system

Abstract

The system according to this embodiment aims to select and execute the optimal action according to the situation inside the store. [Solution] The system according to the embodiment comprises an intelligent unit, an action selection unit, an execution unit, a collection unit, and a provision unit. The intelligent unit understands the situation in the store. The action selection unit selects the optimal action based on the situation understood by the intelligent unit. The execution unit executes the action selected by the action selection unit. The collection unit collects information. The provision unit provides the results.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the flexibility of robots used in restaurants is low, and it is difficult to take appropriate actions according to the in - store situation.

[0005] The system according to the embodiment aims to select and execute an optimal action according to the in - store situation.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an intelligent unit, an action selection unit, an execution unit, a data collection unit, and a provision unit. The intelligent unit understands the situation inside the store. The action selection unit selects the optimal action based on the situation understood by the intelligent unit. The execution unit executes the action selected by the action selection unit. The data collection unit collects information. The provision unit provides the results. [Effects of the Invention]

[0007] The system according to this embodiment can select and execute the optimal action according to the situation inside the store. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 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". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[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. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The robot system for restaurants according to an embodiment of the present invention is a system in which the robot can think, converse, and serve customers according to the situation in the restaurant. This system comprises an intelligent unit for understanding the situation in the restaurant, an action selection unit for selecting the optimal action based on the situation understood by the intelligent unit, an execution unit for executing the action selected by the action selection unit, an information collection unit for collecting information, and a result provision unit for providing results. For example, the robot can perform tasks such as preparing cutlery, providing wet towels and water, taking orders, cleaning tables, cooking, and serving food. The robot can understand the situation in the restaurant and select the optimal action by making full use of its five senses (sight, hearing, touch, smell, taste) and intelligence (language, situation understanding, action identification and selection). For example, it can recognize when a customer is having trouble looking at a menu and make menu suggestions. It can also verbalize customer conversations and respond appropriately. The robot uses PaLM-SayCan to generate optimal movements and makes action selections that take into account the context and the state of the robot. For example, it can perform tasks such as finding customers, guiding customers, taking orders, pouring water, and serving food. The robot can respond in a multimodal manner according to the situation in the store; for example, it can proactively refill glasses if they are empty. It understands the situation in the store by verbalizing visual information using image captioning. This allows the robot to respond flexibly, significantly reducing the workload of restaurants and contributing to solving the labor shortage problem in the food service industry. As a result, the robot system for restaurants can think, converse, and provide customer service on its own according to the situation in the store.

[0029] The robot system for restaurants according to this embodiment comprises an intelligent unit, an action selection unit, an execution unit, a data collection unit, and a serving unit. The intelligent unit is the part that understands the situation inside the restaurant. The intelligent unit can grasp the situation inside the restaurant using sensors such as cameras and microphones. For example, the intelligent unit can analyze customers' facial expressions and movements using a camera to understand the situation inside the restaurant. The intelligent unit can also analyze customers' conversations using a microphone to understand the situation inside the restaurant. The action selection unit is the part that selects the optimal action based on the situation understood by the intelligent unit. For example, the action selection unit can generate the optimal action using PaLM-SayCan. For example, the action selection unit selects an action to perform tasks such as finding a customer, guiding a customer, taking an order, pouring water, and serving food. The execution unit is the part that executes the action selected by the action selection unit. For example, the execution unit can execute the selected action by controlling the robot's arms and wheels. The execution unit performs tasks such as preparing cutlery, providing hand towels and water, taking orders, cleaning tables, cooking, and serving food. The collection unit is the part that collects information. The collection unit can collect information about the situation inside the restaurant using sensors such as cameras and microphones. For example, the collection unit can collect customers' facial expressions and movements using cameras. The collection unit can also collect customers' conversations using microphones. The provision unit is the part that provides results. For example, the provision unit can provide customers with the results performed by the execution unit. For example, the provision unit provides customers with results such as order confirmation and food delivery. As a result, the restaurant robot system according to this embodiment is able to think, converse, and serve customers according to the situation inside the restaurant.

[0030] The intelligent unit is responsible for understanding the situation inside the store. For example, it can use sensors such as cameras and microphones to grasp the situation inside the store. Specifically, cameras acquire high-resolution video in real time and use AI to analyze customers' facial expressions and movements. For example, by analyzing information such as whether a customer is smiling, in distress, or raising their hand, it is possible to understand customer satisfaction and needs. Microphones collect sound from inside the store and use speech recognition technology to analyze customer conversations. This allows the intelligent unit to understand what customers are saying, what they want to order, or if there is a problem. Furthermore, the intelligent unit integrates the data obtained from these sensors to grasp the overall situation inside the store. For example, it monitors the store's congestion level, the status of each table, and the movements of staff in real time and provides information to other units as needed. In this way, the intelligent unit can comprehensively understand the situation inside the store and provide a foundation for taking appropriate action.

[0031] The action selection unit is the part that selects the optimal action based on the situation understood by the intelligence unit. The action selection unit can generate optimal actions using, for example, PaLM-SayCan. Specifically, the action selection unit analyzes the data provided by the intelligence unit and selects the action that is most appropriate for the current situation. For example, if a customer raises their hand, the action selection unit will choose to approach the customer and take their order. Also, if a customer looks distressed, the action selection unit will choose to offer assistance to that customer. Furthermore, the action selection unit has the ability to process multiple tasks simultaneously and can set priorities to efficiently select actions. For example, during busy times, it will prioritize taking orders first, and then perform tasks such as serving food and cleaning tables. In addition, the action selection unit can learn from past data and experience to select more effective actions. As a result, the action selection unit can respond flexibly and quickly according to the situation in the store and provide optimal service.

[0032] The execution unit is the part that executes the actions selected by the action selection unit. For example, the execution unit can control the robot's arms and wheels to perform the selected actions. Specifically, the execution unit performs tasks such as preparing cutlery, providing hand towels and water, taking orders, cleaning tables, cooking, and serving food. For example, the robot's arms can precisely position the cutlery and provide hand towels and water to customers. The robot's wheels can move smoothly around the store and deliver food to each table. Furthermore, the execution unit can monitor its surroundings in real time using sensors and operate safely while avoiding obstacles. For example, if a customer or staff member crosses a passageway, the execution unit can detect their movement and avoid them appropriately. The execution unit can also perform multiple tasks simultaneously according to instructions from the action selection unit. This allows the execution unit to perform tasks efficiently and accurately, improving the quality of service in the store.

[0033] The data collection unit is the part that collects information. The data collection unit can collect information about the store's situation using sensors such as cameras and microphones. Specifically, cameras acquire high-resolution video and collect customers' facial expressions and movements. For example, it collects information such as whether a customer is smiling, looking troubled, or raising their hand. Microphones can also collect audio from the store and record customer conversations. This allows the system to collect information to understand what customers are saying, what they want to order, or if there is a problem. Furthermore, the data collection unit provides the data obtained from these sensors to the intelligent unit in real time, providing a foundation for comprehensively understanding the store's situation. For example, the data collection unit monitors the store's congestion level, the status of each table, and the movements of staff in real time and provides this information to the intelligent unit. This allows the data collection unit to accurately understand the store's situation and provide information for taking appropriate action.

[0034] The delivery unit is the part that delivers results. For example, the delivery unit can deliver the results performed by the execution unit to the customer. Specifically, the delivery unit delivers results such as order confirmation and food delivery to the customer. For example, after the execution unit has served the food, the delivery unit verifies that the food was served correctly and reconfirms the order details with the customer. The delivery unit can also collect feedback from customers and provide information to improve the quality of service. For example, it can check whether the customer is satisfied with the food or if there are any problems and provide that information to the intelligence unit and the behavior selection unit. Furthermore, the delivery unit can also provide additional services and information to the customer. For example, it can recommend desserts or provide information about making reservations for the next visit. In this way, the delivery unit can provide high-quality service to customers and improve their satisfaction.

[0035] The data collection unit can collect information about the store environment. For example, it can use a camera to collect information about the number of customers and the placement of products. It can also use a microphone to collect ambient sounds. For example, it can collect noise levels in the store to obtain data for providing an appropriate acoustic environment. It can also collect information about the brightness of the store lighting to obtain data for providing an appropriate lighting environment. By collecting information about the store environment, the data collection unit enables the robot to select appropriate actions.

[0036] The intelligent unit can analyze information collected by the data collection unit to understand the situation inside the store. For example, the intelligent unit can analyze customers' facial expressions and movements collected using cameras to understand the situation inside the store. It can also analyze customers' conversations collected using microphones to understand the situation inside the store. For example, based on the collected information, the intelligent unit can understand the number of customers and the arrangement of products. For example, the intelligent unit can analyze collected ambient sounds to understand the noise level inside the store. In this way, the intelligent unit can understand the situation inside the store by analyzing the collected information.

[0037] The action selection unit can select the optimal action based on the situation understood by the intelligence unit. For example, the action selection unit generates the optimal action using PaLM-SayCan. The action selection unit selects actions to perform tasks such as finding a customer, guiding a customer, taking an order, pouring water, and serving food. For example, the action selection unit recognizes that a customer is having trouble looking at a menu and makes menu suggestions. The action selection unit can also verbalize the customer's conversation and respond appropriately. In this way, the action selection unit can select the optimal action based on the understood situation.

[0038] The execution unit can perform the actions selected by the action selection unit. For example, the execution unit can control the robot's arms and wheels to perform the selected actions. The execution unit can perform tasks such as preparing cutlery, providing hand towels and water, taking orders, cleaning tables, cooking, and serving food. For example, the execution unit can perform tasks such as finding customers, guiding them, taking orders, pouring water, and serving food. In this way, the robot operates appropriately by the execution unit performing the selected actions.

[0039] The service provider can provide the results performed by the execution unit. For example, the service provider can provide the results performed by the execution unit to the customer. For example, the service provider can provide the customer with results such as order confirmation or food delivery. For example, the service provider can also generate a report of the results performed by the execution unit and provide it to the customer. For example, the service provider can also provide real-time feedback on the results performed by the execution unit. This allows the service provider to provide appropriate services to users by providing the results of the execution.

[0040] The data collection unit can collect real-time data on the store's lighting and acoustic environment to provide an optimal customer service environment. For example, the unit can monitor the brightness of the store's lighting in real time and adjust it to an appropriate level. The unit can also collect data on the store's acoustic environment and manage noise levels to provide a comfortable environment. For example, the unit can collect data on the store's temperature and humidity to maintain a comfortable environment. In this way, the data collection unit can provide an optimal customer service environment by collecting real-time data on the store's lighting and acoustic environment.

[0041] The data collection unit can analyze customer movements and facial expressions to gather information for optimizing service timing. For example, it can analyze customer facial expressions and evaluate satisfaction in real time. It can also analyze customer movements to optimize ordering timing. For instance, it can analyze customer facial expressions and movements in combination to collect information for improving service quality. This allows the data collection unit to optimize service timing by analyzing customer movements and facial expressions.

[0042] The data collection unit can collect temperature and humidity data within the store, obtaining information to maintain a comfortable environment. For example, the unit can monitor the store temperature in real time and adjust it to an appropriate level. The unit can also collect humidity data to maintain a comfortable environment. For instance, it can collect temperature and humidity data together to provide optimal environment information. In this way, the unit can maintain a comfortable environment by collecting temperature and humidity data within the store.

[0043] The data collection unit analyzes customer conversations and collects information to improve service quality. For example, the data collection unit analyzes customer conversations and evaluates satisfaction in real time. Furthermore, the data collection unit can analyze customer conversations and optimize the timing of orders. For example, the data collection unit analyzes customer conversations and collects information to improve service quality. Thus, by analyzing customer conversations, the data collection unit can collect information to improve service quality.

[0044] The intelligent unit can learn customer preferences and past behavioral patterns based on collected data, enabling it to understand situations with greater accuracy. For example, the intelligent unit can learn customer preferences based on collected data and provide optimal service. It can also learn past behavioral patterns based on collected data and provide optimal service. For example, the intelligent unit can learn by combining customer preferences and past behavioral patterns based on collected data and provide optimal service. In this way, the intelligent unit can understand situations with greater accuracy by learning customer preferences and past behavioral patterns.

[0045] The intelligent unit can analyze the store's congestion levels and plan optimal staffing and service delivery. For example, the intelligent unit can analyze the store's congestion levels and plan optimal staffing. Furthermore, the intelligent unit can analyze the store's congestion levels and plan optimal service delivery. For example, the intelligent unit can analyze the store's congestion levels and optimize staffing and service delivery. This allows the intelligent unit to optimize staffing and service delivery by analyzing the store's congestion levels.

[0046] The intelligent unit can estimate the customer's health status based on collected data and analyze information to provide appropriate services. For example, the intelligent unit can estimate the customer's health status based on collected data and provide appropriate services. Furthermore, the intelligent unit can estimate the customer's health status based on collected data and suggest health-conscious menu options. For example, the intelligent unit can estimate the customer's health status based on collected data and provide health-conscious services. In this way, the intelligent unit can analyze information to provide appropriate services by estimating the customer's health status.

[0047] The intelligent unit can analyze audio data from inside the store and provide information for managing noise levels. For example, the intelligent unit can analyze audio data from inside the store and provide information for managing noise levels. Furthermore, the intelligent unit can analyze audio data from inside the store and provide information for reducing noise levels. For example, the intelligent unit can analyze audio data from inside the store and provide information for optimizing noise levels. Thus, by analyzing audio data from inside the store, the intelligent unit can provide information for managing noise levels.

[0048] The action selection unit can generate multiple action options according to the store's situation and select the optimal action. For example, the action selection unit can generate multiple action options according to the store's situation and select the optimal action. Furthermore, the action selection unit can generate multiple action options according to the store's situation and select the optimal action. For example, the action selection unit can generate multiple action options according to the store's situation and select the optimal action. Thus, the action selection unit can select the optimal action by generating multiple action options according to the store's situation.

[0049] The behavior selection unit can learn behavioral patterns with a high success rate based on past behavioral history and optimize the options. For example, the behavior selection unit can learn behavioral patterns with a high success rate based on past behavioral history and optimize the options. Furthermore, the behavior selection unit can learn behavioral patterns with a high success rate based on past behavioral history and optimize the options. For example, the behavior selection unit can learn behavioral patterns with a high success rate based on past behavioral history and optimize the options. In this way, the behavior selection unit can optimize the options by learning behavioral patterns with a high success rate based on past behavioral history.

[0050] The behavior selection unit can apply different behavior selection algorithms depending on the customer base and time of day within the store. For example, the behavior selection unit can apply different behavior selection algorithms depending on the customer base and time of day within the store. In this way, the behavior selection unit can make more appropriate behavior selections by applying different behavior selection algorithms depending on the customer base and time of day within the store.

[0051] The behavior selection unit can select energy-efficient actions based on in-store environmental data. For example, the behavior selection unit can select energy-efficient actions based on in-store environmental data. Furthermore, the behavior selection unit can also select energy-efficient actions based on in-store environmental data. For example, the behavior selection unit can select energy-efficient actions based on in-store environmental data. This enables efficient energy use by allowing the behavior selection unit to select energy-efficient actions based on in-store environmental data.

[0052] The execution unit can monitor the robot's motion accuracy in real time during execution and make corrections as needed. For example, the execution unit can monitor the robot's motion accuracy in real time and automatically correct any errors that occur. The execution unit can also monitor the robot's motion accuracy and perform periodic calibrations. For example, the execution unit can monitor the robot's motion accuracy and issue an alert if an anomaly is detected. This allows the execution unit to monitor the robot's motion accuracy in real time and make corrections as needed, enabling accurate operation.

[0053] The execution unit can process multiple tasks in parallel during execution, enabling efficient work execution. For example, the execution unit can process multiple tasks concurrently, achieving efficient work execution. Furthermore, the execution unit can set task priorities, prioritizing the processing of important tasks. For instance, the execution unit can monitor task progress in real time, enabling efficient work execution. This allows the execution unit to process multiple tasks in parallel, resulting in efficient work execution.

[0054] The execution unit can optimize its operation during execution, taking into account the robot's battery level. For example, the execution unit can monitor the robot's battery level and operate in energy-saving mode when the level is low. The execution unit can also prioritize important tasks, taking the battery level into consideration. For instance, if the battery level is low, the execution unit can automatically return to the charging station. This allows for efficient energy use by optimizing the execution unit's operation while considering the robot's battery level.

[0055] The execution unit can add actions to avoid obstacles in the store during execution. For example, the execution unit can detect obstacles in the store in real time and add actions to avoid them. The execution unit can also map the location of obstacles and calculate the optimal route. For example, the execution unit can plan and execute actions to avoid obstacles in advance. This allows the execution unit to perform safer actions by adding actions to avoid obstacles in the store.

[0056] The service provider can provide more personalized information by referring to the customer's past feedback at the time of delivery. For example, the service provider can refer to the customer's past feedback and provide information tailored to their preferences. Furthermore, the service provider can also refer to the customer's past feedback and provide information that reflects areas for improvement. For example, the service provider can refer to the customer's past feedback and provide a personalized service. This enables the service provider to provide more personalized information by referring to the customer's past feedback.

[0057] The service provider can integrate data from multiple sources to provide comprehensive information at the time of delivery. For example, the service provider can integrate data from multiple sources to provide comprehensive information. Furthermore, the service provider can evaluate the reliability of the data and prioritize the provision of reliable information. For example, the service provider can verify the consistency of the data and provide consistent information. This enables the service provider to provide comprehensive information by integrating data from multiple sources.

[0058] The service provider can provide information in the most optimal format, taking into account the customer's device information at the time of delivery. For example, if the customer is using a smartphone, the service provider can provide information adapted to the screen size. Similarly, if the customer is using a tablet, the service provider can provide information optimized for a larger screen. For instance, if the customer is using a smartwatch, the service provider can provide concise and highly visible information. This allows the service provider to provide more appropriate information by considering the customer's device information.

[0059] The service delivery unit can collaborate with other robots in the store to share information and provide a unified service during delivery. For example, the service delivery unit can collaborate with other robots in the store to share information and provide a unified service. Furthermore, the service delivery unit can receive information from other robots to improve the quality of service. For example, the service delivery unit can cooperate with other robots to provide efficient service. This enables the service delivery unit to provide a unified service by collaborating with other robots in the store and sharing information.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The robot system for restaurants can also be equipped with a health management unit that monitors the user's health condition. This unit can, for example, measure the user's heart rate and body temperature using sensors and monitor their health in real time. Furthermore, the health management unit can suggest appropriate menu items based on the user's health condition. For instance, if the heart rate is high, it can suggest a low-caffeine beverage. If the body temperature is high, it can suggest a cold drink or a light snack. This allows the health management unit to provide more appropriate service based on the user's health condition.

[0062] The robot system for restaurants can also be equipped with an environmental adaptation unit. This unit can, for example, monitor the temperature and humidity of the restaurant in real time and provide an appropriate environment. It can also adjust the brightness of the lighting to create a comfortable atmosphere. For example, it can provide bright lighting during the day and dimmer lighting at night. Furthermore, the environmental adaptation unit can manage the noise level in the restaurant, providing a quiet environment. In this way, the environmental adaptation unit can optimize the restaurant environment and provide a comfortable space for users.

[0063] The robot system for restaurants can also be equipped with an energy management unit. This unit can, for example, monitor the restaurant's electricity consumption in real time, enabling efficient energy use. It can also optimize the use of lighting and air conditioning, reducing energy waste. For instance, it can automatically adjust lighting and air conditioning during off-peak hours. Furthermore, the energy management unit can analyze energy consumption data to improve energy efficiency. In this way, the energy management unit can achieve efficient energy use and support environmentally conscious restaurant operations.

[0064] The robot system for restaurants can also be equipped with a maintenance unit. This unit can, for example, monitor the robot's operating status in real time and respond quickly if an abnormality occurs. It can also perform regular inspections and optimize the robot's operation. For instance, it can monitor the robot's battery level and charge it as needed. Furthermore, it can monitor the wear and tear of the robot's parts and replace them as necessary. This allows the maintenance unit to maintain the robot's operation in optimal condition at all times, ensuring a stable service.

[0065] The robot system for restaurants can also be equipped with a data analysis unit. This unit can collect and analyze, for example, in-store sales data and customer behavior data. Furthermore, based on the collected data, the unit can propose measures to improve sales and customer satisfaction. For instance, it can analyze sales data to identify popular menu items and times of day. It can also analyze customer behavior data to provide services tailored to customer needs. In this way, the data analysis unit can support data-driven business strategies and optimize store operations.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The intelligent unit is responsible for understanding the situation inside the store. The intelligent unit can grasp the situation inside the store using sensors such as cameras and microphones. For example, the intelligent unit can use cameras to analyze customers' facial expressions and movements to understand the situation inside the store. It can also use microphones to analyze customers' conversations to understand the situation inside the store. Step 2: The action selection unit is the part that selects the optimal action based on the situation understood by the intelligence unit. The action selection unit can generate the optimal action using, for example, PaLM-SayCan. The action selection unit selects actions to perform tasks such as finding a customer, guiding a customer, taking an order, pouring water, and serving food. Step 3: The execution unit is the part that executes the action selected by the action selection unit. The execution unit can, for example, control the robot's arms or wheels to perform the selected action. The execution unit can perform tasks such as preparing cutlery, providing hand towels and water, taking orders, cleaning tables, cooking, and serving food. Step 4: The collection unit is the part that collects information. The collection unit can collect information about the store environment using sensors such as cameras and microphones. For example, the collection unit can use cameras to collect customers' facial expressions and movements. The collection unit can also use microphones to collect customers' conversations. Step 5: The serving unit is the part that provides the results. The serving unit can, for example, provide the customer with the results performed by the execution unit. The serving unit provides the customer with results such as order confirmation and food delivery.

[0068] (Example of form 2) The robot system for restaurants according to an embodiment of the present invention is a system in which the robot can think, converse, and serve customers according to the situation in the restaurant. This system comprises an intelligent unit for understanding the situation in the restaurant, an action selection unit for selecting the optimal action based on the situation understood by the intelligent unit, an execution unit for executing the action selected by the action selection unit, an information collection unit for collecting information, and a result provision unit for providing results. For example, the robot can perform tasks such as preparing cutlery, providing wet towels and water, taking orders, cleaning tables, cooking, and serving food. The robot can understand the situation in the restaurant and select the optimal action by making full use of its five senses (sight, hearing, touch, smell, taste) and intelligence (language, situation understanding, action identification and selection). For example, it can recognize when a customer is having trouble looking at a menu and make menu suggestions. It can also verbalize customer conversations and respond appropriately. The robot uses PaLM-SayCan to generate optimal movements and makes action selections that take into account the context and the state of the robot. For example, it can perform tasks such as finding customers, guiding customers, taking orders, pouring water, and serving food. The robot can respond in a multimodal manner according to the situation in the store; for example, it can proactively refill glasses if they are empty. It understands the situation in the store by verbalizing visual information using image captioning. This allows the robot to respond flexibly, significantly reducing the workload of restaurants and contributing to solving the labor shortage problem in the food service industry. As a result, the robot system for restaurants can think, converse, and provide customer service on its own according to the situation in the store.

[0069] The robot system for restaurants according to this embodiment comprises an intelligent unit, an action selection unit, an execution unit, a data collection unit, and a serving unit. The intelligent unit is the part that understands the situation inside the restaurant. The intelligent unit can grasp the situation inside the restaurant using sensors such as cameras and microphones. For example, the intelligent unit can analyze customers' facial expressions and movements using a camera to understand the situation inside the restaurant. The intelligent unit can also analyze customers' conversations using a microphone to understand the situation inside the restaurant. The action selection unit is the part that selects the optimal action based on the situation understood by the intelligent unit. For example, the action selection unit can generate the optimal action using PaLM-SayCan. For example, the action selection unit selects an action to perform tasks such as finding a customer, guiding a customer, taking an order, pouring water, and serving food. The execution unit is the part that executes the action selected by the action selection unit. For example, the execution unit can execute the selected action by controlling the robot's arms and wheels. The execution unit performs tasks such as preparing cutlery, providing hand towels and water, taking orders, cleaning tables, cooking, and serving food. The collection unit is the part that collects information. The collection unit can collect information about the situation inside the restaurant using sensors such as cameras and microphones. For example, the collection unit can collect customers' facial expressions and movements using cameras. The collection unit can also collect customers' conversations using microphones. The provision unit is the part that provides results. For example, the provision unit can provide customers with the results performed by the execution unit. For example, the provision unit provides customers with results such as order confirmation and food delivery. As a result, the restaurant robot system according to this embodiment is able to think, converse, and serve customers according to the situation inside the restaurant.

[0070] The intelligent unit is responsible for understanding the situation inside the store. For example, it can use sensors such as cameras and microphones to grasp the situation inside the store. Specifically, cameras acquire high-resolution video in real time and use AI to analyze customers' facial expressions and movements. For example, by analyzing information such as whether a customer is smiling, in distress, or raising their hand, it is possible to understand customer satisfaction and needs. Microphones collect sound from inside the store and use speech recognition technology to analyze customer conversations. This allows the intelligent unit to understand what customers are saying, what they want to order, or if there is a problem. Furthermore, the intelligent unit integrates the data obtained from these sensors to grasp the overall situation inside the store. For example, it monitors the store's congestion level, the status of each table, and the movements of staff in real time and provides information to other units as needed. In this way, the intelligent unit can comprehensively understand the situation inside the store and provide a foundation for taking appropriate action.

[0071] The action selection unit is the part that selects the optimal action based on the situation understood by the intelligence unit. The action selection unit can generate optimal actions using, for example, PaLM-SayCan. Specifically, the action selection unit analyzes the data provided by the intelligence unit and selects the action that is most appropriate for the current situation. For example, if a customer raises their hand, the action selection unit will choose to approach the customer and take their order. Also, if a customer looks distressed, the action selection unit will choose to offer assistance to that customer. Furthermore, the action selection unit has the ability to process multiple tasks simultaneously and can set priorities to efficiently select actions. For example, during busy times, it will prioritize taking orders first, and then perform tasks such as serving food and cleaning tables. In addition, the action selection unit can learn from past data and experience to select more effective actions. As a result, the action selection unit can respond flexibly and quickly according to the situation in the store and provide optimal service.

[0072] The execution unit is the part that executes the actions selected by the action selection unit. For example, the execution unit can control the robot's arms and wheels to perform the selected actions. Specifically, the execution unit performs tasks such as preparing cutlery, providing hand towels and water, taking orders, cleaning tables, cooking, and serving food. For example, the robot's arms can precisely position the cutlery and provide hand towels and water to customers. The robot's wheels can move smoothly around the store and deliver food to each table. Furthermore, the execution unit can monitor its surroundings in real time using sensors and operate safely while avoiding obstacles. For example, if a customer or staff member crosses a passageway, the execution unit can detect their movement and avoid them appropriately. The execution unit can also perform multiple tasks simultaneously according to instructions from the action selection unit. This allows the execution unit to perform tasks efficiently and accurately, improving the quality of service in the store.

[0073] The data collection unit is the part that collects information. The data collection unit can collect information about the store's situation using sensors such as cameras and microphones. Specifically, cameras acquire high-resolution video and collect customers' facial expressions and movements. For example, it collects information such as whether a customer is smiling, looking troubled, or raising their hand. Microphones can also collect audio from the store and record customer conversations. This allows the system to collect information to understand what customers are saying, what they want to order, or if there is a problem. Furthermore, the data collection unit provides the data obtained from these sensors to the intelligent unit in real time, providing a foundation for comprehensively understanding the store's situation. For example, the data collection unit monitors the store's congestion level, the status of each table, and the movements of staff in real time and provides this information to the intelligent unit. This allows the data collection unit to accurately understand the store's situation and provide information for taking appropriate action.

[0074] The delivery unit is the part that delivers results. For example, the delivery unit can deliver the results performed by the execution unit to the customer. Specifically, the delivery unit delivers results such as order confirmation and food delivery to the customer. For example, after the execution unit has served the food, the delivery unit verifies that the food was served correctly and reconfirms the order details with the customer. The delivery unit can also collect feedback from customers and provide information to improve the quality of service. For example, it can check whether the customer is satisfied with the food or if there are any problems and provide that information to the intelligence unit and the behavior selection unit. Furthermore, the delivery unit can also provide additional services and information to the customer. For example, it can recommend desserts or provide information about making reservations for the next visit. In this way, the delivery unit can provide high-quality service to customers and improve their satisfaction.

[0075] The data collection unit can collect information about the store environment. For example, it can use a camera to collect information about the number of customers and the placement of products. It can also use a microphone to collect ambient sounds. For example, it can collect noise levels in the store to obtain data for providing an appropriate acoustic environment. It can also collect information about the brightness of the store lighting to obtain data for providing an appropriate lighting environment. By collecting information about the store environment, the data collection unit enables the robot to select appropriate actions.

[0076] The intelligent unit can analyze information collected by the data collection unit to understand the situation inside the store. For example, the intelligent unit can analyze customers' facial expressions and movements collected using cameras to understand the situation inside the store. It can also analyze customers' conversations collected using microphones to understand the situation inside the store. For example, based on the collected information, the intelligent unit can understand the number of customers and the arrangement of products. For example, the intelligent unit can analyze collected ambient sounds to understand the noise level inside the store. In this way, the intelligent unit can understand the situation inside the store by analyzing the collected information.

[0077] The action selection unit can select the optimal action based on the situation understood by the intelligence unit. For example, the action selection unit generates the optimal action using PaLM-SayCan. The action selection unit selects actions to perform tasks such as finding a customer, guiding a customer, taking an order, pouring water, and serving food. For example, the action selection unit recognizes that a customer is having trouble looking at a menu and makes menu suggestions. The action selection unit can also verbalize the customer's conversation and respond appropriately. In this way, the action selection unit can select the optimal action based on the understood situation.

[0078] The execution unit can perform the actions selected by the action selection unit. For example, the execution unit can control the robot's arms and wheels to perform the selected actions. The execution unit can perform tasks such as preparing cutlery, providing hand towels and water, taking orders, cleaning tables, cooking, and serving food. For example, the execution unit can perform tasks such as finding customers, guiding them, taking orders, pouring water, and serving food. In this way, the robot operates appropriately by the execution unit performing the selected actions.

[0079] The service provider can provide the results performed by the execution unit. For example, the service provider can provide the results performed by the execution unit to the customer. For example, the service provider can provide the customer with results such as order confirmation or food delivery. For example, the service provider can also generate a report of the results performed by the execution unit and provide it to the customer. For example, the service provider can also provide real-time feedback on the results performed by the execution unit. This allows the service provider to provide appropriate services to users by providing the results of the execution.

[0080] The data collection unit can estimate the user's emotions and adjust the type of information it collects based on the estimated emotions. For example, if the user is relaxed, the data collection unit can collect positive feedback from conversation content and facial expressions. If the user is stressed, the data collection unit can collect the frequency of orders and tone of voice to respond quickly. For example, if the user is in distress, the data collection unit can collect eye movements and hand movements to provide appropriate support. In this way, the data collection unit can collect more relevant information by adjusting the type of information it collects based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0081] The data collection unit can collect real-time data on the store's lighting and acoustic environment to provide an optimal customer service environment. For example, the unit can monitor the brightness of the store's lighting in real time and adjust it to an appropriate level. The unit can also collect data on the store's acoustic environment and manage noise levels to provide a comfortable environment. For example, the unit can collect data on the store's temperature and humidity to maintain a comfortable environment. In this way, the data collection unit can provide an optimal customer service environment by collecting real-time data on the store's lighting and acoustic environment.

[0082] The data collection unit can analyze customer movements and facial expressions to gather information for optimizing service timing. For example, it can analyze customer facial expressions and evaluate satisfaction in real time. It can also analyze customer movements to optimize ordering timing. For instance, it can analyze customer facial expressions and movements in combination to collect information for improving service quality. This allows the data collection unit to optimize service timing by analyzing customer movements and facial expressions.

[0083] The data collection unit can estimate the user's emotions and prioritize the information to collect based on the estimated emotions. For example, if the user is relaxed, the data collection unit will prioritize collecting positive feedback from conversation content and facial expressions. If the user is stressed, the data collection unit can also prioritize collecting order frequency and tone of voice. For example, if the user is distressed, the data collection unit will prioritize collecting eye movements and hand movements. In this way, the data collection unit can prioritize collecting more important information by prioritizing the information to collect based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0084] The data collection unit can collect temperature and humidity data within the store, obtaining information to maintain a comfortable environment. For example, the unit can monitor the store temperature in real time and adjust it to an appropriate level. The unit can also collect humidity data to maintain a comfortable environment. For instance, it can collect temperature and humidity data together to provide optimal environment information. In this way, the unit can maintain a comfortable environment by collecting temperature and humidity data within the store.

[0085] The data collection unit analyzes customer conversations and collects information to improve service quality. For example, the data collection unit analyzes customer conversations and evaluates satisfaction in real time. Furthermore, the data collection unit can analyze customer conversations and optimize the timing of orders. For example, the data collection unit analyzes customer conversations and collects information to improve service quality. Thus, by analyzing customer conversations, the data collection unit can collect information to improve service quality.

[0086] The intelligent unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated emotions. For example, if the user is relaxed, the intelligent unit will apply an analysis algorithm that emphasizes positive feedback. Conversely, if the user is stressed, the intelligent unit can apply an analysis algorithm that emphasizes quick response. For example, if the user is in distress, the intelligent unit will apply an analysis algorithm that emphasizes support. This allows the intelligent unit to perform more appropriate analysis by adjusting the analysis algorithm based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0087] The intelligent unit can learn customer preferences and past behavioral patterns based on collected data, enabling it to understand situations with greater accuracy. For example, the intelligent unit can learn customer preferences based on collected data and provide optimal service. It can also learn past behavioral patterns based on collected data and provide optimal service. For example, the intelligent unit can learn by combining customer preferences and past behavioral patterns based on collected data and provide optimal service. In this way, the intelligent unit can understand situations with greater accuracy by learning customer preferences and past behavioral patterns.

[0088] The intelligent unit can analyze the store's congestion levels and plan optimal staffing and service delivery. For example, the intelligent unit can analyze the store's congestion levels and plan optimal staffing. Furthermore, the intelligent unit can analyze the store's congestion levels and plan optimal service delivery. For example, the intelligent unit can analyze the store's congestion levels and optimize staffing and service delivery. This allows the intelligent unit to optimize staffing and service delivery by analyzing the store's congestion levels.

[0089] The intelligent unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is relaxed, the intelligent unit can provide a display method that includes detailed information. It can also provide a simple and highly visible display method if the user is stressed. For example, if the user is in distress, the intelligent unit can provide a display method that prioritizes quick response. This allows the intelligent unit to provide more appropriate displays by adjusting the display method of the analysis results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The intelligent unit can estimate the customer's health status based on collected data and analyze information to provide appropriate services. For example, the intelligent unit can estimate the customer's health status based on collected data and provide appropriate services. Furthermore, the intelligent unit can estimate the customer's health status based on collected data and suggest health-conscious menu options. For example, the intelligent unit can estimate the customer's health status based on collected data and provide health-conscious services. In this way, the intelligent unit can analyze information to provide appropriate services by estimating the customer's health status.

[0091] The intelligent unit can analyze audio data from inside the store and provide information for managing noise levels. For example, the intelligent unit can analyze audio data from inside the store and provide information for managing noise levels. Furthermore, the intelligent unit can analyze audio data from inside the store and provide information for reducing noise levels. For example, the intelligent unit can analyze audio data from inside the store and provide information for optimizing noise levels. Thus, by analyzing audio data from inside the store, the intelligent unit can provide information for managing noise levels.

[0092] The behavior selection unit can estimate the user's emotions and adjust the criteria for behavior selection based on the estimated emotions. For example, if the user is relaxed, the behavior selection unit may apply behavior selection criteria that prioritize positive feedback. Similarly, if the user is stressed, the behavior selection unit may apply behavior selection criteria that prioritize quick response. For example, if the user is in distress, the behavior selection unit may apply behavior selection criteria that prioritize support. This allows the behavior selection unit to make more appropriate behavioral choices by adjusting the criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0093] The action selection unit can generate multiple action options according to the store's situation and select the optimal action. For example, the action selection unit can generate multiple action options according to the store's situation and select the optimal action. Furthermore, the action selection unit can generate multiple action options according to the store's situation and select the optimal action. For example, the action selection unit can generate multiple action options according to the store's situation and select the optimal action. Thus, the action selection unit can select the optimal action by generating multiple action options according to the store's situation.

[0094] The behavior selection unit can learn behavioral patterns with a high success rate based on past behavioral history and optimize the options. For example, the behavior selection unit can learn behavioral patterns with a high success rate based on past behavioral history and optimize the options. Furthermore, the behavior selection unit can learn behavioral patterns with a high success rate based on past behavioral history and optimize the options. For example, the behavior selection unit can learn behavioral patterns with a high success rate based on past behavioral history and optimize the options. In this way, the behavior selection unit can optimize the options by learning behavioral patterns with a high success rate based on past behavioral history.

[0095] The action selection unit can estimate the user's emotions and determine the priority of action choices based on the estimated emotions. For example, if the user is relaxed, the action selection unit will prioritize action choices that emphasize positive feedback. Similarly, if the user is stressed, the action selection unit can prioritize action choices that emphasize quick response. For example, if the user is in distress, the action selection unit will prioritize action choices that emphasize support. This allows the action selection unit to make more appropriate action choices by prioritizing action choices based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The behavior selection unit can apply different behavior selection algorithms depending on the customer base and time of day within the store. For example, the behavior selection unit can apply different behavior selection algorithms depending on the customer base and time of day within the store. In this way, the behavior selection unit can make more appropriate behavior selections by applying different behavior selection algorithms depending on the customer base and time of day within the store.

[0097] The behavior selection unit can select energy-efficient actions based on in-store environmental data. For example, the behavior selection unit can select energy-efficient actions based on in-store environmental data. Furthermore, the behavior selection unit can also select energy-efficient actions based on in-store environmental data. For example, the behavior selection unit can select energy-efficient actions based on in-store environmental data. This enables efficient energy use by allowing the behavior selection unit to select energy-efficient actions based on in-store environmental data.

[0098] The execution unit can estimate the user's emotions and adjust the speed and intensity of the actions it performs based on the estimated emotions. For example, if the user is relaxed, the execution unit will provide service with relaxed actions. Conversely, if the user is in a hurry, the execution unit can provide service with rapid actions. For example, if the user is stressed, the execution unit will provide service with calm actions. This allows the execution unit to provide more appropriate service by adjusting the speed and intensity of actions based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0099] The execution unit can monitor the robot's motion accuracy in real time during execution and make corrections as needed. For example, the execution unit can monitor the robot's motion accuracy in real time and automatically correct any errors that occur. The execution unit can also monitor the robot's motion accuracy and perform periodic calibrations. For example, the execution unit can monitor the robot's motion accuracy and issue an alert if an anomaly is detected. This allows the execution unit to monitor the robot's motion accuracy in real time and make corrections as needed, enabling accurate operation.

[0100] The execution unit can process multiple tasks in parallel during execution, enabling efficient work execution. For example, the execution unit can process multiple tasks concurrently, achieving efficient work execution. Furthermore, the execution unit can set task priorities, prioritizing the processing of important tasks. For instance, the execution unit can monitor task progress in real time, enabling efficient work execution. This allows the execution unit to process multiple tasks in parallel, resulting in efficient work execution.

[0101] The execution unit can estimate the user's emotions and adjust the order of actions to be performed based on the estimated emotions. For example, if the user is relaxed, the execution unit can flexibly adjust the order of actions. It can also prioritize important actions if the user is in a hurry. For example, if the user is stressed, the execution unit will prioritize calming actions. This allows the execution unit to provide a more appropriate service by adjusting the order of actions based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0102] The execution unit can optimize its operation during execution, taking into account the robot's battery level. For example, the execution unit can monitor the robot's battery level and operate in energy-saving mode when the level is low. The execution unit can also prioritize important tasks, taking the battery level into consideration. For instance, if the battery level is low, the execution unit can automatically return to the charging station. This allows for efficient energy use by optimizing the execution unit's operation while considering the robot's battery level.

[0103] The execution unit can add actions to avoid obstacles in the store during execution. For example, the execution unit can detect obstacles in the store in real time and add actions to avoid them. The execution unit can also map the location of obstacles and calculate the optimal route. For example, the execution unit can plan and execute actions to avoid obstacles in advance. This allows the execution unit to perform safer actions by adding actions to avoid obstacles in the store.

[0104] The information provider can estimate the user's emotions and adjust the format of the information provided based on those emotions. For example, if the user is relaxed, the provider will provide detailed information. If the user is in a hurry, the provider can provide concise information to the point. For example, if the user is stressed, the provider will provide information in a calm tone. This allows the provider to provide more appropriate information by adjusting the format of the information based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0105] The service provider can provide more personalized information by referring to the customer's past feedback at the time of delivery. For example, the service provider can refer to the customer's past feedback and provide information tailored to their preferences. Furthermore, the service provider can also refer to the customer's past feedback and provide information that reflects areas for improvement. For example, the service provider can refer to the customer's past feedback and provide a personalized service. This enables the service provider to provide more personalized information by referring to the customer's past feedback.

[0106] The service provider can integrate data from multiple sources to provide comprehensive information at the time of delivery. For example, the service provider can integrate data from multiple sources to provide comprehensive information. Furthermore, the service provider can evaluate the reliability of the data and prioritize the provision of reliable information. For example, the service provider can verify the consistency of the data and provide consistent information. This enables the service provider to provide comprehensive information by integrating data from multiple sources.

[0107] The information provider can estimate the user's emotions and prioritize the information to be provided based on those emotions. For example, if the user is relaxed, the provider will prioritize providing detailed information. If the user is in a hurry, the provider can also prioritize providing concise information. For example, if the user is stressed, the provider will prioritize providing information in a calm tone. This allows the provider to provide more appropriate information by prioritizing information based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] The service provider can provide information in the most optimal format, taking into account the customer's device information at the time of delivery. For example, if the customer is using a smartphone, the service provider can provide information adapted to the screen size. Similarly, if the customer is using a tablet, the service provider can provide information optimized for a larger screen. For instance, if the customer is using a smartwatch, the service provider can provide concise and highly visible information. This allows the service provider to provide more appropriate information by considering the customer's device information.

[0109] The service delivery unit can collaborate with other robots in the store to share information and provide a unified service during delivery. For example, the service delivery unit can collaborate with other robots in the store to share information and provide a unified service. Furthermore, the service delivery unit can receive information from other robots to improve the quality of service. For example, the service delivery unit can cooperate with other robots to provide efficient service. This enables the service delivery unit to provide a unified service by collaborating with other robots in the store and sharing information.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The robot system for restaurants can also be equipped with a health management unit that monitors the user's health condition. This unit can, for example, measure the user's heart rate and body temperature using sensors and monitor their health in real time. Furthermore, the health management unit can suggest appropriate menu items based on the user's health condition. For instance, if the heart rate is high, it can suggest a low-caffeine beverage. If the body temperature is high, it can suggest a cold drink or a light snack. This allows the health management unit to provide more appropriate service based on the user's health condition.

[0112] The robot system for restaurants can also be equipped with an entertainment unit. This entertainment unit can, for example, play music tailored to the user's preferences. It can also provide quizzes and games tailored to the user's age and interests. For instance, it can offer simple quizzes and puzzles for children and knowledge-testing quizzes for adults. Furthermore, the entertainment unit can estimate the user's emotions and play relaxing music if they wish to relax. This allows the entertainment unit to provide entertainment that is tailored to the user's preferences and emotions.

[0113] The robot system for restaurants can also be equipped with an environmental adaptation unit. This unit can, for example, monitor the temperature and humidity of the restaurant in real time and provide an appropriate environment. It can also adjust the brightness of the lighting to create a comfortable atmosphere. For example, it can provide bright lighting during the day and dimmer lighting at night. Furthermore, the environmental adaptation unit can manage the noise level in the restaurant, providing a quiet environment. In this way, the environmental adaptation unit can optimize the restaurant environment and provide a comfortable space for users.

[0114] The robot system for restaurants can also be equipped with a personalization function. This personalization function can, for example, suggest menus tailored to the user's preferences based on their past order history. It can also manage the user's allergy information and suggest allergy-friendly menus, such as gluten-free or vegan options. Furthermore, it can estimate the user's emotions and suggest relaxing menus if they wish to relax. This allows the personalization function to provide services that are tailored to the user's preferences and emotions.

[0115] The robot system for restaurants can also be equipped with a safety management unit. This unit can, for example, detect and respond quickly to fires or gas leaks within the restaurant. It can also monitor security cameras and detect suspicious activity. For instance, it can issue an alarm if it detects unusual activity. Furthermore, the safety management unit can estimate the user's emotions and provide a reassuring environment if they are feeling stressed. In this way, the safety management unit can ensure the safety of the restaurant and provide users with a safe and comfortable environment.

[0116] The robot system for restaurants can also be equipped with an energy management unit. This unit can, for example, monitor the restaurant's electricity consumption in real time, enabling efficient energy use. It can also optimize the use of lighting and air conditioning, reducing energy waste. For instance, it can automatically adjust lighting and air conditioning during off-peak hours. Furthermore, the energy management unit can analyze energy consumption data to improve energy efficiency. In this way, the energy management unit can achieve efficient energy use and support environmentally conscious restaurant operations.

[0117] The robot system for restaurants can also be equipped with a communication unit. This unit can, for example, understand user needs through dialogue. It can also estimate user emotions and respond appropriately. For instance, if the user is relaxed, it can conduct the conversation in a calm tone. Conversely, if the user is in a hurry, it can respond quickly. This allows the communication unit to facilitate smooth communication with users and provide better service.

[0118] The robot system for restaurants can also be equipped with a maintenance unit. This unit can, for example, monitor the robot's operating status in real time and respond quickly if an abnormality occurs. It can also perform regular inspections and optimize the robot's operation. For instance, it can monitor the robot's battery level and charge it as needed. Furthermore, it can monitor the wear and tear of the robot's parts and replace them as necessary. This allows the maintenance unit to maintain the robot's operation in optimal condition at all times, ensuring a stable service.

[0119] The robot system for restaurants can also be equipped with a data analysis unit. This unit can collect and analyze, for example, in-store sales data and customer behavior data. Furthermore, based on the collected data, the unit can propose measures to improve sales and customer satisfaction. For instance, it can analyze sales data to identify popular menu items and times of day. It can also analyze customer behavior data to provide services tailored to customer needs. In this way, the data analysis unit can support data-driven business strategies and optimize store operations.

[0120] The robot system for restaurants can also be equipped with a feedback unit. This feedback unit can, for example, collect user feedback and use it to improve the service. Furthermore, the feedback unit can estimate the user's emotions and analyze the content of the feedback. For instance, if the user is satisfied, positive feedback can be collected and used to enhance the service. Conversely, if the user is dissatisfied, negative feedback can be collected to identify areas for improvement. This allows the feedback unit to collect feedback based on user emotions and improve the quality of service.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The intelligent unit is responsible for understanding the situation inside the store. The intelligent unit can grasp the situation inside the store using sensors such as cameras and microphones. For example, the intelligent unit can use cameras to analyze customers' facial expressions and movements to understand the situation inside the store. It can also use microphones to analyze customers' conversations to understand the situation inside the store. Step 2: The action selection unit is the part that selects the optimal action based on the situation understood by the intelligence unit. The action selection unit can generate the optimal action using, for example, PaLM-SayCan. The action selection unit selects actions to perform tasks such as finding a customer, guiding a customer, taking an order, pouring water, and serving food. Step 3: The execution unit is the part that executes the action selected by the action selection unit. The execution unit can, for example, control the robot's arms or wheels to perform the selected action. The execution unit can perform tasks such as preparing cutlery, providing hand towels and water, taking orders, cleaning tables, cooking, and serving food. Step 4: The collection unit is the part that collects information. The collection unit can collect information about the store environment using sensors such as cameras and microphones. For example, the collection unit can use cameras to collect customers' facial expressions and movements. The collection unit can also use microphones to collect customers' conversations. Step 5: The serving unit is the part that provides the results. The serving unit can, for example, provide the customer with the results performed by the execution unit. The serving unit provides the customer with results such as order confirmation and food delivery.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the intelligence unit, action selection unit, execution unit, data collection unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the intelligence unit uses the camera 42 and microphone 38B of the smart device 14 to grasp the situation inside the store and analyzes it using the control unit 46A. The action selection unit is implemented in the specific processing unit 290 of the data processing unit 12 and generates the optimal action using PaLM-SayCan. The execution unit controls the robot's arm and wheels using the control unit 46A of the smart device 14 and executes the selected action. The data collection unit collects information using the camera 42 and microphone 38B of the smart device 14 and analyzes it using the control unit 46A. The provision unit provides the results to the customer using the output device 40 of the smart device 14. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed 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 necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the intelligence unit, action selection unit, execution unit, data collection unit, and provision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the intelligence unit uses the camera 42 and microphone 238 of the smart glasses 214 to grasp the situation in the store and analyzes it using the control unit 46A. The action selection unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and generates the optimal action using PaLM-SayCan. The execution unit controls the robot's arm and wheels using the control unit 46A of the smart glasses 214 and executes the selected action. The data collection unit collects information using the camera 42 and microphone 238 of the smart glasses 214 and analyzes it using the control unit 46A. The provision unit provides the results to the customer using the speaker 240 of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, 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 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the intelligence unit, action selection unit, execution unit, data collection unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the intelligence unit uses the camera 42 and microphone 238 of the headset terminal 314 to grasp the situation in the store and analyzes it using the control unit 46A. The action selection unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and generates the optimal action using PaLM-SayCan. The execution unit controls the robot's arms and wheels using the control unit 46A of the headset terminal 314 and executes the selected action. The data collection unit collects information using the camera 42 and microphone 238 of the headset terminal 314 and analyzes it using the control unit 46A. The provision unit provides the results to the customer using the speaker 240 of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed 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 necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the intelligence unit, action selection unit, execution unit, data collection unit, and provision unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the intelligence unit uses the camera 42 and microphone 238 of the robot 414 to grasp the situation inside the store and analyzes it using the control unit 46A. The action selection unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and generates the optimal action using PaLM-SayCan. The execution unit controls the robot's arms and wheels using, for example, the control unit 46A of the robot 414 to execute the selected action. The data collection unit collects information using, for example, the camera 42 and microphone 238 of the robot 414 and analyzes it using the control unit 46A. The provision unit provides the results to the customer using, for example, the speaker 240 of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0186] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) An intelligent unit to understand the situation inside the store, An action selection unit that selects the optimal action based on the situation understood by the aforementioned intelligent unit, An execution unit that executes the action selected by the action selection unit, The information collection unit, A unit that provides results, A system characterized by the following features. (Note 2) The aforementioned collection unit is Gather information about the situation inside the store. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned intelligent unit, The information collected by the aforementioned collection unit is analyzed to understand the situation inside the store. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned action selection unit, The intelligent unit selects the optimal action based on the situation it has understood. The system described in Appendix 1, characterized by the features described herein. (Note 5) The execution unit is, The action selected by the action selection unit is executed. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned supply unit is, The results of the execution performed by the aforementioned execution unit are provided. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is It estimates the user's emotions and adjusts the types of information collected based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 8) The aforementioned collection unit is We collect real-time data on the store's lighting and sound environment to provide the optimal customer service environment. The system described in Appendix 2, characterized by the features described herein. (Note 9) The aforementioned collection unit is We analyze customer movements and facial expressions to collect information that will optimize the timing of service. The system described in Appendix 2, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates the user's emotions and prioritizes the information to collect based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 11) The aforementioned collection unit is We collect temperature and humidity data within the store to maintain a comfortable environment. The system described in Appendix 2, characterized by the features described herein. (Note 12) The aforementioned collection unit is We analyze customer conversations to collect information to improve the quality of our services. The system described in Appendix 2, characterized by the features described herein. (Note 13) The aforementioned intelligent unit, The system estimates the user's emotions and adjusts the analysis algorithm based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 14) The aforementioned intelligent unit, Based on the collected data, the system learns customer preferences and past behavioral patterns to achieve a more accurate understanding of the situation. The system described in Appendix 3, characterized by the features described herein. (Note 15) The aforementioned intelligent unit, Analyze the store's congestion levels to plan optimal staffing and service provision. The system described in Appendix 3, characterized by the features described herein. (Note 16) The aforementioned intelligent unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 17) The aforementioned intelligent unit, Based on the collected data, we estimate the customer's health status and analyze the information to provide appropriate services. The system described in Appendix 3, characterized by the features described herein. (Note 18) The aforementioned intelligent unit, We analyze in-store audio data to provide information for managing noise levels. The system described in Appendix 3, characterized by the features described herein. (Note 19) The aforementioned action selection unit, It estimates the user's emotions and adjusts the criteria for behavioral choices based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 20) The aforementioned action selection unit, Based on the situation in the store, multiple action options are generated, and the optimal action is selected. The system described in Appendix 4, characterized by the features described herein. (Note 21) The aforementioned action selection unit, Based on past behavioral history, it learns high-probability behavioral patterns and optimizes the available options. The system described in Appendix 4, characterized by the features described herein. (Note 22) The aforementioned action selection unit, It estimates the user's emotions and determines the priority of action choices based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 23) The aforementioned action selection unit, Different behavioral selection algorithms are applied depending on the customer base and time of day within the store. The system described in Appendix 4, characterized by the features described herein. (Note 24) The aforementioned action selection unit, Based on in-store environmental data, select energy-efficient actions. The system described in Appendix 4, characterized by the features described herein. (Note 25) The execution unit is, It estimates the user's emotions and adjusts the speed and intensity of actions performed based on those estimated emotions. The system described in Appendix 5, characterized by the features described herein. (Note 26) The execution unit is, During execution, the robot's motion accuracy is monitored in real time, and corrections are made as needed. The system described in Appendix 5, characterized by the features described herein. (Note 27) The execution unit is, During execution, multiple tasks are processed in parallel, enabling efficient work execution. The system described in Appendix 5, characterized by the features described herein. (Note 28) The execution unit is, It estimates the user's emotions and adjusts the order of actions to be performed based on the estimated emotions. The system described in Appendix 5, characterized by the features described herein. (Note 29) The execution unit is, During execution, the robot's operation is optimized considering its remaining battery level. The system described in Appendix 5, characterized by the features described herein. (Note 30) The execution unit is, At runtime, add actions to avoid obstacles inside the store. The system described in Appendix 5, characterized by the features described herein. (Note 31) The aforementioned supply unit is, It estimates the user's emotions and adjusts the format of the information provided based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 32) The aforementioned supply unit is, When providing information, we refer to past customer feedback to offer more personalized information. The system described in Appendix 6, characterized by the features described herein. (Note 33) The aforementioned supply unit is, When providing information, we integrate data from multiple sources to deliver comprehensive information. The system described in Appendix 6, characterized by the features described herein. (Note 34) The aforementioned supply unit is, It estimates the user's emotions and prioritizes the information provided based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 35) The aforementioned supply unit is, When providing information, we will provide it in the most optimal format, taking into account the customer's device information. The system described in Appendix 6, characterized by the features described herein. (Note 36) The aforementioned supply unit is, When providing service, the robots share information in conjunction with other robots in the store to deliver a unified service. The system described in Appendix 6, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An intelligent unit to understand the situation inside the store, An action selection unit that selects the optimal action based on the situation understood by the aforementioned intelligent unit, An execution unit that executes the action selected by the action selection unit, The information collection unit, A unit that provides results, A system characterized by the following features.

2. The aforementioned collection unit is Gather information about the situation inside the store. The system according to feature 1.

3. The aforementioned intelligent unit, The information collected by the aforementioned collection unit is analyzed to understand the situation inside the store. The system according to feature 1.

4. The aforementioned action selection unit, The intelligent unit selects the optimal action based on the situation it has understood. The system according to feature 1.

5. The execution unit is, The action selected by the action selection unit is executed. The system according to feature 1.

6. The aforementioned supply unit is, The results of the execution performed by the aforementioned execution unit are provided. The system according to feature 1.

7. The aforementioned collection unit is It estimates the user's emotions and adjusts the types of information collected based on those estimated emotions. The system according to feature 2.

8. The aforementioned collection unit is We collect real-time data on the store's lighting and sound environment to provide the optimal customer service environment. The system according to feature 2.

9. The aforementioned collection unit is We analyze customer movements and facial expressions to collect information that will optimize the timing of service. The system according to feature 2.

10. The aforementioned collection unit is It estimates the user's emotions and prioritizes the information to collect based on those estimated emotions. The system according to feature 2.

Images