also identified at the same time. 4. The system of claim 3. (Appendix 42) The behavior identification unit is When identifying a behavior, the reactions of other customers are also identified at the same time. 4. The system of claim 3. (Appendix 43) The notification selection unit is Infer customer emotions and select a notification method based on the inferred customer emotions 5. The system of claim 4. (Appendix 44) The notification selection unit is When selecting a notification method, choose the most appropriate method based on the current work situation of the hall staff. 5. The system of claim 4. (Appendix 45) The notification selection unit is When selecting a notification method, refer to past notification history to improve the accuracy of notifications. 5. The system of claim 4. (Appendix 46) The notification selection unit is Infer customer sentiment and customize notifications based on the inferred sentiment 5. The system of claim 4. (Appendix 47) The notification selection unit is When notifying users, use not only audio and visual notifications but also other means such as vibration and light. 5. The system of claim 4. (Appendix 48) The notification selection unit is When notifying customers, the optimal notification method is selected taking into account the location information of the hall staff. 5. The system of claim 4. [Explanation of symbols]

[0213] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. An acquisition unit that acquires video data from a surveillance camera; an analysis unit that analyzes the eating habits of customers based on the video data acquired by the acquisition unit; A detection unit that detects abnormal behavior of a customer based on the video data acquired by the acquisition unit; a notification unit that notifies a hall staff member based on the information obtained by the analysis unit and the detection unit. A system characterized by:

2. The analysis unit is Equipped with a detailed analysis section that analyzes eating habits in detail 2. The system of claim 1 .

3. The detection unit is Equipped with a behavior identification unit that detects specific behaviors 2. The system of claim 1 .

4. The notification unit is Equipped with a notification selection section for selecting the notification method 2. The system of claim 1 .

5. The acquisition unit is Acquire video data from surveillance cameras in real time 2. The system of claim 1 .

6. The notification unit is Provide audio or visual notifications to hall staff 2. The system of claim 1 .

7. The acquisition unit is Estimate customer emotions and adjust the timing of video data acquisition based on the estimated customer emotions 2. The system of claim 1 .

8. The acquisition unit is When acquiring video data, change the acquisition method according to specific time periods or congestion situations.

2. The system of claim 1 .

9. The acquisition unit is Focus on a specific area or table when capturing video data 2. The system of claim 1 .

Images