system

Abstract

The system according to this embodiment aims to improve the efficiency of staff command and response in the operation of large stores. [Solution] The system according to the embodiment comprises an information gathering unit, an instruction unit, a response unit, and a notification unit. The information gathering unit collects camera footage from within the store and intercom communications between staff. The instruction unit issues instructions to on-site employees based on the information collected by the information gathering unit. The response unit responds to inquiries from on-site employees based on the instructions issued by the instruction unit. The notification unit notifies the supervisor of important inquiries handled by the response unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 was a problem that the staff's command and response in the operation of large stores were not efficiently carried out.

[0005] The system according to the embodiment aims to improve the efficiency of staff command and response in the operation of large stores.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an information gathering unit, an instruction unit, a response unit, and a notification unit. The information gathering unit collects camera footage from within the store and intercom communications between staff. The instruction unit issues instructions to on-site employees based on the information collected by the information gathering unit. The response unit responds to inquiries from on-site employees based on the instructions issued by the instruction unit. The notification unit notifies the supervisor of important inquiries handled by the response unit. [Effects of the Invention]

[0007] The system according to this embodiment can streamline the command and response of staff in the operation of large stores. [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 applicable 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. [[ID=IS]]

[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 store operation support system according to an embodiment of the present invention is a system for supporting the operation of large stores. This system uses an AI agent to streamline the command of staff. First, the store operation support system has an AI agent that collects camera footage from inside the store and intercom conversations between staff. Next, the AI ​​agent issues instructions to on-site employees based on the collected information. The AI ​​agent also automatically and immediately responds to inquiries from on-site employees. Furthermore, the AI ​​agent connects important inquiries and problems to a supervisor. This system improves operational efficiency and reduces the burden on employees. For example, the store operation support system collects camera footage from inside the store in real time, and the AI ​​agent analyzes that footage. For example, the AI ​​agent can grasp the congestion situation from the camera footage and issue appropriate instructions. The store operation support system also collects intercom conversations between staff, and the AI ​​agent analyzes their content. For example, the AI ​​agent can prioritize the collection of highly urgent information from intercom conversations and respond quickly. Furthermore, the store operation support system has an AI agent that automatically and immediately responds to inquiries from on-site employees. For example, an AI agent can analyze inquiries and provide appropriate answers. Furthermore, the store operations support system uses the AI ​​agent to notify supervisors of important inquiries and problems. For instance, the AI ​​agent can notify supervisors of important inquiries in real time, prompting a quick response. This allows the store operations support system to improve operational efficiency and reduce the burden on employees. It also improves the quality of service to customers and ensures smooth store operations. In short, the store operations support system can improve operational efficiency and reduce the burden on employees.

[0029] The store operation support system according to this embodiment comprises an information collection unit, an instruction unit, a response unit, and a notification unit. The information collection unit collects camera footage from within the store and intercom conversations between staff. The information collection unit can collect footage from within the store using, for example, fixed cameras or mobile cameras. The information collection unit can also collect intercom conversations in real time. For example, the information collection unit can collect and analyze voice data between staff. The instruction unit issues instructions to on-site employees based on the information collected by the information collection unit. The instruction unit can analyze the collected information and generate appropriate instructions using, for example, an AI agent. For example, the instruction unit can issue instructions to adjust staff deployment according to congestion levels. The response unit responds to inquiries from on-site employees based on the instructions issued by the instruction unit. The response unit can analyze the content of inquiries and provide appropriate answers using, for example, an AI agent. For example, the response unit can immediately respond to inquiries regarding product inventory status. The notification unit notifies the commanding staff of important inquiries handled by the response unit. The notification unit can, for example, use an AI agent to notify command staff of important inquiries in real time. For example, the notification unit can prioritize notifying highly urgent inquiries to encourage a quick response. As a result, the store operation support system according to this embodiment can improve operational efficiency and reduce the burden on employees.

[0030] The Information Gathering Department collects camera footage from within the store and intercom conversations between staff. For example, the Information Gathering Department can collect video footage from within the store using fixed or mobile cameras. Fixed cameras are installed in key areas of the store, constantly monitoring a certain range. Mobile cameras, on the other hand, are mounted on robots or drones, allowing them to move freely within the store while collecting footage. This enables the department to understand blind spots and detailed situations in specific areas that fixed cameras cannot cover. The Information Gathering Department can also collect intercom conversations in real time. Intercoms are an important tool for facilitating communication among staff, and collecting audio data allows the department to understand staff movements and instructions. For example, the Information Gathering Department can collect and analyze audio data from staff conversations. Speech recognition technology is used to convert conversations into text data and extract important information. This allows the Information Gathering Department to understand the situation within the store in real time and provide basic data for taking appropriate action. Furthermore, the Information Gathering Department can store the collected data on a cloud server and integrate it with other systems and departments. For example, collected video and audio data can be made accessible to the analysis and instruction units, and the data can be shared as needed. This allows the information collection unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The command unit issues instructions to on-site employees based on information collected by the information gathering unit. The command unit can, for example, use an AI agent to analyze the collected information and generate appropriate instructions. The AI ​​agent uses machine learning algorithms to analyze the collected data and detect patterns and trends. For example, the command unit can issue instructions to adjust staff deployment according to congestion levels. Specifically, it analyzes camera footage within the store to understand customer flow and dwell time, thereby identifying congested areas. Based on this, the AI ​​agent proposes appropriate staff deployment and issues instructions to on-site employees. Furthermore, the command unit supports efficient operations by analyzing intercom communications to understand staff movements and instructions. For example, it can instruct other staff to provide appropriate support while one staff member is replenishing merchandise. In addition, the command unit can utilize historical data and statistical information to issue instructions for long-term operational improvement and efficiency. For example, it can optimize staff deployment during specific times or days of the week based on past congestion data. The command unit can also use anomaly detection algorithms to detect unusual patterns or abnormal situations and issue instructions for early response. This allows the control unit to not only grasp the situation in real time, but also to handle long-term business improvements and anomaly detection, thereby improving the reliability and efficiency of the entire system.

[0032] The response unit handles inquiries from on-site employees based on instructions issued by the instruction unit. The response unit can, for example, use an AI agent to analyze inquiries and provide appropriate answers. The AI ​​agent uses natural language processing technology to understand inquiries and generate appropriate responses. For instance, the response unit can instantly respond to inquiries regarding product inventory status. Specifically, the AI ​​agent accesses the inventory management system and checks the current inventory status to provide a quick and accurate answer. The response unit can also handle customer inquiries. For example, if a customer is looking for a specific product, the AI ​​agent provides optimal guidance based on in-store inventory status and product placement information. Furthermore, the response unit can utilize past inquiry data to analyze trends and patterns in inquiries and propose improvements to operations. For example, if there are many inquiries about a particular product, it might suggest increasing the inventory of that product or reviewing its placement within the store. Additionally, the response unit can use anomaly detection algorithms to detect unusual inquiries or abnormal situations and respond promptly. This allows the response unit to not only handle real-time inquiries but also long-term operational improvements and anomaly detection, improving the overall reliability and efficiency of the system.

[0033] The notification unit notifies commanding personnel of important inquiries handled by the response unit. The notification unit can, for example, use an AI agent to notify commanding personnel of important inquiries in real time. The AI ​​agent analyzes the content of inquiries and evaluates their importance and urgency. For example, the notification unit can prioritize notifications for highly urgent inquiries to encourage a quick response. Specifically, the AI ​​agent analyzes the content of inquiries and extracts highly urgent and important information. Based on this, it notifies commanding personnel in real time to encourage a quick response. In addition, the notification unit can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information by using not only smartphone notifications but also voice calls, SMS, and email. Furthermore, the notification unit can continuously improve the accuracy and effectiveness of notifications by utilizing past notification data. For example, by analyzing past notification data and optimizing the timing and content of notifications, it can provide more effective notifications. In addition, the notification unit can use anomaly detection algorithms to detect unusual patterns and abnormal situations and issue warnings early. This allows the notification unit to handle not only real-time notifications but also long-term business improvements and anomaly detection, thereby improving the reliability and efficiency of the entire system.

[0034] The information gathering unit can focus on collecting camera footage from specific areas or time periods. For example, it can focus on collecting camera footage from areas where congestion is expected in the store. For instance, it might prioritize collecting footage from around cash registers or entrances. It can also concentrate camera footage collection during peak hours. For example, it might focus on collecting footage during lunchtime or in the evening when congestion is high. Furthermore, it can prioritize collecting camera footage from areas where specific events are taking place. For example, it might focus on collecting footage from areas where sales or promotional events are being held. This allows the information gathering unit to easily understand congestion and event situations by focusing camera footage on specific areas or time periods. Some or all of the above processing in the information gathering unit may be performed using AI, or not. For example, the information gathering unit can input footage from specific areas or time periods into the AI, which can then select areas or time periods to prioritize for analysis.

[0035] The information gathering department can analyze intercom communications in real time and prioritize the collection of important information. For example, the information gathering department can prioritize the collection of highly urgent information from intercom communications. For example, the information gathering department can prioritize the collection of urgent communications and trouble reports between staff. The information gathering department can also prioritize the collection of important information related to customer service from intercom communications. For example, the information gathering department can prioritize the collection of customer complaints and inquiries. Furthermore, the information gathering department can also prioritize the collection of important information related to coordination between staff from intercom communications. For example, the information gathering department can prioritize the collection of requests for cooperation and instructions between staff. As a result, the information gathering department can analyze intercom communications in real time and prioritize the collection of important information, enabling a rapid response. Some or all of the above processing in the information gathering department may be performed using AI, or not. For example, the information gathering department can input intercom communications into AI, which can analyze important information in real time and prioritize its collection.

[0036] The information gathering unit can collect camera footage while considering changes in temperature and lighting within the store. For example, if the temperature inside the store is high, the information gathering unit can increase the collection of camera footage to support staff health management. For example, the information gathering unit can measure the temperature inside the store using a temperature sensor and focus on collecting footage from areas with high temperatures. The information gathering unit can also increase the collection of camera footage when the lighting inside the store is dim to ensure visibility. For example, the information gathering unit can measure changes in the lighting inside the store using an illuminance sensor and focus on collecting footage from areas with dim lighting. Furthermore, the information gathering unit can adjust the camera footage collection area according to changes in temperature and lighting inside the store. For example, the information gathering unit can adjust the camera's orientation based on changes in temperature and lighting to collect footage from important areas. This allows the information gathering unit to collect camera footage while considering changes in temperature and lighting inside the store, enabling staff health management and ensuring visibility. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input temperature and lighting data into the AI, which can then adjust the camera image collection area and frequency.

[0037] The information gathering unit can collect staff location information along with intercom communications. For example, the information gathering unit can collect staff current locations in real time along with intercom communications. For example, the information gathering unit can collect staff location information using GPS or beacons and associate it with intercom communications. The information gathering unit can also prioritize the collection of staff location information based on the content of intercom communications. For example, if an urgent intercom communication occurs, the information gathering unit will prioritize the collection of that staff member's location information. Furthermore, the information gathering unit can understand staff movements by combining intercom communications and location information. For example, the information gathering unit can analyze staff location information in chronological order to understand staff movement patterns. This makes it easier for the information gathering unit to understand staff movements by collecting intercom communications and location information together. Some or all of the above processing in the information gathering unit may be performed using AI, or not. For example, the information gathering unit can input intercom communications and location information into AI, which can analyze staff movements in real time.

[0038] The instruction unit can generate optimal instructions by referring to the staff's past behavioral history when issuing instructions. For example, the instruction unit can instruct the staff on the optimal work procedure based on their past behavioral history. For example, the instruction unit can analyze past behavioral data and generate an efficient work procedure. The instruction unit can also suggest efficient work methods based on the staff's past behavioral history. For example, the instruction unit can suggest ways to improve work efficiency based on past behavioral data. Furthermore, the instruction unit can analyze the staff's past behavioral history and issue instructions at the appropriate time. For example, the instruction unit can issue instructions based on past behavioral data according to the progress of the work. In this way, the instruction unit enables efficient work by generating optimal instructions by referring to the staff's past behavioral history. Some or all of the above processes in the instruction unit may be performed using AI, for example, or without AI. For example, the instruction unit can input past behavioral data into AI, and the AI ​​can generate optimal instructions.

[0039] The command center can adjust the priority of instructions according to the situation on site. For example, it can issue instructions that should be prioritized based on the congestion level at the site. For example, it can issue instructions to deploy staff to areas where congestion is expected. The command center can also issue instructions requiring emergency response depending on the nature of the trouble at the site. For example, it can issue instructions to dispatch staff to the area where the trouble has occurred. Furthermore, the command center can issue efficient instructions based on the staff deployment situation at the site. For example, it can grasp the staff deployment situation and issue instructions for the optimal deployment. This allows the command center to respond quickly and appropriately by adjusting the priority of instructions according to the situation on site. Some or all of the above processes in the command center may be performed using AI, for example, or not. For example, the command center can input site situation data into the AI, which can then adjust the priority of instructions.

[0040] The instruction unit can adjust the level of detail of instructions according to the skill level of the staff when issuing instructions. For example, if the staff has a high skill level, the instruction unit will issue concise instructions. For example, the instruction unit will issue concise and to-the-point instructions to highly skilled staff. The instruction unit can also issue detailed instructions if the staff has a low skill level. For example, the instruction unit will issue detailed instructions including specific steps to less skilled staff. Furthermore, the instruction unit can adjust the level of detail of instructions appropriately according to the skill level of the staff. For example, the instruction unit will evaluate the skill level of the staff and adjust the level of detail of the instructions based on that. In this way, the instruction unit can issue appropriate instructions by adjusting the level of detail of instructions according to the skill level of the staff. Some or all of the above processes in the instruction unit may be performed using AI, for example, or not using AI. For example, the instruction unit can input staff skill level data into AI, and the AI ​​can adjust the level of detail of the instructions.

[0041] The instruction unit can generate instructions while considering customer behavior within the store. For example, the instruction unit can grasp customer behavior within the store in real time and issue appropriate instructions. For example, the instruction unit can issue instructions to adjust staff allocation based on customer behavior data. The instruction unit can also issue instructions to adjust staff allocation according to customer behavior. For example, the instruction unit can analyze customer behavior and issue efficient instructions. Furthermore, the instruction unit can analyze customer behavior and issue efficient instructions. For example, the instruction unit can issue instructions to adjust staff allocation based on customer behavior. As a result, customer service becomes smoother when the instruction unit generates instructions while considering customer behavior within the store. Some or all of the above processes in the instruction unit may be performed using AI, for example, or not using AI. For example, the instruction unit can input customer behavior data into AI, and the AI ​​can generate optimal instructions.

[0042] The response unit can select the optimal response method by referring to past inquiry history when handling inquiries. For example, the response unit can select the optimal response method based on past inquiry history. For example, the response unit can analyze past inquiry data and select an efficient response method. The response unit can also propose an efficient response method based on past inquiry history. For example, the response unit can propose ways to improve the efficiency of responses based on past inquiry data. Furthermore, the response unit can analyze past inquiry history and provide a response method at the appropriate time. For example, the response unit can provide a response method based on past inquiry data according to the progress of the response. In this way, the response unit can efficiently handle inquiries by selecting the optimal response method by referring to past inquiry history. Some or all of the above processes in the response unit may be performed using AI, for example, or without using AI. For example, the response unit can input past inquiry data into AI, and the AI ​​can select the optimal response method.

[0043] The response unit can adjust the priority of responses according to the situation on site when handling inquiries. For example, the response unit can select inquiries that should be prioritized based on the congestion level at the site. For example, the response unit will prioritize inquiries in areas where congestion is expected. The response unit can also select inquiries that require urgent attention based on the nature of the trouble at the site. For example, the response unit will prioritize inquiries in areas where trouble has occurred. Furthermore, the response unit can select the most efficient response method according to the staffing situation at the site. For example, the response unit will understand the staffing situation and select the optimal response method. This allows the response unit to respond quickly and appropriately by adjusting the priority of responses according to the situation on site. Some or all of the above processes in the response unit may be performed using AI, for example, or not. For example, the response unit can input on-site situation data into the AI, which can then adjust the priority of responses.

[0044] The support unit can adjust the level of detail in its responses to inquiries according to the skill level of the staff member. For example, if the staff member has a high skill level, the support unit can provide a concise response. For example, the support unit can provide a concise and to-the-point response to a highly skilled staff member. The support unit can also provide a detailed response if the staff member has a low skill level. For example, the support unit can provide a detailed response including specific steps to a less skilled staff member. Furthermore, the support unit can adjust the level of detail in its responses appropriately according to the staff member's skill level. For example, the support unit can evaluate the staff member's skill level and adjust the level of detail in its responses based on that evaluation. This allows the support unit to provide appropriate responses by adjusting the level of detail in its responses according to the staff member's skill level. Some or all of the above processes in the support unit may be performed using AI, for example, or not. For example, the support unit can input staff skill level data into the AI, which can then adjust the level of detail in its responses.

[0045] The customer service department can respond to inquiries while considering customer movements within the store. For example, the customer service department can grasp customer movements within the store in real time and respond appropriately. For example, the customer service department can adjust staff allocation based on customer movement data. The customer service department can also adjust staff allocation according to customer movements. For example, the customer service department can analyze customer movements and respond efficiently. Furthermore, the customer service department can analyze customer movements and respond efficiently. For example, the customer service department can adjust staff allocation based on customer movements. As a result, customer service becomes smoother when the customer service department responds while considering customer movements within the store. Some or all of the above processes in the customer service department may be performed using AI, for example, or not using AI. For example, the customer service department can input customer movement data into AI, and the AI ​​can perform the optimal response.

[0046] The notification unit can select the optimal notification method by referring to past notification history when notifying important inquiries. For example, the notification unit can select the optimal notification method based on past notification history. For example, the notification unit can analyze past notification data and select an efficient notification method. The notification unit can also propose an efficient notification method based on past notification history. For example, the notification unit can propose ways to improve notification efficiency based on past notification data. Furthermore, the notification unit can analyze past notification history and provide a notification method at the appropriate time. For example, the notification unit can provide a notification method according to the timing of the notification based on past notification data. In this way, the notification unit can efficiently notify by selecting the optimal notification method by referring to past notification history. Some or all of the above processes in the notification unit may be performed using AI, for example, or without using AI. For example, the notification unit can input past notification data into AI, and the AI ​​can select the optimal notification method.

[0047] The notification unit can adjust the priority of notifications according to the situation on site when notifying important inquiries. For example, the notification unit can select inquiries that should be notified with priority based on the congestion level at the site. For example, the notification unit will prioritize notifications for inquiries in areas where congestion is expected. The notification unit can also prioritize notifications for inquiries requiring urgent response based on the trouble situation at the site. For example, the notification unit will prioritize notifications for inquiries in areas where trouble has occurred. Furthermore, the notification unit can select an efficient notification method according to the deployment status of staff at the site. For example, the notification unit can grasp the staff deployment status and select the optimal notification method. This allows the notification unit to respond quickly and appropriately by adjusting the priority of notifications according to the situation on site. Some or all of the above processes in the notification unit may be performed using AI, for example, or not using AI. For example, the notification unit can input site situation data into AI, and the AI ​​can adjust the priority of notifications.

[0048] The notification unit can adjust the level of detail of notifications when notifying important inquiries, according to the skill level of the commanding officer receiving the notification. For example, if the commanding officer has a high skill level, the notification unit will provide a concise notification. For example, the notification unit will provide a concise and to-the-point notification to a highly skilled commanding officer. The notification unit can also provide a detailed notification if the commanding officer has a low skill level. For example, the notification unit will provide a detailed notification including specific procedures to a less skilled commanding officer. Furthermore, the notification unit can adjust the level of detail of notifications appropriately according to the commanding officer's skill level. For example, the notification unit will evaluate the commanding officer's skill level and adjust the level of detail of the notification based on that evaluation. This allows the notification unit to provide appropriate notifications by adjusting the level of detail according to the commanding officer's skill level. Some or all of the above processes in the notification unit may be performed using AI, or not using AI. For example, the notification unit can input commanding officer skill level data into AI, and the AI ​​can adjust the level of detail of the notification.

[0049] The notification unit can consider customer activity within the store when notifying customers of important inquiries. For example, the notification unit can grasp customer activity within the store in real time and notify customers at the appropriate time. For example, the notification unit can notify customers to adjust staff allocation based on customer activity data. The notification unit can also notify customers to adjust staff allocation based on customer activity. For example, the notification unit can analyze customer activity and provide efficient notifications. Furthermore, the notification unit can analyze customer activity and provide efficient notifications. For example, the notification unit can notify customers to adjust staff allocation based on customer activity. As a result, customer service becomes smoother when the notification unit notifies customers considering customer activity within the store. Some or all of the above processes in the notification unit may be performed using AI, for example, or not using AI. For example, the notification unit can input customer activity data into AI, and the AI ​​can provide the most appropriate notification.

[0050] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0051] The store operations support system can further analyze customer purchase history and optimize the placement of products within the store based on customer purchasing trends. For example, the information gathering unit collects and analyzes customer purchase history data. Based on the analysis results, the instruction unit can issue instructions to place products that customers frequently purchase in prominent locations within the store. It can also issue instructions to promote specific products based on customer purchasing trends. Furthermore, it can adjust product placement according to seasons and events based on customer purchase history. In this way, the store operations support system can improve sales by optimizing product placement based on customer purchasing trends.

[0052] The store operations support system can further monitor staff health and adjust work assignments based on their health status. For example, the information gathering unit collects and analyzes staff health data. Based on the analysis results, the instruction unit can assign high-load tasks to staff with good health, and low-load tasks to staff with poor health. It can also adjust break times according to staff health. In this way, the store operations support system can support staff health management by adjusting work assignments based on staff health status.

[0053] The store operations support system can further monitor the sound environment within the store and adjust staff placement based on that environment. For example, the information gathering unit collects and analyzes sound data from within the store. Based on the analysis results, the instruction unit can issue instructions to place staff in noisy areas. It can also issue instructions to place staff in quiet areas. Furthermore, by adjusting staff placement according to the sound environment, the efficiency of customer service can be improved. In this way, the store operations support system can optimize the environment within the store by adjusting staff placement based on the sound environment.

[0054] The store operations support system can further analyze customer purchase history and optimize promotions based on customer purchasing trends. For example, the information gathering unit collects and analyzes customer purchase history data. Based on the analysis results, the instruction unit can issue instructions to promote products that customers frequently purchase. It can also issue instructions to discount specific products based on customer purchasing trends. Furthermore, it can adjust promotions according to seasons and events based on customer purchase history. In this way, the store operations support system can improve sales by optimizing promotions based on customer purchasing trends.

[0055] The store operations support system can further analyze customer purchase history and optimize inventory management based on customer purchasing trends. For example, the information gathering unit collects and analyzes customer purchase history data. Based on the analysis results, the instruction unit can issue instructions to increase the inventory of best-selling items. It can also issue instructions to reduce the inventory of items that tend to remain unsold. Furthermore, it can adjust inventory management according to seasons and events. In this way, the store operations support system can efficiently manage inventory by optimizing inventory management based on customer purchasing trends.

[0056] The store operations support system can further analyze customer purchase history and optimize marketing strategies based on customer purchasing trends. For example, the information gathering unit collects and analyzes customer purchase history data. Based on the analysis results, the instruction unit can issue instructions to implement marketing campaigns targeting products that customers frequently purchase. It can also issue instructions to adjust marketing strategies for specific customer segments based on customer purchasing trends. Furthermore, it can adjust marketing strategies according to seasons and events. In this way, the store operations support system can achieve effective marketing activities by optimizing marketing strategies based on customer purchasing trends.

[0057] The following briefly describes the processing flow for example form 1.

[0058] Step 1: The information gathering unit collects camera footage from within the store and intercom conversations between staff. For example, it can collect video footage from within the store using fixed or mobile cameras and collect intercom conversations in real time. The information gathering unit can also collect and analyze audio data from staff conversations. Step 2: The instruction unit issues instructions to on-site employees based on the information collected by the information gathering unit. For example, it can analyze the collected information using an AI agent and generate appropriate instructions. It can also issue instructions to adjust staff deployment according to congestion levels. Step 3: The response unit responds to inquiries from on-site employees based on instructions issued by the instruction unit. For example, it can use an AI agent to analyze the content of inquiries and provide appropriate answers. It can also provide immediate answers to inquiries regarding product inventory status. Step 4: The notification unit notifies the commanding staff of important inquiries handled by the response unit. For example, an AI agent can be used to notify commanding staff of important inquiries in real time. High-priority inquiries can be notified to encourage a quick response.

[0059] (Example of form 2) The store operation support system according to an embodiment of the present invention is a system for supporting the operation of large stores. This system uses an AI agent to streamline the command of staff. First, the store operation support system has an AI agent that collects camera footage from inside the store and intercom conversations between staff. Next, the AI ​​agent issues instructions to on-site employees based on the collected information. The AI ​​agent also automatically and immediately responds to inquiries from on-site employees. Furthermore, the AI ​​agent connects important inquiries and problems to a supervisor. This system improves operational efficiency and reduces the burden on employees. For example, the store operation support system collects camera footage from inside the store in real time, and the AI ​​agent analyzes that footage. For example, the AI ​​agent can grasp the congestion situation from the camera footage and issue appropriate instructions. The store operation support system also collects intercom conversations between staff, and the AI ​​agent analyzes their content. For example, the AI ​​agent can prioritize the collection of highly urgent information from intercom conversations and respond quickly. Furthermore, the store operation support system has an AI agent that automatically and immediately responds to inquiries from on-site employees. For example, an AI agent can analyze inquiries and provide appropriate answers. Furthermore, the store operations support system uses the AI ​​agent to notify supervisors of important inquiries and problems. For instance, the AI ​​agent can notify supervisors of important inquiries in real time, prompting a quick response. This allows the store operations support system to improve operational efficiency and reduce the burden on employees. It also improves the quality of service to customers and ensures smooth store operations. In short, the store operations support system can improve operational efficiency and reduce the burden on employees.

[0060] The store operation support system according to this embodiment comprises an information collection unit, an instruction unit, a response unit, and a notification unit. The information collection unit collects camera footage from within the store and intercom conversations between staff. The information collection unit can collect footage from within the store using, for example, fixed cameras or mobile cameras. The information collection unit can also collect intercom conversations in real time. For example, the information collection unit can collect and analyze voice data between staff. The instruction unit issues instructions to on-site employees based on the information collected by the information collection unit. The instruction unit can analyze the collected information and generate appropriate instructions using, for example, an AI agent. For example, the instruction unit can issue instructions to adjust staff deployment according to congestion levels. The response unit responds to inquiries from on-site employees based on the instructions issued by the instruction unit. The response unit can analyze the content of inquiries and provide appropriate answers using, for example, an AI agent. For example, the response unit can immediately respond to inquiries regarding product inventory status. The notification unit notifies the commanding staff of important inquiries handled by the response unit. The notification unit can, for example, use an AI agent to notify command staff of important inquiries in real time. For example, the notification unit can prioritize notifying highly urgent inquiries to encourage a quick response. As a result, the store operation support system according to this embodiment can improve operational efficiency and reduce the burden on employees.

[0061] The Information Gathering Department collects camera footage from within the store and intercom conversations between staff. For example, the Information Gathering Department can collect video footage from within the store using fixed or mobile cameras. Fixed cameras are installed in key areas of the store, constantly monitoring a certain range. Mobile cameras, on the other hand, are mounted on robots or drones, allowing them to move freely within the store while collecting footage. This enables the department to understand blind spots and detailed situations in specific areas that fixed cameras cannot cover. The Information Gathering Department can also collect intercom conversations in real time. Intercoms are an important tool for facilitating communication among staff, and collecting audio data allows the department to understand staff movements and instructions. For example, the Information Gathering Department can collect and analyze audio data from staff conversations. Speech recognition technology is used to convert conversations into text data and extract important information. This allows the Information Gathering Department to understand the situation within the store in real time and provide basic data for taking appropriate action. Furthermore, the Information Gathering Department can store the collected data on a cloud server and integrate it with other systems and departments. For example, collected video and audio data can be made accessible to the analysis and instruction units, and the data can be shared as needed. This allows the information collection unit to collect data efficiently and effectively, improving the overall system performance.

[0062] The command unit issues instructions to on-site employees based on information collected by the information gathering unit. The command unit can, for example, use an AI agent to analyze the collected information and generate appropriate instructions. The AI ​​agent uses machine learning algorithms to analyze the collected data and detect patterns and trends. For example, the command unit can issue instructions to adjust staff deployment according to congestion levels. Specifically, it analyzes camera footage within the store to understand customer flow and dwell time, thereby identifying congested areas. Based on this, the AI ​​agent proposes appropriate staff deployment and issues instructions to on-site employees. Furthermore, the command unit supports efficient operations by analyzing intercom communications to understand staff movements and instructions. For example, it can instruct other staff to provide appropriate support while one staff member is replenishing merchandise. In addition, the command unit can utilize historical data and statistical information to issue instructions for long-term operational improvement and efficiency. For example, it can optimize staff deployment during specific times or days of the week based on past congestion data. The command unit can also use anomaly detection algorithms to detect unusual patterns or abnormal situations and issue instructions for early response. This allows the control unit to not only grasp the situation in real time, but also to handle long-term business improvements and anomaly detection, thereby improving the reliability and efficiency of the entire system.

[0063] The response unit handles inquiries from on-site employees based on instructions issued by the instruction unit. The response unit can, for example, use an AI agent to analyze inquiries and provide appropriate answers. The AI ​​agent uses natural language processing technology to understand inquiries and generate appropriate responses. For instance, the response unit can instantly respond to inquiries regarding product inventory status. Specifically, the AI ​​agent accesses the inventory management system and checks the current inventory status to provide a quick and accurate answer. The response unit can also handle customer inquiries. For example, if a customer is looking for a specific product, the AI ​​agent provides optimal guidance based on in-store inventory status and product placement information. Furthermore, the response unit can utilize past inquiry data to analyze trends and patterns in inquiries and propose improvements to operations. For example, if there are many inquiries about a particular product, it might suggest increasing the inventory of that product or reviewing its placement within the store. Additionally, the response unit can use anomaly detection algorithms to detect unusual inquiries or abnormal situations and respond promptly. This allows the response unit to not only handle real-time inquiries but also long-term operational improvements and anomaly detection, improving the overall reliability and efficiency of the system.

[0064] The notification unit notifies commanding personnel of important inquiries handled by the response unit. The notification unit can, for example, use an AI agent to notify commanding personnel of important inquiries in real time. The AI ​​agent analyzes the content of inquiries and evaluates their importance and urgency. For example, the notification unit can prioritize notifications for highly urgent inquiries to encourage a quick response. Specifically, the AI ​​agent analyzes the content of inquiries and extracts highly urgent and important information. Based on this, it notifies commanding personnel in real time to encourage a quick response. In addition, the notification unit can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information by using not only smartphone notifications but also voice calls, SMS, and email. Furthermore, the notification unit can continuously improve the accuracy and effectiveness of notifications by utilizing past notification data. For example, by analyzing past notification data and optimizing the timing and content of notifications, it can provide more effective notifications. In addition, the notification unit can use anomaly detection algorithms to detect unusual patterns and abnormal situations and issue warnings early. This allows the notification unit to handle not only real-time notifications but also long-term business improvements and anomaly detection, thereby improving the reliability and efficiency of the entire system.

[0065] The information gathering unit can estimate the emotions of staff members and adjust the camera footage analysis method based on the estimated emotions. For example, the information gathering unit can capture staff members' facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, the information gathering unit can calculate an emotion score based on changes in facial expressions. The information gathering unit can also analyze staff members' voices and estimate their emotions. For example, the information gathering unit can analyze the tone and speed of their voices and calculate an emotion score. Furthermore, the information gathering unit can analyze staff members' behavioral data and estimate their emotions. For example, the information gathering unit can analyze staff members' movements and postures and calculate an emotion score. This allows the information gathering unit to adjust the camera footage analysis method according to the emotions of the staff members. For example, if a staff member is stressed, the information gathering unit can quickly analyze the camera footage to aim for early detection of problems. If a staff member is relaxed, the information gathering unit can analyze the camera footage using the normal analysis method. Furthermore, if a staff member is tired, the information gathering unit can simplify the camera footage analysis and prioritize the analysis of only the important parts. This allows the information gathering department to adjust the camera footage analysis method according to the staff's emotions, enabling early detection of problems and priority analysis of critical areas. Emotion estimation is achieved using emotion estimation functions, 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.

[0066] The information gathering unit can focus on collecting camera footage from specific areas or time periods. For example, it can focus on collecting camera footage from areas where congestion is expected in the store. For instance, it might prioritize collecting footage from around cash registers or entrances. It can also concentrate camera footage collection during peak hours. For example, it might focus on collecting footage during lunchtime or in the evening when congestion is high. Furthermore, it can prioritize collecting camera footage from areas where specific events are taking place. For example, it might focus on collecting footage from areas where sales or promotional events are being held. This allows the information gathering unit to easily understand congestion and event situations by focusing camera footage on specific areas or time periods. Some or all of the above processing in the information gathering unit may be performed using AI, or not. For example, the information gathering unit can input footage from specific areas or time periods into the AI, which can then select areas or time periods to prioritize for analysis.

[0067] The information gathering department can analyze intercom communications in real time and prioritize the collection of important information. For example, the information gathering department can prioritize the collection of highly urgent information from intercom communications. For example, the information gathering department can prioritize the collection of urgent communications and trouble reports between staff. The information gathering department can also prioritize the collection of important information related to customer service from intercom communications. For example, the information gathering department can prioritize the collection of customer complaints and inquiries. Furthermore, the information gathering department can also prioritize the collection of important information related to coordination between staff from intercom communications. For example, the information gathering department can prioritize the collection of requests for cooperation and instructions between staff. As a result, the information gathering department can analyze intercom communications in real time and prioritize the collection of important information, enabling a rapid response. Some or all of the above processing in the information gathering department may be performed using AI, or not. For example, the information gathering department can input intercom communications into AI, which can analyze important information in real time and prioritize its collection.

[0068] The information gathering unit can estimate staff emotions and adjust the frequency of collecting intercom conversations based on the estimated emotions. For example, the information gathering unit can capture staff facial expressions with a camera and estimate emotions using an emotion estimation algorithm. For example, the information gathering unit can calculate an emotion score based on changes in facial expressions. The information gathering unit can also analyze staff voices to estimate emotions. For example, the information gathering unit can analyze voice tone and speed to calculate an emotion score. Furthermore, the information gathering unit can analyze staff behavioral data to estimate emotions. For example, the information gathering unit can analyze staff movements and posture to calculate an emotion score. This allows the information gathering unit to adjust the frequency of collecting intercom conversations according to staff emotions. For example, if staff are stressed, the information gathering unit can collect intercom conversations more frequently to aim for early detection of problems. Conversely, if staff are relaxed, the information gathering unit can collect intercom conversations at the normal frequency. Furthermore, if staff are tired, the information gathering unit can reduce the frequency of collecting intercom conversations and prioritize collecting only the important parts. This allows the information gathering department to adjust the frequency of collecting intercom conversations according to the staff's emotions, enabling early detection of problems and priority collection of important information. Emotion estimation is achieved using emotion estimation functions, 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.

[0069] The information gathering unit can collect camera footage while considering changes in temperature and lighting within the store. For example, if the temperature inside the store is high, the information gathering unit can increase the collection of camera footage to support staff health management. For example, the information gathering unit can measure the temperature inside the store using a temperature sensor and focus on collecting footage from areas with high temperatures. The information gathering unit can also increase the collection of camera footage when the lighting inside the store is dim to ensure visibility. For example, the information gathering unit can measure changes in the lighting inside the store using an illuminance sensor and focus on collecting footage from areas with dim lighting. Furthermore, the information gathering unit can adjust the camera footage collection area according to changes in temperature and lighting inside the store. For example, the information gathering unit can adjust the camera's orientation based on changes in temperature and lighting to collect footage from important areas. This allows the information gathering unit to collect camera footage while considering changes in temperature and lighting inside the store, enabling staff health management and ensuring visibility. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input temperature and lighting data into the AI, which can then adjust the camera image collection area and frequency.

[0070] The information gathering unit can collect staff location information along with intercom communications. For example, the information gathering unit can collect staff current locations in real time along with intercom communications. For example, the information gathering unit can collect staff location information using GPS or beacons and associate it with intercom communications. The information gathering unit can also prioritize the collection of staff location information based on the content of intercom communications. For example, if an urgent intercom communication occurs, the information gathering unit will prioritize the collection of that staff member's location information. Furthermore, the information gathering unit can understand staff movements by combining intercom communications and location information. For example, the information gathering unit can analyze staff location information in chronological order to understand staff movement patterns. This makes it easier for the information gathering unit to understand staff movements by collecting intercom communications and location information together. Some or all of the above processing in the information gathering unit may be performed using AI, or not. For example, the information gathering unit can input intercom communications and location information into AI, which can analyze staff movements in real time.

[0071] The instruction unit can estimate the emotions of staff and adjust the way instructions are expressed based on the estimated emotions. For example, the instruction unit can capture the staff's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, the instruction unit can calculate an emotion score based on changes in facial expressions. The instruction unit can also analyze the staff's voice and estimate their emotions. For example, the instruction unit can analyze the tone and speed of their voice and calculate an emotion score. Furthermore, the instruction unit can analyze the staff's behavioral data and estimate their emotions. For example, the instruction unit can analyze the staff's movements and posture and calculate an emotion score. This allows the instruction unit to adjust the way instructions are expressed according to the staff's emotions. For example, if the staff is stressed, the instruction unit can give concise and clear instructions. If the staff is relaxed, the instruction unit can give detailed instructions. Furthermore, if the staff is tired, the instruction unit can give simple and easy-to-understand instructions. In this way, the instruction unit improves the comprehension of instructions by adjusting the way instructions are expressed according to the staff'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.

[0072] The instruction unit can generate optimal instructions by referring to the staff's past behavioral history when issuing instructions. For example, the instruction unit can instruct the staff on the optimal work procedure based on their past behavioral history. For example, the instruction unit can analyze past behavioral data and generate an efficient work procedure. The instruction unit can also suggest efficient work methods based on the staff's past behavioral history. For example, the instruction unit can suggest ways to improve work efficiency based on past behavioral data. Furthermore, the instruction unit can analyze the staff's past behavioral history and issue instructions at the appropriate time. For example, the instruction unit can issue instructions based on past behavioral data according to the progress of the work. In this way, the instruction unit enables efficient work by generating optimal instructions by referring to the staff's past behavioral history. Some or all of the above processes in the instruction unit may be performed using AI, for example, or without AI. For example, the instruction unit can input past behavioral data into AI, and the AI ​​can generate optimal instructions.

[0073] The command center can adjust the priority of instructions according to the situation on site. For example, it can issue instructions that should be prioritized based on the congestion level at the site. For example, it can issue instructions to deploy staff to areas where congestion is expected. The command center can also issue instructions requiring emergency response depending on the nature of the trouble at the site. For example, it can issue instructions to dispatch staff to the area where the trouble has occurred. Furthermore, the command center can issue efficient instructions based on the staff deployment situation at the site. For example, it can grasp the staff deployment situation and issue instructions for the optimal deployment. This allows the command center to respond quickly and appropriately by adjusting the priority of instructions according to the situation on site. Some or all of the above processes in the command center may be performed using AI, for example, or not. For example, the command center can input site situation data into the AI, which can then adjust the priority of instructions.

[0074] The instruction unit can estimate the emotions of staff members and adjust the timing of instructions based on the estimated emotions. For example, the instruction unit can capture the staff member's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, the instruction unit can calculate an emotion score based on changes in facial expressions. The instruction unit can also analyze the staff member's voice and estimate their emotions. For example, the instruction unit can analyze the tone and speed of their voice and calculate an emotion score. Furthermore, the instruction unit can analyze the staff member's behavioral data and estimate their emotions. For example, the instruction unit can analyze the staff member's movements and posture and calculate an emotion score. This allows the instruction unit to adjust the timing of instructions according to the staff member's emotions. For example, if the staff member is stressed, the instruction unit can delay the timing of instructions. Conversely, if the staff member is relaxed, the instruction unit can issue instructions at the normal timing. Furthermore, if the staff member is tired, the instruction unit can issue instructions earlier. In this way, the instruction unit can issue instructions at the appropriate time by adjusting the timing according to the staff member'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.

[0075] The instruction unit can adjust the level of detail of instructions according to the skill level of the staff when issuing instructions. For example, if the staff has a high skill level, the instruction unit will issue concise instructions. For example, the instruction unit will issue concise and to-the-point instructions to highly skilled staff. The instruction unit can also issue detailed instructions if the staff has a low skill level. For example, the instruction unit will issue detailed instructions including specific steps to less skilled staff. Furthermore, the instruction unit can adjust the level of detail of instructions appropriately according to the skill level of the staff. For example, the instruction unit will evaluate the skill level of the staff and adjust the level of detail of the instructions based on that. In this way, the instruction unit can issue appropriate instructions by adjusting the level of detail of instructions according to the skill level of the staff. Some or all of the above processes in the instruction unit may be performed using AI, for example, or not using AI. For example, the instruction unit can input staff skill level data into AI, and the AI ​​can adjust the level of detail of the instructions.

[0076] The instruction unit can generate instructions while considering customer behavior within the store. For example, the instruction unit can grasp customer behavior within the store in real time and issue appropriate instructions. For example, the instruction unit can issue instructions to adjust staff allocation based on customer behavior data. The instruction unit can also issue instructions to adjust staff allocation according to customer behavior. For example, the instruction unit can analyze customer behavior and issue efficient instructions. Furthermore, the instruction unit can analyze customer behavior and issue efficient instructions. For example, the instruction unit can issue instructions to adjust staff allocation based on customer behavior. As a result, customer service becomes smoother when the instruction unit generates instructions while considering customer behavior within the store. Some or all of the above processes in the instruction unit may be performed using AI, for example, or not using AI. For example, the instruction unit can input customer behavior data into AI, and the AI ​​can generate optimal instructions.

[0077] The support unit can estimate the emotions of staff members and adjust its response methods based on those estimates. For example, the support unit can capture a staff member's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. For example, the support unit can calculate an emotion score based on changes in facial expression. The support unit can also analyze a staff member's voice to estimate their emotions. For example, it can analyze the tone and speed of their voice to calculate an emotion score. Furthermore, the support unit can analyze a staff member's behavioral data to estimate their emotions. For example, it can analyze a staff member's movements and posture to calculate an emotion score. This allows the support unit to adjust its response methods according to the staff member's emotions. For example, if a staff member is stressed, the support unit can provide a concise and clear response. If a staff member is relaxed, the support unit can provide a detailed response. Furthermore, if a staff member is tired, the support unit can provide a simple and easy-to-understand response. This enables the support unit to provide appropriate responses by adjusting its response methods according to the staff member'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.

[0078] The response unit can select the optimal response method by referring to past inquiry history when handling inquiries. For example, the response unit can select the optimal response method based on past inquiry history. For example, the response unit can analyze past inquiry data and select an efficient response method. The response unit can also propose an efficient response method based on past inquiry history. For example, the response unit can propose ways to improve the efficiency of responses based on past inquiry data. Furthermore, the response unit can analyze past inquiry history and provide a response method at the appropriate time. For example, the response unit can provide a response method based on past inquiry data according to the progress of the response. In this way, the response unit can efficiently handle inquiries by selecting the optimal response method by referring to past inquiry history. Some or all of the above processes in the response unit may be performed using AI, for example, or without using AI. For example, the response unit can input past inquiry data into AI, and the AI ​​can select the optimal response method.

[0079] The response unit can adjust the priority of responses according to the situation on site when handling inquiries. For example, the response unit can select inquiries that should be prioritized based on the congestion level at the site. For example, the response unit will prioritize inquiries in areas where congestion is expected. The response unit can also select inquiries that require urgent attention based on the nature of the trouble at the site. For example, the response unit will prioritize inquiries in areas where trouble has occurred. Furthermore, the response unit can select the most efficient response method according to the staffing situation at the site. For example, the response unit will understand the staffing situation and select the optimal response method. This allows the response unit to respond quickly and appropriately by adjusting the priority of responses according to the situation on site. Some or all of the above processes in the response unit may be performed using AI, for example, or not. For example, the response unit can input on-site situation data into the AI, which can then adjust the priority of responses.

[0080] The support unit can estimate the emotions of staff members and adjust the timing of inquiries based on those estimated emotions. For example, the support unit can capture the staff member's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, the support unit can calculate an emotion score based on changes in facial expressions. The support unit can also analyze the staff member's voice and estimate their emotions. For example, the support unit can analyze the tone and speed of their voice and calculate an emotion score. Furthermore, the support unit can analyze the staff member's behavioral data and estimate their emotions. For example, the support unit can analyze the staff member's movements and posture and calculate an emotion score. This allows the support unit to adjust the timing of inquiries according to the staff member's emotions. For example, if the support unit is stressed, it can delay the response. If the support unit is relaxed, it can respond at the normal time. Furthermore, if the support unit is tired, it can speed up the response. In this way, the support unit can adjust the timing of inquiries according to the staff member's emotions, enabling responses at the appropriate time. 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.

[0081] The support unit can adjust the level of detail in its responses to inquiries according to the skill level of the staff member. For example, if the staff member has a high skill level, the support unit can provide a concise response. For example, the support unit can provide a concise and to-the-point response to a highly skilled staff member. The support unit can also provide a detailed response if the staff member has a low skill level. For example, the support unit can provide a detailed response including specific steps to a less skilled staff member. Furthermore, the support unit can adjust the level of detail in its responses appropriately according to the staff member's skill level. For example, the support unit can evaluate the staff member's skill level and adjust the level of detail in its responses based on that evaluation. This allows the support unit to provide appropriate responses by adjusting the level of detail in its responses according to the staff member's skill level. Some or all of the above processes in the support unit may be performed using AI, for example, or not. For example, the support unit can input staff skill level data into the AI, which can then adjust the level of detail in its responses.

[0082] The customer service department can respond to inquiries while considering customer movements within the store. For example, the customer service department can grasp customer movements within the store in real time and respond appropriately. For example, the customer service department can adjust staff allocation based on customer movement data. The customer service department can also adjust staff allocation according to customer movements. For example, the customer service department can analyze customer movements and respond efficiently. Furthermore, the customer service department can analyze customer movements and respond efficiently. For example, the customer service department can adjust staff allocation based on customer movements. As a result, customer service becomes smoother when the customer service department responds while considering customer movements within the store. Some or all of the above processes in the customer service department may be performed using AI, for example, or not using AI. For example, the customer service department can input customer movement data into AI, and the AI ​​can perform the optimal response.

[0083] The notification unit can estimate the emotions of staff members and adjust the way notifications are presented based on the estimated emotions. For example, the notification unit can capture the staff member's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, the notification unit can calculate an emotion score based on changes in facial expressions. The notification unit can also analyze the staff member's voice and estimate their emotions. For example, the notification unit can analyze the tone and speed of their voice and calculate an emotion score. Furthermore, the notification unit can analyze the staff member's behavioral data and estimate their emotions. For example, the notification unit can analyze the staff member's movements and posture and calculate an emotion score. This allows the notification unit to adjust the way notifications are presented according to the staff member's emotions. For example, if the staff member is stressed, the notification unit can provide a concise and clear notification. If the staff member is relaxed, the notification unit can provide a detailed notification. Furthermore, if the staff member is tired, the notification unit can provide a simple and easy-to-understand notification. As a result, the notification unit improves the comprehension of notifications by adjusting the way notifications are presented according to the staff member'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.

[0084] The notification unit can select the optimal notification method by referring to past notification history when notifying important inquiries. For example, the notification unit can select the optimal notification method based on past notification history. For example, the notification unit can analyze past notification data and select an efficient notification method. The notification unit can also propose an efficient notification method based on past notification history. For example, the notification unit can propose ways to improve notification efficiency based on past notification data. Furthermore, the notification unit can analyze past notification history and provide a notification method at the appropriate time. For example, the notification unit can provide a notification method according to the timing of the notification based on past notification data. In this way, the notification unit can efficiently notify by selecting the optimal notification method by referring to past notification history. Some or all of the above processes in the notification unit may be performed using AI, for example, or without using AI. For example, the notification unit can input past notification data into AI, and the AI ​​can select the optimal notification method.

[0085] The notification unit can adjust the priority of notifications according to the situation on site when notifying important inquiries. For example, the notification unit can select inquiries that should be notified with priority based on the congestion level at the site. For example, the notification unit will prioritize notifications for inquiries in areas where congestion is expected. The notification unit can also prioritize notifications for inquiries requiring urgent response based on the trouble situation at the site. For example, the notification unit will prioritize notifications for inquiries in areas where trouble has occurred. Furthermore, the notification unit can select an efficient notification method according to the deployment status of staff at the site. For example, the notification unit can grasp the staff deployment status and select the optimal notification method. This allows the notification unit to respond quickly and appropriately by adjusting the priority of notifications according to the situation on site. Some or all of the above processes in the notification unit may be performed using AI, for example, or not using AI. For example, the notification unit can input site situation data into AI, and the AI ​​can adjust the priority of notifications.

[0086] The notification unit can estimate the emotions of staff members and adjust the timing of notifications based on those emotions. For example, the notification unit can capture a staff member's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. For example, the notification unit can calculate an emotion score based on changes in facial expression. The notification unit can also analyze a staff member's voice to estimate their emotions. For example, the notification unit can analyze the tone and speed of their voice to calculate an emotion score. Furthermore, the notification unit can analyze a staff member's behavioral data to estimate their emotions. For example, the notification unit can analyze a staff member's movements and posture to calculate an emotion score. This allows the notification unit to adjust the timing of notifications according to the staff member's emotions. For example, if a staff member is feeling stressed, the notification unit can delay the timing of the notification. Conversely, if a staff member is relaxed, the notification unit can send a notification at the normal timing. Furthermore, if a staff member is tired, the notification unit can speed up the timing of the notification. In this way, the notification unit can adjust the timing of notifications according to the staff member's emotions, enabling notifications to be sent at the appropriate time. 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 notification unit can adjust the level of detail of notifications when notifying important inquiries, according to the skill level of the commanding officer receiving the notification. For example, if the commanding officer has a high skill level, the notification unit will provide a concise notification. For example, the notification unit will provide a concise and to-the-point notification to a highly skilled commanding officer. The notification unit can also provide a detailed notification if the commanding officer has a low skill level. For example, the notification unit will provide a detailed notification including specific procedures to a less skilled commanding officer. Furthermore, the notification unit can adjust the level of detail of notifications appropriately according to the commanding officer's skill level. For example, the notification unit will evaluate the commanding officer's skill level and adjust the level of detail of the notification based on that evaluation. This allows the notification unit to provide appropriate notifications by adjusting the level of detail according to the commanding officer's skill level. Some or all of the above processes in the notification unit may be performed using AI, or not using AI. For example, the notification unit can input commanding officer skill level data into AI, and the AI ​​can adjust the level of detail of the notification.

[0088] The notification unit can consider customer activity within the store when notifying customers of important inquiries. For example, the notification unit can grasp customer activity within the store in real time and notify customers at the appropriate time. For example, the notification unit can notify customers to adjust staff allocation based on customer activity data. The notification unit can also notify customers to adjust staff allocation based on customer activity. For example, the notification unit can analyze customer activity and provide efficient notifications. Furthermore, the notification unit can analyze customer activity and provide efficient notifications. For example, the notification unit can notify customers to adjust staff allocation based on customer activity. As a result, customer service becomes smoother when the notification unit notifies customers considering customer activity within the store. Some or all of the above processes in the notification unit may be performed using AI, for example, or not using AI. For example, the notification unit can input customer activity data into AI, and the AI ​​can provide the most appropriate notification.

[0089] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0090] The store operations support system can further analyze customer purchase history and optimize the placement of products within the store based on customer purchasing trends. For example, the information gathering unit collects and analyzes customer purchase history data. Based on the analysis results, the instruction unit can issue instructions to place products that customers frequently purchase in prominent locations within the store. It can also issue instructions to promote specific products based on customer purchasing trends. Furthermore, it can adjust product placement according to seasons and events based on customer purchase history. In this way, the store operations support system can improve sales by optimizing product placement based on customer purchasing trends.

[0091] The store operations support system can further monitor staff health and adjust work assignments based on their health status. For example, the information gathering unit collects and analyzes staff health data. Based on the analysis results, the instruction unit can assign high-load tasks to staff with good health, and low-load tasks to staff with poor health. It can also adjust break times according to staff health. In this way, the store operations support system can support staff health management by adjusting work assignments based on staff health status.

[0092] The store operation support system can further estimate customer emotions and adjust customer service methods based on those estimated emotions. For example, the information gathering unit captures customer facial expressions with a camera and estimates emotions using an emotion estimation algorithm. Based on the estimation results, the instruction unit can instruct friendly service if the customer is relaxed. It can also instruct quick and courteous service if the customer is stressed. Furthermore, it can instruct calm service if the customer is agitated. In this way, the store operation support system can improve customer satisfaction by adjusting customer service methods based on customer emotions.

[0093] The store operations support system can further monitor the sound environment within the store and adjust staff placement based on that environment. For example, the information gathering unit collects and analyzes sound data from within the store. Based on the analysis results, the instruction unit can issue instructions to place staff in noisy areas. It can also issue instructions to place staff in quiet areas. Furthermore, by adjusting staff placement according to the sound environment, the efficiency of customer service can be improved. In this way, the store operations support system can optimize the environment within the store by adjusting staff placement based on the sound environment.

[0094] The store operations support system can further estimate staff emotions and adjust break times based on those estimates. For example, the information gathering unit captures staff facial expressions with a camera and uses an emotion estimation algorithm to estimate their emotions. Based on the estimation results, the instruction unit can instruct staff to take an earlier break if they are feeling stressed. It can also instruct them to take a normal break if they are relaxed. Furthermore, it can instruct them to take a longer break if they are tired. In this way, the store operations support system can support staff health management by adjusting break times based on staff emotions.

[0095] The store operations support system can further analyze customer purchase history and optimize promotions based on customer purchasing trends. For example, the information gathering unit collects and analyzes customer purchase history data. Based on the analysis results, the instruction unit can issue instructions to promote products that customers frequently purchase. It can also issue instructions to discount specific products based on customer purchasing trends. Furthermore, it can adjust promotions according to seasons and events based on customer purchase history. In this way, the store operations support system can improve sales by optimizing promotions based on customer purchasing trends.

[0096] The store operations support system can further estimate staff emotions and adjust training programs based on those estimates. For example, the information gathering unit can capture staff facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. Based on the estimation results, the instruction unit can issue instructions to provide a relaxing training program if the staff member is feeling stressed. It can also issue instructions to provide a normal training program if the staff member is relaxed. Furthermore, it can issue instructions to provide a lighter training program if the staff member is tired. In this way, the store operations support system can support staff skill improvement by adjusting training programs based on staff emotions.

[0097] The store operations support system can further analyze customer purchase history and optimize inventory management based on customer purchasing trends. For example, the information gathering unit collects and analyzes customer purchase history data. Based on the analysis results, the instruction unit can issue instructions to increase the inventory of best-selling items. It can also issue instructions to reduce the inventory of items that tend to remain unsold. Furthermore, it can adjust inventory management according to seasons and events. In this way, the store operations support system can efficiently manage inventory by optimizing inventory management based on customer purchasing trends.

[0098] The store operations support system can further estimate staff emotions and adjust feedback methods based on those estimated emotions. For example, the information gathering unit can capture staff facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. Based on the estimation results, the instruction unit can issue instructions to provide positive feedback if the staff member is feeling stressed. It can also issue instructions to provide detailed feedback if the staff member is relaxed. Furthermore, it can issue instructions to provide concise feedback if the staff member is tired. In this way, the store operations support system can improve staff motivation by adjusting feedback methods based on staff emotions.

[0099] The store operations support system can further analyze customer purchase history and optimize marketing strategies based on customer purchasing trends. For example, the information gathering unit collects and analyzes customer purchase history data. Based on the analysis results, the instruction unit can issue instructions to implement marketing campaigns targeting products that customers frequently purchase. It can also issue instructions to adjust marketing strategies for specific customer segments based on customer purchasing trends. Furthermore, it can adjust marketing strategies according to seasons and events. In this way, the store operations support system can achieve effective marketing activities by optimizing marketing strategies based on customer purchasing trends.

[0100] The following briefly describes the processing flow for example form 2.

[0101] Step 1: The information gathering unit collects camera footage from within the store and intercom conversations between staff. For example, it can collect video footage from within the store using fixed or mobile cameras and collect intercom conversations in real time. The information gathering unit can also collect and analyze audio data from staff conversations. Step 2: The instruction unit issues instructions to on-site employees based on the information collected by the information gathering unit. For example, it can analyze the collected information using an AI agent and generate appropriate instructions. It can also issue instructions to adjust staff deployment according to congestion levels. Step 3: The response unit responds to inquiries from on-site employees based on instructions issued by the instruction unit. For example, it can use an AI agent to analyze the content of inquiries and provide appropriate answers. It can also provide immediate answers to inquiries regarding product inventory status. Step 4: The notification unit notifies the commanding staff of important inquiries handled by the response unit. For example, an AI agent can be used to notify commanding staff of important inquiries in real time. High-priority inquiries can be notified to encourage a quick response.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] Each of the multiple elements described above, including the information gathering unit, instruction unit, response unit, and notification unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the information gathering unit collects video and audio data from inside the store using the camera 42 and microphone 38B of the smart device 14. The instruction unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and analyzes the collected information to generate appropriate instructions. The response unit is implemented in the specific processing unit 46A of the smart device 14, for example, and analyzes the content of the inquiry to provide an appropriate answer. The notification unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and notifies the commanding staff of important inquiries. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0106] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.).

[0118] 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.

[0119] 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.

[0120] 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.

[0121] Each of the multiple elements described above, including the information gathering unit, instruction unit, response unit, and notification unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the information gathering unit collects video and audio data from within the store using the camera 42 and microphone 238 of the smart glasses 214. The instruction unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and analyzes the collected information to generate appropriate instructions. The response unit is implemented in the specific processing unit 46A of the smart glasses 214, for example, and analyzes the content of the inquiry to provide an appropriate response. The notification unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and notifies the commanding staff of important inquiries. 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.

[0122] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] Each of the multiple elements described above, including the information gathering unit, instruction unit, response unit, and notification unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the information gathering unit collects video and audio data from within the store using the camera 42 and microphone 238 of the headset terminal 314. The instruction unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and analyzes the collected information to generate appropriate instructions. The response unit is implemented in the specific processing unit 46A of the headset terminal 314, for example, and analyzes the content of the inquiry to provide an appropriate response. The notification unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and notifies the commanding staff of important inquiries. 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.

[0138] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] Each of the multiple elements described above, including the information gathering unit, instruction unit, response unit, and notification unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the information gathering unit collects video and audio data from inside the store using the camera 42 and microphone 238 of the robot 414. The instruction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which analyzes the collected information and generates appropriate instructions. The response unit is implemented, for example, by the control unit 46A of the robot 414, which analyzes the content of the inquiry and provides an appropriate answer. The notification unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which notifies the commanding staff of important inquiries. The correspondence between each unit and the devices and control units is not limited to the example described above, and various modifications are possible.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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."

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] (Note 1) The information gathering department collects camera footage from inside the store and intercom conversations between staff, Based on the information collected by the aforementioned information gathering unit, the instruction unit issues instructions to on-site employees, A response unit that responds to inquiries from on-site employees based on instructions issued by the aforementioned instruction unit, The system includes a notification unit that notifies the commanding officer of important inquiries handled by the aforementioned response unit. A system characterized by the following features. (Note 2) The aforementioned information gathering unit, The system estimates the emotions of the staff and adjusts the camera footage analysis method based on the estimated emotions of the staff. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned information gathering unit, When collecting camera footage, focus on collecting data from specific areas or time periods. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned information gathering unit, The system analyzes intercom communications in real time and prioritizes the collection of important information. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned information gathering unit, The system estimates staff emotions and adjusts the frequency of collecting intercom communications based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned information gathering unit, When collecting camera footage, the system takes into account changes in temperature and lighting within the store. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned information gathering unit, When collecting intercom conversations, staff location information is also collected. The system described in Appendix 1, characterized by the features described herein. (Note 8) The indicator unit is, The system estimates the emotions of the staff and adjusts the way instructions are phrased based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The indicator unit is, When issuing instructions, the system generates optimal instructions by referring to the staff's past behavioral history. The system described in Appendix 1, characterized by the features described herein. (Note 10) The indicator unit is, When giving instructions, adjust the priority of those instructions according to the situation on site. The system described in Appendix 1, characterized by the features described herein. (Note 11) The indicator unit is, The system estimates the emotions of the staff and adjusts the timing of instructions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The indicator unit is, When giving instructions, adjust the level of detail according to the skill level of the staff. The system described in Appendix 1, characterized by the features described herein. (Note 13) The indicator unit is, When issuing instructions, the system generates instructions while taking into account customer behavior within the store. The system described in Appendix 1, characterized by the features described herein. (Note 14) The corresponding part is, The system estimates the emotions of staff members and adjusts how inquiries are handled based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The corresponding part is, When responding to inquiries, refer to past inquiry history to select the most appropriate response method. The system described in Appendix 1, characterized by the features described herein. (Note 16) The corresponding part is, When responding to inquiries, we adjust the priority of responses according to the situation on site. The system described in Appendix 1, characterized by the features described herein. (Note 17) The corresponding part is, The system estimates the emotions of staff members and adjusts the timing of responses to inquiries based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The corresponding part is, When handling inquiries, we adjust the level of detail in the response according to the skill level of the staff member. The system described in Appendix 1, characterized by the features described herein. (Note 19) The corresponding part is, When handling inquiries, we take into consideration the movements of customers within the store. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned notification unit, The system estimates staff members' emotions and adjusts the way notifications are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned notification unit, When notifying about important inquiries, the system will refer to past notification history to select the most appropriate notification method. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned notification unit, When notifying about important inquiries, we adjust the notification priority according to the situation on site. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned notification unit, We estimate the emotions of our staff and adjust the timing of notifications based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned notification unit, When notifying important inquiries, adjust the level of detail in the notification according to the skill level of the supervisory staff member receiving the notification. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned notification unit, When notifying customers of important inquiries, the notification should take into account customer activity within the store. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0174] 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. The information gathering department collects camera footage from inside the store and intercom communications between staff, Based on the information collected by the aforementioned information gathering unit, the instruction unit issues instructions to on-site employees, A response unit that responds to inquiries from on-site employees based on instructions issued by the aforementioned instruction unit, The system includes a notification unit that notifies the commanding officer of important inquiries handled by the aforementioned response unit. A system characterized by the following features.

2. The aforementioned information gathering unit, The system estimates the emotions of the staff and adjusts the camera footage analysis method based on the estimated emotions of the staff. The system according to feature 1.

3. The aforementioned information gathering unit, When collecting camera footage, focus on collecting data from specific areas or time periods. The system according to feature 1.

4. The aforementioned information gathering unit, The system analyzes intercom communications in real time and prioritizes the collection of important information. The system according to feature 1.

5. The aforementioned information gathering unit, The system estimates staff emotions and adjusts the frequency of collecting intercom communications based on the estimated emotions. The system according to feature 1.

6. The aforementioned information gathering unit, When collecting camera footage, the system takes into account changes in temperature and lighting within the store. The system according to feature 1.

7. The aforementioned information gathering unit, When collecting intercom conversations, staff location information is also collected. The system according to feature 1.

8. The indicator unit is, The system estimates the emotions of the staff and adjusts the way instructions are phrased based on those estimated emotions. The system according to feature 1.

9. The indicator unit is, When issuing instructions, the system generates optimal instructions by referring to the staff's past behavioral history. The system according to feature 1.

Images