system

Abstract

The system according to this embodiment aims to efficiently receive customer requests and to gather registered information and preferences. [Solution] The system according to this embodiment comprises a reception unit, a hearing unit, a preference hearing unit, and a provision unit. The reception unit receives customer requests. The hearing unit hears customer registration information based on the information received by the reception unit. The preference hearing unit hears customer preferences based on the information heard by the hearing unit. The provision unit provides the information collected by the preference hearing unit to human staff.

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 and includes 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, the process of efficiently receiving customer requests and hearing registration information and wishes is complicated, and there is a risk that the customer service time will be long.

[0005] The system according to the embodiment aims to efficiently receive customer requests and hear registration information and wishes.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a hearing unit, a preference hearing unit, and a provision unit. The reception unit receives customer requests. The hearing unit hears customer registration information based on the information received by the reception unit. The preference hearing unit hears customer preferences based on the information heard by the hearing unit. The provision unit provides the information collected by the preference hearing unit to human staff. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently receive customer requests and gather registration information and preferences. [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 controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The reception robot system according to an embodiment of the present invention is a system that streamlines customer service at SoftBank shops and reduces customer service time. The reception robot system temporarily receives customer requests, hears the customer's current registration information, and hears the customer's wishes. As a result, human staff can respond smoothly based on the information collected by the robot, reducing customer service time. For example, if a customer wants to purchase a new smartphone, the reception robot system receives that request. Next, the reception robot system checks information such as the customer's contract details and usage status. This allows the system to understand the customer's current situation. Furthermore, the reception robot system listens to the customer's detailed requests, such as the smartphone model and plan they want. This allows the system to understand the customer's specific wishes. This mechanism allows human staff to respond smoothly based on the information collected by the robot, reducing customer service time. For example, by having the robot collect customer requests, registration information, and wishes in advance, human staff can respond quickly based on that information. This reduces customer waiting times and improves customer satisfaction. In addition, having the robot handle customer service also solves the problem of labor shortages. For example, by having the robot conduct basic interviews, human staff can concentrate on more specialized responses. This improves overall operational efficiency and streamlines customer service. The reception robot system efficiently receives customer requests, gathers registration information and preferences, and provides this information to staff, thereby reducing customer service time and ensuring smoother customer interactions.

[0029] The reception robot system according to this embodiment comprises a reception unit, a hearing unit, a preference hearing unit, and a service provision unit. The reception unit receives customer requests. For example, if a customer wants to purchase a new smartphone, the reception unit can receive that request. The reception unit can also receive requests if a customer wants to change their contract details. Furthermore, the reception unit can also receive requests if a customer wants to cancel a service. The hearing unit hears the customer's registration information based on the information received by the reception unit. For example, the hearing unit can confirm information such as the customer's contract details and usage status. The hearing unit can also confirm basic information such as the customer's name, address, and contact information. Furthermore, the hearing unit can also confirm the customer's past usage history and service usage status. The preference hearing unit hears the customer's preferences based on the information heard by the hearing unit. For example, the preference hearing unit can hear detailed requests from the customer, such as the desired smartphone model and plan. Furthermore, the Request Hearing Unit can also hear the content and conditions of the services that the customer desires. In addition, the Request Hearing Unit can also hear the customer's desired changes to the contract or the reasons for cancellation. The Service Provision Unit provides the information collected by the Request Hearing Unit to human staff. The Service Provision Unit can, for example, organize the collected information so that staff can respond quickly. The Service Provision Unit can also provide information to reduce customer waiting times. Furthermore, the Service Provision Unit can provide information to alleviate the problem of labor shortages by having robots handle customer service. As a result, the reception robot system according to this embodiment can efficiently receive customer requests, hear registration information and preferences, and provide them to staff, thereby shortening customer service time and making customer service smoother.

[0030] The reception desk receives customer requests. For example, if a customer wants to purchase a new smartphone, the reception desk can accept that request. The reception desk can also accept requests from customers who wish to change their contract details. Furthermore, the reception desk can accept requests from customers who wish to cancel a service. When a customer visits the store, the reception desk first provides an interface to confirm their request. For example, a touch panel display or voice recognition system can be used to allow customers to easily input their requests. With a touch panel display, customers can input their requests by tapping options, and with a voice recognition system, customers can input their requests by speaking. This allows customers to communicate their requests intuitively, and the reception desk can quickly process them. The reception desk can also verify the customer's identity when accepting their request. For example, if a customer presents a membership card or identification, the reception desk can verify their identity and accept their request. This allows the reception desk to process requests based on accurate information and ensure customer trust. Furthermore, after receiving a customer's request, the reception department can register that request in a database and provide the information necessary for subsequent processing. For example, if a customer wants to purchase a new smartphone, the reception department registers the request in the database and provides inventory information and the information necessary for the purchase procedure. Also, if a customer wants to change the terms of their contract, the reception department registers the request in the database and provides the information necessary for the change procedure. This allows the reception department to efficiently receive customer requests and proceed with subsequent processing smoothly.

[0031] The Hearing Department interviews customers to gather registration information based on the information received by the Reception Department. The Hearing Department can, for example, verify information such as the customer's contract details and usage history. It can also verify basic information such as the customer's name, address, and contact information. Furthermore, the Hearing Department can verify the customer's past usage history and service usage status. To verify customer registration information, the Hearing Department accesses the database and retrieves the necessary information. For example, to verify the customer's contract details and usage history, it retrieves contract information and usage history from the database. It also retrieves basic customer information such as the customer's name, address, and contact information from the database. This allows the Hearing Department to verify customer registration information based on accurate information. Furthermore, when verifying customer registration information, the Hearing Department can ask the customer additional questions. For example, it may ask additional questions to obtain more detailed information about the customer's contract details and usage history. Also, if there have been any changes to the customer's basic information, the Hearing Department will confirm the changes with the customer. This allows the interviewing department to accurately grasp customer registration information and provide the information necessary for subsequent processing.

[0032] The Customer Preferences Department conducts interviews to understand customer preferences based on information gathered by the Customer Interview Department. For example, the Customer Preferences Department can gather detailed requests such as the desired smartphone model and plan. It can also gather information on the content and conditions of services the customer desires. Furthermore, it can gather information on contract changes or reasons for cancellation. The Customer Preferences Department asks detailed questions to accurately understand customer preferences. For example, if a customer wants to purchase a new smartphone, the Customer Preferences Department will ask about detailed requests such as the desired model, color, and storage capacity. It will also inquire about the conditions of the customer's desired plan, such as data usage and call time. This allows the Customer Preferences Department to accurately understand the customer's specific needs. Additionally, the Customer Preferences Department can offer suggestions to customers while gathering their preferences. For example, it can provide information on stock availability and campaigns for the desired smartphone model, suggesting the best option for the customer. It can also suggest the most suitable plan based on the customer's usage. This allows the customer needs assessment department to accurately understand customer preferences and provide them with the most suitable proposals.

[0033] The service department provides human staff with information collected by the needs assessment department. For example, the service department can organize the collected information to enable staff to respond quickly. It can also provide information to reduce customer waiting times. Furthermore, the service department can provide information to address labor shortages by enabling robots to handle customer interactions. The service department organizes and prioritizes the collected information to enable staff to respond quickly. For example, it categorizes information according to customer requests and needs, allowing staff to quickly obtain the necessary information. To reduce customer waiting times, the service department prepares information in advance based on customer requests, enabling staff to respond quickly. This allows the service department to reduce customer waiting times and streamline customer service. Furthermore, the service department provides appropriate information to staff to address labor shortages by enabling robots to handle customer interactions. For example, it provides staff with necessary information when robots handle customer interactions, enabling the robots to respond appropriately. Additionally, robot customer interactions reduce the burden on staff and enable efficient business operations. This will allow the service department to handle customer inquiries smoothly, resolve labor shortages, and improve operational efficiency.

[0034] The reception area includes a basic information collection unit that collects basic customer information. The basic information collection unit can collect basic information such as the customer's name, address, and contact information. It can also collect information such as the customer's age and gender. Furthermore, it can collect information such as the customer's occupation and income. This improves the efficiency of the reception process by collecting basic customer information. Some or all of the above-described processing in the basic information collection unit may be performed using AI, for example, or without AI. For example, the basic information collection unit can provide the AI ​​with basic information such as the customer's name, address, and contact information as input, and the AI ​​can organize the customer's basic information based on this information.

[0035] The interviewing unit includes a contract information acquisition unit that automatically acquires customer contract details and usage status. The contract information acquisition unit can, for example, automatically acquire customer contract details and usage status. The contract information acquisition unit can acquire information such as the type of contract, contract period, and contract conditions of the customer. It can also acquire information such as the frequency of use, usage time, and number of uses of the customer. Furthermore, the contract information acquisition unit can acquire the customer's past usage history and service usage status. This improves the efficiency of interviews by automatically acquiring customer contract details and usage status. Some or all of the above processing in the contract information acquisition unit may be performed using AI, for example, or without using AI. For example, the contract information acquisition unit can provide customer contract details and usage status as input to the AI, and the AI ​​can organize customer contract details and usage status based on this information.

[0036] The Customer Needs Assessment Department includes a Proposal Department that provides optimal proposals based on customer needs. The Proposal Department can, for example, provide optimal proposals based on customer needs. The Proposal Department can also provide cost-effective proposals. Furthermore, the Proposal Department can propose optimal plans and services based on customer needs. This improves customer satisfaction by providing optimal proposals based on customer needs. Some or all of the above processes in the Proposal Department may be performed using AI, for example, or not. For example, the Proposal Department can provide information based on customer needs as input to the AI, and the AI ​​can make optimal proposals based on this information.

[0037] The information provision department includes an information organization department that organizes the collected information so that staff can respond quickly. The information organization department can, for example, organize the collected information so that staff can respond quickly. The information organization department can, for example, clarify the classification method and organization procedure of the information. The information organization department can also determine the priority of the information and organize important information first. Furthermore, the information organization department can provide the information organization results to the staff to support a quick response. In this way, by organizing the collected information, staff can respond quickly. Some or all of the above processing in the information organization department may be performed using AI, for example, or not using AI. For example, the information organization department can provide the collected information as input to the AI, and the AI ​​can organize the information based on this information.

[0038] The service unit includes a waiting time reduction unit for reducing customer waiting times. The waiting time reduction unit can, for example, provide methods for reducing customer waiting times. The waiting time reduction unit can, for example, clarify methods for measuring waiting times and means for reducing them. The waiting time reduction unit can also evaluate the effectiveness of waiting time reduction and suggest areas for improvement. Furthermore, the waiting time reduction unit can monitor customer waiting times in real time and take action as needed. This improves customer satisfaction by reducing customer waiting times. Some or all of the above-described processes in the waiting time reduction unit may be performed using AI, for example, or without AI. For example, the waiting time reduction unit can provide customer waiting time data as input to the AI, and the AI ​​can suggest methods for reducing waiting times based on this data.

[0039] The service provider includes a labor shortage resolution unit that addresses the problem of labor shortages by having robots handle customer service. The labor shortage resolution unit can, for example, provide a method for resolving labor shortages by having robots handle customer service. The labor shortage resolution unit can, for example, clarify means to alleviate staff shortages and workload overload. The labor shortage resolution unit can also define the scope and procedures of tasks that robots will handle. Furthermore, the labor shortage resolution unit can evaluate the effectiveness of robot implementation and propose areas for improvement. In this way, the labor shortage problem is resolved by having robots handle customer service. Some or all of the above processing in the labor shortage resolution unit may be performed using AI, for example, or without AI. For example, the labor shortage resolution unit can provide robot response data as input to the AI, and the AI ​​can propose methods for resolving labor shortages based on this data.

[0040] The reception desk can select the most appropriate response by referring to the customer's past visit history at the time of check-in. For example, if the customer has visited frequently in the past, the reception desk can address the customer by name and provide a friendly response. If it is the customer's first visit, the reception desk can also provide a polite guide and basic information. Furthermore, if the reception desk has a history of using a particular service, it can prioritize providing information related to that service. This allows the reception desk to select the most appropriate response by referring to the customer's past visit history. Some or all of the above processing at the reception desk may be performed using AI, for example, or not. For example, the reception desk can provide customer visit history data as input to the AI, which can then select the most appropriate response based on this data.

[0041] The reception desk can prioritize responses based on the customer's current situation and needs at the time of reception. For example, if a customer is in a hurry, the reception desk can respond quickly and guide them before other customers. The reception desk can also prioritize assigning staff relevant to a customer's specific problem. Furthermore, if a customer requests multiple services, the reception desk can prioritize the most important services first. This enables efficient service by prioritizing responses based on the customer's current situation and needs. Some or all of the above processes at the reception desk may be performed using AI, or not. For example, the reception desk can provide customer situation and needs data as input to the AI, which can then use this data to determine the priority of responses.

[0042] The reception desk can take into account the customer's geographical location to provide the best possible service at the time of check-in. For example, if a customer has traveled a long distance, the reception desk can provide prompt service and reduce waiting times. If a customer has traveled from nearby, the reception desk can prioritize other customers who are in a hurry. Furthermore, if a customer has traveled from a specific region, the reception desk can provide information relevant to that region. This allows for optimal service by considering the customer's geographical location. Some or all of the above processing at the reception desk may be performed using AI, or not. For example, the reception desk can provide the AI ​​with the customer's geographical location as input, and the AI ​​can use this information to provide the best possible service.

[0043] The reception desk can analyze a customer's social media activity and obtain relevant information at the time of reception. For example, if a customer mentions a particular service on social media, the reception desk can provide information related to that service. Furthermore, if a customer expresses dissatisfaction on social media, the reception desk can respond quickly and resolve the issue. Additionally, if a customer shows interest in a particular campaign on social media, the reception desk can provide information related to that campaign. This allows for the acquisition of relevant information by analyzing the customer's social media activity. Some or all of the above processing at the reception desk may be performed using AI, or not. For example, the reception desk can provide customer social media data as input to an AI, which can then use this data to obtain relevant information.

[0044] The interviewing unit can select the most appropriate questions during the interview by referring to the customer's past contract history. For example, the interviewing unit can ask relevant questions based on the services the customer has used in the past. It can also ask questions related to the customer's current usage based on their contract history. Furthermore, the interviewing unit can analyze the customer's contract history and select the most appropriate questions. This allows for the selection of optimal questions by referring to the customer's past contract history. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or not. For example, the interviewing unit can provide customer contract history data as input to the AI, which can then select the most appropriate questions based on this data.

[0045] The interviewing unit can adjust the order of questions based on the customer's current usage during the interview. For example, the interviewing unit can prioritize questions related to the services the customer is currently using. It can also ask questions in order of importance, depending on the customer's usage. Furthermore, the interviewing unit can analyze the customer's usage and determine the optimal order of questions. This allows for efficient interviews by adjusting the order of questions based on the customer's current usage. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or not. For example, the interviewing unit can provide customer usage data as input to the AI, which can then adjust the order of questions based on this data.

[0046] The interviewing unit can ask optimal questions during interviews, taking into account the customer's geographical location. For example, if a customer has traveled a long distance, the interviewing unit can ask about services relevant to their area. If a customer has traveled nearby, the interviewing unit can ask about services relevant to their local area. Furthermore, if a customer has traveled from a specific region, the interviewing unit can provide information relevant to that region. This allows for optimal questioning by considering the customer's geographical location. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or without AI. For example, the interviewing unit can provide the AI ​​with the customer's geographical location as input, and the AI ​​can ask optimal questions based on this information.

[0047] The interviewing department can analyze the customer's social media activity during the interview and obtain relevant information. For example, if the customer mentions a particular service on social media, the interviewing department can ask questions related to that service. Similarly, if the customer expresses dissatisfaction on social media, the interviewing department can ask questions related to that issue. Furthermore, if the customer shows interest in a particular campaign on social media, the interviewing department can ask questions related to that campaign. This allows the interviewing department to obtain relevant information by analyzing the customer's social media activity. Some or all of the above processing in the interviewing department may be performed using AI, for example, or not. For example, the interviewing department can provide the AI ​​with the customer's social media data as input, and the AI ​​can obtain relevant information based on this data.

[0048] The preference hearing unit can select the most appropriate questions during a preference hearing by referring to the customer's past preference history. For example, the preference hearing unit can ask relevant questions based on services the customer has requested in the past. It can also ask questions related to the customer's current needs based on their preference history. Furthermore, the preference hearing unit can analyze the customer's preference history and select the most appropriate questions. This allows for the selection of optimal questions by referring to the customer's past preference history. Some or all of the above processes in the preference hearing unit may be performed using AI, for example, or not. For example, the preference hearing unit can provide customer preference history data as input to the AI, which can then select the most appropriate questions based on this data.

[0049] The preference hearing unit can adjust the order of questions based on the customer's current needs during the preference hearing. For example, the preference hearing unit can prioritize questions related to the services the customer currently desires. Alternatively, the preference hearing unit can ask questions in order of importance, depending on the customer's needs. Furthermore, the preference hearing unit can analyze the customer's needs and determine the optimal order of questions. This allows for efficient hearing by adjusting the order of questions based on the customer's current needs. Some or all of the above processing in the preference hearing unit may be performed using AI, for example, or not. For example, the preference hearing unit can provide customer needs data as input to the AI, which can then adjust the order of questions based on this data.

[0050] The preference-gathering unit can ask optimal questions during the preference-gathering process, taking into account the customer's geographical location. For example, if a customer visits from a distant location, the preference-gathering unit can ask about services relevant to that area. If a customer visits from a nearby location, the preference-gathering unit can also ask about services relevant to that area. Furthermore, if a customer visits from a specific region, the preference-gathering unit can provide information relevant to that region. This allows for optimal questioning by considering the customer's geographical location. Some or all of the above processing in the preference-gathering unit may be performed using AI, for example, or without AI. For example, the preference-gathering unit can provide the AI ​​with the customer's geographical location as input, and the AI ​​can ask optimal questions based on this information.

[0051] The preference hearing department can analyze the customer's social media activity during the preference hearing and obtain relevant information. For example, if the customer mentions a particular service on social media, the preference hearing department can ask questions related to that service. It can also ask questions related to complaints expressed on social media. Furthermore, if the customer shows interest in a particular campaign on social media, the preference hearing department can ask questions related to that campaign. This allows the department to obtain relevant information by analyzing the customer's social media activity. Some or all of the above processing in the preference hearing department may be performed using AI, for example, or not. For example, the preference hearing department can provide the AI ​​with the customer's social media data as input, and the AI ​​can obtain relevant information based on this data.

[0052] The service provider can provide optimal information by referring to the customer's past interaction history at the time of service provision. For example, the service provider can provide relevant information based on services the customer has used in the past. Furthermore, the service provider can provide information related to the customer's current needs from the customer's interaction history. In addition, the service provider can analyze the customer's interaction history and provide the most appropriate information. This allows the service provider to provide optimal information by referring to the customer's past interaction history. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can provide customer interaction history data as input to the AI, which can then provide optimal information based on this data.

[0053] The service provider can prioritize information based on the customer's current situation at the time of delivery. For example, if the customer is in a hurry, the service provider can respond quickly and prioritize providing the most important information. Furthermore, if the customer has a specific problem, the service provider can prioritize providing information related to that problem. Additionally, if the customer desires multiple services, the service provider can prioritize providing information related to the most important service. This enables efficient information delivery by prioritizing information based on the customer's current situation. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can provide customer situation data as input to the AI, which can then prioritize information based on this data.

[0054] The service provider can provide optimal information by considering the customer's geographical location at the time of delivery. For example, if a customer visits from a distant location, the service provider can prioritize providing information relevant to that area. Furthermore, if a customer visits from a nearby location, the service provider can provide information relevant to nearby services. In addition, if a customer visits from a specific region, the service provider can provide information relevant to that region. This enables the provision of optimal information by considering the customer's geographical location. Some or all of the above processing in the service provider may be performed using AI, or without AI. For example, the service provider can provide the AI ​​with the customer's geographical location as input, and the AI ​​can provide optimal information based on this information.

[0055] The service provider can analyze the customer's social media activity and provide relevant information at the time of delivery. For example, if the customer mentions a particular service on social media, the service provider can provide information related to that service. Furthermore, if the customer expresses dissatisfaction on social media, the service provider can provide information related to that issue. Additionally, if the customer shows interest in a particular campaign on social media, the service provider can provide information related to that campaign. This allows the service provider to provide relevant information by analyzing the customer's social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can provide customer social media data as input to an AI, which can then use this data to provide relevant information.

[0056] The basic information collection unit can select the optimal collection method by referring to the customer's past basic information when collecting basic information. For example, the basic information collection unit can prioritize the collection of relevant information based on the basic information the customer has provided in the past. The basic information collection unit can also collect information related to the customer's current needs from the customer's basic information history. Furthermore, the basic information collection unit can analyze the customer's basic information history and select the most appropriate collection method. This allows the optimal collection method to be selected by referring to the customer's past basic information. Some or all of the above processing in the basic information collection unit may be performed using AI, for example, or not using AI. For example, the basic information collection unit can provide the AI ​​with the customer's basic information history data as input, and the AI ​​can select the optimal collection method based on this data.

[0057] The basic information collection unit can select the optimal collection method when collecting basic information, taking into account the customer's geographical location. For example, if a customer visits from a distant location, the basic information collection unit can prioritize collecting information related to that region. Furthermore, if a customer visits from a nearby location, the basic information collection unit can also collect information related to nearby services. In addition, if a customer visits from a specific region, the basic information collection unit can collect information related to that region. This allows for the optimal collection method by considering the customer's geographical location. Some or all of the above processing in the basic information collection unit may be performed using AI, for example, or without AI. For example, the basic information collection unit can provide the AI ​​with the customer's geographical location as input, and the AI ​​can select the optimal collection method based on this information.

[0058] The contract information acquisition unit can select the optimal acquisition method by referring to the customer's past contract history when acquiring contract information. For example, the contract information acquisition unit can prioritize the acquisition of relevant information based on contract information the customer has used in the past. The contract information acquisition unit can also acquire information related to the customer's current needs from the customer's contract history. Furthermore, the contract information acquisition unit can analyze the customer's contract history and select the most appropriate acquisition method. This allows the optimal acquisition method to be selected by referring to the customer's past contract history. Some or all of the above processing in the contract information acquisition unit may be performed using AI, for example, or without AI. For example, the contract information acquisition unit can provide customer contract history data as input to the AI, and the AI ​​can select the optimal acquisition method based on this data.

[0059] The contract information acquisition unit can select the optimal acquisition method when acquiring contract information, taking into account the customer's geographical location. For example, if a customer visits from a distant location, the contract information acquisition unit can prioritize acquiring information related to that region. Furthermore, if a customer visits from a nearby location, the contract information acquisition unit can acquire information related to nearby services. In addition, if a customer visits from a specific region, the contract information acquisition unit can acquire information related to that region. This allows for the optimal acquisition method by considering the customer's geographical location. Some or all of the above processing in the contract information acquisition unit may be performed using AI, for example, or without AI. For example, the contract information acquisition unit can provide the customer's geographical location information as input to the AI, which can then select the optimal acquisition method based on this information.

[0060] The proposal department can make optimal proposals by referring to the customer's past preference history when making a proposal. For example, the proposal department can make relevant proposals based on services the customer has requested in the past. It can also make proposals related to the customer's current needs based on the customer's preference history. Furthermore, the proposal department can analyze the customer's preference history and make the most appropriate proposal. In this way, it can make optimal proposals by referring to the customer's past preference history. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can provide customer preference history data as input to the AI, and the AI ​​can make optimal proposals based on this data.

[0061] The proposal department can make optimal suggestions by considering the customer's geographical location. For example, if a customer visits from a distant location, the proposal department can prioritize suggestions related to that area. If a customer visits from nearby, the proposal department can also make suggestions related to nearby services. Furthermore, if a customer visits from a specific region, the proposal department can make suggestions related to that region. This makes it possible to make optimal suggestions by considering the customer's geographical location. Some or all of the above processing in the proposal department may be performed using AI, for example, or not. For example, the proposal department can provide the AI ​​with the customer's geographical location as input, and the AI ​​can make optimal suggestions based on this information.

[0062] The information organization unit can select the optimal organization method by referring to the customer's past information when organizing information. For example, the information organization unit can prioritize organizing relevant information based on information the customer has provided in the past. The information organization unit can also organize information related to the customer's current needs from the customer's information history. Furthermore, the information organization unit can analyze the customer's information history and select the most appropriate organization method. This allows the optimal organization method to be selected by referring to the customer's past information. Some or all of the above processes in the information organization unit may be performed using AI, for example, or not using AI. For example, the information organization unit can provide customer information history data as input to the AI, and the AI ​​can select the optimal organization method based on this data.

[0063] The information organization unit can select the optimal organization method when organizing information, taking into account the customer's geographical location. For example, if a customer visits from a distant location, the information organization unit can prioritize organizing information related to that region. Furthermore, if a customer visits from a nearby location, the information organization unit can organize information related to nearby services. In addition, if a customer visits from a specific region, the information organization unit can organize information related to that region. This allows for the optimal organization method by considering the customer's geographical location. Some or all of the above processing in the information organization unit may be performed using AI, for example, or without AI. For example, the information organization unit can provide the AI ​​with the customer's geographical location as input, and the AI ​​can select the optimal organization method based on this information.

[0064] The waiting time reduction unit can select the optimal reduction method by referring to the customer's past waiting time history when reducing waiting times. For example, if a customer has been made to wait for a long time in the past, the waiting time reduction unit can select a method to reduce waiting time based on that history. The waiting time reduction unit can also select a reduction method related to the customer's current needs from the customer's waiting time history. Furthermore, the waiting time reduction unit can analyze the customer's waiting time history and select the most appropriate reduction method. In this way, the optimal reduction method can be selected by referring to the customer's past waiting time history. Some or all of the above processing in the waiting time reduction unit may be performed using AI, for example, or without using AI. For example, the waiting time reduction unit can provide customer waiting time history data as input to the AI, and the AI ​​can select the optimal reduction method based on this data.

[0065] The waiting time reduction unit can select the optimal method of reducing waiting times by considering the customer's geographical location information. For example, if a customer comes from a distant location, the unit can prioritize procedures related to that area. Similarly, if a customer comes from a nearby location, the unit can prioritize procedures related to that area. Furthermore, if a customer comes from a specific region, the unit can prioritize procedures related to that region. This allows for the optimal reduction method by considering the customer's geographical location information. Some or all of the above-described processes in the waiting time reduction unit may be performed using AI, for example, or without AI. For instance, the waiting time reduction unit can provide the AI ​​with the customer's geographical location information as input, and the AI ​​can select the optimal reduction method based on this information.

[0066] The Labor Shortage Resolution Unit can select the optimal solution when resolving a labor shortage by referring to the customer's past interaction history. For example, if a customer has been kept waiting for a long time in the past, the Labor Shortage Resolution Unit can select a solution based on that history. The Labor Shortage Resolution Unit can also select a solution related to the current needs from the customer's interaction history. Furthermore, the Labor Shortage Resolution Unit can analyze the customer's interaction history and select the most appropriate solution. In this way, the optimal solution can be selected by referring to the customer's past interaction history. Some or all of the above processes in the Labor Shortage Resolution Unit may be performed using AI, for example, or not using AI. For example, the Labor Shortage Resolution Unit can provide customer interaction history data as input to the AI, and the AI ​​can select the optimal solution based on this data.

[0067] The Labor Shortage Resolution Department can select the optimal solution when addressing labor shortages, taking into account the customer's geographical location. For example, if a customer visits from a distant location, the Labor Shortage Resolution Department can prioritize procedures related to that region. Furthermore, if a customer visits from a nearby location, the Labor Shortage Resolution Department can prioritize procedures related to that region. This allows for the selection of the optimal solution by considering the customer's geographical location. Some or all of the above-described processes in the Labor Shortage Resolution Department may be performed using AI, or not. For example, the Labor Shortage Resolution Department can provide the AI ​​with the customer's geographical location as input, and the AI ​​can select the optimal solution based on this information.

[0068] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0069] The reception robot system can make optimal suggestions by referring to the customer's past purchase history when receiving customer requests. For example, it can suggest new smartphones and plans that meet the customer's current needs based on the smartphone models and plans the customer has purchased in the past. It can also suggest related services based on the customer's past service usage history. Furthermore, it can analyze the customer's past purchase history to make the most appropriate suggestions. In this way, it can make optimal suggestions by referring to the customer's past purchase history. Some or all of the above processing at the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can provide customer purchase history data as input to the AI, which can then make optimal suggestions based on this data.

[0070] The reception robot system can adjust its response to customer requests based on the customer's current health condition. For example, if a customer is feeling unwell, it can respond quickly and ask only the necessary questions. If the customer is healthy, it can ask more detailed questions to understand their specific needs. Furthermore, it can analyze the customer's health condition and select the most appropriate response. By adjusting the response based on the customer's health condition, customer satisfaction can be improved. Some or all of the above processes at the reception desk may be performed using AI, for example, or not. For example, the reception desk can provide customer health data as input to the AI, which can then select the most appropriate response based on this data.

[0071] The reception robot system can adjust its response method when receiving customer requests by referring to the customer's past feedback. For example, it can provide a response that matches the customer's preferences based on feedback the customer has provided in the past. Also, if the customer has expressed dissatisfaction in the past, it can prioritize taking action to resolve that dissatisfaction. Furthermore, it can analyze customer feedback and select the optimal response method. This allows the system to select the optimal response method by referring to the customer's past feedback. Some or all of the above processes in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can provide customer feedback data as input to the AI, and the AI ​​can select the optimal response method based on this data.

[0072] The reception robot system can adjust its response method when receiving customer requests, taking into account the customer's current weather information. For example, if a customer visits on a rainy day, it can respond quickly and reduce waiting times. If a customer visits on a sunny day, it can ask more detailed questions to understand their specific needs. Furthermore, it can analyze the customer's weather information and select the most appropriate response method. By adjusting the response method according to the customer's weather information, customer satisfaction can be improved. Some or all of the above processes at the reception desk may be performed using AI, for example, or not. For example, the reception desk can provide customer weather information data as input to the AI, which can then select the most appropriate response method based on this data.

[0073] The reception robot system can adjust its response to customer requests by considering the customer's current traffic situation. For example, if a customer arrives late due to traffic congestion, the system can respond quickly and reduce waiting time. If a customer arrives smoothly, the system can ask detailed questions to understand their specific needs. Furthermore, it can analyze the customer's traffic situation and select the most appropriate response. By adjusting the response based on the customer's traffic situation, customer satisfaction can be improved. Some or all of the above processes at the reception desk may be performed using AI, for example, or not. For example, the reception desk can provide customer traffic data as input to the AI, which can then select the most appropriate response based on this data.

[0074] The following briefly describes the processing flow for example form 1.

[0075] Step 1: The reception desk receives customer requests. For example, it can receive requests from customers who want to purchase a new smartphone, change their contract details, or cancel a service. Step 2: The interviewing department interviews customers to gather registration information based on the information received by the reception department. For example, they can confirm basic information such as the customer's contract details, usage status, name, address, contact information, and past usage history. Step 3: The Customer Feedback Department conducts a customer feedback session based on the information gathered by the Customer Feedback Department. For example, they can gather detailed requests such as the desired smartphone model and plan, service content and conditions, contract changes, and reasons for cancellation. Step 4: The service department provides the information collected by the needs assessment department to human staff. For example, the collected information can be organized so that staff can respond quickly. It can also provide information to reduce customer waiting times or information to address labor shortages by having robots handle customer service.

[0076] (Example of form 2) The reception robot system according to an embodiment of the present invention is a system that streamlines customer service at SoftBank shops and reduces customer service time. The reception robot system temporarily receives customer requests, hears the customer's current registration information, and hears the customer's wishes. As a result, human staff can respond smoothly based on the information collected by the robot, reducing customer service time. For example, if a customer wants to purchase a new smartphone, the reception robot system receives that request. Next, the reception robot system checks information such as the customer's contract details and usage status. This allows the system to understand the customer's current situation. Furthermore, the reception robot system listens to the customer's detailed requests, such as the smartphone model and plan they want. This allows the system to understand the customer's specific wishes. This mechanism allows human staff to respond smoothly based on the information collected by the robot, reducing customer service time. For example, by having the robot collect customer requests, registration information, and wishes in advance, human staff can respond quickly based on that information. This reduces customer waiting times and improves customer satisfaction. In addition, having the robot handle customer service also solves the problem of labor shortages. For example, by having the robot conduct basic interviews, human staff can concentrate on more specialized responses. This improves overall operational efficiency and streamlines customer service. The reception robot system efficiently receives customer requests, gathers registration information and preferences, and provides this information to staff, thereby reducing customer service time and ensuring smoother customer interactions.

[0077] The reception robot system according to this embodiment comprises a reception unit, a hearing unit, a preference hearing unit, and a service provision unit. The reception unit receives customer requests. For example, if a customer wants to purchase a new smartphone, the reception unit can receive that request. The reception unit can also receive requests if a customer wants to change their contract details. Furthermore, the reception unit can also receive requests if a customer wants to cancel a service. The hearing unit hears the customer's registration information based on the information received by the reception unit. For example, the hearing unit can confirm information such as the customer's contract details and usage status. The hearing unit can also confirm basic information such as the customer's name, address, and contact information. Furthermore, the hearing unit can also confirm the customer's past usage history and service usage status. The preference hearing unit hears the customer's preferences based on the information heard by the hearing unit. For example, the preference hearing unit can hear detailed requests from the customer, such as the desired smartphone model and plan. Furthermore, the Request Hearing Unit can also hear the content and conditions of the services that the customer desires. In addition, the Request Hearing Unit can also hear the customer's desired changes to the contract or the reasons for cancellation. The Service Provision Unit provides the information collected by the Request Hearing Unit to human staff. The Service Provision Unit can, for example, organize the collected information so that staff can respond quickly. The Service Provision Unit can also provide information to reduce customer waiting times. Furthermore, the Service Provision Unit can provide information to alleviate the problem of labor shortages by having robots handle customer service. As a result, the reception robot system according to this embodiment can efficiently receive customer requests, hear registration information and preferences, and provide them to staff, thereby shortening customer service time and making customer service smoother.

[0078] The reception desk receives customer requests. For example, if a customer wants to purchase a new smartphone, the reception desk can accept that request. The reception desk can also accept requests from customers who wish to change their contract details. Furthermore, the reception desk can accept requests from customers who wish to cancel a service. When a customer visits the store, the reception desk first provides an interface to confirm their request. For example, a touch panel display or voice recognition system can be used to allow customers to easily input their requests. With a touch panel display, customers can input their requests by tapping options, and with a voice recognition system, customers can input their requests by speaking. This allows customers to communicate their requests intuitively, and the reception desk can quickly process them. The reception desk can also verify the customer's identity when accepting their request. For example, if a customer presents a membership card or identification, the reception desk can verify their identity and accept their request. This allows the reception desk to process requests based on accurate information and ensure customer trust. Furthermore, after receiving a customer's request, the reception department can register that request in a database and provide the information necessary for subsequent processing. For example, if a customer wants to purchase a new smartphone, the reception department registers the request in the database and provides inventory information and the information necessary for the purchase procedure. Also, if a customer wants to change the terms of their contract, the reception department registers the request in the database and provides the information necessary for the change procedure. This allows the reception department to efficiently receive customer requests and proceed with subsequent processing smoothly.

[0079] The Hearing Department interviews customers to gather registration information based on the information received by the Reception Department. The Hearing Department can, for example, verify information such as the customer's contract details and usage history. It can also verify basic information such as the customer's name, address, and contact information. Furthermore, the Hearing Department can verify the customer's past usage history and service usage status. To verify customer registration information, the Hearing Department accesses the database and retrieves the necessary information. For example, to verify the customer's contract details and usage history, it retrieves contract information and usage history from the database. It also retrieves basic customer information such as the customer's name, address, and contact information from the database. This allows the Hearing Department to verify customer registration information based on accurate information. Furthermore, when verifying customer registration information, the Hearing Department can ask the customer additional questions. For example, it may ask additional questions to obtain more detailed information about the customer's contract details and usage history. Also, if there have been any changes to the customer's basic information, the Hearing Department will confirm the changes with the customer. This allows the interviewing department to accurately grasp customer registration information and provide the information necessary for subsequent processing.

[0080] The Customer Preferences Department conducts interviews to understand customer preferences based on information gathered by the Customer Interview Department. For example, the Customer Preferences Department can gather detailed requests such as the desired smartphone model and plan. It can also gather information on the content and conditions of services the customer desires. Furthermore, it can gather information on contract changes or reasons for cancellation. The Customer Preferences Department asks detailed questions to accurately understand customer preferences. For example, if a customer wants to purchase a new smartphone, the Customer Preferences Department will ask about detailed requests such as the desired model, color, and storage capacity. It will also inquire about the conditions of the customer's desired plan, such as data usage and call time. This allows the Customer Preferences Department to accurately understand the customer's specific needs. Additionally, the Customer Preferences Department can offer suggestions to customers while gathering their preferences. For example, it can provide information on stock availability and campaigns for the desired smartphone model, suggesting the best option for the customer. It can also suggest the most suitable plan based on the customer's usage. This allows the customer needs assessment department to accurately understand customer preferences and provide them with the most suitable proposals.

[0081] The service department provides human staff with information collected by the needs assessment department. For example, the service department can organize the collected information to enable staff to respond quickly. It can also provide information to reduce customer waiting times. Furthermore, the service department can provide information to address labor shortages by enabling robots to handle customer interactions. The service department organizes and prioritizes the collected information to enable staff to respond quickly. For example, it categorizes information according to customer requests and needs, allowing staff to quickly obtain the necessary information. To reduce customer waiting times, the service department prepares information in advance based on customer requests, enabling staff to respond quickly. This allows the service department to reduce customer waiting times and streamline customer service. Furthermore, the service department provides appropriate information to staff to address labor shortages by enabling robots to handle customer interactions. For example, it provides staff with necessary information when robots handle customer interactions, enabling the robots to respond appropriately. Additionally, robot customer interactions reduce the burden on staff and enable efficient business operations. This will allow the service department to handle customer inquiries smoothly, resolve labor shortages, and improve operational efficiency.

[0082] The reception area includes a basic information collection unit that collects basic customer information. The basic information collection unit can collect basic information such as the customer's name, address, and contact information. It can also collect information such as the customer's age and gender. Furthermore, it can collect information such as the customer's occupation and income. This improves the efficiency of the reception process by collecting basic customer information. Some or all of the above-described processing in the basic information collection unit may be performed using AI, for example, or without AI. For example, the basic information collection unit can provide the AI ​​with basic information such as the customer's name, address, and contact information as input, and the AI ​​can organize the customer's basic information based on this information.

[0083] The interviewing unit includes a contract information acquisition unit that automatically acquires customer contract details and usage status. The contract information acquisition unit can, for example, automatically acquire customer contract details and usage status. The contract information acquisition unit can acquire information such as the type of contract, contract period, and contract conditions of the customer. It can also acquire information such as the frequency of use, usage time, and number of uses of the customer. Furthermore, the contract information acquisition unit can acquire the customer's past usage history and service usage status. This improves the efficiency of interviews by automatically acquiring customer contract details and usage status. Some or all of the above processing in the contract information acquisition unit may be performed using AI, for example, or without using AI. For example, the contract information acquisition unit can provide customer contract details and usage status as input to the AI, and the AI ​​can organize customer contract details and usage status based on this information.

[0084] The Customer Needs Assessment Department includes a Proposal Department that provides optimal proposals based on customer needs. The Proposal Department can, for example, provide optimal proposals based on customer needs. The Proposal Department can also provide cost-effective proposals. Furthermore, the Proposal Department can propose optimal plans and services based on customer needs. This improves customer satisfaction by providing optimal proposals based on customer needs. Some or all of the above processes in the Proposal Department may be performed using AI, for example, or not. For example, the Proposal Department can provide information based on customer needs as input to the AI, and the AI ​​can make optimal proposals based on this information.

[0085] The information provision department includes an information organization department that organizes the collected information so that staff can respond quickly. The information organization department can, for example, organize the collected information so that staff can respond quickly. The information organization department can, for example, clarify the classification method and organization procedure of the information. The information organization department can also determine the priority of the information and organize important information first. Furthermore, the information organization department can provide the information organization results to the staff to support a quick response. In this way, by organizing the collected information, staff can respond quickly. Some or all of the above processing in the information organization department may be performed using AI, for example, or not using AI. For example, the information organization department can provide the collected information as input to the AI, and the AI ​​can organize the information based on this information.

[0086] The service unit includes a waiting time reduction unit for reducing customer waiting times. The waiting time reduction unit can, for example, provide methods for reducing customer waiting times. The waiting time reduction unit can, for example, clarify methods for measuring waiting times and means for reducing them. The waiting time reduction unit can also evaluate the effectiveness of waiting time reduction and suggest areas for improvement. Furthermore, the waiting time reduction unit can monitor customer waiting times in real time and take action as needed. This improves customer satisfaction by reducing customer waiting times. Some or all of the above-described processes in the waiting time reduction unit may be performed using AI, for example, or without AI. For example, the waiting time reduction unit can provide customer waiting time data as input to the AI, and the AI ​​can suggest methods for reducing waiting times based on this data.

[0087] The service provider includes a labor shortage resolution unit that addresses the problem of labor shortages by having robots handle customer service. The labor shortage resolution unit can, for example, provide a method for resolving labor shortages by having robots handle customer service. The labor shortage resolution unit can, for example, clarify means to alleviate staff shortages and workload overload. The labor shortage resolution unit can also define the scope and procedures of tasks that robots will handle. Furthermore, the labor shortage resolution unit can evaluate the effectiveness of robot implementation and propose areas for improvement. In this way, the labor shortage problem is resolved by having robots handle customer service. Some or all of the above processing in the labor shortage resolution unit may be performed using AI, for example, or without AI. For example, the labor shortage resolution unit can provide robot response data as input to the AI, and the AI ​​can propose methods for resolving labor shortages based on this data.

[0088] The reception desk can estimate the customer's emotions and adjust its response based on those emotions. For example, if the customer is stressed, the reception desk can respond in a calm voice and ask simple questions. If the customer is relaxed, the reception desk can respond in a friendly tone and ask more detailed questions. Furthermore, if the customer is in a hurry, the reception desk can respond quickly and ask only the essential questions. By adjusting the reception desk's response according to the customer's emotions, customer satisfaction is improved. 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. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0089] The reception desk can select the most appropriate response by referring to the customer's past visit history at the time of check-in. For example, if the customer has visited frequently in the past, the reception desk can address the customer by name and provide a friendly response. If it is the customer's first visit, the reception desk can also provide a polite guide and basic information. Furthermore, if the reception desk has a history of using a particular service, it can prioritize providing information related to that service. This allows the reception desk to select the most appropriate response by referring to the customer's past visit history. Some or all of the above processing at the reception desk may be performed using AI, for example, or not. For example, the reception desk can provide customer visit history data as input to the AI, which can then select the most appropriate response based on this data.

[0090] The reception desk can prioritize responses based on the customer's current situation and needs at the time of reception. For example, if a customer is in a hurry, the reception desk can respond quickly and guide them before other customers. The reception desk can also prioritize assigning staff relevant to a customer's specific problem. Furthermore, if a customer requests multiple services, the reception desk can prioritize the most important services first. This enables efficient service by prioritizing responses based on the customer's current situation and needs. Some or all of the above processes at the reception desk may be performed using AI, or not. For example, the reception desk can provide customer situation and needs data as input to the AI, which can then use this data to determine the priority of responses.

[0091] The reception desk can estimate the customer's emotions and adjust the order of service based on the estimated emotions. For example, if a customer is feeling anxious, the reception desk can prioritize them and provide reassurance. Conversely, if a customer is relaxed, the reception desk can prioritize other customers who are in a hurry. Furthermore, if a customer is angry, the reception desk can respond quickly and prioritize problem resolution. By adjusting the order of service according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0092] The reception desk can take into account the customer's geographical location to provide the best possible service at the time of check-in. For example, if a customer has traveled a long distance, the reception desk can provide prompt service and reduce waiting times. If a customer has traveled from nearby, the reception desk can prioritize other customers who are in a hurry. Furthermore, if a customer has traveled from a specific region, the reception desk can provide information relevant to that region. This allows for optimal service by considering the customer's geographical location. Some or all of the above processing at the reception desk may be performed using AI, or not. For example, the reception desk can provide the AI ​​with the customer's geographical location as input, and the AI ​​can use this information to provide the best possible service.

[0093] The reception desk can analyze a customer's social media activity and obtain relevant information at the time of reception. For example, if a customer mentions a particular service on social media, the reception desk can provide information related to that service. Furthermore, if a customer expresses dissatisfaction on social media, the reception desk can respond quickly and resolve the issue. Additionally, if a customer shows interest in a particular campaign on social media, the reception desk can provide information related to that campaign. This allows for the acquisition of relevant information by analyzing the customer's social media activity. Some or all of the above processing at the reception desk may be performed using AI, or not. For example, the reception desk can provide customer social media data as input to an AI, which can then use this data to obtain relevant information.

[0094] The interviewing unit can estimate the customer's emotions and adjust its interviewing method based on the estimated emotions. For example, if the customer is nervous, the interviewing unit can respond in a calm voice and ask simple questions. If the customer is relaxed, the interviewing unit can respond in a friendly tone and ask detailed questions. Furthermore, if the customer is in a hurry, the interviewing unit can respond quickly and ask only the necessary questions. By adjusting the interviewing method according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the interviewing unit may be performed using AI or not using AI. For example, the interviewing unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0095] The interviewing unit can select the most appropriate questions during the interview by referring to the customer's past contract history. For example, the interviewing unit can ask relevant questions based on the services the customer has used in the past. It can also ask questions related to the customer's current usage based on their contract history. Furthermore, the interviewing unit can analyze the customer's contract history and select the most appropriate questions. This allows for the selection of optimal questions by referring to the customer's past contract history. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or not. For example, the interviewing unit can provide customer contract history data as input to the AI, which can then select the most appropriate questions based on this data.

[0096] The interviewing unit can adjust the order of questions based on the customer's current usage during the interview. For example, the interviewing unit can prioritize questions related to the services the customer is currently using. It can also ask questions in order of importance, depending on the customer's usage. Furthermore, the interviewing unit can analyze the customer's usage and determine the optimal order of questions. This allows for efficient interviews by adjusting the order of questions based on the customer's current usage. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or not. For example, the interviewing unit can provide customer usage data as input to the AI, which can then adjust the order of questions based on this data.

[0097] The interview unit can estimate the customer's emotions and adjust the interview content based on the estimated emotions. For example, if the customer is feeling anxious, the interview unit can ask questions that provide reassurance. If the customer is relaxed, the interview unit can ask questions that elicit detailed information. Furthermore, if the customer is in a hurry, the interview unit can ask questions that quickly gather necessary information. By adjusting the interview content according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the interview unit may be performed using AI, or not using AI. For example, the interview unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0098] The interviewing unit can ask optimal questions during interviews, taking into account the customer's geographical location. For example, if a customer has traveled a long distance, the interviewing unit can ask about services relevant to their area. If a customer has traveled nearby, the interviewing unit can ask about services relevant to their local area. Furthermore, if a customer has traveled from a specific region, the interviewing unit can provide information relevant to that region. This allows for optimal questioning by considering the customer's geographical location. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or without AI. For example, the interviewing unit can provide the AI ​​with the customer's geographical location as input, and the AI ​​can ask optimal questions based on this information.

[0099] The interviewing department can analyze the customer's social media activity during the interview and obtain relevant information. For example, if the customer mentions a particular service on social media, the interviewing department can ask questions related to that service. Similarly, if the customer expresses dissatisfaction on social media, the interviewing department can ask questions related to that issue. Furthermore, if the customer shows interest in a particular campaign on social media, the interviewing department can ask questions related to that campaign. This allows the interviewing department to obtain relevant information by analyzing the customer's social media activity. Some or all of the above processing in the interviewing department may be performed using AI, for example, or not. For example, the interviewing department can provide the AI ​​with the customer's social media data as input, and the AI ​​can obtain relevant information based on this data.

[0100] The preference assessment unit can estimate the customer's emotions and adjust the preferred assessment method based on the estimated emotions. For example, if the customer is nervous, the preference assessment unit can respond in a calm voice and ask simple questions. If the customer is relaxed, the preference assessment unit can respond in a friendly tone and ask detailed questions. Furthermore, if the customer is in a hurry, the preference assessment unit can respond quickly and ask only the necessary questions. By adjusting the preferred assessment method according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the preference assessment unit may be performed using AI or not using AI. For example, the preference assessment unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0101] The preference hearing unit can select the most appropriate questions during a preference hearing by referring to the customer's past preference history. For example, the preference hearing unit can ask relevant questions based on services the customer has requested in the past. It can also ask questions related to the customer's current needs based on their preference history. Furthermore, the preference hearing unit can analyze the customer's preference history and select the most appropriate questions. This allows for the selection of optimal questions by referring to the customer's past preference history. Some or all of the above processes in the preference hearing unit may be performed using AI, for example, or not. For example, the preference hearing unit can provide customer preference history data as input to the AI, which can then select the most appropriate questions based on this data.

[0102] The preference hearing unit can adjust the order of questions based on the customer's current needs during the preference hearing. For example, the preference hearing unit can prioritize questions related to the services the customer currently desires. Alternatively, the preference hearing unit can ask questions in order of importance, depending on the customer's needs. Furthermore, the preference hearing unit can analyze the customer's needs and determine the optimal order of questions. This allows for efficient hearing by adjusting the order of questions based on the customer's current needs. Some or all of the above processing in the preference hearing unit may be performed using AI, for example, or not. For example, the preference hearing unit can provide customer needs data as input to the AI, which can then adjust the order of questions based on this data.

[0103] The desire assessment unit can estimate the customer's emotions and adjust the desired assessment content based on the estimated emotions. For example, if the customer is feeling anxious, the desire assessment unit can ask questions that provide reassurance. If the customer is relaxed, the desire assessment unit can ask questions that elicit detailed information. Furthermore, if the customer is in a hurry, the desire assessment unit can ask questions that quickly gather necessary information. By adjusting the desired assessment content according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the desire assessment unit may be performed using AI or not using AI. For example, the desire assessment unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0104] The preference-gathering unit can ask optimal questions during the preference-gathering process, taking into account the customer's geographical location. For example, if a customer visits from a distant location, the preference-gathering unit can ask about services relevant to that area. If a customer visits from a nearby location, the preference-gathering unit can also ask about services relevant to that area. Furthermore, if a customer visits from a specific region, the preference-gathering unit can provide information relevant to that region. This allows for optimal questioning by considering the customer's geographical location. Some or all of the above processing in the preference-gathering unit may be performed using AI, for example, or without AI. For example, the preference-gathering unit can provide the AI ​​with the customer's geographical location as input, and the AI ​​can ask optimal questions based on this information.

[0105] The preference hearing department can analyze the customer's social media activity during the preference hearing and obtain relevant information. For example, if the customer mentions a particular service on social media, the preference hearing department can ask questions related to that service. It can also ask questions related to complaints expressed on social media. Furthermore, if the customer shows interest in a particular campaign on social media, the preference hearing department can ask questions related to that campaign. This allows the department to obtain relevant information by analyzing the customer's social media activity. Some or all of the above processing in the preference hearing department may be performed using AI, for example, or not. For example, the preference hearing department can provide the AI ​​with the customer's social media data as input, and the AI ​​can obtain relevant information based on this data.

[0106] The service provider can estimate the customer's emotions and adjust the way information is delivered based on those estimated emotions. For example, if the customer is nervous, the service provider can deliver information in a calm voice and provide a simple explanation. If the customer is relaxed, the service provider can deliver information in a friendly tone and provide a detailed explanation. Furthermore, if the customer is in a hurry, the service provider can deliver information quickly and provide a concise explanation. By adjusting the way information is delivered according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0107] The service provider can provide optimal information by referring to the customer's past interaction history at the time of service provision. For example, the service provider can provide relevant information based on services the customer has used in the past. Furthermore, the service provider can provide information related to the customer's current needs from the customer's interaction history. In addition, the service provider can analyze the customer's interaction history and provide the most appropriate information. This allows the service provider to provide optimal information by referring to the customer's past interaction history. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can provide customer interaction history data as input to the AI, which can then provide optimal information based on this data.

[0108] The service provider can prioritize information based on the customer's current situation at the time of delivery. For example, if the customer is in a hurry, the service provider can respond quickly and prioritize providing the most important information. Furthermore, if the customer has a specific problem, the service provider can prioritize providing information related to that problem. Additionally, if the customer desires multiple services, the service provider can prioritize providing information related to the most important service. This enables efficient information delivery by prioritizing information based on the customer's current situation. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can provide customer situation data as input to the AI, which can then prioritize information based on this data.

[0109] The information delivery unit can estimate the customer's emotions and adjust the order in which information is delivered based on the estimated emotions. For example, if the customer is feeling anxious, the information delivery unit can prioritize providing reassuring information. If the customer is relaxed, the information delivery unit can also provide detailed information in order. Furthermore, if the customer is in a hurry, the information delivery unit can prioritize providing information that is needed quickly. By adjusting the order in which information is delivered according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the information delivery unit may be performed using AI, for example, or not using AI. For example, the information delivery unit can provide customer facial expression data as input to the generative AI, and the generative AI can estimate the customer's emotions based on this data.

[0110] The service provider can provide optimal information by considering the customer's geographical location at the time of delivery. For example, if a customer visits from a distant location, the service provider can prioritize providing information relevant to that area. Furthermore, if a customer visits from a nearby location, the service provider can provide information relevant to nearby services. In addition, if a customer visits from a specific region, the service provider can provide information relevant to that region. This enables the provision of optimal information by considering the customer's geographical location. Some or all of the above processing in the service provider may be performed using AI, or without AI. For example, the service provider can provide the AI ​​with the customer's geographical location as input, and the AI ​​can provide optimal information based on this information.

[0111] The service provider can analyze the customer's social media activity and provide relevant information at the time of delivery. For example, if the customer mentions a particular service on social media, the service provider can provide information related to that service. Furthermore, if the customer expresses dissatisfaction on social media, the service provider can provide information related to that issue. Additionally, if the customer shows interest in a particular campaign on social media, the service provider can provide information related to that campaign. This allows the service provider to provide relevant information by analyzing the customer's social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can provide customer social media data as input to an AI, which can then use this data to provide relevant information.

[0112] The basic information gathering unit can estimate the customer's emotions and adjust the method of collecting basic information based on the estimated emotions. For example, if the customer is nervous, the basic information gathering unit can respond in a calm voice and ask simple questions. If the customer is relaxed, the basic information gathering unit can respond in a friendly tone and ask detailed questions. Furthermore, if the customer is in a hurry, the basic information gathering unit can respond quickly and ask only the necessary questions. By adjusting the method of collecting basic information according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the basic information gathering unit may be performed using AI or not using AI. For example, the basic information gathering unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0113] The basic information collection unit can select the optimal collection method by referring to the customer's past basic information when collecting basic information. For example, the basic information collection unit can prioritize the collection of relevant information based on the basic information the customer has provided in the past. The basic information collection unit can also collect information related to the customer's current needs from the customer's basic information history. Furthermore, the basic information collection unit can analyze the customer's basic information history and select the most appropriate collection method. This allows the optimal collection method to be selected by referring to the customer's past basic information. Some or all of the above processing in the basic information collection unit may be performed using AI, for example, or not using AI. For example, the basic information collection unit can provide the AI ​​with the customer's basic information history data as input, and the AI ​​can select the optimal collection method based on this data.

[0114] The basic information collection unit can estimate the customer's emotions and adjust the order in which basic information is collected based on the estimated emotions. For example, if the customer is feeling anxious, the basic information collection unit can prioritize collecting information that provides reassurance. If the customer is relaxed, the basic information collection unit can also collect detailed information in order. Furthermore, if the customer is in a hurry, the basic information collection unit can prioritize collecting information that is needed quickly. By adjusting the order in which basic information is collected according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the basic information collection unit may be performed using AI or not using AI. For example, the basic information collection unit can provide customer facial expression data as input to the generative AI, and the generative AI can estimate the customer's emotions based on this data.

[0115] The basic information collection unit can select the optimal collection method when collecting basic information, taking into account the customer's geographical location. For example, if a customer visits from a distant location, the basic information collection unit can prioritize collecting information related to that region. Furthermore, if a customer visits from a nearby location, the basic information collection unit can also collect information related to nearby services. In addition, if a customer visits from a specific region, the basic information collection unit can collect information related to that region. This allows for the optimal collection method by considering the customer's geographical location. Some or all of the above processing in the basic information collection unit may be performed using AI, for example, or without AI. For example, the basic information collection unit can provide the AI ​​with the customer's geographical location as input, and the AI ​​can select the optimal collection method based on this information.

[0116] The contract information acquisition unit can estimate the customer's emotions and adjust the method of acquiring contract information based on the estimated emotions. For example, if the customer is nervous, the contract information acquisition unit can respond in a calm voice and ask simple questions. If the customer is relaxed, the contract information acquisition unit can respond in a friendly tone and ask detailed questions. Furthermore, if the customer is in a hurry, the contract information acquisition unit can respond quickly and ask only the minimum necessary questions. By adjusting the method of acquiring contract information according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the contract information acquisition unit may be performed using AI or not using AI. For example, the contract information acquisition unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0117] The contract information acquisition unit can select the optimal acquisition method by referring to the customer's past contract history when acquiring contract information. For example, the contract information acquisition unit can prioritize the acquisition of relevant information based on contract information the customer has used in the past. The contract information acquisition unit can also acquire information related to the customer's current needs from the customer's contract history. Furthermore, the contract information acquisition unit can analyze the customer's contract history and select the most appropriate acquisition method. This allows the optimal acquisition method to be selected by referring to the customer's past contract history. Some or all of the above processing in the contract information acquisition unit may be performed using AI, for example, or without AI. For example, the contract information acquisition unit can provide customer contract history data as input to the AI, and the AI ​​can select the optimal acquisition method based on this data.

[0118] The contract information acquisition unit can estimate the customer's emotions and adjust the order in which contract information is acquired based on the estimated emotions. For example, if the customer is feeling anxious, the contract information acquisition unit can prioritize acquiring information that provides reassurance. If the customer is relaxed, the contract information acquisition unit can also acquire detailed information in order. Furthermore, if the customer is in a hurry, the contract information acquisition unit can prioritize acquiring information that is needed quickly. By adjusting the order in which contract information is acquired according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the contract information acquisition unit may be performed using AI, or not using AI. For example, the contract information acquisition unit can provide customer facial expression data as input to the generative AI, and the generative AI can estimate the customer's emotions based on this data.

[0119] The contract information acquisition unit can select the optimal acquisition method when acquiring contract information, taking into account the customer's geographical location. For example, if a customer visits from a distant location, the contract information acquisition unit can prioritize acquiring information related to that region. Furthermore, if a customer visits from a nearby location, the contract information acquisition unit can acquire information related to nearby services. In addition, if a customer visits from a specific region, the contract information acquisition unit can acquire information related to that region. This allows for the optimal acquisition method by considering the customer's geographical location. Some or all of the above processing in the contract information acquisition unit may be performed using AI, for example, or without AI. For example, the contract information acquisition unit can provide the customer's geographical location information as input to the AI, which can then select the optimal acquisition method based on this information.

[0120] The proposal department can estimate the customer's emotions and adjust its approach to proposals based on those emotions. For example, if the customer is nervous, the proposal department can respond in a calm voice and make simple proposals. If the customer is relaxed, the proposal department can respond in a friendly tone and make detailed proposals. Furthermore, if the customer is in a hurry, the proposal department can respond quickly and make concise proposals. By adjusting the approach to proposals according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the proposal department may be performed using AI or not. For example, the proposal department can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0121] The proposal department can make optimal proposals by referring to the customer's past preference history when making a proposal. For example, the proposal department can make relevant proposals based on services the customer has requested in the past. It can also make proposals related to the customer's current needs based on the customer's preference history. Furthermore, the proposal department can analyze the customer's preference history and make the most appropriate proposal. In this way, it can make optimal proposals by referring to the customer's past preference history. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can provide customer preference history data as input to the AI, and the AI ​​can make optimal proposals based on this data.

[0122] The suggestion unit can estimate the customer's emotions and adjust the order of suggestions based on those emotions. For example, if the customer is feeling anxious, the suggestion unit can prioritize suggestions that provide reassurance. If the customer is relaxed, the suggestion unit can also provide detailed suggestions in sequence. Furthermore, if the customer is in a hurry, the suggestion unit can prioritize suggestions that are needed quickly. By adjusting the order of suggestions according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0123] The proposal department can make optimal suggestions by considering the customer's geographical location. For example, if a customer visits from a distant location, the proposal department can prioritize suggestions related to that area. If a customer visits from nearby, the proposal department can also make suggestions related to nearby services. Furthermore, if a customer visits from a specific region, the proposal department can make suggestions related to that region. This makes it possible to make optimal suggestions by considering the customer's geographical location. Some or all of the above processing in the proposal department may be performed using AI, for example, or not. For example, the proposal department can provide the AI ​​with the customer's geographical location as input, and the AI ​​can make optimal suggestions based on this information.

[0124] The information organization unit can estimate the customer's emotions and adjust the information organization method based on the estimated emotions. For example, if the customer is nervous, the information organization unit can respond in a calm voice and use a simple organization method. If the customer is relaxed, the information organization unit can respond in a friendly tone and use a detailed organization method. Furthermore, if the customer is in a hurry, the information organization unit can respond quickly and use a concise organization method. By adjusting the information organization method according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the information organization unit may be performed using AI or not using AI. For example, the information organization unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0125] The information organization unit can select the optimal organization method by referring to the customer's past information when organizing information. For example, the information organization unit can prioritize organizing relevant information based on information the customer has provided in the past. The information organization unit can also organize information related to the customer's current needs from the customer's information history. Furthermore, the information organization unit can analyze the customer's information history and select the most appropriate organization method. This allows the optimal organization method to be selected by referring to the customer's past information. Some or all of the above processes in the information organization unit may be performed using AI, for example, or not using AI. For example, the information organization unit can provide customer information history data as input to the AI, and the AI ​​can select the optimal organization method based on this data.

[0126] The information organization unit can estimate the customer's emotions and adjust the order in which information is organized based on the estimated emotions. For example, if the customer is feeling anxious, the information organization unit can prioritize organizing information that provides a sense of security. If the customer is relaxed, the information organization unit can also organize detailed information in order. Furthermore, if the customer is in a hurry, the information organization unit can prioritize organizing information that is needed quickly. By adjusting the order in which information is organized according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the information organization unit may be performed using AI, or not using AI. For example, the information organization unit can provide customer facial expression data as input to the generative AI, and the generative AI can estimate the customer's emotions based on this data.

[0127] The information organization unit can select the optimal organization method when organizing information, taking into account the customer's geographical location. For example, if a customer visits from a distant location, the information organization unit can prioritize organizing information related to that region. Furthermore, if a customer visits from a nearby location, the information organization unit can organize information related to nearby services. In addition, if a customer visits from a specific region, the information organization unit can organize information related to that region. This allows for the optimal organization method by considering the customer's geographical location. Some or all of the above processing in the information organization unit may be performed using AI, for example, or without AI. For example, the information organization unit can provide the AI ​​with the customer's geographical location as input, and the AI ​​can select the optimal organization method based on this information.

[0128] The waiting time reduction unit can estimate the customer's emotions and adjust the waiting time reduction method based on the estimated emotions. For example, if the customer is nervous, the waiting time reduction unit can respond in a calm voice and reduce the waiting time with a simple procedure. If the customer is relaxed, the waiting time reduction unit can respond in a friendly tone and reduce the waiting time with a detailed procedure. Furthermore, if the customer is in a hurry, the waiting time reduction unit can respond quickly and reduce the waiting time with a concise procedure. By adjusting the waiting time reduction method according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the waiting time reduction unit may be performed using AI or not using AI. For example, the waiting time reduction unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0129] The waiting time reduction unit can select the optimal reduction method by referring to the customer's past waiting time history when reducing waiting times. For example, if a customer has been made to wait for a long time in the past, the waiting time reduction unit can select a method to reduce waiting time based on that history. The waiting time reduction unit can also select a reduction method related to the customer's current needs from the customer's waiting time history. Furthermore, the waiting time reduction unit can analyze the customer's waiting time history and select the most appropriate reduction method. In this way, the optimal reduction method can be selected by referring to the customer's past waiting time history. Some or all of the above processing in the waiting time reduction unit may be performed using AI, for example, or without using AI. For example, the waiting time reduction unit can provide customer waiting time history data as input to the AI, and the AI ​​can select the optimal reduction method based on this data.

[0130] The waiting time reduction unit can estimate the customer's emotions and adjust the order in which waiting times are reduced based on the estimated emotions. For example, if the customer is feeling anxious, the waiting time reduction unit can prioritize procedures that provide reassurance. If the customer is relaxed, the waiting time reduction unit can also proceed with detailed procedures in order. Furthermore, if the customer is in a hurry, the waiting time reduction unit can prioritize procedures that are needed quickly. By adjusting the order in which waiting times are reduced according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the waiting time reduction unit may be performed using AI, for example, or not using AI. For example, the waiting time reduction unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0131] The waiting time reduction unit can select the optimal method of reducing waiting times by considering the customer's geographical location information. For example, if a customer comes from a distant location, the unit can prioritize procedures related to that area. Similarly, if a customer comes from a nearby location, the unit can prioritize procedures related to that area. Furthermore, if a customer comes from a specific region, the unit can prioritize procedures related to that region. This allows for the optimal reduction method by considering the customer's geographical location information. Some or all of the above-described processes in the waiting time reduction unit may be performed using AI, for example, or without AI. For instance, the waiting time reduction unit can provide the AI ​​with the customer's geographical location information as input, and the AI ​​can select the optimal reduction method based on this information.

[0132] The staffing shortage resolution unit can estimate customer emotions and adjust the method of resolving staffing shortages based on the estimated customer emotions. For example, if a customer is nervous, the staffing shortage resolution unit can respond in a calm voice and resolve the staffing shortage with a simple procedure. If a customer is relaxed, the staffing shortage resolution unit can respond in a friendly tone and resolve the staffing shortage with a detailed procedure. Furthermore, if a customer is in a hurry, the staffing shortage resolution unit can respond quickly and resolve the staffing shortage with a concise procedure. By adjusting the method of resolving staffing shortages according to customer emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the staffing shortage resolution unit may be performed using AI, for example, or without AI. For example, the labor shortage resolution unit provides customer facial expression data as input to a generating AI, which can then estimate the customer's emotions based on this data.

[0133] The Labor Shortage Resolution Unit can select the optimal solution when resolving a labor shortage by referring to the customer's past interaction history. For example, if a customer has been kept waiting for a long time in the past, the Labor Shortage Resolution Unit can select a solution based on that history. The Labor Shortage Resolution Unit can also select a solution related to the current needs from the customer's interaction history. Furthermore, the Labor Shortage Resolution Unit can analyze the customer's interaction history and select the most appropriate solution. In this way, the optimal solution can be selected by referring to the customer's past interaction history. Some or all of the above processes in the Labor Shortage Resolution Unit may be performed using AI, for example, or not using AI. For example, the Labor Shortage Resolution Unit can provide customer interaction history data as input to the AI, and the AI ​​can select the optimal solution based on this data.

[0134] The labor shortage resolution unit can estimate customer emotions and adjust the order of resolving labor shortages based on the estimated customer emotions. For example, if a customer is feeling anxious, the labor shortage resolution unit can prioritize procedures that provide reassurance. If a customer is relaxed, the labor shortage resolution unit can also proceed with detailed procedures in order. Furthermore, if a customer is in a hurry, the labor shortage resolution unit can prioritize procedures that are needed quickly. By adjusting the order of resolving labor shortages according to customer emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the labor shortage resolution unit may be performed using AI, for example, or not using AI. For example, the labor shortage resolution unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0135] The Labor Shortage Resolution Department can select the optimal solution when addressing labor shortages, taking into account the customer's geographical location. For example, if a customer visits from a distant location, the Labor Shortage Resolution Department can prioritize procedures related to that region. Furthermore, if a customer visits from a nearby location, the Labor Shortage Resolution Department can prioritize procedures related to that region. This allows for the selection of the optimal solution by considering the customer's geographical location. Some or all of the above-described processes in the Labor Shortage Resolution Department may be performed using AI, or not. For example, the Labor Shortage Resolution Department can provide the AI ​​with the customer's geographical location as input, and the AI ​​can select the optimal solution based on this information.

[0136] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0137] The reception robot system can make optimal suggestions by referring to the customer's past purchase history when receiving customer requests. For example, it can suggest new smartphones and plans that meet the customer's current needs based on the smartphone models and plans the customer has purchased in the past. It can also suggest related services based on the customer's past service usage history. Furthermore, it can analyze the customer's past purchase history to make the most appropriate suggestions. In this way, it can make optimal suggestions by referring to the customer's past purchase history. Some or all of the above processing at the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can provide customer purchase history data as input to the AI, which can then make optimal suggestions based on this data.

[0138] The reception robot system can adjust its response to customer requests based on the customer's current health condition. For example, if a customer is feeling unwell, it can respond quickly and ask only the necessary questions. If the customer is healthy, it can ask more detailed questions to understand their specific needs. Furthermore, it can analyze the customer's health condition and select the most appropriate response. By adjusting the response based on the customer's health condition, customer satisfaction can be improved. Some or all of the above processes at the reception desk may be performed using AI, for example, or not. For example, the reception desk can provide customer health data as input to the AI, which can then select the most appropriate response based on this data.

[0139] The reception robot system can adjust its response method when receiving customer requests by referring to the customer's past feedback. For example, it can provide a response that matches the customer's preferences based on feedback the customer has provided in the past. Also, if the customer has expressed dissatisfaction in the past, it can prioritize taking action to resolve that dissatisfaction. Furthermore, it can analyze customer feedback and select the optimal response method. This allows the system to select the optimal response method by referring to the customer's past feedback. Some or all of the above processes in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can provide customer feedback data as input to the AI, and the AI ​​can select the optimal response method based on this data.

[0140] The reception robot system can adjust its response method when receiving customer requests, taking into account the customer's current weather information. For example, if a customer visits on a rainy day, it can respond quickly and reduce waiting times. If a customer visits on a sunny day, it can ask more detailed questions to understand their specific needs. Furthermore, it can analyze the customer's weather information and select the most appropriate response method. By adjusting the response method according to the customer's weather information, customer satisfaction can be improved. Some or all of the above processes at the reception desk may be performed using AI, for example, or not. For example, the reception desk can provide customer weather information data as input to the AI, which can then select the most appropriate response method based on this data.

[0141] The reception robot system can adjust its response to customer requests by considering the customer's current traffic situation. For example, if a customer arrives late due to traffic congestion, the system can respond quickly and reduce waiting time. If a customer arrives smoothly, the system can ask detailed questions to understand their specific needs. Furthermore, it can analyze the customer's traffic situation and select the most appropriate response. By adjusting the response based on the customer's traffic situation, customer satisfaction can be improved. Some or all of the above processes at the reception desk may be performed using AI, for example, or not. For example, the reception desk can provide customer traffic data as input to the AI, which can then select the most appropriate response based on this data.

[0142] The reception robot system can estimate a customer's emotions and adjust its reception approach based on those emotions. For example, if a customer is stressed, it can respond in a calm voice and ask simple questions. If a customer is relaxed, it can respond in a friendly tone and ask more detailed questions. Furthermore, if a customer is in a hurry, it can respond quickly and ask only the essential questions. By adjusting the reception approach according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception area may be performed using AI or not. For example, the reception area can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0143] The reception robot system can estimate a customer's emotions and adjust the order of service based on those emotions. For example, if a customer is feeling anxious, it can prioritize serving them and provide reassurance. If a customer is relaxed, it can prioritize serving other customers who are in a hurry. Furthermore, if a customer is angry, it can respond quickly and prioritize problem resolution. By adjusting the order of service according to the customer's emotions, customer satisfaction can be improved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception area may be performed using AI or not. For example, the reception area can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0144] The reception robot system can estimate the customer's emotions and adjust its interviewing method based on the estimated emotions. For example, if the customer is nervous, it can respond in a calm voice and ask simple questions. If the customer is relaxed, it can respond in a friendly tone and ask detailed questions. Furthermore, if the customer is in a hurry, it can respond quickly and ask only the necessary questions. By adjusting the interviewing method according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the interviewing unit may be performed using AI or not using AI. For example, the interviewing unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0145] The reception robot system can estimate the customer's emotions and adjust the content of the interview based on the estimated emotions. For example, if the customer is feeling anxious, it can ask questions that provide reassurance. If the customer is relaxed, it can ask questions that elicit detailed information. Furthermore, if the customer is in a hurry, it can ask questions that quickly gather necessary information. By adjusting the content of the interview according to the customer's emotions, customer satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the interview unit may be performed using AI, or not using AI. For example, the interview unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0146] The reception robot system can estimate the customer's emotions and adjust the preferred interview method based on the estimated emotions. For example, if the customer is nervous, it can respond in a calm voice and ask simple questions. If the customer is relaxed, it can respond in a friendly tone and ask detailed questions. Furthermore, if the customer is in a hurry, it can respond quickly and ask only the necessary questions. This improves customer satisfaction by adjusting the preferred interview method according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the preference interview unit may be performed using AI or not. For example, the preference interview unit can provide customer facial expression data as input to the generative AI, which can estimate the customer's emotions based on this data.

[0147] The following briefly describes the processing flow for example form 2.

[0148] Step 1: The reception desk receives customer requests. For example, it can receive requests from customers who want to purchase a new smartphone, change their contract details, or cancel a service. Step 2: The interviewing department interviews customers to gather registration information based on the information received by the reception department. For example, they can confirm basic information such as the customer's contract details, usage status, name, address, contact information, and past usage history. Step 3: The Customer Feedback Department conducts a customer feedback session based on the information gathered by the Customer Feedback Department. For example, they can gather detailed requests such as the desired smartphone model and plan, service content and conditions, contract changes, and reasons for cancellation. Step 4: The service department provides the information collected by the needs assessment department to human staff. For example, the collected information can be organized so that staff can respond quickly. It can also provide information to reduce customer waiting times or information to address labor shortages by having robots handle customer service.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] Each of the multiple elements described above, including the reception unit, hearing unit, preference hearing unit, and provision unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives customer requests. The hearing unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and hears the customer's registration information. The preference hearing unit is implemented by, for example, the control unit 46A of the smart device 14 and hears the customer's preferences. The provision unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides the collected information to the staff. 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.

[0153] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] Each of the multiple elements described above, including the reception unit, hearing unit, preference hearing unit, and provision unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives customer requests. The hearing unit is implemented by the specific processing unit 290 of the data processing unit 12 and hears the customer's registration information. The preference hearing unit is implemented by the control unit 46A of the smart glasses 214 and hears the customer's preferences. The provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides the collected information to the staff. 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.

[0169] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.).

[0181] 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.

[0182] 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.

[0183] 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.

[0184] Each of the multiple elements described above, including the reception unit, hearing unit, preference hearing unit, and provision unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives customer requests. The hearing unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and hears the customer's registration information. The preference hearing unit is implemented by, for example, the control unit 46A of the headset terminal 314 and hears the customer's preferences. The provision unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides the collected information to the staff. 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.

[0185] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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).

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.).

[0198] 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.

[0199] 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.

[0200] 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.

[0201] Each of the multiple elements described above, including the reception unit, hearing unit, preference hearing unit, and provision unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives customer requests. The hearing unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and hears the customer's registration information. The preference hearing unit is implemented by, for example, the control unit 46A of the robot 414 and hears the customer's preferences. The provision unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides the collected information to the staff. 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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."

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] (Note 1) A reception desk that handles customer requests, Based on the information received by the aforementioned reception department, the interviewing department interviews customers to gather their registration information. A desire-gathering unit that gathers customer preferences based on the information gathered by the aforementioned hearing unit, The system includes a provisioning unit that provides information collected by the aforementioned preference hearing unit to human staff. A system characterized by the following features. (Note 2) The aforementioned reception unit is It includes a basic information collection unit that collects basic customer information. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned hearing section is, It is equipped with a contract information acquisition unit that automatically retrieves customer contract details and usage status. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned preference hearing section is, We have a proposal department that provides optimal solutions based on customer needs. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, The facility includes an information organization department to organize collected information and enable staff to respond quickly. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned supply unit is, It is equipped with a waiting time reduction unit to shorten customer waiting times. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned supply unit is, The company has a department dedicated to addressing labor shortages by having robots handle customer service. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is The system estimates the customer's emotions and adjusts the receptionist's response based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is At the time of reception, the system will refer to the customer's past visit history to select the most appropriate course of action. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is At the time of reception, we determine the priority of our response based on the customer's current situation and needs. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is The system estimates customer emotions and adjusts the order of service based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is At the time of registration, we will take into account the customer's geographical location to provide the most appropriate service. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is During registration, we analyze the customer's social media activity and obtain relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned hearing section is, We estimate the customer's emotions and adjust the interview method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned hearing section is, During the interview, we select the most appropriate questions by referring to the customer's past contract history. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned hearing section is, During the interview, adjust the order of questions based on the customer's current usage. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned hearing section is, We estimate the customer's emotions and adjust the content of the interview based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned hearing section is, When conducting interviews, we ask the most appropriate questions, taking into account the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned hearing section is, During the interview, we analyze the customer's social media activity and obtain relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned preference hearing section is, We estimate the customer's emotions and adjust the preferred interview method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned preference hearing section is, During the initial consultation to understand the customer's needs, we select the most appropriate questions by referring to their past request history. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned preference hearing section is, During the initial consultation to understand the customer's needs, we adjust the order of the questions based on their current requirements. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned preference hearing section is, We estimate the customer's emotions and adjust the desired interview content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned preference hearing section is, When conducting a consultation to understand the customer's needs, we will ask the most appropriate questions, taking into account their geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned preference hearing section is, During the initial consultation to understand the customer's needs, we analyze their social media activity and gather relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, We estimate customer emotions and adjust how information is delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing information, we refer to the customer's past interaction history to provide the most relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, When providing information, we prioritize it based on the customer's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, The system estimates customer emotions and adjusts the order in which information is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When providing information, we will consider the customer's geographical location to provide the most relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned supply unit is, When providing the service, we analyze the customer's social media activity and provide relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned basic information collection unit is: We estimate customer emotions and adjust how we collect basic information based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned basic information collection unit is: When collecting basic information, the optimal collection method is selected by referring to the customer's past basic information. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned basic information collection unit is: We estimate customer emotions and adjust the order in which basic information is collected based on the estimated customer emotions. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned basic information collection unit is: When collecting basic information, the optimal collection method is selected considering the customer's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned contract information acquisition unit, We estimate customer sentiment and adjust how contract information is acquired based on that estimated sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned contract information acquisition unit, When acquiring contract information, the system selects the most suitable acquisition method by referring to the customer's past contract history. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned contract information acquisition unit, The system estimates customer sentiment and adjusts the order in which contract information is retrieved based on the estimated sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned contract information acquisition unit, When acquiring contract information, the optimal acquisition method is selected considering the customer's geographical location. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned proposal section is, We estimate the customer's emotions and adjust the approach to making suggestions based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned proposal section is, When making a proposal, refer to the customer's past wish history to make an optimal proposal The system according to appended note 4, characterized by this (Appended note 42) The proposal department Estimate the customer's sentiment and adjust the order of proposals based on the estimated customer sentiment The system according to appended note 4, characterized by this (Appended note 43) The proposal department When making a proposal, consider the customer's geographical location information to make an optimal proposal The system according to appended note 4, characterized by this (Appended note 44) The information sorting department Estimate the customer's sentiment and adjust the information sorting method based on the estimated customer sentiment The system according to appended note 5, characterized by this (Appended note 45) The information sorting department When sorting information, refer to the customer's past information to select an optimal sorting method The system according to appended note 5, characterized by this (Appended note 46) The information sorting department Estimate the customer's sentiment and adjust the information sorting order based on the estimated customer sentiment The system according to appended note 5, characterized by this (Appended note 47) The information sorting department When sorting information, consider the customer's geographical location information to select an optimal sorting method The system according to appended note 5, characterized by this (Appended note 48) The waiting time shortening department Estimate the customer's sentiment and adjust the waiting time shortening method based on the estimated customer sentiment The system according to appended note 6, characterized by this (Appended note 49) The waiting time shortening department When shortening the waiting time, refer to the customer's past waiting time history to select an optimal shortening method The system described in Appendix 6, characterized by the features described herein. (Note 50) The aforementioned waiting time reduction unit is, The system estimates customer emotions and adjusts the order of waiting time reductions based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 51) The aforementioned waiting time reduction unit is, When reducing waiting times, the optimal method of reduction is selected by considering the customer's geographical location. The system described in Appendix 6, characterized by the features described herein. (Note 52) The aforementioned department for resolving labor shortages, We estimate customer emotions and adjust methods to address labor shortages based on those estimated emotions. The system described in Appendix 7, characterized by the features described herein. (Note 53) The aforementioned department for resolving labor shortages, When addressing labor shortages, the optimal solution is selected by referring to the customer's past interaction history. The system described in Appendix 7, characterized by the features described herein. (Note 54) The aforementioned department for resolving labor shortages, The system estimates customer emotions and adjusts the order in which to address labor shortages based on those estimated emotions. The system described in Appendix 7, characterized by the features described herein. (Note 55) The aforementioned department for resolving labor shortages, When addressing labor shortages, the optimal solution is selected by considering the customer's geographical location. The system described in Appendix 7, characterized by the features described herein. [Explanation of symbols]

[0221] 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. A reception desk that handles customer requests, Based on the information received by the aforementioned reception department, the interviewing department interviews customers to gather their registration information. A desire-gathering unit that gathers customer preferences based on the information gathered by the aforementioned hearing unit, The system includes a provisioning unit that provides information collected by the aforementioned preference hearing unit to human staff. A system characterized by the following features.

2. The aforementioned reception unit is It includes a basic information collection unit that collects basic customer information. The system according to feature 1.

3. The aforementioned hearing section is, It is equipped with a contract information acquisition unit that automatically retrieves customer contract details and usage status. The system according to feature 1.

4. The aforementioned preference hearing section is, We have a proposal department that provides optimal solutions based on customer needs. The system according to feature 1.

5. The aforementioned supply unit is, The facility includes an information organization department to organize collected information and enable staff to respond quickly. The system according to feature 1.

6. The aforementioned supply unit is, It is equipped with a waiting time reduction unit to shorten customer waiting times. The system according to feature 1.

7. The aforementioned supply unit is, The company has a department dedicated to addressing labor shortages by having robots handle customer service. The system according to feature 1.

8. The aforementioned reception unit is The system estimates the customer's emotions and adjusts the receptionist's response based on those estimated emotions. The system according to feature 1.

9. The aforementioned reception unit is At the time of reception, the system will refer to the customer's past visit history to select the most appropriate course of action. The system according to feature 1.

Images