System

Abstract

To reduce cost corresponding to shop counter correspondence while maintaining customer satisfaction in a system related to an embodiment.SOLUTION: According to an embodiment, a system includes an authentication part, a correspondence part, and a management part. The authentication part authenticates a customer. The correspondence part uses customer information authenticated by the authentication part to perform correspondence. The management part manages correspondence to be performed by the correspondence part.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] Conventional technology has the problem that the cost of handling inquiries at shop counters is high, making it difficult to reduce costs while maintaining customer satisfaction.

[0005] The system according to the embodiment aims to reduce the cost of handling inquiries at shop counters while maintaining customer satisfaction. [Means for solving the problem]

[0006] The system according to the embodiment includes an authentication unit, a response unit, and a management unit. The authentication unit authenticates a customer. The response unit performs a response by utilizing customer information authenticated by the authentication unit. The management unit manages the response performed by the response unit. Effect of the Invention

[0007] The system according to the embodiment can reduce the cost of handling inquiries at a shop counter while maintaining customer satisfaction. [Brief description of the drawings]

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

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The system according to the embodiment of the present invention is a system that maintains customer satisfaction while reducing the cost of shop counter response by utilizing generation AI. In this system, the response by a shop clerk is 1,000 yen per time, and the response by the AI ​​self-booth is free. As a result, customers can use the AI ​​self-booth for free, and costs can be reduced. In the AI ​​self-booth, customer authentication is performed and response is performed using customer information. For example, when a customer enters the booth, the customer is identified by face recognition, fingerprint recognition, voice recognition, two-dimensional code (e.g., QR code (registered trademark)) recognition, etc., and the optimal response is performed based on the customer's past usage history, contract information, preferences, and behavior patterns. As a result, customers can receive prompt and accurate service, and satisfaction is improved. In addition, the AI ​​self-booth can operate 24 hours a day, and customers can use it at any time. As a result, it is possible to respond even outside the store's business hours, improving customer convenience. Furthermore, the AI ​​self-booth can analyze the content of inquiries from customers and provide appropriate answers. For example, the AI ​​automatically responds to general inquiries such as changes to fee plans, confirmation of contract details, troubleshooting, and proposals for new services. This reduces the burden on store clerks and cuts call center costs. In this way, by installing an AI self-service booth that utilizes generative AI, it is possible to reduce the cost of handling store counters while maintaining customer satisfaction. This allows the system to maintain customer satisfaction while reducing the cost of handling store counters.

[0029] The system according to the embodiment includes an authentication unit, a response unit, and a management unit. The authentication unit authenticates a customer. The authentication unit can authenticate a customer using, for example, face authentication, fingerprint authentication, voice authentication, two-dimensional code authentication, or other methods. For example, the authentication unit can recognize the face of a customer using face authentication technology to identify the customer. The authentication unit can also recognize the fingerprint of a customer using fingerprint authentication technology to identify the customer. Furthermore, the authentication unit can recognize the voice of a customer using voice authentication technology to identify the customer. The two-dimensional code authentication technology can also be used to scan a two-dimensional code presented by a customer and identify the customer. The response unit uses the customer information authenticated by the authentication unit to respond. The response unit can respond, for example, by changing a fee plan, checking the contract details, troubleshooting, proposing a new service, and the like. For example, the response unit can carry out a procedure to change a customer's fee plan. The response unit can also check the contract details of a customer and provide necessary information. Furthermore, the response unit can respond to troubleshooting inquiries from customers and solve problems. It can also propose new services and provide optimal services to customers. The management unit manages the responses performed by the response unit. The management unit can, for example, manage the 24-hour operation of the AI ​​self-service booth. The management unit can monitor the operation status of the AI ​​self-service booth and perform maintenance as necessary. This allows the system to efficiently perform customer authentication, response, and management.

[0030] The authentication unit authenticates the customer. The authentication unit can authenticate the customer using methods such as face recognition, fingerprint recognition, voice recognition, and two-dimensional code recognition. Specifically, face recognition technology identifies the customer by taking a picture of the customer's face using a camera and comparing it with pre-registered face data. The face recognition algorithm extracts facial features and compares them with existing data in a database. Fingerprint authentication technology reads the customer's fingerprint using a fingerprint scanner and compares it with registered fingerprint data. High accuracy of authentication is possible by analyzing the fine details of the fingerprint. Voice authentication technology records the customer's voice and analyzes the voice waveform and voiceprint for authentication. Voice authentication is particularly effective in situations where a telephone or voice assistant is used. Two-dimensional code authentication technology scans a two-dimensional code presented by the customer and identifies the customer based on that information. The two-dimensional code contains the customer's ID and authentication information, and authentication is completed quickly by simply scanning it. These authentication methods can be used alone or multiple methods can be combined to perform multi-factor authentication. Using multi-factor authentication can further strengthen security. For example, by combining face recognition and fingerprint recognition, higher reliability can be ensured. The authentication unit can use these technologies to quickly and accurately authenticate customers and improve the security of the entire system.

[0031] The response section responds by utilizing the customer information authenticated by the authentication section. The response section can respond by, for example, changing the fee plan, confirming the contract details, troubleshooting, proposing new services, etc. Specifically, in the procedure for changing the fee plan, the system analyzes the customer's current plan and usage status and proposes the optimal plan. Based on the customer's past usage data, the system automatically calculates the most cost-effective plan and presents it to the customer. In the confirmation of the contract details, the system quickly searches the customer's contract information and provides the necessary information. For example, the expiration date of the contract and details of available services can be displayed immediately. In the troubleshooting, the system identifies the cause of the problem and provides a solution in response to an inquiry from a customer. The system refers to past trouble data and an FAQ database and presents the optimal solution. In the proposal of a new service, the system analyzes the customer's usage history and preferences and proposes the optimal service. For example, if a customer frequently uses a particular service, it can propose new options or upgrades related to that service. Through these functions, the response section can respond quickly and accurately to customers and improve customer satisfaction. In addition, the response section can collect feedback from customers and use it to improve the service. This enables the department to respond flexibly to customer needs, improving the efficiency and effectiveness of the entire system.

[0032] The management department manages the response performed by the response department. For example, the management department can manage the 24-hour operation of the AI ​​self-service booth. Specifically, it monitors the operation status of the AI ​​self-service booth in real time and responds immediately if an abnormality occurs. The management department is equipped with a dashboard for monitoring the operation status, and the operation status and usage status of each booth can be grasped at a glance. If an abnormality is detected, the management department automatically issues an alert and notifies the maintenance team. When the maintenance team receives the alert, they rush to the site and solve the problem. The management department formulates a regular maintenance schedule to ensure long-term stable operation of the AI ​​self-service booth. In addition, the management department analyzes operation data and seeks efficient operation methods. For example, it analyzes the time periods when it is frequently used and the operation rate of a specific booth, and optimally allocates resources. This maximizes the operation efficiency of the AI ​​self-service booth and provides high-quality service to customers. The management department also collects feedback from customers and uses it to improve services. For example, if a customer is dissatisfied with the usability of a specific booth, the design and functions of the booth are improved based on that feedback. This enables the management department to improve the operational efficiency of the entire system and customer satisfaction.

[0033] The authentication unit may include face authentication, fingerprint authentication, voice authentication, and two-dimensional code authentication. The authentication unit may, for example, use face authentication technology to recognize the face of a customer and identify the customer. The face authentication technology may, for example, use a face recognition algorithm to analyze the features of the customer's face and compare them with face data in a database to perform authentication. The fingerprint authentication technology may, for example, use a fingerprint sensor to read the customer's fingerprint and compare them with fingerprint data in a database to perform authentication. The voice authentication technology may, for example, use a microphone to record the customer's voice and compare them with voice data in a database to perform authentication. The two-dimensional code authentication technology may, for example, use a two-dimensional code scanner to read a two-dimensional code presented by the customer and analyze the data of the two-dimensional code to perform authentication. As a result, the authentication unit provides a variety of authentication methods, thereby improving customer convenience. A part or all of the above-mentioned processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit may input a face recognition algorithm to the generation AI and cause the generation AI to execute face authentication processing.

[0034] The response unit can change the fee plan, check the contract details, troubleshoot, and propose new services. The response unit can, for example, carry out a procedure to change the fee plan of the customer. Changing the fee plan includes, for example, a procedure to change from the plan currently subscribed by the customer to another plan. The response unit can also check the contract details of the customer and provide necessary information. Checking the contract details includes, for example, a procedure to check the details and contract conditions of the service currently subscribed by the customer. The response unit can also respond to troubleshooting inquiries from customers and solve problems. Troubleshooting includes, for example, a procedure to solve technical problems faced by the customer and problems related to the use of the service. The response unit can also propose new services and provide optimal services to the customer. Proposing new services includes, for example, a procedure to propose new services suitable for the customer based on the customer's usage history and preferences. This allows the response unit to respond to the needs of the customer by performing various responses. Part or all of the above-mentioned processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit can input the customer's usage history into the generation AI and have the generation AI execute a proposal for an optimal service.

[0035] The management unit can manage the constant operation of the AI ​​self-booth. For example, the management unit can monitor the operation status of the AI ​​self-booth in real time and perform maintenance as necessary. The operation status of the AI ​​self-booth includes data such as operation time, operation rate, and frequency of use. The management unit can use a sensor or a monitoring system to monitor the operation status of the AI ​​self-booth. For example, the management unit can monitor the operation status in real time using a sensor installed in the AI ​​self-booth. The management unit can also adjust the maintenance schedule based on the operation status of the AI ​​self-booth. For example, the management unit can minimize the impact on customers by performing maintenance during a time period when the operation rate of the AI ​​self-booth is low. This allows the management unit to manage the 24-hour operation of the AI ​​self-booth, and customers can use the service at any time. Some or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input operation status data of the AI ​​self-booth to the generation AI and cause the generation AI to adjust the maintenance schedule.

[0036] The response unit can respond by analyzing the customer's preferences and behavioral patterns. The response unit can, for example, analyze the customer's past usage history and purchase history to identify the customer's preferences. The analysis of preferences is performed, for example, based on data on products purchased by the customer in the past and services used by the customer. The response unit can also analyze the customer's behavioral patterns to identify the customer's usage frequency and visiting time period. The analysis of behavioral patterns is performed, for example, based on data such as the frequency and time period when the customer visits the shop, and the type of service used. This allows the response unit to respond optimally based on the customer's preferences and behavioral patterns. For example, the response unit can preferentially suggest services that the customer has used in the past. In addition, the response unit can provide services at optimal times based on the customer's behavioral patterns. Furthermore, the response unit can suggest new services based on the customer's preferences and behavioral patterns. This allows the response unit to respond according to the individual needs of the customer. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can input customer preference data into the generation AI and have the generation AI execute optimal service suggestions.

[0037] The authentication unit can analyze the past authentication history of the customer and propose an appropriate authentication method. The authentication unit can, for example, analyze the past authentication history of the customer and propose an optimal authentication method. The past authentication history includes, for example, authentication methods used by the customer in the past and authentication success / failure history. The authentication unit can preferentially propose the authentication method used most frequently by the customer based on the past authentication history. For example, if the customer has frequently used face authentication in the past, the authentication unit can preferentially propose face authentication. The authentication unit can also predict and propose an authentication method to be used in a specific time period from the past authentication history. For example, if the customer has used fingerprint authentication in a specific time period, the authentication unit can propose fingerprint authentication for that time period. Furthermore, the authentication unit can analyze the past authentication history and propose the most efficient authentication method. As a result, the authentication unit provides the optimal authentication method based on the past authentication history, thereby improving authentication efficiency. Part or all of the above-mentioned processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can input past authentication history data to the generation AI and cause the generation AI to execute a proposal of an optimal authentication method.

[0038] The authentication unit can customize the authentication means based on the customer's current situation and environment at the time of authentication. For example, when the customer is in a noisy environment, the authentication unit can avoid voice authentication and suggest face authentication or fingerprint authentication. In a noisy environment, the accuracy of voice authentication may decrease, so the authentication unit preferentially suggests face authentication or fingerprint authentication. For example, the authentication unit can detect the surrounding noise level with a sensor and make a decision to avoid voice authentication. In addition, when the customer is in a dark place, it can also avoid face authentication and suggest fingerprint authentication or two-dimensional code authentication. In a dark place, the accuracy of face authentication may decrease, so the authentication unit preferentially suggests fingerprint authentication or two-dimensional code authentication. For example, the authentication unit can detect the surrounding lighting conditions with a sensor and make a decision to avoid face authentication. Furthermore, when the customer's hands are full, it can also suggest voice authentication or face authentication. As a result, the authentication unit provides an authentication means according to the customer's current situation and environment, thereby improving the accuracy of authentication. A part or all of the above-mentioned processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can input environmental data into the generation AI and have the generation AI propose the optimal authentication method.

[0039] The authentication unit can select the optimal authentication method in consideration of the customer's location information at the time of authentication. For example, when the customer is at home, the authentication unit can prioritize face authentication or fingerprint authentication. At home, the accuracy of face authentication and fingerprint authentication is high, so the authentication unit preferentially proposes these methods. For example, the authentication unit can acquire the customer's location information using GPS data or Wi-Fi location information to confirm that the customer is at home. In addition, when the customer is in a public place, it is also possible to avoid voice authentication and propose two-dimensional code authentication. In public places, the accuracy of voice authentication may be reduced, so the authentication unit preferentially proposes two-dimensional code authentication. For example, the authentication unit can confirm that the customer is in a public place based on the customer's location information. Furthermore, when the customer is overseas, it is also possible to propose an internationally recognized authentication method. As a result, the authentication unit provides the optimal authentication method based on the customer's geographic location information, thereby improving the accuracy of authentication. A part or all of the above-mentioned processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can input location information data into the generation AI and have the generation AI propose the optimal authentication method.

[0040] The authentication unit can analyze the customer's SNS activity at the time of authentication and suggest a related authentication means. For example, if the customer frequently posts face photos on social media, the authentication unit can suggest face authentication. The analysis of SNS activity is performed, for example, based on the content and frequency of posts made by the customer on social media. The authentication unit can analyze the customer's SNS activity and suggest the optimal authentication means. For example, if the customer frequently uses voice messages on social media, voice authentication can be suggested. Also, if the customer uses two-dimensional codes on social media, two-dimensional code authentication can be suggested. In this way, the authentication unit provides the optimal authentication means based on the social media activity, thereby improving the accuracy of authentication. Part or all of the above-mentioned processing in the authentication unit may be performed, for example, using AI, or may be performed without using AI. For example, the authentication unit can input SNS activity data to the generation AI and cause the generation AI to execute a suggestion of the optimal authentication means.

[0041] The response unit can select an appropriate response method by referring to the customer's past usage history when responding. The response unit can, for example, select the optimal response method by referring to the customer's past usage history. The past usage history includes, for example, services used by the customer in the past, products purchased, and inquiry history. The response unit can preferentially propose the service used most frequently by the customer based on the past usage history. For example, if the customer has frequently used a specific service in the past, the response unit can preferentially propose that service. The response unit can also predict and propose a service to be used in a specific time period from the past usage history. For example, if the customer has used a specific service in a specific time period, the response unit can propose that service in that time period. Furthermore, the response unit can analyze the past usage history and propose the most efficient response method. As a result, the response unit provides the optimal response method based on the past usage history, thereby improving the accuracy of the response. Part or all of the above-mentioned processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit can input past usage history data to the generation AI and cause the generation AI to execute the proposal of the optimal response method.

[0042] The response unit can customize the response means based on the customer's current contract status and usage status when responding. The response unit can, for example, propose the optimal option based on the plan to which the customer currently subscribes. The current contract status includes, for example, details of the service to which the customer currently subscribes and the contract conditions. The response unit can also analyze the usage status of the customer and propose the most suitable service. The usage status includes, for example, the frequency and time period when the customer uses the service, the type of service used, and the like. This allows the response unit to provide the optimal response means based on the customer's current contract status and usage status. For example, the response unit can propose the optimal option based on the plan to which the customer currently subscribes. The response unit can also analyze the usage status of the customer and propose the most suitable service. Furthermore, the response unit can propose special offers and discounts according to the customer's contract status. This allows the response unit to provide the optimal response means based on the current contract status and usage status, thereby improving the accuracy of the response. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can input current contract status data into the generation AI and have the generation AI propose the optimal response measures.

[0043] The response unit can select the optimal response method by considering the customer's location information when responding. For example, when the customer is at home, the response unit can propose remote support. At home, remote support is the optimal response method, so the response unit proposes this. For example, the response unit can obtain the customer's location information using GPS data or Wi-Fi location information to confirm that the customer is at home. In addition, when the customer is in a public place, a concise response can be performed. In public places, detailed explanations may be difficult, so the response unit prioritizes concise responses. For example, the response unit can confirm that the customer is in a public place based on the customer's location information. Furthermore, when the customer is overseas, international support can be proposed. As a result, the response unit provides the optimal response method based on the geographic location information of the customer, thereby improving the accuracy of the response. Part or all of the above-mentioned processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit can input location information data to the generation AI and cause the generation AI to execute a proposal for the optimal response method.

[0044] The response unit can analyze the customer's SNS activity and suggest relevant response measures when responding. For example, if the customer frequently posts questions on social media, the response unit can suggest online chat support. The analysis of SNS activity is performed, for example, based on the content and frequency of posts made by the customer on social media. The response unit can analyze the customer's SNS activity and suggest optimal response measures. For example, if the customer mentions a specific service on social media, information related to the service can be provided. In addition, if the customer expresses dissatisfaction on social media, a quick response can be made to resolve the problem. As a result, the response unit provides optimal response measures based on social media activities, thereby improving the accuracy of response. Part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can input SNS activity data to a generation AI and cause the generation AI to execute a proposal of optimal response measures.

[0045] The management unit can apply an appropriate management algorithm by referring to past management data during management. The management unit can, for example, select an optimal management algorithm based on past management data. The past management data includes, for example, past management history and management results. The management unit can analyze the past management data and apply the most efficient management algorithm. For example, the management unit can predict and apply a management algorithm to be applied to a specific time period based on the past management data. As a result, the management unit provides an optimal management algorithm based on the past management data, thereby improving the accuracy of management. A part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input past management data to a generation AI and cause the generation AI to select an optimal management algorithm.

[0046] The management unit can customize the management means based on the operation status and usage status of the AI ​​self-booth during management. The management unit can, for example, monitor the operation status of the AI ​​self-booth in real time and apply the optimal management means. The operation status includes, for example, data such as operation time, operation rate, and maintenance status. The management unit can analyze the usage status of the AI ​​self-booth and apply the most efficient management means. The usage status includes, for example, data such as frequency of use, time period of use, and type of service used. This allows the management unit to provide the optimal management means based on the operation status and usage status of the AI ​​self-booth. For example, the management unit can monitor the operation status of the AI ​​self-booth in real time and apply the optimal management means. In addition, the management unit can analyze the usage status of the AI ​​self-booth and apply the most efficient management means. Furthermore, the management unit can customize the management means based on the operation status and usage status of the AI ​​self-booth. As a result, the management unit provides the optimal management means based on the operation status and usage status, thereby improving the accuracy of management. A part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management department can input operational status data into the generation AI and have the generation AI propose optimal management measures.

[0047] The management unit can select the optimal management method in consideration of the location distribution of the AI ​​self-booths during management. The management unit can select the optimal management method based on, for example, the geographical distribution of the AI ​​self-booths. The location distribution includes, for example, geographical distribution and user distribution. The management unit can analyze the geographical distribution of the AI ​​self-booths and select the most efficient management method. For example, the management unit can predict and apply a management method to be applied to a specific area based on the geographical distribution. As a result, the management unit provides an optimal management method based on the geographical distribution, thereby improving the accuracy of management. A part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input geographical distribution data to the generation AI and cause the generation AI to select the optimal management method.

[0048] The management unit can improve the accuracy of management by referring to the related information of the AI ​​self-booth during management. The management unit can improve the accuracy of management, for example, based on the related data of the AI ​​self-booth. The related information includes, for example, past usage history and customer feedback. The management unit can analyze the related data of the AI ​​self-booth and apply the most efficient management method. For example, the management unit can predict and apply a management method to be applied to a specific time period based on the related data. As a result, the management unit provides an optimal management method based on the related data, thereby improving the accuracy of management. Part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input the related data to the generation AI and cause the generation AI to select the optimal management method.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The authentication unit can monitor the health condition of a customer and select an authentication method based on the health condition. For example, the authentication unit can measure the customer's heart rate and blood pressure with a sensor to evaluate the health condition. If the health condition is not good, the authentication unit can suggest a simpler authentication method. The authentication unit can also determine whether a specific authentication method is suitable based on the customer's health data. For example, if the customer has high blood pressure, fingerprint authentication can be avoided and facial authentication can be suggested. In this way, the authentication unit can improve the accuracy of authentication and the comfort of the customer by providing an authentication method according to the customer's health condition.

[0051] The response unit can analyze the purchase history of the customer and propose optimal services based on the purchase history. For example, the response unit can propose new related products and services based on products and services purchased by the customer in the past. The response unit can also analyze the purchasing patterns of the customer and make proposals tailored to specific seasons and events. For example, if the customer has purchased a specific product during the Christmas season in the past, the response unit can propose a similar product for the Christmas season. Furthermore, the response unit can propose special discounts and promotions based on the purchase history of the customer. In this way, the response unit can improve customer satisfaction by providing optimal services based on the purchase history of the customer.

[0052] The management unit can provide a management method for monitoring the energy consumption of the AI ​​self-service booth and optimizing energy efficiency. For example, the management unit can monitor the operation status of the AI ​​self-service booth in real time and collect energy consumption data. If energy consumption is high, the management unit can adjust the operation schedule and take measures to reduce energy consumption. The management unit can also formulate a maintenance schedule for improving energy efficiency. For example, energy efficiency can be optimized by performing maintenance during times when energy consumption is low. In this way, the management unit can optimize the energy consumption of the AI ​​self-service booth and reduce operation costs.

[0053] The management department can collect feedback from users of the AI ​​self-booth and improve the management method based on the feedback. For example, the management department can analyze the feedback provided by the user and identify problems with the operation of the AI ​​self-booth. In addition, based on the feedback, the management department can take improvement measures according to the needs of the user. For example, if a user is dissatisfied with a particular function, measures can be implemented to improve the function. In addition, the management department can add new functions of the AI ​​self-booth based on the feedback. In this way, the management department can improve the operation of the AI ​​self-booth based on the user's feedback and improve user satisfaction.

[0054] The support department can select the optimal response method by taking into account the customer's location information. For example, if the customer is at home, remote support can be suggested. At home, remote support is the optimal response method, so the support department suggests this. Also, if the customer is in a public place, a concise response can be provided. In public places, detailed explanations may be difficult, so the support department prioritizes concise responses. Furthermore, if the customer is overseas, international support can be suggested. This allows the support department to provide the optimal response method based on the customer's geographic location information, improving the accuracy of the response.

[0055] The process flow of the first embodiment will be briefly described below.

[0056] Step 1: The authentication unit authenticates the customer. The authentication unit can authenticate the customer using methods such as facial recognition, fingerprint authentication, voice authentication, and two-dimensional code authentication. For example, the authentication unit can use facial recognition technology to recognize the customer's face and identify the customer. The authentication unit can also use fingerprint authentication technology to recognize the customer's fingerprint and identify the customer. Furthermore, the authentication unit can use voice authentication technology to recognize the customer's voice and identify the customer. The authentication unit can also use two-dimensional code authentication technology to scan a two-dimensional code presented by the customer and identify the customer. Step 2: The response department responds by utilizing the customer information authenticated by the authentication department. The response department can, for example, change the rate plan, check the contract details, troubleshoot, propose new services, and so on. For example, the response department can carry out procedures to change the customer's rate plan. The response department can also check the details of the customer's contract and provide necessary information. Furthermore, the response department can respond to troubleshooting inquiries from customers and resolve problems. It can also propose new services and provide optimal services to customers. Step 3: The management department manages the response performed by the response department. The management department can, for example, manage the 24-hour operation of the AI ​​self-service booth. The management department can monitor the operation status of the AI ​​self-service booth and perform maintenance as necessary.

[0057] (Example 2) The system according to the embodiment of the present invention is a system that maintains customer satisfaction while reducing the cost of shop counter response by utilizing generation AI. In this system, the response by a shop clerk is 1,000 yen per time, and the response by the AI ​​self-booth is free. As a result, customers can use the AI ​​self-booth for free, and costs can be reduced. In the AI ​​self-booth, customer authentication is performed and response is performed using customer information. For example, when a customer enters the booth, the customer is identified by face recognition, fingerprint recognition, voice recognition, two-dimensional code (e.g., QR code) recognition, etc., and the optimal response is performed based on the customer's past usage history, contract information, preferences, and behavior patterns. As a result, customers can receive prompt and accurate service, and satisfaction is improved. In addition, the AI ​​self-booth can operate 24 hours a day, and customers can use it at any time. As a result, it is possible to respond even outside the store's business hours, improving customer convenience. Furthermore, the AI ​​self-booth can analyze the content of inquiries from customers and provide appropriate answers. For example, the AI ​​automatically responds to general inquiries such as changes to fee plans, confirmation of contract details, troubleshooting, and proposals for new services. This reduces the burden on store clerks and cuts call center costs. In this way, by installing an AI self-service booth that utilizes generative AI, it is possible to reduce the cost of handling store counters while maintaining customer satisfaction. This allows the system to maintain customer satisfaction while reducing the cost of handling store counters.

[0058] The system according to the embodiment includes an authentication unit, a response unit, and a management unit. The authentication unit authenticates a customer. The authentication unit can authenticate a customer using, for example, face authentication, fingerprint authentication, voice authentication, two-dimensional code authentication, or other methods. For example, the authentication unit can recognize the face of a customer using face authentication technology to identify the customer. The authentication unit can also recognize the fingerprint of a customer using fingerprint authentication technology to identify the customer. Furthermore, the authentication unit can recognize the voice of a customer using voice authentication technology to identify the customer. The two-dimensional code authentication technology can also be used to scan a two-dimensional code presented by a customer and identify the customer. The response unit uses the customer information authenticated by the authentication unit to respond. The response unit can respond, for example, by changing a fee plan, checking the contract details, troubleshooting, proposing a new service, and the like. For example, the response unit can carry out a procedure to change a customer's fee plan. The response unit can also check the contract details of a customer and provide necessary information. Furthermore, the response unit can respond to troubleshooting inquiries from customers and solve problems. It can also propose new services and provide optimal services to customers. The management unit manages the responses performed by the response unit. The management unit can, for example, manage the 24-hour operation of the AI ​​self-service booth. The management unit can monitor the operation status of the AI ​​self-service booth and perform maintenance as necessary. This allows the system to efficiently perform customer authentication, response, and management.

[0059] The authentication unit authenticates the customer. The authentication unit can authenticate the customer using methods such as face recognition, fingerprint recognition, voice recognition, and two-dimensional code recognition. Specifically, face recognition technology identifies the customer by taking a picture of the customer's face using a camera and comparing it with pre-registered face data. The face recognition algorithm extracts facial features and compares them with existing data in a database. Fingerprint authentication technology reads the customer's fingerprint using a fingerprint scanner and compares it with registered fingerprint data. High accuracy of authentication is possible by analyzing the fine details of the fingerprint. Voice authentication technology records the customer's voice and analyzes the voice waveform and voiceprint for authentication. Voice authentication is particularly effective in situations where a telephone or voice assistant is used. Two-dimensional code authentication technology scans a two-dimensional code presented by the customer and identifies the customer based on that information. The two-dimensional code contains the customer's ID and authentication information, and authentication is completed quickly by simply scanning it. These authentication methods can be used alone or multiple methods can be combined to perform multi-factor authentication. Using multi-factor authentication can further strengthen security. For example, by combining face recognition and fingerprint recognition, higher reliability can be ensured. The authentication unit can use these technologies to quickly and accurately authenticate customers and improve the security of the entire system.

[0060] The response section responds by utilizing the customer information authenticated by the authentication section. The response section can respond by, for example, changing the fee plan, confirming the contract details, troubleshooting, proposing new services, etc. Specifically, in the procedure for changing the fee plan, the system analyzes the customer's current plan and usage status and proposes the optimal plan. Based on the customer's past usage data, the system automatically calculates the most cost-effective plan and presents it to the customer. In the confirmation of the contract details, the system quickly searches the customer's contract information and provides the necessary information. For example, the expiration date of the contract and details of available services can be displayed immediately. In the troubleshooting, the system identifies the cause of the problem and provides a solution in response to an inquiry from a customer. The system refers to past trouble data and an FAQ database and presents the optimal solution. In the proposal of a new service, the system analyzes the customer's usage history and preferences and proposes the optimal service. For example, if a customer frequently uses a particular service, it can propose new options or upgrades related to that service. Through these functions, the response section can respond quickly and accurately to customers and improve customer satisfaction. In addition, the response section can collect feedback from customers and use it to improve the service. This enables the department to respond flexibly to customer needs, improving the efficiency and effectiveness of the entire system.

[0061] The management department manages the response performed by the response department. For example, the management department can manage the 24-hour operation of the AI ​​self-service booth. Specifically, it monitors the operation status of the AI ​​self-service booth in real time and responds immediately if an abnormality occurs. The management department is equipped with a dashboard for monitoring the operation status, and the operation status and usage status of each booth can be grasped at a glance. If an abnormality is detected, the management department automatically issues an alert and notifies the maintenance team. When the maintenance team receives the alert, they rush to the site and solve the problem. The management department formulates a regular maintenance schedule to ensure long-term stable operation of the AI ​​self-service booth. In addition, the management department analyzes operation data and seeks efficient operation methods. For example, it analyzes the time periods when it is frequently used and the operation rate of a specific booth, and optimally allocates resources. This maximizes the operation efficiency of the AI ​​self-service booth and provides high-quality service to customers. The management department also collects feedback from customers and uses it to improve services. For example, if a customer is dissatisfied with the usability of a specific booth, the design and functions of the booth are improved based on that feedback. This enables the management department to improve the operational efficiency of the entire system and customer satisfaction.

[0062] The authentication unit may include face authentication, fingerprint authentication, voice authentication, and two-dimensional code authentication. The authentication unit may, for example, use face authentication technology to recognize the face of a customer and identify the customer. The face authentication technology may, for example, use a face recognition algorithm to analyze the features of the customer's face and compare them with face data in a database to perform authentication. The fingerprint authentication technology may, for example, use a fingerprint sensor to read the customer's fingerprint and compare them with fingerprint data in a database to perform authentication. The voice authentication technology may, for example, use a microphone to record the customer's voice and compare them with voice data in a database to perform authentication. The two-dimensional code authentication technology may, for example, use a two-dimensional code scanner to read a two-dimensional code presented by the customer and analyze the data of the two-dimensional code to perform authentication. As a result, the authentication unit provides a variety of authentication methods, thereby improving customer convenience. A part or all of the above-mentioned processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit may input a face recognition algorithm to the generation AI and cause the generation AI to execute face authentication processing.

[0063] The response unit can change the fee plan, check the contract details, troubleshoot, and propose new services. The response unit can, for example, carry out a procedure to change the fee plan of the customer. Changing the fee plan includes, for example, a procedure to change from the plan currently subscribed by the customer to another plan. The response unit can also check the contract details of the customer and provide necessary information. Checking the contract details includes, for example, a procedure to check the details and contract conditions of the service currently subscribed by the customer. The response unit can also respond to troubleshooting inquiries from customers and solve problems. Troubleshooting includes, for example, a procedure to solve technical problems faced by the customer and problems related to the use of the service. The response unit can also propose new services and provide optimal services to the customer. Proposing new services includes, for example, a procedure to propose new services suitable for the customer based on the customer's usage history and preferences. This allows the response unit to respond to the needs of the customer by performing various responses. Part or all of the above-mentioned processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit can input the customer's usage history into the generation AI and have the generation AI execute a proposal for an optimal service.

[0064] The management unit can manage the constant operation of the AI ​​self-booth. For example, the management unit can monitor the operation status of the AI ​​self-booth in real time and perform maintenance as necessary. The operation status of the AI ​​self-booth includes data such as operation time, operation rate, and frequency of use. The management unit can use a sensor or a monitoring system to monitor the operation status of the AI ​​self-booth. For example, the management unit can monitor the operation status in real time using a sensor installed in the AI ​​self-booth. The management unit can also adjust the maintenance schedule based on the operation status of the AI ​​self-booth. For example, the management unit can minimize the impact on customers by performing maintenance during a time period when the operation rate of the AI ​​self-booth is low. This allows the management unit to manage the 24-hour operation of the AI ​​self-booth, and customers can use the service at any time. Some or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input operation status data of the AI ​​self-booth to the generation AI and cause the generation AI to adjust the maintenance schedule.

[0065] The response unit can respond by analyzing the customer's preferences and behavioral patterns. The response unit can, for example, analyze the customer's past usage history and purchase history to identify the customer's preferences. The analysis of preferences is performed, for example, based on data on products purchased by the customer in the past and services used by the customer. The response unit can also analyze the customer's behavioral patterns to identify the customer's usage frequency and visiting time period. The analysis of behavioral patterns is performed, for example, based on data such as the frequency and time period when the customer visits the shop, and the type of service used. This allows the response unit to respond optimally based on the customer's preferences and behavioral patterns. For example, the response unit can preferentially suggest services that the customer has used in the past. In addition, the response unit can provide services at optimal times based on the customer's behavioral patterns. Furthermore, the response unit can suggest new services based on the customer's preferences and behavioral patterns. This allows the response unit to respond according to the individual needs of the customer. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can input customer preference data into the generation AI and have the generation AI execute optimal service suggestions.

[0066] The authentication unit can estimate the emotional state of the customer and select an authentication method based on the estimated emotional state of the customer. For example, the authentication unit can capture the facial expression of the customer with a camera and estimate the emotional state using an emotion estimation algorithm. For example, the authentication unit can use facial expression recognition technology to analyze changes in the facial expression of the customer and estimate the emotional state. The authentication unit can also record the voice of the customer and estimate the emotional state using a voice analysis technology. For example, the authentication unit can use voice recognition technology to analyze the tone and speed of the customer's voice and estimate the emotional state. Furthermore, the authentication unit can collect the biometric data of the customer (heart rate and electrodermal activity) with a sensor and estimate the emotional state using an emotion estimation algorithm. For example, the authentication unit can estimate the emotional state based on the fluctuation of the heart rate. This allows the authentication unit to provide an authentication method according to the emotional state of the customer and reduce stress for the customer. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI. Some or all of the above-mentioned processes in the authentication unit may be performed using AI, or may be performed without using AI. For example, the authentication unit may input facial expression data of a customer to a generation AI and cause the generation AI to estimate an emotional state.

[0067] The authentication unit can analyze the past authentication history of the customer and propose an appropriate authentication method. The authentication unit can, for example, analyze the past authentication history of the customer and propose an optimal authentication method. The past authentication history includes, for example, authentication methods used by the customer in the past and authentication success / failure history. The authentication unit can preferentially propose the authentication method used most frequently by the customer based on the past authentication history. For example, if the customer has frequently used face authentication in the past, the authentication unit can preferentially propose face authentication. The authentication unit can also predict and propose an authentication method to be used in a specific time period from the past authentication history. For example, if the customer has used fingerprint authentication in a specific time period, the authentication unit can propose fingerprint authentication for that time period. Furthermore, the authentication unit can analyze the past authentication history and propose the most efficient authentication method. As a result, the authentication unit provides the optimal authentication method based on the past authentication history, thereby improving authentication efficiency. Part or all of the above-mentioned processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can input past authentication history data to the generation AI and cause the generation AI to execute a proposal of an optimal authentication method.

[0068] The authentication unit can customize the authentication means based on the customer's current situation and environment at the time of authentication. For example, when the customer is in a noisy environment, the authentication unit can avoid voice authentication and suggest face authentication or fingerprint authentication. In a noisy environment, the accuracy of voice authentication may decrease, so the authentication unit preferentially suggests face authentication or fingerprint authentication. For example, the authentication unit can detect the surrounding noise level with a sensor and make a decision to avoid voice authentication. In addition, when the customer is in a dark place, it can also avoid face authentication and suggest fingerprint authentication or two-dimensional code authentication. In a dark place, the accuracy of face authentication may decrease, so the authentication unit preferentially suggests fingerprint authentication or two-dimensional code authentication. For example, the authentication unit can detect the surrounding lighting conditions with a sensor and make a decision to avoid face authentication. Furthermore, when the customer's hands are full, it can also suggest voice authentication or face authentication. As a result, the authentication unit provides an authentication means according to the customer's current situation and environment, thereby improving the accuracy of authentication. A part or all of the above-mentioned processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can input environmental data into the generation AI and have the generation AI propose the optimal authentication method.

[0069] The authentication unit can estimate the emotional state of the customer and determine the priority of authentication based on the estimated emotional state of the customer. For example, the authentication unit can capture the facial expression of the customer with a camera and estimate the emotional state using an emotion estimation algorithm. For example, the authentication unit can use facial expression recognition technology to analyze changes in the facial expression of the customer and estimate the emotional state. The authentication unit can also record the voice of the customer and estimate the emotional state using a voice analysis technology. For example, the authentication unit can use voice recognition technology to analyze the tone and speed of the customer's voice and estimate the emotional state. Furthermore, the authentication unit can collect the biometric data of the customer (heart rate and electrodermal activity) with a sensor and estimate the emotional state using an emotion estimation algorithm. For example, the authentication unit can estimate the emotional state based on the fluctuation of the heart rate. This allows the authentication unit to provide an authentication priority according to the emotional state of the customer, and reduce the stress of the customer. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI. Some or all of the above-mentioned processes in the authentication unit may be performed using AI, or may be performed without using AI. For example, the authentication unit may input facial expression data of a customer to a generation AI and cause the generation AI to estimate an emotional state.

[0070] The authentication unit can select the optimal authentication method in consideration of the customer's location information at the time of authentication. For example, when the customer is at home, the authentication unit can prioritize face authentication or fingerprint authentication. At home, the accuracy of face authentication and fingerprint authentication is high, so the authentication unit preferentially proposes these methods. For example, the authentication unit can acquire the customer's location information using GPS data or Wi-Fi location information to confirm that the customer is at home. In addition, when the customer is in a public place, it is also possible to avoid voice authentication and propose two-dimensional code authentication. In public places, the accuracy of voice authentication may be reduced, so the authentication unit preferentially proposes two-dimensional code authentication. For example, the authentication unit can confirm that the customer is in a public place based on the customer's location information. Furthermore, when the customer is overseas, it is also possible to propose an internationally recognized authentication method. As a result, the authentication unit provides the optimal authentication method based on the customer's geographic location information, thereby improving the accuracy of authentication. A part or all of the above-mentioned processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can input location information data into the generation AI and have the generation AI propose the optimal authentication method.

[0071] The authentication unit can analyze the customer's SNS activity at the time of authentication and suggest a related authentication means. For example, if the customer frequently posts face photos on social media, the authentication unit can suggest face authentication. The analysis of SNS activity is performed, for example, based on the content and frequency of posts made by the customer on social media. The authentication unit can analyze the customer's SNS activity and suggest the optimal authentication means. For example, if the customer frequently uses voice messages on social media, voice authentication can be suggested. Also, if the customer uses two-dimensional codes on social media, two-dimensional code authentication can be suggested. In this way, the authentication unit provides the optimal authentication means based on the social media activity, thereby improving the accuracy of authentication. Part or all of the above-mentioned processing in the authentication unit may be performed, for example, using AI, or may be performed without using AI. For example, the authentication unit can input SNS activity data to the generation AI and cause the generation AI to execute a suggestion of the optimal authentication means.

[0072] The corresponding unit can estimate the emotional state of the customer and adjust the manner of expression of the response based on the estimated emotional state of the customer. For example, the corresponding unit can capture the facial expression of the customer with a camera and estimate the emotional state using an emotion estimation algorithm. For example, the corresponding unit can use facial expression recognition technology to analyze changes in the facial expression of the customer and estimate the emotional state. The corresponding unit can also record the voice of the customer and estimate the emotional state using a voice analysis technology. For example, the corresponding unit can use voice recognition technology to analyze the tone and speed of the customer's voice and estimate the emotional state. Furthermore, the corresponding unit can collect the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotional state using an emotion estimation algorithm. For example, the corresponding unit can estimate the emotional state based on the fluctuation of the heart rate. This allows the corresponding unit to provide a method of expression of the response according to the emotional state of the customer, improving customer satisfaction. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the correspondence unit may be performed, for example, using AI or may be performed without using AI. For example, the correspondence unit may input facial expression data of a customer to the generation AI and cause the generation AI to estimate an emotional state.

[0073] The response unit can select an appropriate response method by referring to the customer's past usage history when responding. The response unit can, for example, select the optimal response method by referring to the customer's past usage history. The past usage history includes, for example, services used by the customer in the past, products purchased, and inquiry history. The response unit can preferentially propose the service used most frequently by the customer based on the past usage history. For example, if the customer has frequently used a specific service in the past, the response unit can preferentially propose that service. The response unit can also predict and propose a service to be used in a specific time period from the past usage history. For example, if the customer has used a specific service in a specific time period, the response unit can propose that service in that time period. Furthermore, the response unit can analyze the past usage history and propose the most efficient response method. As a result, the response unit provides the optimal response method based on the past usage history, thereby improving the accuracy of the response. Part or all of the above-mentioned processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit can input past usage history data to the generation AI and cause the generation AI to execute the proposal of the optimal response method.

[0074] The response unit can customize the response means based on the customer's current contract status and usage status when responding. The response unit can, for example, propose the optimal option based on the plan to which the customer currently subscribes. The current contract status includes, for example, details of the service to which the customer currently subscribes and the contract conditions. The response unit can also analyze the usage status of the customer and propose the most suitable service. The usage status includes, for example, the frequency and time period when the customer uses the service, the type of service used, and the like. This allows the response unit to provide the optimal response means based on the customer's current contract status and usage status. For example, the response unit can propose the optimal option based on the plan to which the customer currently subscribes. The response unit can also analyze the usage status of the customer and propose the most suitable service. Furthermore, the response unit can propose special offers and discounts according to the customer's contract status. This allows the response unit to provide the optimal response means based on the current contract status and usage status, thereby improving the accuracy of the response. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can input current contract status data into the generation AI and have the generation AI propose the optimal response measures.

[0075] The corresponding unit can estimate the emotional state of the customer and determine the priority of the response based on the estimated emotional state of the customer. For example, the corresponding unit can capture the facial expression of the customer with a camera and estimate the emotional state using an emotion estimation algorithm. For example, the corresponding unit can analyze the change in the facial expression of the customer using facial expression recognition technology to estimate the emotional state. The corresponding unit can also record the voice of the customer and estimate the emotional state using a voice analysis technology. For example, the corresponding unit can analyze the tone and speed of the customer's voice using voice recognition technology to estimate the emotional state. Furthermore, the corresponding unit can collect the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotional state using an emotion estimation algorithm. For example, the corresponding unit can estimate the emotional state based on the fluctuation of the heart rate. This allows the corresponding unit to provide a priority of the response according to the emotional state of the customer, improving customer satisfaction. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI. A part or all of the above-mentioned processing in the corresponding unit may be performed using, for example, AI, or may be performed without using AI. For example, the corresponding unit may input facial expression data of the customer to the generating AI and cause the generating AI to estimate the emotional state.

[0076] The response unit can select the optimal response method by considering the customer's location information when responding. For example, when the customer is at home, the response unit can propose remote support. At home, remote support is the optimal response method, so the response unit proposes this. For example, the response unit can obtain the customer's location information using GPS data or Wi-Fi location information to confirm that the customer is at home. In addition, when the customer is in a public place, a concise response can be performed. In public places, detailed explanations may be difficult, so the response unit prioritizes concise responses. For example, the response unit can confirm that the customer is in a public place based on the customer's location information. Furthermore, when the customer is overseas, international support can be proposed. As a result, the response unit provides the optimal response method based on the geographic location information of the customer, thereby improving the accuracy of the response. Part or all of the above-mentioned processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit can input location information data to the generation AI and cause the generation AI to execute a proposal for the optimal response method.

[0077] The response unit can analyze the customer's SNS activity and suggest relevant response measures when responding. For example, if the customer frequently posts questions on social media, the response unit can suggest online chat support. The analysis of SNS activity is performed, for example, based on the content and frequency of posts made by the customer on social media. The response unit can analyze the customer's SNS activity and suggest optimal response measures. For example, if the customer mentions a specific service on social media, information related to the service can be provided. In addition, if the customer expresses dissatisfaction on social media, a quick response can be made to resolve the problem. As a result, the response unit provides optimal response measures based on social media activities, thereby improving the accuracy of response. Part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can input SNS activity data to a generation AI and cause the generation AI to execute a proposal of optimal response measures.

[0078] The management unit can estimate the emotional state of the customer and adjust the management method based on the estimated emotional state of the customer. For example, the management unit can capture the facial expression of the customer with a camera and estimate the emotional state using an emotion estimation algorithm. For example, the management unit can use facial expression recognition technology to analyze changes in the facial expression of the customer and estimate the emotional state. The management unit can also record the voice of the customer and estimate the emotional state using a voice analysis technology. For example, the management unit can use voice recognition technology to analyze the tone and speed of the customer's voice and estimate the emotional state. Furthermore, the management unit can collect the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotional state using an emotion estimation algorithm. For example, the management unit can estimate the emotional state based on the fluctuation of the heart rate. This allows the management unit to provide a management method according to the emotional state of the customer, improving the efficiency of management. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI. Some or all of the above-mentioned processes in the management unit may be performed using AI or may be performed without using AI. For example, the management unit may input facial expression data of a customer to the generation AI and cause the generation AI to estimate the emotional state.

[0079] The management unit can apply an appropriate management algorithm by referring to past management data during management. The management unit can, for example, select an optimal management algorithm based on past management data. The past management data includes, for example, past management history and management results. The management unit can analyze the past management data and apply the most efficient management algorithm. For example, the management unit can predict and apply a management algorithm to be applied to a specific time period based on the past management data. As a result, the management unit provides an optimal management algorithm based on the past management data, thereby improving the accuracy of management. A part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input past management data to a generation AI and cause the generation AI to select an optimal management algorithm.

[0080] The management unit can customize the management means based on the operation status and usage status of the AI ​​self-booth during management. The management unit can, for example, monitor the operation status of the AI ​​self-booth in real time and apply the optimal management means. The operation status includes, for example, data such as operation time, operation rate, and maintenance status. The management unit can analyze the usage status of the AI ​​self-booth and apply the most efficient management means. The usage status includes, for example, data such as frequency of use, time period of use, and type of service used. This allows the management unit to provide the optimal management means based on the operation status and usage status of the AI ​​self-booth. For example, the management unit can monitor the operation status of the AI ​​self-booth in real time and apply the optimal management means. In addition, the management unit can analyze the usage status of the AI ​​self-booth and apply the most efficient management means. Furthermore, the management unit can customize the management means based on the operation status and usage status of the AI ​​self-booth. As a result, the management unit provides the optimal management means based on the operation status and usage status, thereby improving the accuracy of management. A part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management department can input operational status data into the generation AI and have the generation AI propose optimal management measures.

[0081] The management unit can estimate the emotional state of the customer and determine the priority of management based on the estimated emotional state of the customer. For example, the management unit can capture the facial expression of the customer with a camera and estimate the emotional state using an emotion estimation algorithm. For example, the management unit can use facial expression recognition technology to analyze changes in the facial expression of the customer and estimate the emotional state. The management unit can also record the voice of the customer and estimate the emotional state using a voice analysis technology. For example, the management unit can use voice recognition technology to analyze the tone and speed of the customer's voice and estimate the emotional state. Furthermore, the management unit can collect the biometric data of the customer (heart rate and electrodermal activity) with a sensor and estimate the emotional state using an emotion estimation algorithm. For example, the management unit can estimate the emotional state based on the fluctuation of the heart rate. This allows the management unit to provide a priority of management according to the emotional state of the customer, improving the efficiency of management. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI. Some or all of the above-mentioned processes in the management unit may be performed using AI or may be performed without using AI. For example, the management unit may input facial expression data of a customer to the generation AI and cause the generation AI to estimate the emotional state.

[0082] The management unit can select the optimal management method in consideration of the location distribution of the AI ​​self-booths during management. The management unit can select the optimal management method based on, for example, the geographical distribution of the AI ​​self-booths. The location distribution includes, for example, geographical distribution and user distribution. The management unit can analyze the geographical distribution of the AI ​​self-booths and select the most efficient management method. For example, the management unit can predict and apply a management method to be applied to a specific area based on the geographical distribution. As a result, the management unit provides an optimal management method based on the geographical distribution, thereby improving the accuracy of management. A part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input geographical distribution data to the generation AI and cause the generation AI to select the optimal management method.

[0083] The management unit can improve the accuracy of management by referring to the related information of the AI ​​self-booth during management. The management unit can improve the accuracy of management, for example, based on the related data of the AI ​​self-booth. The related information includes, for example, past usage history and customer feedback. The management unit can analyze the related data of the AI ​​self-booth and apply the most efficient management method. For example, the management unit can predict and apply a management method to be applied to a specific time period based on the related data. As a result, the management unit provides an optimal management method based on the related data, thereby improving the accuracy of management. Part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input the related data to the generation AI and cause the generation AI to select the optimal management method.

[0084] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0085] The authentication unit can monitor the health condition of a customer and select an authentication method based on the health condition. For example, the authentication unit can measure the customer's heart rate and blood pressure with a sensor to evaluate the health condition. If the health condition is not good, the authentication unit can suggest a simpler authentication method. The authentication unit can also determine whether a specific authentication method is suitable based on the customer's health data. For example, if the customer has high blood pressure, fingerprint authentication can be avoided and facial authentication can be suggested. In this way, the authentication unit can improve the accuracy of authentication and the comfort of the customer by providing an authentication method according to the customer's health condition.

[0086] The response unit can analyze the purchase history of the customer and propose optimal services based on the purchase history. For example, the response unit can propose new related products and services based on products and services purchased by the customer in the past. The response unit can also analyze the purchasing patterns of the customer and make proposals tailored to specific seasons and events. For example, if the customer has purchased a specific product during the Christmas season in the past, the response unit can propose a similar product for the Christmas season. Furthermore, the response unit can propose special discounts and promotions based on the purchase history of the customer. In this way, the response unit can improve customer satisfaction by providing optimal services based on the purchase history of the customer.

[0087] The management unit can provide a management method for monitoring the energy consumption of the AI ​​self-service booth and optimizing energy efficiency. For example, the management unit can monitor the operation status of the AI ​​self-service booth in real time and collect energy consumption data. If energy consumption is high, the management unit can adjust the operation schedule and take measures to reduce energy consumption. The management unit can also formulate a maintenance schedule for improving energy efficiency. For example, energy efficiency can be optimized by performing maintenance during times when energy consumption is low. In this way, the management unit can optimize the energy consumption of the AI ​​self-service booth and reduce operation costs.

[0088] The response unit can estimate the emotional state of the customer and adjust the tone and language of the response based on the estimated emotional state. For example, if the customer is feeling stressed, the response unit can respond in a calmer, more reassuring tone. Also, if the customer is excited, the response unit can respond in a calm, more collected tone. Furthermore, the response unit can adjust the content of the response according to the emotional state of the customer. For example, if the customer is feeling dissatisfied, the response unit can prioritize a response to quickly resolve the problem. In this way, the response unit can improve customer satisfaction by responding according to the emotional state of the customer.

[0089] The authentication unit can estimate the emotional state of the customer and adjust the difficulty of the authentication based on the estimated emotional state. For example, the authentication unit can suggest an easier authentication method if the customer is nervous, and can suggest a normal authentication method if the customer is relaxed. Furthermore, the authentication unit can adjust the authentication procedure according to the emotional state of the customer. For example, if the customer is impatient, the authentication procedure can be simplified to quickly complete the authentication. In this way, the authentication unit can improve the accuracy of authentication and the comfort of the customer by providing an authentication method according to the emotional state of the customer.

[0090] The management department can collect feedback from users of the AI ​​self-booth and improve the management method based on the feedback. For example, the management department can analyze the feedback provided by the user and identify problems with the operation of the AI ​​self-booth. In addition, based on the feedback, the management department can take improvement measures according to the needs of the user. For example, if a user is dissatisfied with a particular function, measures can be implemented to improve the function. In addition, the management department can add new functions of the AI ​​self-booth based on the feedback. In this way, the management department can improve the operation of the AI ​​self-booth based on the user's feedback and improve user satisfaction.

[0091] The response unit can estimate the emotional state of the customer and determine the priority of the response based on the estimated emotional state. For example, if a customer is very dissatisfied, the response unit can prioritize the response to that customer. Also, if the customer is satisfied, the response unit can prioritize the response to other customers. Furthermore, the response unit can adjust the content of the response according to the emotional state of the customer. For example, if the customer is feeling anxious, the response unit can prioritize a response that provides a sense of security. In this way, the response unit can improve customer satisfaction by responding according to the emotional state of the customer.

[0092] The authentication unit can estimate the emotional state of a customer and determine the priority of authentication based on the estimated emotional state. For example, if a customer is very nervous, the authentication unit can prioritize authentication of that customer. Also, if the customer is relaxed, the authentication unit can prioritize authentication of other customers. Furthermore, the authentication unit can adjust the authentication procedure according to the emotional state of the customer. For example, if the customer is impatient, the authentication procedure can be simplified to quickly complete the authentication. In this way, the authentication unit can improve the accuracy of authentication and the comfort of the customer by providing an authentication method according to the emotional state of the customer.

[0093] The management unit can estimate the emotional state of the user of the AI ​​self-booth and adjust the management method based on the estimated emotional state. For example, if the user is feeling stressed, the management unit can take measures to reduce the user's stress. Also, if the user is satisfied, the management unit can provide a management method for maintaining that state. Furthermore, the management unit can adjust the functions of the AI ​​self-booth according to the emotional state of the user. For example, if the user is feeling dissatisfied, the management unit can identify the cause and quickly respond to improve the user's satisfaction. In this way, the management unit can improve user satisfaction by providing a management method according to the user's emotional state.

[0094] The support department can select the optimal response method by taking into account the customer's location information. For example, if the customer is at home, remote support can be suggested. At home, remote support is the optimal response method, so the support department suggests this. Also, if the customer is in a public place, a concise response can be provided. In public places, detailed explanations may be difficult, so the support department prioritizes concise responses. Furthermore, if the customer is overseas, international support can be suggested. This allows the support department to provide the optimal response method based on the customer's geographic location information, improving the accuracy of the response.

[0095] The process flow of the second embodiment will be briefly described below.

[0096] Step 1: The authentication unit authenticates the customer. The authentication unit can authenticate the customer using methods such as facial recognition, fingerprint authentication, voice authentication, and two-dimensional code authentication. For example, the authentication unit can use facial recognition technology to recognize the customer's face and identify the customer. The authentication unit can also use fingerprint authentication technology to recognize the customer's fingerprint and identify the customer. Furthermore, the authentication unit can use voice authentication technology to recognize the customer's voice and identify the customer. The authentication unit can also use two-dimensional code authentication technology to scan a two-dimensional code presented by the customer and identify the customer. Step 2: The response department responds by utilizing the customer information authenticated by the authentication department. The response department can, for example, change the rate plan, check the contract details, troubleshoot, propose new services, and so on. For example, the response department can carry out procedures to change the customer's rate plan. The response department can also check the details of the customer's contract and provide necessary information. Furthermore, the response department can respond to troubleshooting inquiries from customers and resolve problems. It can also propose new services and provide optimal services to customers. Step 3: The management department manages the response performed by the response department. The management department can, for example, manage the 24-hour operation of the AI ​​self-service booth. The management department can monitor the operation status of the AI ​​self-service booth and perform maintenance as necessary.

[0097] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0098] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0099] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0100] Each of the multiple elements including the authentication unit, the response unit, and the management unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the authentication unit recognizes the face and voice of the customer using the camera 42 and the microphone 38B of the smart device 14, and identifies the customer by the control unit 46A. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and performs responses such as changing the customer's fee plan and confirming the contract details. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and monitors the operation status of the AI ​​self-booth and performs maintenance as necessary. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0101] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0102] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0108] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0111] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0114] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0115] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0116] Each of the multiple elements including the authentication unit, the correspondence unit, and the management unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the authentication unit recognizes the face and voice of the customer using the camera 42 and the microphone 238 of the smart glasses 214, and identifies the customer by the control unit 46A. The correspondence unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and performs responses such as changing the customer's fee plan and confirming the contract details. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and monitors the operating status of the AI ​​self-booth and performs maintenance as necessary. The correspondence relationship between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0117] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0118] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0124] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0127] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0131] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements including the authentication unit, the correspondence unit, and the management unit described above is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the authentication unit recognizes the face and voice of the customer using the camera 42 and the microphone 238 of the headset terminal 314, and identifies the customer by the control unit 46A. The correspondence unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and responds by changing the customer's fee plan and confirming the contract details. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and monitors the operation status of the AI ​​self-booth and performs maintenance as necessary. The correspondence relationship between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0133] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0134] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0140] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0141] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0142] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0144] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0145] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0148] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0149] Each of the multiple elements including the authentication unit, the response unit, and the management unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the authentication unit recognizes the face and voice of the customer using the camera 42 and the microphone 238 of the robot 414, and identifies the customer by the control unit 46A. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and responds by changing the customer's fee plan and confirming the contract details. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and monitors the operating status of the AI ​​self-booth and performs maintenance as necessary. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0150] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0151] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0152] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0153] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0154] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0155] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0156] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0157] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0158] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0159] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0160] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0161] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0162] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0163] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0164] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0165] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0166] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0167] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0168] (Appendix 1) an authentication unit for authenticating a customer; a response unit that uses the customer information authenticated by the authentication unit to respond to the request; A management unit that manages the response performed by the response unit. A system characterized by: (Appendix 2) The authentication unit This can include face recognition, fingerprint recognition, voice recognition, and 2D code recognition. 2. The system of claim 1, (Appendix 3) The corresponding portion is Change pricing plans, check contract details, troubleshoot, and propose new services 2. The system of claim 1, (Appendix 4) The management unit Manage the continuous operation of AI selfie booths 2. The system of claim 1, (Appendix 5) The corresponding portion is Analyze customer preferences and behavior patterns and respond accordingly 2. The system of claim 1, (Appendix 6) The authentication unit To estimate an emotional state of a customer and to select an authentication method based on the estimated emotional state of the customer. 2. The system of claim 1, (Appendix 7) The authentication unit Analyze the customer's past authentication history and suggest appropriate authentication methods 2. The system of claim 1, (Appendix 8) The authentication unit Customize authentication methods based on the customer's current situation and environment at the time of authentication 2. The system of claim 1, (Appendix 9) The authentication unit Estimating a customer's emotional state and determining authentication priorities based on the estimated customer's emotional state 2. The system of claim 1, (Appendix 10) The authentication unit When authenticating, select the optimal authentication method taking into account the customer's location information 2. The system of claim 1, (Appendix 11) The authentication unit During authentication, analyze the customer's social media activity and suggest relevant authentication methods 2. The system of claim 1, (Appendix 12) The corresponding portion is Inferring a customer's emotional state and adjusting the way you express yourself based on the inferred emotional state of the customer 2. The system of claim 1, (Appendix 13) The corresponding portion is When responding, select the appropriate response method by referring to the customer's past usage history. 2. The system of claim 1, (Appendix 14) The corresponding portion is When responding, tailor the response based on the customer's current contract status and usage 2. The system of claim 1, (Appendix 15) The corresponding portion is Estimate the emotional state of the customer and prioritize responses based on the estimated emotional state of the customer 2. The system of claim 1, (Appendix 16) The corresponding portion is When responding, the optimal response method is selected taking into account the customer's location information 2. The system of claim 1, (Appendix 17) The corresponding portion is When responding, analyze the customer's social media activity and suggest relevant responses 2. The system of claim 1, (Appendix 18) The management unit Estimating a customer's emotional state and adjusting management methods based on the estimated customer's emotional state 2. The system of claim 1, (Appendix 19) The management unit During management, past management data is referenced to apply appropriate management algorithms 2. The system of claim 1, (Appendix 20) The management unit When managing, customize management methods based on the operation and usage status of the AI ​​self-service booth. 2. The system of claim 1, (Appendix 21) The management unit Estimating a customer's emotional state and determining management priorities based on the estimated customer's emotional state 2. The system of claim 1, (Appendix 22) The management unit When managing, the optimal management method is selected taking into account the location distribution of AI self-service booths. 2. The system of claim 1, (Appendix 23) The management unit When managing, refer to relevant information from the AI ​​selfie booth to improve management accuracy. 2. The system of claim 1, [Explanation of symbols]

[0169] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an authentication unit for authenticating a customer; a response unit that uses the customer information authenticated by the authentication unit to respond to the request; A management unit that manages the response performed by the response unit. A system characterized by:

2. The authentication unit This can include face recognition, fingerprint recognition, voice recognition, and two-dimensional code recognition.

2. The system of claim 1 .

3. The corresponding portion is Change pricing plans, check contract details, troubleshoot, and propose new services 2. The system of claim 1 .

4. The management unit Manage the continuous operation of AI self-service booths 2. The system of claim 1 .

5. The corresponding portion is Analyze customer preferences and behavior patterns and respond accordingly 2. The system of claim 1 .

6. The authentication unit To estimate an emotional state of a customer and to select an authentication method based on the estimated emotional state of the customer.

2. The system of claim 1 .

7. The authentication unit Analyze the customer's past authentication history and suggest appropriate authentication methods 2. The system of claim 1 .

8. The authentication unit Customize authentication methods based on the customer's current situation and environment at the time of authentication 2. The system of claim 1 .

Images