System

Abstract

To give guidance and respond to a customer appropriately depending on the customer's emotion.SOLUTION: A system according to an embodiment includes a determination unit, a guide unit and a notification unit. The determination unit determines a customer's emotion. The guide unit guides the customer on the basis of the emotion determined by the determination unit. The notification unit gives stuff a notice urging response to the customer if the emotion determined by the determination unit is the predetermined emotion.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] With conventional technology, it was difficult to provide hospitality to customers in an unmanned reception system.

[0005] The system according to the embodiment aims to provide appropriate guidance and responses based on the customer's emotions. [Means for solving the problem]

[0006] The system according to the embodiment includes a determination unit, a guidance unit, and a notification unit. The determination unit determines the emotion of the customer. The guidance unit provides guidance to the customer based on the emotion determined by the determination unit. The notification unit notifies a staff member to prompt them to handle the customer when the emotion determined by the determination unit is a predetermined emotion. Effect of the Invention

[0007] The system according to the embodiment can provide appropriate guidance and responses based on the customer's emotions. [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 the 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 automated reception system according to the embodiment of the present invention is a system that recognizes the emotions of customers and provides guidance based on them. This system analyzes the customer's facial expressions and tone of voice to determine the emotions. Next, guidance is provided to the customer based on the determined emotions. For example, if the customer is lively and happy, the system provides tourist information about the surrounding area, and if the customer is confused, the system provides a simple explanation of how to use the reception. Also, if the customer is tired, the system provides information about hot springs and relaxation facilities, and if the customer is irritated, the staff will respond to avoid trouble. If suspicious movements are detected, a crime prevention check is performed. Furthermore, if a specific emotion value is determined, the staff is notified, leading to the staff's hospitality and response. For example, if the customer is irritated or behaving suspiciously, the staff is notified and can respond quickly. This system makes it possible to realize hospitality for customers even with an unmanned reception system and promote digital transformation of hotels. As a result, the automated reception system can realize hospitality for customers even with an unmanned reception system by recognizing the customer's emotions and providing appropriate guidance and notifications based on them.

[0029] The automated reception system according to the embodiment includes a determination unit, a guidance unit, and a notification unit. The determination unit determines the emotion of the customer. The emotion of the customer includes, for example, joy, anger, sadness, and the like, but is not limited to such examples. For example, in order to analyze the facial expression of the customer, the determination unit detects facial feature points and determines the emotion using a facial expression recognition algorithm. In addition, the determination unit can perform voice frequency analysis and volume analysis to analyze the tone of the customer's voice and determine the emotion. For example, the determination unit determines that the emotion of joy is indicated when the tone of the customer's voice is high. In addition, the determination unit can also determine that the emotion of sadness is indicated when the tone of the customer's voice is low. The guidance unit provides guidance to the customer based on the emotion determined by the determination unit. The guidance includes, for example, voice guidance and screen display, but is not limited to such examples. For example, when the customer is energetic and happy, the guidance unit provides tourist information about nearby areas. In addition, when the customer is confused, the guidance unit can gently explain how to use the reception. Furthermore, the guidance unit can provide guidance to hot springs or relaxation facilities if the customer is tired. The notification unit provides a notification to staff to encourage them to respond to the customer if the emotion determined by the determination unit is a specific emotion. The notification includes, for example, an alert sound or a message display, but is not limited to such examples. For example, if the customer is irritated, the notification unit notifies staff to avoid trouble. Furthermore, if the customer is behaving suspiciously, the notification unit can also notify staff to check for crime prevention. As a result, the automated reception system according to the embodiment can recognize the customer's emotions and provide appropriate guidance and notifications based on them, thereby realizing hospitality for customers even in an unmanned reception system.

[0030] The determination unit determines the emotion of the customer. The emotion of the customer includes, for example, joy, anger, sadness, etc., but is not limited to such examples. For example, in order to analyze the facial expression of the customer, the determination unit detects facial feature points and determines the emotion using a facial expression recognition algorithm. Specifically, the positions and shapes of the eyes, mouth, eyebrows, etc. are detected as facial feature points, and the emotion of the customer is determined by analyzing the changes in these feature points. For example, when the eyes are narrowed and the corners of the mouth are raised, it is determined that the emotion of joy is indicated. Also, when the eyebrows are lowered and the mouth is closed, it can be determined that the emotion of sadness is indicated. Furthermore, the determination unit can perform voice frequency analysis and volume analysis to analyze the tone of the customer's voice and determine the emotion. Specifically, in the voice frequency analysis, the frequency components of the customer's voice are analyzed, and when there are a lot of high frequency components, it is determined that the emotion of joy is indicated, and when there are a lot of low frequency components, it is determined that the emotion of sadness is indicated. Also, in the volume analysis, the volume of the voice is analyzed, and when there is a loud voice, it is determined that the emotion of anger is indicated, and when there is a quiet voice, it is determined that the emotion of sadness is indicated. This allows the determination unit to accurately determine the customer's emotions by analyzing the customer's facial expressions and tone of voice. Furthermore, the determination unit processes the analysis results in real time and can immediately determine the customer's emotions. This makes it possible to respond quickly according to the customer's emotions.

[0031] The guidance unit provides guidance to the customer based on the emotion determined by the determination unit. The guidance includes, for example, voice guidance and screen display, but is not limited to such examples. For example, when the customer is lively and happy, the guidance unit provides nearby tourist information. Specifically, when the customer is smiling and has a happy expression, the guidance unit provides nearby tourist spot and event information by voice guidance and screen display. In addition, when the customer is confused, the guidance unit can gently explain how to use the reception. Specifically, when the customer has a confused expression, the guidance unit provides voice guidance and screen display that carefully explains how to operate the reception and the usage procedure. Furthermore, when the customer is tired, the guidance unit can also provide guidance on hot springs and relaxation facilities. Specifically, when the customer has a tired expression, the guidance unit provides information on nearby hot spring facilities and relaxation facilities and guides the customer to places where he can refresh himself. This allows the guidance unit to provide appropriate guidance according to the customer's emotions, and improve customer satisfaction. Furthermore, the guidance unit can monitor the customer's reaction in real time and adjust the guidance content as appropriate. For example, if a customer shows no interest in the information, the information department can continue to attract the customer's interest by providing a different information content. This allows the information department to respond flexibly to customer needs, thereby further improving customer satisfaction.

[0032] The notification unit notifies the staff to prompt them to respond to the customer when the emotion determined by the determination unit is a specific emotion. The notification includes, for example, an alert sound and a message display, but is not limited to such examples. For example, when the customer is irritated, the notification unit notifies the staff to avoid trouble. Specifically, when the customer has an angry expression, the notification unit notifies the staff with an alert sound or a message display to prompt a quick response. In addition, when the customer is behaving suspiciously, the notification unit can also notify the staff to check for crime prevention. Specifically, when the customer is behaving suspiciously, the notification unit notifies the staff with an alert sound or a message display to prompt them to check the situation. In this way, the notification unit can provide an appropriate notification according to the customer's emotion or behavior, and can realize early detection of trouble and crime prevention measures. Furthermore, the notification unit can record the notification content and analyze it later. For example, the notification history regarding the customer's emotion or behavior can be saved and later checked by the staff, which can be used to improve the response and analyze the cause of the trouble. In this way, the notification unit can contribute to improving the quality of customer service and preventing the recurrence of trouble. Furthermore, the notification unit can combine multiple notification methods to reliably transmit information. For example, important information can be reliably conveyed to staff by using not only alert sounds and message displays, but also emails and SMS. This allows the notification unit to quickly and reliably transmit information and improve the quality of customer service.

[0033] The acquisition unit acquires information indicating the behavior of the customer, the determination unit determines the abnormal behavior of the customer, and the notification unit can notify the staff of a crime prevention check when the determination unit determines the abnormal behavior of the customer. The acquisition unit, for example, acquires information indicating the behavior of the customer. The behavior includes, for example, the speed of movement and the pattern of movement, but is not limited to such examples. The acquisition unit, for example, captures the customer's movement with a camera and analyzes the speed and pattern of the movement. The determination unit determines the abnormal behavior of the customer based on the information acquired by the acquisition unit. The abnormal behavior includes, for example, a sudden change in the speed of movement and a movement that does not follow a specific pattern, but is not limited to such examples. For example, the determination unit determines the abnormal behavior when the customer's movement suddenly becomes faster. The determination unit can also determine the abnormal behavior when the customer's movement does not follow a specific pattern. The notification unit notifies the staff of a crime prevention check when the determination unit determines the abnormal behavior. The notification includes, for example, an alert sound and a message display, but is not limited to such examples. For example, when an abnormal movement is detected, the notification unit notifies the staff with an alert sound. Also, when an abnormal movement is detected, the notification unit can notify the staff with a message display. This makes it possible to detect suspicious movements and notify security checks, thereby enhancing security. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit, the determination unit, and the notification unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the acquisition unit can input data on the customer's movements to the generation AI and cause the generation AI to execute a judgment of abnormal movements. Also, the notification unit can cause the generation AI to execute the notification content based on the data on abnormal movements.

[0034] The determination unit can improve the determination accuracy by considering the customer's past purchase history and stay history. The determination unit improves the determination accuracy by considering, for example, the customer's past purchase history and stay history. The purchase history includes, for example, purchase date and time and purchased products, but is not limited to such examples. The stay history includes, for example, stay time and stay location, but is not limited to such examples. The determination unit estimates the current emotion, for example, based on products and services purchased by the customer in the past. The determination unit can also estimate the current emotion based on the place where the customer stayed in the past and the service used. Furthermore, the determination unit can analyze the customer's past purchase history and stay history and reflect the change pattern of emotion in the determination. As a result, more accurate emotion determination is possible by considering the past purchase history and stay history. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the judgment unit can input customer purchase history and stay history data into the generation AI and have the generation AI judge emotions.

[0035] The determination unit can analyze the surrounding environmental sound and background sound when determining the customer's emotion and use it as auxiliary information for emotion determination. For example, when determining the customer's emotion, the determination unit analyzes the surrounding environmental sound and background sound and use it as auxiliary information for emotion determination. The environmental sound includes, for example, voice collection by a microphone and a voice analysis algorithm, but is not limited to such examples. The background sound includes, for example, noise filtering and voice separation technology, but is not limited to such examples. For example, when the surroundings are noisy, the determination unit determines that the customer is stressed and guides the customer to a quiet place. In addition, when the surroundings are quiet, the determination unit can determine that the customer is relaxed and guide the customer to tourist information. Furthermore, when the surrounding environmental sound changes suddenly, the determination unit can determine that the customer's emotion has also changed and take appropriate measures. This makes it possible to perform more accurate emotion determination by analyzing the environmental sound and background sound. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the determination unit may be performed, for example, using AI, or may be performed without using AI. For example, the determination unit may input environmental sound or background sound data to the generation AI and cause the generation AI to perform emotion determination.

[0036] The guidance unit can select the optimal guidance method by referring to the past guidance history of the customer when providing guidance. The guidance unit, for example, selects the optimal guidance method by referring to the past guidance history of the customer when providing guidance. The guidance history includes, for example, database storage and history search, but is not limited to such examples. The guidance unit selects the current guidance method based on the guidance method used by the customer in the past, for example. The guidance unit can also select the most effective guidance method from the past guidance history of the customer. Furthermore, the guidance unit can analyze the past guidance history of the customer and select a guidance method that reflects a change pattern of emotions. This makes it possible to provide more appropriate guidance by referring to the past guidance history. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the guidance unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the guidance unit can input the guidance history data of the customer to the generation AI and cause the generation AI to select the guidance method.

[0037] The guidance unit can customize the guidance content according to the customer's current stay situation and purpose when providing guidance. The guidance unit customizes the guidance content according to the customer's current stay situation and purpose when providing guidance, for example. The stay situation includes, for example, the stay time and the stay location, but is not limited to such examples. The purpose includes, for example, the purpose of sightseeing and the purpose of business, but is not limited to such examples. For example, if the customer is staying for sightseeing, the guidance unit prioritizes the guidance of tourist information. In addition, if the customer is staying for business purposes, the guidance unit can also prioritize the guidance of business-related information. Furthermore, the guidance unit can customize the optimal guidance content according to the customer's stay situation and purpose. As a result, more appropriate guidance can be provided by providing guidance according to the stay situation and purpose. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the guidance unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the information section can input customer stay data and purpose data into the generation AI and have the generation AI customize the information content.

[0038] The guidance unit can provide optimal guidance contents in consideration of the geographical location information of the customer when providing guidance. The guidance unit provides optimal guidance contents in consideration of the geographical location information of the customer when providing guidance, for example. The geographical location information includes, for example, GPS data and location information services, but is not limited to such examples. For example, when the customer is near a hotel, the guidance unit provides nearby tourist information. In addition, when the customer is inside the hotel, the guidance unit can also prioritize guidance of facilities within the hotel. Furthermore, the guidance unit can provide optimal guidance contents based on the geographical location information of the customer. As a result, more appropriate guidance can be provided by taking the geographical location information into consideration. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the guidance unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the guidance unit can input the geographical location information data of the customer to the generation AI and cause the generation AI to generate the guidance contents.

[0039] The guidance unit can analyze the social media activity of the customer at the time of guidance and provide related guidance content. The guidance unit can, for example, analyze the social media activity of the customer at the time of guidance and provide related guidance content. Social media activity includes, for example, the content of posts and the number of likes, but is not limited to such examples. The guidance unit can provide guidance content based on, for example, places and events in which the customer showed interest on social media. The guidance unit can also estimate current interests and concerns from the social media activity of the customer and provide related guidance content. Furthermore, the guidance unit can analyze the social media activity of the customer and provide optimal guidance content. This makes it possible to provide more appropriate guidance by analyzing social media activity. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the guidance unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the guidance unit can input the social media data of the customer to the generation AI and cause the generation AI to generate the guidance content.

[0040] The notification unit can select the optimal notification method by referring to the past notification history of the customer at the time of notification. The notification unit, for example, refers to the past notification history of the customer at the time of notification and selects the optimal notification method. The notification history includes, for example, database storage and history search, but is not limited to such examples. The notification unit selects the current notification method, for example, based on the notification method used by the customer in the past. The notification unit can also select the most effective notification method from the past notification history of the customer. Furthermore, the notification unit can analyze the past notification history of the customer and select a notification method that reflects the change pattern of emotions. As a result, more appropriate notification can be made by referring to the past notification history. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input the notification history data of the customer to the generation AI and cause the generation AI to select the notification method.

[0041] The notification unit can customize the notification content according to the customer's current stay status and purpose at the time of notification. The notification unit customizes the notification content according to the customer's current stay status and purpose at the time of notification, for example. The stay status includes, for example, the stay time and the stay location, but is not limited to such examples. The purpose includes, for example, the purpose of tourism and the purpose of business, but is not limited to such examples. For example, if the customer is staying for tourism, the notification unit prioritizes the notification of tourist information. In addition, if the customer is staying for business purposes, the notification unit can also prioritize the notification of business-related information. Furthermore, the notification unit can customize the optimal notification content according to the customer's stay status and purpose. As a result, by providing a notification according to the stay status and purpose, a more appropriate response is possible. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input customer stay data and purpose data into the generation AI and have the generation AI customize the notification content.

[0042] The notification unit can provide optimal notification contents in consideration of the geographical location information of the customer at the time of notification. The notification unit, for example, provides optimal notification contents in consideration of the geographical location information of the customer at the time of notification. The geographical location information includes, for example, GPS data and location information services, but is not limited to such examples. For example, when the customer is near a hotel, the notification unit notifies the customer of nearby tourist information. In addition, when the customer is inside the hotel, the notification unit can also provide a notification that prioritizes guidance on facilities within the hotel. Furthermore, the notification unit can also provide optimal notification contents based on the geographical location information of the customer. As a result, more appropriate notification is possible by considering the geographical location information. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input the geographical location information data of the customer to the generation AI and cause the generation AI to execute generation of the notification content.

[0043] The notification unit can analyze the social media activity of the customer at the time of notification and provide related notification content. The notification unit can, for example, analyze the social media activity of the customer at the time of notification and provide related notification content. Social media activity includes, for example, the content of posts and the number of likes, but is not limited to such examples. The notification unit can provide notification content based on, for example, places and events in which the customer showed interest on social media. The notification unit can also estimate current interests and concerns from the social media activity of the customer and provide related notification content. Furthermore, the notification unit can analyze the social media activity of the customer and provide optimal notification content. This makes it possible to provide more appropriate notification by analyzing social media activity. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the notification unit can input the social media data of the customer to the generation AI and cause the generation AI to generate the notification content.

[0044] The acquisition unit can select the optimal acquisition method by referring to the customer's past behavior history at the time of acquisition. The acquisition unit, for example, refers to the customer's past behavior history at the time of acquisition and selects the optimal acquisition method. The behavior history includes, for example, database storage and history search, but is not limited to such examples. The acquisition unit acquires related information based on, for example, places visited by the customer in the past and services used by the customer. The acquisition unit can also estimate the customer's current interests and concerns from the customer's past behavior history and acquire optimal information. Furthermore, the acquisition unit can analyze the customer's past behavior history and select the most effective information acquisition method. As a result, more appropriate information acquisition is possible by referring to the past behavior history. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input customer behavior history data into the generation AI and have the generation AI select an information acquisition method.

[0045] The acquisition unit can customize the information to be acquired according to the customer's current stay situation and purpose at the time of acquisition. The acquisition unit customizes the information to be acquired according to the customer's current stay situation and purpose at the time of acquisition, for example. The stay situation includes, for example, a stay time and a stay location, but is not limited to such examples. The purpose includes, for example, a sightseeing purpose and a business purpose, but is not limited to such examples. For example, when the customer is staying for sightseeing, the acquisition unit preferentially acquires sightseeing information. In addition, when the customer is staying for business purposes, the acquisition unit can also preferentially acquire business-related information. Furthermore, the acquisition unit can customize and acquire optimal information according to the customer's stay situation and purpose. As a result, by acquiring information according to the stay situation and purpose, it becomes possible to provide more appropriate information. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the acquisition unit can input customer stay data and purpose data into the generation AI and have the generation AI customize the information.

[0046] The acquisition unit can preferentially acquire information with high relevance in consideration of the geographical location information of the customer at the time of acquisition. For example, the acquisition unit preferentially acquires information with high relevance in consideration of the geographical location information of the customer at the time of acquisition. The geographical location information includes, for example, GPS data and location information services, but is not limited to such examples. For example, when the customer is near a hotel, the acquisition unit preferentially acquires nearby tourist information. In addition, when the customer is inside the hotel, the acquisition unit can also preferentially acquire information on facilities within the hotel. Furthermore, the acquisition unit can also preferentially acquire optimal information based on the geographical location information of the customer. This makes it possible to acquire more appropriate information by considering the geographical location information. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the acquisition unit can input the customer's geographic location information data to the generation AI and cause the generation AI to acquire information.

[0047] The acquisition unit can analyze the social media activity of the customer at the time of acquisition and acquire related information. The acquisition unit, for example, analyzes the social media activity of the customer at the time of acquisition and acquires related information. The social media activity includes, for example, the content of posts and the number of likes, but is not limited to such examples. The acquisition unit acquires related information based on, for example, places and events in which the customer showed interest on social media. The acquisition unit can also estimate current interests and concerns from the social media activity of the customer and acquire related information. Furthermore, the acquisition unit can analyze the social media activity of the customer and acquire optimal information. This makes it possible to acquire more appropriate information by analyzing the social media activity. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input the social media data of the customer to the generation AI and cause the generation AI to execute information acquisition.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The automated reception system may further include a health management unit that monitors the health condition of the customer. The health management unit obtains biometric information such as the customer's body temperature, heart rate, and blood pressure, and evaluates the customer's health condition based on this data. For example, if the customer's body temperature is high, it may indicate a fever, so the system can provide information about nearby medical facilities. Also, if the customer's heart rate is abnormally high, it may indicate stress or tension, so the system can provide information about relaxation facilities. Furthermore, if the customer's blood pressure is high, advice can be provided to reduce health risks. This makes it possible to provide more personalized service by providing information according to the customer's health condition.

[0050] The automated reception system may further include a learning unit that learns the customer's preferences and hobbies. The learning unit learns the customer's preferences and hobbies based on the customer's past behavioral history, survey results, and the like. For example, it is possible to suggest new tourist spots and services that the customer may be interested in based on tourist spots that the customer has visited in the past and services that the customer has used. Also, if a customer likes restaurants of a particular genre, it is possible to introduce new restaurants of that genre. Furthermore, if a customer likes a particular activity, it is also possible to introduce events and facilities related to that activity. In this way, customer satisfaction can be improved by providing guidance that matches the customer's preferences and hobbies.

[0051] The automated reception system may further include a prediction unit that predicts the customer's behavior during their stay. The prediction unit predicts the customer's next behavior based on the customer's past behavior history and current situation. For example, if the customer has previously performed a specific activity at a specific time of day, a similar activity can be suggested for that time of day. Also, if the customer has a tendency to use a specific service after visiting a specific place, the service can be provided in advance. Furthermore, if the customer plans to participate in a specific event, information related to the event can be provided. This makes it possible to provide smoother service by predicting the customer's behavior and providing guidance.

[0052] The automated reception system may further include a translation unit that automatically translates the language of the customer. The translation unit automatically detects the customer's native language and translates the guidance content into that language. For example, guidance can be provided in English to an English-speaking customer, and in Chinese to a Chinese-speaking customer. In addition, if a customer speaks multiple languages, the translation unit can select the most appropriate language among them to provide guidance. Furthermore, if a customer uses specific technical terms, the translation unit can also appropriately translate the terms and provide guidance. This makes it possible to provide guidance to customers across language barriers, making it possible to accommodate international customers.

[0053] The automated reception system may further include a feedback unit that collects customer feedback. The feedback unit collects feedback on the services and guidance used by customers and uses it to improve the system. For example, a survey may be conducted to evaluate whether the customer is satisfied with the guidance. Also, if a customer is dissatisfied with a particular service, the service may be improved based on that feedback. Furthermore, if a customer suggests a new service or guidance content, the system may be updated based on that suggestion. In this way, better service may be provided by reflecting customer feedback.

[0054] The process flow of the first embodiment will be briefly described below.

[0055] Step 1: The determination unit determines the customer's emotions. Customer emotions include, for example, joy, anger, sadness, and the like. In order to analyze the customer's facial expression, the determination unit detects facial feature points and determines the emotion using a facial expression recognition algorithm. In addition, in order to analyze the tone of the customer's voice, it is also possible to determine the emotion by performing voice frequency analysis and volume analysis. For example, if the customer's voice tone is high, it is determined that the emotion indicates joy, and if the tone of the voice is low, it is determined that the emotion indicates sadness. Step 2: The guidance unit provides guidance to the customer based on the emotion determined by the determination unit. Guidance includes voice guidance and screen display. For example, if the customer is lively and happy, it can provide nearby tourist information, and if the customer is confused, it can provide a simple explanation of how to use the reception desk. Also, if the customer is tired, it can provide information about hot springs and relaxation facilities. Step 3: If the emotion determined by the determination unit is a specific emotion, the notification unit notifies the staff to prompt them to take action regarding the customer. The notification may include an alert sound or a message display. For example, if the customer is irritated, the staff may be notified to avoid trouble, and if the customer is behaving suspiciously, the staff may be notified to check for crime prevention.

[0056] (Example 2) The automated reception system according to the embodiment of the present invention is a system that recognizes the emotions of customers and provides guidance based on them. This system analyzes the customer's facial expressions and tone of voice to determine the emotions. Next, guidance is provided to the customer based on the determined emotions. For example, if the customer is lively and happy, the system provides tourist information about the surrounding area, and if the customer is confused, the system provides a simple explanation of how to use the reception. Also, if the customer is tired, the system provides information about hot springs and relaxation facilities, and if the customer is irritated, the staff will respond to avoid trouble. If suspicious movements are detected, a crime prevention check is performed. Furthermore, if a specific emotion value is determined, the staff is notified, leading to the staff's hospitality and response. For example, if the customer is irritated or behaving suspiciously, the staff is notified and can respond quickly. This system makes it possible to realize hospitality for customers even with an unmanned reception system and promote digital transformation of hotels. As a result, the automated reception system can realize hospitality for customers even with an unmanned reception system by recognizing the customer's emotions and providing appropriate guidance and notifications based on them.

[0057] The automated reception system according to the embodiment includes a determination unit, a guidance unit, and a notification unit. The determination unit determines the emotion of the customer. The emotion of the customer includes, for example, joy, anger, sadness, and the like, but is not limited to such examples. For example, in order to analyze the facial expression of the customer, the determination unit detects facial feature points and determines the emotion using a facial expression recognition algorithm. In addition, the determination unit can perform voice frequency analysis and volume analysis to analyze the tone of the customer's voice and determine the emotion. For example, the determination unit determines that the emotion of joy is indicated when the tone of the customer's voice is high. In addition, the determination unit can also determine that the emotion of sadness is indicated when the tone of the customer's voice is low. The guidance unit provides guidance to the customer based on the emotion determined by the determination unit. The guidance includes, for example, voice guidance and screen display, but is not limited to such examples. For example, when the customer is energetic and happy, the guidance unit provides tourist information about nearby areas. In addition, when the customer is confused, the guidance unit can gently explain how to use the reception. Furthermore, the guidance unit can provide guidance to hot springs or relaxation facilities if the customer is tired. The notification unit provides a notification to staff to encourage them to respond to the customer if the emotion determined by the determination unit is a specific emotion. The notification includes, for example, an alert sound or a message display, but is not limited to such examples. For example, if the customer is irritated, the notification unit notifies staff to avoid trouble. Furthermore, if the customer is behaving suspiciously, the notification unit can also notify staff to check for crime prevention. As a result, the automated reception system according to the embodiment can recognize the customer's emotions and provide appropriate guidance and notifications based on them, thereby realizing hospitality for customers even in an unmanned reception system.

[0058] The determination unit determines the emotion of the customer. The emotion of the customer includes, for example, joy, anger, sadness, etc., but is not limited to such examples. For example, in order to analyze the facial expression of the customer, the determination unit detects facial feature points and determines the emotion using a facial expression recognition algorithm. Specifically, the positions and shapes of the eyes, mouth, eyebrows, etc. are detected as facial feature points, and the emotion of the customer is determined by analyzing the changes in these feature points. For example, when the eyes are narrowed and the corners of the mouth are raised, it is determined that the emotion of joy is indicated. Also, when the eyebrows are lowered and the mouth is closed, it can be determined that the emotion of sadness is indicated. Furthermore, the determination unit can perform voice frequency analysis and volume analysis to analyze the tone of the customer's voice and determine the emotion. Specifically, in the voice frequency analysis, the frequency components of the customer's voice are analyzed, and when there are a lot of high frequency components, it is determined that the emotion of joy is indicated, and when there are a lot of low frequency components, it is determined that the emotion of sadness is indicated. Also, in the volume analysis, the volume of the voice is analyzed, and when there is a loud voice, it is determined that the emotion of anger is indicated, and when there is a quiet voice, it is determined that the emotion of sadness is indicated. This allows the determination unit to accurately determine the customer's emotions by analyzing the customer's facial expressions and tone of voice. Furthermore, the determination unit processes the analysis results in real time and can immediately determine the customer's emotions. This makes it possible to respond quickly according to the customer's emotions.

[0059] The guidance unit provides guidance to the customer based on the emotion determined by the determination unit. The guidance includes, for example, voice guidance and screen display, but is not limited to such examples. For example, when the customer is lively and happy, the guidance unit provides nearby tourist information. Specifically, when the customer is smiling and has a happy expression, the guidance unit provides nearby tourist spot and event information by voice guidance and screen display. In addition, when the customer is confused, the guidance unit can gently explain how to use the reception. Specifically, when the customer has a confused expression, the guidance unit provides voice guidance and screen display that carefully explains how to operate the reception and the usage procedure. Furthermore, when the customer is tired, the guidance unit can also provide guidance on hot springs and relaxation facilities. Specifically, when the customer has a tired expression, the guidance unit provides information on nearby hot spring facilities and relaxation facilities and guides the customer to places where he can refresh himself. This allows the guidance unit to provide appropriate guidance according to the customer's emotions, and improve customer satisfaction. Furthermore, the guidance unit can monitor the customer's reaction in real time and adjust the guidance content as appropriate. For example, if a customer shows no interest in the information, the information department can continue to attract the customer's interest by providing a different information content. This allows the information department to respond flexibly to customer needs, thereby further improving customer satisfaction.

[0060] The notification unit notifies the staff to prompt them to respond to the customer when the emotion determined by the determination unit is a specific emotion. The notification includes, for example, an alert sound and a message display, but is not limited to such examples. For example, when the customer is irritated, the notification unit notifies the staff to avoid trouble. Specifically, when the customer has an angry expression, the notification unit notifies the staff with an alert sound or a message display to prompt a quick response. In addition, when the customer is behaving suspiciously, the notification unit can also notify the staff to check for crime prevention. Specifically, when the customer is behaving suspiciously, the notification unit notifies the staff with an alert sound or a message display to prompt them to check the situation. In this way, the notification unit can provide an appropriate notification according to the customer's emotion or behavior, and can realize early detection of trouble and crime prevention measures. Furthermore, the notification unit can record the notification content and analyze it later. For example, the notification history regarding the customer's emotion or behavior can be saved and later checked by the staff, which can be used to improve the response and analyze the cause of the trouble. In this way, the notification unit can contribute to improving the quality of customer service and preventing the recurrence of trouble. Furthermore, the notification unit can combine multiple notification methods to reliably transmit information. For example, important information can be reliably conveyed to staff by using not only alert sounds and message displays, but also emails and SMS. This allows the notification unit to quickly and reliably transmit information and improve the quality of customer service.

[0061] The determination unit can determine the emotion of the customer based on the facial expression and tone of voice of the customer. For example, the determination unit detects facial feature points to analyze the facial expression of the customer and determines the emotion using a facial expression recognition algorithm. For example, the determination unit detects facial feature points of the customer and determines the emotion of joy when the customer is smiling. In addition, the determination unit can also determine the emotion of anger when the customer is frowning. Furthermore, the determination unit can perform voice frequency analysis and volume analysis to analyze the tone of the customer's voice and determine the emotion. For example, the determination unit determines that the emotion of joy is indicated when the tone of the customer's voice is high. In addition, the determination unit can also determine that the emotion of sadness is indicated when the tone of the customer's voice is low. This enables more accurate emotion determination by determining the emotion based on the facial expression and tone of voice 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. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit may input facial expression data of a customer to a generation AI and cause the generation AI to estimate emotions.

[0062] The determination unit determines an emotion value indicating the emotional state of the customer, and the notification unit can notify when the emotion value determined by the determination unit is a specific emotion value. The determination unit, for example, determines an emotion value indicating the emotional state of the customer. The emotion value includes, for example, a numerical scale and an evaluation standard, but is not limited to such examples. The determination unit, for example, analyzes the facial expression and tone of voice of the customer to calculate the emotion value. For example, the determination unit can calculate the emotion value based on the degree of the customer's smile and the pitch of the tone of the voice. The notification unit notifies when the emotion value determined by the determination unit is a specific emotion value. The specific emotion value includes, for example, a threshold setting and a specific numerical range, but is not limited to such examples. For example, the notification unit notifies the staff when the emotion value is high. In addition, the notification unit can also notify the staff to take a specific action when the emotion value is low. In this way, by notifying based on the emotion value, it is possible to quickly respond to a specific emotional state. 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 a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processes in the determination unit and the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the determination unit may input the emotion value of the customer to the generation AI and cause the generation AI to calculate the emotion value. Also, the notification unit may cause the generation AI to execute notification content based on the emotion value.

[0063] The guidance unit can provide guidance according to the emotion determined by the determination unit. The guidance unit provides guidance according to the emotion determined by the determination unit, for example. The guidance according to the emotion includes, for example, a guidance message or guidance means corresponding to the emotion, but is not limited to such an example. For example, when the customer is lively and happy, the guidance unit provides tourist information in a bright and cheerful tone. In addition, when the customer is confused, the guidance unit can also explain how to use the reception in a gentle tone. Furthermore, when the customer is tired, the guidance unit can also guide the customer to hot springs and relaxation facilities in a calm tone. This makes it possible to improve customer satisfaction by providing guidance according to the emotion of the customer. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such an example. A part or all of the above-mentioned processing in the guidance unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the guidance unit can input the emotion data of the customer to the generation AI and cause the generation AI to generate the guidance content.

[0064] The guidance unit can provide guidance according to the emotion, customer characteristics, and time period determined by the determination unit. The guidance unit provides guidance according to, for example, the emotion, customer characteristics, and time period determined by the determination unit. The customer characteristics include, for example, age, gender, purchase history, and the like, but are not limited to such examples. For example, if the customer is a young person, the guidance unit provides tourist information for young people. Also, if the customer is an elderly person, the guidance unit can provide relaxation facilities for elderly people. The time period includes, for example, morning, afternoon, and evening, but are not limited to such examples. For example, the guidance unit can provide breakfast guidance in the morning time period and dinner guidance in the evening time period. This makes it possible to provide a more personalized service by providing guidance according to the customer's attributes and time period. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the guidance unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the information section can input customer attribute data and time period data into the generation AI and have the generation AI generate the information content.

[0065] The acquisition unit acquires information indicating the behavior of the customer, the determination unit determines the abnormal behavior of the customer, and the notification unit can notify the staff of a crime prevention check when the determination unit determines the abnormal behavior of the customer. The acquisition unit, for example, acquires information indicating the behavior of the customer. The behavior includes, for example, the speed of movement and the pattern of movement, but is not limited to such examples. The acquisition unit, for example, captures the customer's movement with a camera and analyzes the speed and pattern of the movement. The determination unit determines the abnormal behavior of the customer based on the information acquired by the acquisition unit. The abnormal behavior includes, for example, a sudden change in the speed of movement and a movement that does not follow a specific pattern, but is not limited to such examples. For example, the determination unit determines the abnormal behavior when the customer's movement suddenly becomes faster. The determination unit can also determine the abnormal behavior when the customer's movement does not follow a specific pattern. The notification unit notifies the staff of a crime prevention check when the determination unit determines the abnormal behavior. The notification includes, for example, an alert sound and a message display, but is not limited to such examples. For example, when an abnormal movement is detected, the notification unit notifies the staff with an alert sound. Also, when an abnormal movement is detected, the notification unit can notify the staff with a message display. This makes it possible to detect suspicious movements and notify security checks, thereby enhancing security. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit, the determination unit, and the notification unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the acquisition unit can input data on the customer's movements to the generation AI and cause the generation AI to execute a judgment of abnormal movements. Also, the notification unit can cause the generation AI to execute the notification content based on the data on abnormal movements.

[0066] The determination unit can estimate the customer's emotion and dynamically adjust the determination algorithm based on the estimated customer's emotion. The determination unit, for example, estimates the customer's emotion and dynamically adjusts the determination algorithm based on the estimated customer's emotion. The determination algorithm includes, for example, a machine learning algorithm and a rule-based algorithm, but is not limited to such examples. For example, when the customer is smiling, the determination unit determines the emotion as positive and makes the guidance content brighter. In addition, when the customer is frowning, the determination unit can also determine the emotion as negative and make the guidance content calmer. Furthermore, when the customer has a blank expression, the determination unit can also determine the emotion as neutral and provide standard guidance content. This makes it possible to dynamically adjust the determination algorithm based on the customer's emotion, thereby enabling more appropriate guidance. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the judgment unit can input customer emotion data to the generation AI and cause the generation AI to adjust the judgment algorithm.

[0067] The determination unit can analyze the customer's past emotion history and reflect the emotion change pattern in the determination. The determination unit can, for example, analyze the customer's past emotion history and reflect the emotion change pattern in the determination. The emotion history includes, for example, database storage and time series analysis, but is not limited to such examples. For example, if the customer has visited many times in the past, the determination unit estimates the current emotion based on the past emotion history. In addition, if the customer has shown negative emotions in a specific situation in the past, the determination unit can also carefully handle similar situations. Furthermore, the determination unit can preferentially guide the customer to places and services where the customer has shown positive emotions in the past. This makes it possible to more accurately determine emotions by analyzing the past emotion history. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the judgment unit can input a customer's past emotional data into the generation AI and have the generation AI analyze patterns of changes in emotions.

[0068] The determination unit can determine the emotion using biometric information such as body temperature and heart rate in addition to the facial expression and tone of voice of the customer. The determination unit determines the emotion using biometric information such as body temperature and heart rate in addition to the facial expression and tone of voice of the customer. The biometric information includes, for example, a body temperature sensor and a heart rate monitor, but is not limited to such examples. For example, when the body temperature of the customer is high, the determination unit determines that the customer is in a stressed or excited state, and provides guidance that allows the customer to relax. In addition, when the heart rate of the customer is low, the determination unit can determine that the customer is in a relaxed state, and provide active guidance such as tourist information. Furthermore, when the biometric information of the customer changes suddenly, the determination unit can determine that an emergency response is required and notify the staff. This makes it possible to perform more accurate emotion determination by using the biometric information. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the judgment unit can input a customer's biometric data into the generation AI and have the generation AI judge emotions.

[0069] The determination unit can estimate the customer's emotion and adjust the reliability of the determination result based on the estimated customer's emotion. The determination unit, for example, estimates the customer's emotion and adjusts the reliability of the determination result based on the estimated customer's emotion. The reliability includes, for example, a probability value and a reliability interval, but is not limited to such examples. For example, when the customer's emotion is clearly determined, the determination unit provides guidance with a high reliability. In addition, when the customer's emotion is ambiguous, the determination unit can set the reliability low and prompt the staff to check. Furthermore, when the customer's emotion changes suddenly, the determination unit can reevaluate the reliability and take appropriate measures. As a result, more appropriate guidance can be provided by adjusting the reliability based on the emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the judgment unit can input customer emotion data to the generation AI and cause the generation AI to adjust the reliability.

[0070] The determination unit can improve the determination accuracy by considering the customer's past purchase history and stay history. The determination unit improves the determination accuracy by considering, for example, the customer's past purchase history and stay history. The purchase history includes, for example, purchase date and time and purchased products, but is not limited to such examples. The stay history includes, for example, stay time and stay location, but is not limited to such examples. The determination unit estimates the current emotion, for example, based on products and services purchased by the customer in the past. The determination unit can also estimate the current emotion based on the place where the customer stayed in the past and the service used. Furthermore, the determination unit can analyze the customer's past purchase history and stay history and reflect the change pattern of emotion in the determination. As a result, more accurate emotion determination is possible by considering the past purchase history and stay history. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the judgment unit can input customer purchase history and stay history data into the generation AI and have the generation AI judge emotions.

[0071] The determination unit can analyze the surrounding environmental sound and background sound when determining the customer's emotion and use it as auxiliary information for emotion determination. For example, when determining the customer's emotion, the determination unit analyzes the surrounding environmental sound and background sound and use it as auxiliary information for emotion determination. The environmental sound includes, for example, voice collection by a microphone and a voice analysis algorithm, but is not limited to such examples. The background sound includes, for example, noise filtering and voice separation technology, but is not limited to such examples. For example, when the surroundings are noisy, the determination unit determines that the customer is stressed and guides the customer to a quiet place. In addition, when the surroundings are quiet, the determination unit can determine that the customer is relaxed and guide the customer to tourist information. Furthermore, when the surrounding environmental sound changes suddenly, the determination unit can determine that the customer's emotion has also changed and take appropriate measures. This makes it possible to perform more accurate emotion determination by analyzing the environmental sound and background sound. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the determination unit may be performed, for example, using AI, or may be performed without using AI. For example, the determination unit may input environmental sound or background sound data to the generation AI and cause the generation AI to perform emotion determination.

[0072] The guidance unit can estimate the emotion of the customer and adjust the tone and expression of the guidance content based on the estimated emotion of the customer. The guidance unit, for example, estimates the emotion of the customer and adjusts the tone and expression of the guidance content based on the estimated emotion of the customer. The tone of the guidance content includes, for example, the pitch of the voice and the speed of speech, but is not limited to such examples. The expression method includes, for example, the use of words and gestures, but is not limited to such examples. For example, when the customer is lively and happy, the guidance unit guides the customer to tourist information in a bright and lively tone. In addition, when the customer is confused, the guidance unit can also explain how to use the reception in a gentle tone. Furthermore, when the customer is tired, the guidance unit can also guide the customer to hot springs and relaxation facilities in a calm tone. This makes it possible to provide more appropriate guidance by adjusting the guidance content based on the emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the guidance unit may be performed using, for example, AI, or may be performed without using AI. For example, the guidance unit may input customer emotion data to the generation AI and have the generation AI adjust the guidance content.

[0073] The guidance unit can select the optimal guidance method by referring to the past guidance history of the customer when providing guidance. The guidance unit, for example, selects the optimal guidance method by referring to the past guidance history of the customer when providing guidance. The guidance history includes, for example, database storage and history search, but is not limited to such examples. The guidance unit selects the current guidance method based on the guidance method used by the customer in the past, for example. The guidance unit can also select the most effective guidance method from the past guidance history of the customer. Furthermore, the guidance unit can analyze the past guidance history of the customer and select a guidance method that reflects a change pattern of emotions. This makes it possible to provide more appropriate guidance by referring to the past guidance history. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the guidance unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the guidance unit can input the guidance history data of the customer to the generation AI and cause the generation AI to select the guidance method.

[0074] The guidance unit can customize the guidance content according to the customer's current stay situation and purpose when providing guidance. The guidance unit customizes the guidance content according to the customer's current stay situation and purpose when providing guidance, for example. The stay situation includes, for example, the stay time and the stay location, but is not limited to such examples. The purpose includes, for example, the purpose of sightseeing and the purpose of business, but is not limited to such examples. For example, if the customer is staying for sightseeing, the guidance unit prioritizes the guidance of tourist information. In addition, if the customer is staying for business purposes, the guidance unit can also prioritize the guidance of business-related information. Furthermore, the guidance unit can customize the optimal guidance content according to the customer's stay situation and purpose. As a result, more appropriate guidance can be provided by providing guidance according to the stay situation and purpose. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the guidance unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the information section can input customer stay data and purpose data into the generation AI and have the generation AI customize the information content.

[0075] The guidance unit can estimate the emotion of the customer and determine the priority of guidance based on the estimated emotion of the customer. The guidance unit, for example, estimates the emotion of the customer and determines the priority of guidance based on the estimated emotion of the customer. The priority of guidance includes, for example, urgency and importance, but is not limited to such examples. For example, when the customer is irritated, the guidance unit prioritizes guidance that staff will handle in order to avoid trouble. In addition, when the customer is tired, the guidance unit can also prioritize guidance of hot springs and relaxation facilities. Furthermore, when the customer is energetic and happy, the guidance unit can also prioritize guidance of tourist information. As a result, more appropriate guidance can be provided by determining the priority of guidance based on emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the guidance unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the guidance unit can input customer emotion data into the generation AI and have the generation AI determine the priority of guidance.

[0076] The guidance unit can provide optimal guidance contents in consideration of the geographical location information of the customer when providing guidance. The guidance unit provides optimal guidance contents in consideration of the geographical location information of the customer when providing guidance, for example. The geographical location information includes, for example, GPS data and location information services, but is not limited to such examples. For example, when the customer is near a hotel, the guidance unit provides nearby tourist information. In addition, when the customer is inside the hotel, the guidance unit can also prioritize guidance of facilities within the hotel. Furthermore, the guidance unit can provide optimal guidance contents based on the geographical location information of the customer. As a result, more appropriate guidance can be provided by taking the geographical location information into consideration. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the guidance unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the guidance unit can input the geographical location information data of the customer to the generation AI and cause the generation AI to generate the guidance contents.

[0077] The guidance unit can analyze the social media activity of the customer at the time of guidance and provide related guidance content. The guidance unit can, for example, analyze the social media activity of the customer at the time of guidance and provide related guidance content. Social media activity includes, for example, the content of posts and the number of likes, but is not limited to such examples. The guidance unit can provide guidance content based on, for example, places and events in which the customer showed interest on social media. The guidance unit can also estimate current interests and concerns from the social media activity of the customer and provide related guidance content. Furthermore, the guidance unit can analyze the social media activity of the customer and provide optimal guidance content. This makes it possible to provide more appropriate guidance by analyzing social media activity. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the guidance unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the guidance unit can input the social media data of the customer to the generation AI and cause the generation AI to generate the guidance content.

[0078] The notification unit can estimate the customer's emotion and adjust the notification content based on the estimated customer's emotion. The notification unit, for example, estimates the customer's emotion and adjusts the notification content based on the estimated customer's emotion. The notification content includes, for example, message content and notification means, but is not limited to such examples. For example, when the customer is irritated, the notification unit quickly notifies the staff and encourages them to take action to avoid trouble. In addition, when the customer is tired, the notification unit can also notify the staff of relaxation facilities. Furthermore, when the customer is energetic and happy, the notification unit can also notify the staff of tourist information. This allows for more appropriate response by adjusting the notification content based on emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input customer emotion data into the generation AI and have the generation AI adjust the content of the notification.

[0079] The notification unit can select the optimal notification method by referring to the past notification history of the customer at the time of notification. The notification unit, for example, refers to the past notification history of the customer at the time of notification and selects the optimal notification method. The notification history includes, for example, database storage and history search, but is not limited to such examples. The notification unit selects the current notification method, for example, based on the notification method used by the customer in the past. The notification unit can also select the most effective notification method from the past notification history of the customer. Furthermore, the notification unit can analyze the past notification history of the customer and select a notification method that reflects the change pattern of emotions. As a result, more appropriate notification can be made by referring to the past notification history. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input the notification history data of the customer to the generation AI and cause the generation AI to select the notification method.

[0080] The notification unit can customize the notification content according to the customer's current stay status and purpose at the time of notification. The notification unit customizes the notification content according to the customer's current stay status and purpose at the time of notification, for example. The stay status includes, for example, the stay time and the stay location, but is not limited to such examples. The purpose includes, for example, the purpose of tourism and the purpose of business, but is not limited to such examples. For example, if the customer is staying for tourism, the notification unit prioritizes the notification of tourist information. In addition, if the customer is staying for business purposes, the notification unit can also prioritize the notification of business-related information. Furthermore, the notification unit can customize the optimal notification content according to the customer's stay status and purpose. As a result, by providing a notification according to the stay status and purpose, a more appropriate response is possible. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input customer stay data and purpose data into the generation AI and have the generation AI customize the notification content.

[0081] The notification unit can estimate the emotion of the customer and determine the priority of the notification based on the estimated emotion of the customer. The notification unit, for example, estimates the emotion of the customer and determines the priority of the notification based on the estimated emotion of the customer. The priority of the notification includes, for example, urgency and importance, but is not limited to such examples. For example, when the customer is irritated, the notification unit prioritizes a notification that the staff will respond to in order to avoid trouble. In addition, when the customer is tired, the notification unit can also prioritize a notification of a relaxation facility. Furthermore, when the customer is energetic and having fun, the notification unit can also prioritize a notification of tourist information. This enables a more appropriate response by determining the priority of the notification based on the emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input customer emotion data into the generation AI and have the generation AI determine the priority of notifications.

[0082] The notification unit can provide optimal notification contents in consideration of the geographical location information of the customer at the time of notification. The notification unit, for example, provides optimal notification contents in consideration of the geographical location information of the customer at the time of notification. The geographical location information includes, for example, GPS data and location information services, but is not limited to such examples. For example, when the customer is near a hotel, the notification unit notifies the customer of nearby tourist information. In addition, when the customer is inside the hotel, the notification unit can also provide a notification that prioritizes guidance on facilities within the hotel. Furthermore, the notification unit can also provide optimal notification contents based on the geographical location information of the customer. As a result, more appropriate notification is possible by considering the geographical location information. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input the geographical location information data of the customer to the generation AI and cause the generation AI to execute generation of the notification content.

[0083] The notification unit can analyze the social media activity of the customer at the time of notification and provide related notification content. The notification unit can, for example, analyze the social media activity of the customer at the time of notification and provide related notification content. Social media activity includes, for example, the content of posts and the number of likes, but is not limited to such examples. The notification unit can provide notification content based on, for example, places and events in which the customer showed interest on social media. The notification unit can also estimate current interests and concerns from the social media activity of the customer and provide related notification content. Furthermore, the notification unit can analyze the social media activity of the customer and provide optimal notification content. This makes it possible to provide more appropriate notification by analyzing social media activity. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the notification unit can input the social media data of the customer to the generation AI and cause the generation AI to generate the notification content.

[0084] The acquisition unit can estimate the customer's emotion and adjust the type of information to be acquired based on the estimated customer's emotion. The acquisition unit, for example, estimates the customer's emotion and adjusts the type of information to be acquired based on the estimated customer's emotion. The type of information to be acquired includes, for example, the customer's attributes and current situation, but is not limited to such examples. For example, when the customer is lively and having fun, the acquisition unit preferentially acquires tourist information and activity information. In addition, when the customer is tired, the acquisition unit can also preferentially acquire information on relaxation facilities and rest spots. Furthermore, when the customer is irritated, the acquisition unit can also preferentially acquire information for avoiding trouble. This makes it possible to provide more appropriate information by adjusting the type of information to be acquired based on emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input customer emotion data into the generation AI and cause the generation AI to adjust the type of information to be acquired.

[0085] The acquisition unit can select the optimal acquisition method by referring to the customer's past behavior history at the time of acquisition. The acquisition unit, for example, refers to the customer's past behavior history at the time of acquisition and selects the optimal acquisition method. The behavior history includes, for example, database storage and history search, but is not limited to such examples. The acquisition unit acquires related information based on, for example, places visited by the customer in the past and services used by the customer. The acquisition unit can also estimate the customer's current interests and concerns from the customer's past behavior history and acquire optimal information. Furthermore, the acquisition unit can analyze the customer's past behavior history and select the most effective information acquisition method. As a result, more appropriate information acquisition is possible by referring to the past behavior history. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input customer behavior history data into the generation AI and have the generation AI select an information acquisition method.

[0086] The acquisition unit can customize the information to be acquired according to the customer's current stay situation and purpose at the time of acquisition. The acquisition unit customizes the information to be acquired according to the customer's current stay situation and purpose at the time of acquisition, for example. The stay situation includes, for example, a stay time and a stay location, but is not limited to such examples. The purpose includes, for example, a sightseeing purpose and a business purpose, but is not limited to such examples. For example, when the customer is staying for sightseeing, the acquisition unit preferentially acquires sightseeing information. In addition, when the customer is staying for business purposes, the acquisition unit can also preferentially acquire business-related information. Furthermore, the acquisition unit can customize and acquire optimal information according to the customer's stay situation and purpose. As a result, by acquiring information according to the stay situation and purpose, it becomes possible to provide more appropriate information. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the acquisition unit can input customer stay data and purpose data into the generation AI and have the generation AI customize the information.

[0087] The acquisition unit can estimate the customer's emotion and determine the priority of information to be acquired based on the estimated customer's emotion. The acquisition unit, for example, estimates the customer's emotion and determines the priority of information to be acquired based on the estimated customer's emotion. The priority of information includes, for example, urgency and importance, but is not limited to such examples. For example, when the customer is irritated, the acquisition unit preferentially acquires information for avoiding trouble. In addition, when the customer is tired, the acquisition unit can also preferentially acquire information on relaxation facilities and rest spots. Furthermore, when the customer is energetic and having fun, the acquisition unit can also preferentially acquire tourist information and activity information. This makes it possible to provide more appropriate information by determining the priority of information based on emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input customer emotion data into the generation AI and have the generation AI determine the priority of the information.

[0088] The acquisition unit can preferentially acquire information with high relevance in consideration of the geographical location information of the customer at the time of acquisition. For example, the acquisition unit preferentially acquires information with high relevance in consideration of the geographical location information of the customer at the time of acquisition. The geographical location information includes, for example, GPS data and location information services, but is not limited to such examples. For example, when the customer is near a hotel, the acquisition unit preferentially acquires nearby tourist information. In addition, when the customer is inside the hotel, the acquisition unit can also preferentially acquire information on facilities within the hotel. Furthermore, the acquisition unit can also preferentially acquire optimal information based on the geographical location information of the customer. This makes it possible to acquire more appropriate information by considering the geographical location information. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the acquisition unit can input the customer's geographic location information data to the generation AI and cause the generation AI to acquire information.

[0089] The acquisition unit can analyze the social media activity of the customer at the time of acquisition and acquire related information. The acquisition unit, for example, analyzes the social media activity of the customer at the time of acquisition and acquires related information. The social media activity includes, for example, the content of posts and the number of likes, but is not limited to such examples. The acquisition unit acquires related information based on, for example, places and events in which the customer showed interest on social media. The acquisition unit can also estimate current interests and concerns from the social media activity of the customer and acquire related information. Furthermore, the acquisition unit can analyze the social media activity of the customer and acquire optimal information. This makes it possible to acquire more appropriate information by analyzing the social media activity. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input the social media data of the customer to the generation AI and cause the generation AI to execute information acquisition.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The automated reception system may further include a health management unit that monitors the health condition of the customer. The health management unit obtains biometric information such as the customer's body temperature, heart rate, and blood pressure, and evaluates the customer's health condition based on this data. For example, if the customer's body temperature is high, it may indicate a fever, so the system can provide information about nearby medical facilities. Also, if the customer's heart rate is abnormally high, it may indicate stress or tension, so the system can provide information about relaxation facilities. Furthermore, if the customer's blood pressure is high, advice can be provided to reduce health risks. This makes it possible to provide more personalized service by providing information according to the customer's health condition.

[0092] The automated reception system may further include a learning unit that learns the customer's preferences and hobbies. The learning unit learns the customer's preferences and hobbies based on the customer's past behavioral history, survey results, and the like. For example, it is possible to suggest new tourist spots and services that the customer may be interested in based on tourist spots that the customer has visited in the past and services that the customer has used. Also, if a customer likes restaurants of a particular genre, it is possible to introduce new restaurants of that genre. Furthermore, if a customer likes a particular activity, it is also possible to introduce events and facilities related to that activity. In this way, customer satisfaction can be improved by providing guidance that matches the customer's preferences and hobbies.

[0093] The automated reception system may further include a prediction unit that predicts the customer's behavior during their stay. The prediction unit predicts the customer's next behavior based on the customer's past behavior history and current situation. For example, if the customer has previously performed a specific activity at a specific time of day, a similar activity can be suggested for that time of day. Also, if the customer has a tendency to use a specific service after visiting a specific place, the service can be provided in advance. Furthermore, if the customer plans to participate in a specific event, information related to the event can be provided. This makes it possible to provide smoother service by predicting the customer's behavior and providing guidance.

[0094] The automated reception system may further include a translation unit that automatically translates the language of the customer. The translation unit automatically detects the customer's native language and translates the guidance content into that language. For example, guidance can be provided in English to an English-speaking customer, and in Chinese to a Chinese-speaking customer. In addition, if a customer speaks multiple languages, the translation unit can select the most appropriate language among them to provide guidance. Furthermore, if a customer uses specific technical terms, the translation unit can also appropriately translate the terms and provide guidance. This makes it possible to provide guidance to customers across language barriers, making it possible to accommodate international customers.

[0095] The automated reception system may further include a feedback unit that collects customer feedback. The feedback unit collects feedback on the services and guidance used by customers and uses it to improve the system. For example, a survey may be conducted to evaluate whether the customer is satisfied with the guidance. Also, if a customer is dissatisfied with a particular service, the service may be improved based on that feedback. Furthermore, if a customer suggests a new service or guidance content, the system may be updated based on that suggestion. In this way, better service may be provided by reflecting customer feedback.

[0096] The automated reception system can further estimate the customer's emotions and adjust the tone and expression of the guidance based on the estimated customer's emotions. For example, if the customer is cheerful and happy, tourist information can be provided in a bright and cheerful tone. If the customer is confused, how to use the reception can be explained in a gentle tone. Furthermore, if the customer is tired, hot springs and relaxation facilities can be provided in a calm tone. In this way, customer satisfaction can be improved by providing guidance that matches the customer's emotions.

[0097] The automated reception system can further estimate the customer's emotions and prioritize the information provided based on the estimated customer's emotions. For example, if a customer is irritated, it can prioritize providing information to staff to avoid trouble. If the customer is tired, it can prioritize providing information about hot springs and relaxation facilities. Furthermore, if the customer is energetic and happy, it can prioritize providing tourist information. In this way, it becomes possible to provide more appropriate guidance by prioritizing the information provided based on the customer's emotions.

[0098] The automated reception system can further estimate the customer's emotions and customize the guidance content based on the estimated customer's emotions. For example, if the customer is energetic and happy, it can provide information about activities and events. If the customer is confused, it can prioritize guidance on how to use the system and basic information. Furthermore, if the customer is tired, it can provide guidance on relaxation facilities and rest spots. This makes it possible to provide more personalized service by customizing the guidance content according to the customer's emotions.

[0099] The automated reception system can further estimate the customer's emotions and adjust the timing of guidance based on the estimated customer's emotions. For example, if a customer is irritated, a staff member can immediately provide the appropriate guidance. Also, if the customer is tired, the system can provide early guidance on relaxation facilities. Furthermore, if the customer is energetic and happy, the system can provide tourist information at an appropriate time. In this way, more appropriate service can be provided by adjusting the timing of guidance based on the customer's emotions.

[0100] The automated reception system can further estimate the customer's emotions and adjust the reliability of the guidance content based on the estimated customer's emotions. For example, if the customer's emotions are clearly determined, guidance can be provided with a high reliability. If the customer's emotions are unclear, the reliability can be set low to prompt staff to check. Furthermore, if the customer's emotions change suddenly, the reliability can be reevaluated and appropriate action can be taken. This makes it possible to provide more appropriate guidance by adjusting the reliability of the guidance content based on the customer's emotions.

[0101] The process flow of the second embodiment will be briefly described below.

[0102] Step 1: The determination unit determines the customer's emotions. Customer emotions include, for example, joy, anger, sadness, and the like. In order to analyze the customer's facial expression, the determination unit detects facial feature points and determines the emotion using a facial expression recognition algorithm. In addition, in order to analyze the tone of the customer's voice, it is also possible to determine the emotion by performing voice frequency analysis and volume analysis. For example, if the customer's voice tone is high, it is determined that the emotion indicates joy, and if the tone of the voice is low, it is determined that the emotion indicates sadness. Step 2: The guidance unit provides guidance to the customer based on the emotion determined by the determination unit. Guidance includes voice guidance and screen display. For example, if the customer is lively and happy, it can provide nearby tourist information, and if the customer is confused, it can provide a simple explanation of how to use the reception desk. Also, if the customer is tired, it can provide information about hot springs and relaxation facilities. Step 3: If the emotion determined by the determination unit is a specific emotion, the notification unit notifies the staff to prompt them to take action regarding the customer. The notification may include an alert sound or a message display. For example, if the customer is irritated, the staff may be notified to avoid trouble, and if the customer is behaving suspiciously, the staff may be notified to check for crime prevention.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12. For example, the guidance unit is realized by the control unit 46A of the smart device 14. For example, the notification unit is realized by the specific processing unit 290 of the data processing device 12. For example, the acquisition unit is realized by the camera 42 of the smart device 14. For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12. For example, the notification unit is realized by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12. For example, the guidance unit is realized by the control unit 46A of the smart glasses 214. For example, the notification unit is realized by the specific processing unit 290 of the data processing device 12. For example, the acquisition unit is realized by the camera 42 of the smart glasses 214. For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12. For example, the notification unit is realized by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12. For example, the guidance unit is realized by the control unit 46A of the headset type terminal 314. For example, the notification unit is realized by the specific processing unit 290 of the data processing device 12. For example, the acquisition unit is realized by the camera 42 of the headset type terminal 314. For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12. For example, the notification unit is realized by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12. For example, the guidance unit is realized by the control unit 46A of the robot 414. For example, the notification unit is realized by the specific processing unit 290 of the data processing device 12. For example, the acquisition unit is realized by the camera 42 of the robot 414. For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12. For example, the notification unit is realized by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0160] 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.

[0161] 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."

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] (Appendix 1) A determination unit for determining customer emotions; a guidance unit that provides guidance to the customer based on the emotion determined by the determination unit; a notification unit that notifies a staff member to prompt the staff member to take action when the emotion determined by the determination unit is a predetermined emotion. A system characterized by: (Appendix 2) The determination unit is Determining the customer's emotions based on the customer's facial expressions and tone of voice. 2. The system of claim 1, (Appendix 3) The determination unit is determining an emotion value indicative of an emotional state of the customer; The notification unit is When the emotion value determined by the determination unit is a specific emotion value, the notification is performed. 2. The system of claim 1, (Appendix 4) The guide unit is Providing guidance according to the emotion determined by the determination unit 2. The system of claim 1, (Appendix 5) The guide unit is Providing guidance according to the emotion determined by the determination unit, the customer's characteristics, and the time period 2. The system of claim 1, (Appendix 6) An acquisition unit that acquires information indicating customer behavior, The determination unit is Determining abnormal behavior of the customer; The notification unit is When the determination unit determines that the customer is behaving abnormally, a staff member is notified of a crime prevention check. 2. The system of claim 1, (Appendix 7) The determination unit is Infer customer sentiment and dynamically adjust the judgment algorithm based on the inferred customer sentiment 2. The system of claim 1, (Appendix 8) The determination unit is Analyze the customer's past emotion history and reflect the emotion change patterns in the judgment 2. The system of claim 1, (Appendix 9) The determination unit is In addition to facial expressions and tone of voice, the system uses biometric information such as body temperature and heart rate to determine a customer's emotions. 2. The system of claim 1, (Appendix 10) The determination unit is Inferring customer sentiment and adjusting the confidence of the judgment result based on the estimated customer sentiment 2. The system of claim 1, (Appendix 11) The determination unit is Improve accuracy of judgment by considering customers' past purchase history and stay history 2. The system of claim 1, (Appendix 12) The determination unit is When determining a customer's emotions, the surrounding environmental and background sounds are analyzed and used as auxiliary information for emotion determination. 2. The system of claim 1, (Appendix 13) The guide unit is Infer customer sentiment and adjust the tone and language of your communications based on that sentiment 2. The system of claim 1, (Appendix 14) The guide unit is When providing guidance, refer to the customer's past guidance history and select the most appropriate guidance method. 2. The system of claim 1, (Appendix 15) The guide unit is When providing guidance, customize the content of the guidance according to the customer's current stay status and purpose. 2. The system of claim 1, (Appendix 16) The guide unit is Estimate customer sentiment and prioritize announcements based on the estimated customer sentiment 2. The system of claim 1, (Appendix 17) The guide unit is When providing guidance, provide optimal guidance content by considering the customer's geographic location information 2. The system of claim 1, (Appendix 18) The guide unit is Analyze customers' social media activity when providing information to them and provide them with relevant information 2. The system of claim 1, (Appendix 19) The notification unit is Infer customer sentiment and tailor notifications based on the inferred sentiment 2. The system of claim 1, (Appendix 20) The notification unit is When notifying, refer to the customer's past notification history and select the optimal notification method. 2. The system of claim 1, (Appendix 21) The notification unit is Customize the notification content based on the customer's current status and purpose 2. The system of claim 1, (Appendix 22) The notification unit is Estimate customer sentiment and prioritize notifications based on estimated customer sentiment 2. The system of claim 1, (Appendix 23) The notification unit is When sending notifications, the system considers the geographic location of the customer to provide the most appropriate notification content. 2. The system of claim 1, (Appendix 24) The notification unit is At the time of notification, analyze the social media activity of customers and provide relevant notification content 2. The system of claim 1, (Appendix 25) The acquisition unit is Infer customer sentiment and adjust the type of information you get based on the inferred customer sentiment 2. The system of claim 1, (Appendix 26) The acquisition unit is When acquiring data, the system refers to the customer's past behavioral history and selects the optimal acquisition method. 2. The system of claim 1, (Appendix 27) The acquisition unit is At the time of acquisition, customize the information acquired based on the customer's current stay status and purpose 2. The system of claim 1, (Appendix 28) The acquisition unit is Estimate customer sentiment and prioritize information to be retrieved based on the estimated customer sentiment 2. The system of claim 1, (Appendix 29) The acquisition unit is At the time of retrieval, the geographic location of the customer is taken into account to prioritize retrieval of the most relevant information 2. The system of claim 1, (Appendix 30) The acquisition unit is Upon capture, analyze your social media activity to capture relevant information 2. The system of claim 1, [Explanation of symbols]

[0175] 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. A determination unit for determining customer emotions; a guidance unit that provides guidance to the customer based on the emotion determined by the determination unit; a notification unit that notifies a staff member to prompt the staff member to take action when the emotion determined by the determination unit is a predetermined emotion. A system characterized by:

2. The determination unit is Determining the customer's emotions based on the customer's facial expressions and tone of voice.

2. The system of claim 1 .

3. The determination unit is determining an emotion value indicative of an emotional state of the customer; The notification unit is When the emotion value determined by the determination unit is a specific emotion value, the notification is performed.

2. The system of claim 1 .

4. The guide portion is Providing guidance according to the emotion determined by the determination unit 2. The system of claim 1 .

5. The guide portion is Providing guidance according to the emotion determined by the determination unit, the customer's characteristics, and the time period 2. The system of claim 1 .

6. An acquisition unit that acquires information indicating the behavior of the customer, The determination unit is determining abnormal behavior of the customer; The notification unit is When the determination unit determines that the customer is behaving abnormally, a staff member is notified of a crime prevention check.

2. The system of claim 1 .

7. The determination unit is Estimating the customer's sentiment and dynamically adjusting a judgment algorithm based on the estimated customer's sentiment.

2. The system of claim 1 .

8. The determination unit is The past emotion history of the customer is analyzed, and emotion change patterns are reflected in the judgment.

2. The system of claim 1 .

Images