system

Abstract

The system according to this embodiment aims to streamline inquiry handling and provide appropriate responses based on the user's emotional state. [Solution] The system according to the embodiment comprises an analysis unit, a reception unit, a generation unit, an emotion analysis unit, and an escalation unit. The analysis unit analyzes text, images, and audio. The reception unit receives inquiries. The generation unit generates responses based on the results analyzed by the analysis unit. The emotion analysis unit performs real-time emotion analysis. The escalation unit performs escalation based on the emotional state detected by the emotion analysis unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the efficiency of inquiry response and appropriate response based on the emotional state of the user are not sufficiently achieved, and there is room for improvement.

[0005] The system according to the embodiment aims to improve the efficiency of inquiry response and make appropriate responses based on the emotional state of the user.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a reception unit, a generation unit, an emotion analysis unit, and an escalation unit. The analysis unit analyzes text, images, and audio. The reception unit receives inquiries. The generation unit generates responses based on the results analyzed by the analysis unit. The emotion analysis unit performs real-time emotion analysis. The escalation unit performs escalation based on the emotional state detected by the emotion analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can streamline inquiry handling and provide appropriate responses based on the user's emotional state. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The chatbot system according to an embodiment of the present invention is an advanced chatbot that utilizes multimodal AI capable of analyzing text, images, and audio to respond to inquiries from merchants 24 / 7. This chatbot system provides rapid and efficient support to merchants, improving merchant satisfaction and ultimately promoting increased transaction volume and commissions. It also includes a real-time sentiment analysis function to detect the user's emotional state and quickly escalate the issue to a specialized support team. For example, it responds to inquiries from merchants using multimodal AI capable of analyzing text, images, and audio. For instance, if a merchant makes a text-based inquiry, the generating AI uses natural language processing technology to provide an accurate and rapid response. If an image is sent, the generating AI analyzes the image and suggests the optimal location for a QR code (registered trademark) based on, for example, a store layout image. Furthermore, if a voice message is sent, the generating AI converts the voice into text and provides a response similar to the text analysis. Next, the chatbot is multilingual, supporting not only Japanese but also multiple other languages. This enhances support for foreign owners and staff. For example, the generating AI responds quickly and accurately to inquiries in multiple languages ​​such as English and Chinese. Furthermore, the chatbot is equipped with advanced FAQ functionality, not only providing instant answers to frequently asked questions but also learning from past inquiry history to offer more accurate support. For example, if a similar inquiry has been made in the past, it can quickly provide an answer based on that history. It also has troubleshooting capabilities, automatically detecting problems such as payment issues and system errors and suggesting solutions. It can also escalate issues to a specialized support team if necessary. For example, if a payment error occurs, the generated AI will identify the cause and suggest a solution. In addition, the chatbot analyzes merchant transaction data and provides specific advice to improve sales. For example, it can improve sales by suggesting that campaigns be run during specific time periods. Finally, a real-time sentiment analysis function detects the user's emotional state and quickly escalates to a specialized support team if the customer is feeling frustrated.This will further enhance the customer experience and dramatically improve the speed of problem resolution. This multimodal AI chatbot will be a powerful tool to strengthen merchant support and drive increased transaction volume and commissions. By providing fast and accurate support, it will improve merchant satisfaction and ultimately contribute to business growth. In addition, real-time sentiment analysis capabilities will further enhance the customer experience and dramatically improve the speed of problem resolution. As a result, the chatbot system will provide fast and efficient support to merchants, improve merchant satisfaction, and ultimately drive increased transaction volume and commissions.

[0029] The chatbot system according to this embodiment comprises an analysis unit, a reception unit, a generation unit, an emotion analysis unit, and an escalation unit. The analysis unit analyzes text, images, and audio. The analysis unit uses, for example, natural language processing technology to perform text analysis. For example, the analysis unit uses morphological analysis to analyze the meaning of text. The analysis unit also uses image recognition technology to perform image analysis. For example, the analysis unit uses an object detection algorithm to identify objects in an image. The analysis unit also uses speech recognition technology to perform audio analysis. For example, the analysis unit uses a speech recognition algorithm to convert audio into text. The reception unit receives inquiries. The reception unit can receive inquiries in the form of text, images, and audio. For example, the reception unit can receive text messages. The reception unit can also receive image files. The reception unit can also receive audio messages. The generation unit generates responses based on the results analyzed by the analysis unit. The generation unit generates responses using, for example, a generation AI. For example, the generation unit generates responses in natural language using a text generation AI. The generation unit can also generate image-based responses using image generation AI. The generation unit can also generate voice-based responses using voice generation AI. The sentiment analysis unit performs real-time sentiment analysis. For example, the sentiment analysis unit estimates emotions by analyzing a user's text messages. For example, the sentiment analysis unit extracts emotions from text using natural language processing technology. The sentiment analysis unit can also estimate emotions by analyzing a user's voice messages. For example, the sentiment analysis unit extracts emotions from voice using voice analysis technology. The sentiment analysis unit can also estimate emotions by analyzing a user's images. For example, the sentiment analysis unit extracts emotions from facial expressions using image analysis technology. The escalation unit performs escalation based on the emotional state detected by the sentiment analysis unit. For example, if a user is feeling frustrated, the escalation unit escalates the issue to a specialized support team. For example, if the sentiment analysis unit detects frustration, the escalation unit immediately notifies the support team.Furthermore, the escalation unit can quickly escalate a user's case if they require urgent support. For example, if the sentiment analysis unit detects an urgent emotional state, the escalation unit immediately notifies the support team. As a result, the chatbot system according to this embodiment can provide fast and efficient support by analyzing text, images, and audio, performing real-time sentiment analysis, and escalating as needed.

[0030] The analysis unit analyzes text, images, and audio. For example, the analysis unit uses natural language processing technology to perform text analysis. Specifically, it uses morphological analysis to analyze the meaning of text and understand its context and intent. Morphological analysis is a technology that divides text into words and identifies the part of speech and meaning of each word. This allows for accurate understanding of user inquiries and appropriate responses. The analysis unit also uses image recognition technology to perform image analysis. For example, it uses an object detection algorithm to identify objects in an image and recognize their type and location. An object detection algorithm is a technology that identifies specific patterns and features in an image and classifies objects based on them. This allows for the extraction of necessary information from images sent by users and enables appropriate responses. Furthermore, the analysis unit uses speech recognition technology to perform audio analysis. For example, it uses a speech recognition algorithm to convert audio into text and analyze that text. A speech recognition algorithm is a technology that analyzes audio signals and identifies phonemes and words. This allows for accurate understanding of content and appropriate responses even when users make inquiries by voice. The analysis unit combines these technologies to analyze diverse data such as text, images, and audio, enabling a comprehensive understanding of user inquiries.

[0031] The reception department receives inquiries. The reception department can receive inquiries in the form of text, images, and audio. Specifically, it provides an interface for receiving text messages and receives text entered by users. It also provides an interface for receiving image files and receives images uploaded by users. Furthermore, it provides an interface for receiving audio messages and receives audio recorded by users. Through these interfaces, the reception department can receive a variety of inquiries from users. For example, if a user sends a text message, the reception department receives the message and sends it to the analysis department. If a user uploads an image, the reception department receives the image and sends it to the analysis department. If a user records and sends an audio message, the reception department receives the audio and sends it to the analysis department. This allows the reception department to quickly and accurately receive inquiries from users and forward them to the analysis department.

[0032] The generation unit generates answers based on the results analyzed by the analysis unit. The generation unit generates answers using, for example, generation AI. Specifically, it generates answers in natural language using text generation AI. Text generation AI is a technology that generates appropriate answers based on the user's inquiry and the analysis results. For example, if a user asks about how to use a product, the generation unit generates an answer that includes specific procedures and advice. The generation unit can also generate image-based answers using image generation AI. For example, if a user sends an image of a faulty part of a product, the generation unit analyzes the image and generates and provides images of repair methods and replacement parts. Furthermore, the generation unit can also generate voice-based answers using voice generation AI. For example, if a user makes an inquiry by voice, the generation unit generates a voice response to that inquiry and provides it to the user. By combining these technologies, the generation unit can generate the optimal answer to the user's inquiry and provide it quickly and accurately.

[0033] The sentiment analysis unit performs real-time sentiment analysis. For example, the sentiment analysis unit estimates emotions by analyzing a user's text messages. Specifically, it extracts emotions from text using natural language processing technology. Natural language processing technology is a technique that analyzes the emotional meaning of words and phrases in text and estimates the user's emotional state. For example, if a user uses words that express dissatisfaction or anger, the sentiment analysis unit detects that emotion and takes an appropriate response. The sentiment analysis unit can also estimate emotions by analyzing a user's voice messages. Specifically, it extracts emotions from voice using voice analysis technology. Voice analysis technology is a technique that analyzes the characteristics of a voice signal and estimates the user's emotional state. For example, it analyzes the tone, pitch, and speed of the user's voice to determine whether the user is tense or relaxed. Furthermore, the sentiment analysis unit can also estimate emotions by analyzing a user's image. Specifically, it extracts emotions from facial expressions using image analysis technology. Image analysis technology is a technique that analyzes facial expressions, eye movements, mouth shapes, etc., and estimates the user's emotional state. For example, if a user is smiling, the emotion analysis unit detects that emotion and takes appropriate action. By combining these technologies, the emotion analysis unit can comprehensively understand the user's emotional state and take appropriate action in real time.

[0034] The escalation unit performs escalation based on the emotional state detected by the emotion analysis unit. For example, if a user is feeling frustrated, the escalation unit will escalate the issue to a specialized support team. Specifically, if the emotion analysis unit detects user frustration, the escalation unit immediately notifies the support team and requests assistance. The support team can understand the user's inquiry and emotional state and provide appropriate support. The escalation unit can also quickly escalate if the user requires urgent support. Specifically, if the emotion analysis unit detects an urgent emotional state of the user, the escalation unit immediately notifies the support team and requests prompt assistance. The support team can understand the user's urgent inquiry and emotional state and provide prompt and appropriate support. Through these functions, the escalation unit can provide appropriate support according to the user's emotional state and offer fast and efficient support. As a result, the chatbot system according to this embodiment can provide fast and efficient support by analyzing text, images, and audio, performing real-time emotion analysis, and escalating as needed.

[0035] The multilingual support unit provides multilingual support. The multilingual support unit supports multiple languages, such as English, Japanese, and Chinese. The multilingual support unit translates text using, for example, generative AI. For example, the multilingual support unit translates English text into Japanese using text generation AI. Furthermore, the multilingual support unit can translate speech using speech recognition technology. For example, the multilingual support unit converts English speech into Japanese text using speech recognition technology, and then converts it back into Japanese speech using generative AI. Additionally, the multilingual support unit can translate text within images using image recognition technology. For example, the multilingual support unit detects English text within an image using image recognition technology and translates it into Japanese using generative AI. This allows the multilingual support unit to enhance support for foreign owners and staff.

[0036] The troubleshooting department performs troubleshooting. For example, the troubleshooting department automatically detects problems such as payment issues and system errors. The troubleshooting department identifies the cause of the problem using, for example, generative AI. For example, the troubleshooting department analyzes error messages using text generation AI and identifies the cause. The troubleshooting department can also analyze screenshots of system errors using image recognition technology. For example, the troubleshooting department detects error messages using image recognition technology and identifies the cause using generative AI. The troubleshooting department can also analyze voice messages using speech recognition technology. For example, the troubleshooting department converts voice messages to text using speech recognition technology and identifies the cause using generative AI. Based on the identified cause, the troubleshooting department proposes solutions. For example, the troubleshooting department generates solutions using generative AI. For example, the troubleshooting department generates solutions using text generation AI. The troubleshooting department can also escalate issues to a specialized support team as needed. For example, the troubleshooting department uses generative AI to determine the need for escalation and notifies the support team. This allows the troubleshooting department to automatically detect payment issues and system errors and propose solutions.

[0037] The advisory department provides personalized advice. For example, the advisory department analyzes the transaction data of member stores and provides specific advice for increasing sales. For example, the advisory department analyzes transaction data using generative AI. For example, the advisory department analyzes transaction data using text generation AI and generates advice for increasing sales. The advisory department can also analyze transaction data using image recognition technology. For example, the advisory department analyzes sales data graphs using image recognition technology and generates advice using generative AI. The advisory department can also analyze transaction data using speech recognition technology. For example, the advisory department converts speech data into text using speech recognition technology and generates advice using generative AI. The advisory department can, for example, suggest running campaigns during specific time periods. For example, the advisory department analyzes transaction data and suggests running campaigns during times when sales are low. The advisory department can also suggest promoting specific products. For example, the advisory department analyzes transaction data and suggests promoting products with low sales. This allows the advisory department to analyze transaction data and provide specific advice for increasing sales.

[0038] The analysis unit can improve analysis accuracy by referring to the user's past inquiry history when analyzing text, images, and audio. For example, the analysis unit can refer to text messages previously sent by the user and provide analysis results for similar inquiries. For example, the analysis unit can retrieve past inquiry history from a database and compare it with the current inquiry. The analysis unit can also check if similar problems are occurring based on images previously sent by the user. For example, the analysis unit can analyze past image data and compare it with the current image. The analysis unit can also analyze audio messages previously sent by the user and provide answers to similar inquiries. For example, the analysis unit can analyze past audio data and compare it with the current audio. In this way, the analysis unit improves analysis accuracy by referring to past inquiry history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI.

[0039] The analysis unit can apply different analysis algorithms depending on the category of the query content during analysis. For example, the analysis unit can apply a natural language processing algorithm to text-based queries. For instance, it can analyze the meaning of text using morphological analysis or contextual analysis. The analysis unit can also apply an image recognition algorithm to image-based queries. For example, it can analyze the content of an image using object detection or image classification algorithms. The analysis unit can also apply a speech recognition algorithm to speech-based queries. For example, it can convert speech to text using a speech recognition algorithm and then perform text analysis. This improves the accuracy of the analysis by allowing the analysis unit to apply the most appropriate analysis algorithm for the query content. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI.

[0040] The analysis unit can customize the analysis results by taking into account the user's geographical location information during analysis. For example, if the user is in a specific region, the analysis unit will prioritize analyzing information related to that region. For example, the analysis unit will acquire geographical location information and prioritize analyzing data related to that region. The analysis unit can also customize the analysis results based on the characteristics of a different region if the user is in a different region. For example, the analysis unit will acquire geographical location information and adjust the analysis results based on the characteristics of that region. The analysis unit can also update the analysis results in real time based on the user's current location if the user is on the move. For example, the analysis unit will acquire geographical location information in real time and update the analysis results based on the current location. In this way, the analysis unit can provide more appropriate analysis results by taking geographical location information into account. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0041] The analysis unit can analyze users' social media activity during analysis and reflect relevant information in the analysis. For example, the analysis unit can customize the analysis results based on information shared by users on social media. For example, the analysis unit can acquire the content of social media posts and reflect it in the analysis. The analysis unit can also identify interests and concerns from users' social media activity and reflect them in the analysis results. For example, the analysis unit can analyze social media activity data to identify users' interests and concerns. The analysis unit can also include solutions to problems posted by users on social media in the analysis results. For example, the analysis unit can analyze the content of social media posts and provide solutions to problems. In this way, the accuracy of the analysis results is improved by reflecting social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0042] The reception department can select the optimal reception method by referring to the user's past inquiry history at the time of reception. For example, the reception department can propose the optimal method based on the reception methods the user has used in the past. For example, the reception department can retrieve past inquiry history from the database and propose the most suitable method for the current inquiry. The reception department can also select the most efficient reception method from the user's past inquiry history. For example, the reception department can analyze past inquiry history and select the optimal reception method. The reception department can also prioritize providing reception methods that the user has preferred to use in the past. For example, the reception department prioritizes methods that the user has preferred to use based on past inquiry history. In this way, the reception department can select the optimal reception method by referring to past inquiry history. Some or all of the above processing in the reception department may be performed using AI, for example, or without using AI.

[0043] The reception desk can select the optimal reception method at the time of reception, taking into account the user's device information. For example, if the user is using a smartphone, the reception desk can provide a mobile-friendly reception method. For example, the reception desk can acquire device information and provide a reception method optimized for smartphones. The reception desk can also provide a reception method optimized for larger screens if the user is using a tablet. For example, the reception desk can acquire device information and provide a reception method optimized for tablets. The reception desk can also provide a reception method that includes detailed information if the user is using a desktop. For example, the reception desk can acquire device information and provide a reception method optimized for desktops. In this way, the reception desk can provide the optimal reception method by taking device information into consideration. Some or all of the above processing in the reception desk may be performed using AI, for example, or without using AI.

[0044] The generation unit can adjust the level of detail in the response based on the importance of the inquiry when generating the response. For example, the generation unit can generate a detailed response for high-importance inquiries. For example, the generation unit can evaluate the importance of the inquiry and generate a detailed response if it is highly important. The generation unit can also generate a concise response for low-importance inquiries. For example, the generation unit can evaluate the importance of the inquiry and generate a concise response if it is not highly important. The generation unit can also adjust the level of detail in the response in stages according to the importance. For example, the generation unit can evaluate the importance of the inquiry and adjust the level of detail in the response according to the importance. This allows the generation unit to provide more appropriate responses by adjusting the level of detail in the response according to the importance of the inquiry. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI.

[0045] The generation unit can apply different generation algorithms depending on the category of the inquiry when generating an answer. For example, the generation unit can apply a natural language generation algorithm to text-based inquiries. For example, the generation unit can generate an answer in natural language using a text generation AI. The generation unit can also apply an image analysis algorithm to image-based inquiries. For example, the generation unit can generate an image-based answer using an image generation AI. The generation unit can also apply a speech generation algorithm to speech-based inquiries. For example, the generation unit can generate a speech-based answer using a speech generation AI. This improves the accuracy of the answer by allowing the generation unit to apply the most appropriate generation algorithm for the inquiry. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without using AI.

[0046] The generation unit can determine the priority of responses based on the submission timing of the inquiry when generating responses. For example, the generation unit can generate responses quickly for urgent inquiries. For example, the generation unit evaluates the submission timing and generates a response quickly if the urgency is high. The generation unit can also generate responses with normal priority for regular inquiries. For example, the generation unit evaluates the submission timing and generates a response with normal priority if the urgency is low. The generation unit can also adjust the priority of responses in stages according to the submission timing. For example, the generation unit evaluates the submission timing and adjusts the priority of responses according to the urgency. This allows the generation unit to respond quickly by determining the priority of responses according to the submission timing. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI.

[0047] The generation unit can adjust the order of responses based on the relevance of the queries when generating answers. For example, the generation unit can prioritize generating answers for highly relevant queries. For example, the generation unit can evaluate the relevance of queries and, if highly relevant, prioritize generating answers. The generation unit can also generate answers for less relevant queries in the normal order. For example, the generation unit can evaluate the relevance of queries and, if less relevant, generate answers in the normal order. The generation unit can also adjust the order of responses in stages according to relevance. For example, the generation unit can evaluate the relevance of queries and adjust the order of responses according to relevance. This allows the generation unit to provide more appropriate answers by adjusting the order of responses according to relevance. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI.

[0048] The sentiment analysis unit can improve the accuracy of its analysis by referring to the user's past emotional states during sentiment analysis. For example, the sentiment analysis unit analyzes the user's current emotional state based on emotional data from the user's past experiences. For example, the sentiment analysis unit retrieves past emotional data from a database and incorporates it into the current sentiment analysis. The sentiment analysis unit can also predict the user's current emotional state by referring to the user's past emotional patterns. For example, the sentiment analysis unit analyzes past emotional patterns to predict the current emotional state. The sentiment analysis unit can also identify the user's current emotional state by analyzing their past emotional history. For example, the sentiment analysis unit analyzes their past emotional history to identify the current emotional state. As a result, the sentiment analysis unit improves the accuracy of its sentiment analysis by referring to past emotional states. Some or all of the above processes in the sentiment analysis unit may be performed using AI, for example, or without using AI.

[0049] The sentiment analysis unit can apply different analysis algorithms based on the user's utterances and tone during sentiment analysis. For example, the sentiment analysis unit can apply a natural language processing algorithm based on the user's utterances. For example, the sentiment analysis unit analyzes the utterances and estimates the emotions. The sentiment analysis unit can also apply a speech analysis algorithm based on the user's utterance tone. For example, the sentiment analysis unit analyzes the utterance tone and estimates the emotions. Furthermore, the sentiment analysis unit can combine the user's utterances and tone to apply a complex sentiment analysis algorithm. For example, the sentiment analysis unit analyzes the utterances and tone and estimates the emotions. This improves the accuracy of sentiment analysis by allowing the sentiment analysis unit to apply the most appropriate analysis algorithm according to the utterances and tone. Some or all of the above-described processes in the sentiment analysis unit may be performed using AI, for example, or without AI.

[0050] The sentiment analysis unit can customize the analysis results by taking into account the user's geographical location information during sentiment analysis. For example, if the user is in a specific region, the sentiment analysis unit will prioritize analyzing sentiment data related to that region. For example, the sentiment analysis unit will acquire geographical location information and prioritize analyzing data related to that region. The sentiment analysis unit can also customize the sentiment analysis results based on the characteristics of a different region if the user is in a different region. For example, the sentiment analysis unit will acquire geographical location information and adjust the analysis results based on the characteristics of that region. The sentiment analysis unit can also update the sentiment analysis results in real time based on the user's current location if the user is on the move. For example, the sentiment analysis unit will acquire geographical location information in real time and update the analysis results based on the current location. In this way, the sentiment analysis unit can provide more appropriate sentiment analysis results by taking geographical location information into account. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without using AI.

[0051] The sentiment analysis unit can analyze a user's social media activity during sentiment analysis and reflect relevant information in the analysis. For example, the sentiment analysis unit can customize the sentiment analysis results based on information shared by the user on social media. For example, the sentiment analysis unit can acquire the content of social media posts and reflect it in the analysis. The sentiment analysis unit can also identify interests and concerns from the user's social media activity and reflect them in the sentiment analysis results. For example, the sentiment analysis unit can analyze social media activity data to identify the user's interests and concerns. The sentiment analysis unit can also include the user's feelings about issues expressed on social media in the analysis results. For example, the sentiment analysis unit can analyze the content of social media posts and provide feelings about the issues. In this way, the sentiment analysis unit can improve the accuracy of sentiment analysis by reflecting social media activity. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without using AI.

[0052] The escalation unit can select the optimal escalation method by referring to the user's past inquiry history during escalation. For example, the escalation unit may propose the optimal method based on the methods the user has used to escalate issues in the past. For example, the escalation unit may retrieve past inquiry history from a database and propose the most suitable method for the current escalation. The escalation unit can also select the most efficient escalation method from the user's past inquiry history. For example, the escalation unit may analyze past inquiry history and select the optimal escalation method. The escalation unit may also prioritize providing escalation methods that the user has preferred to use in the past. For example, the escalation unit may prioritize methods that the user has preferred to use based on past inquiry history. In this way, the escalation unit can select the optimal escalation method by referring to past inquiry history. Some or all of the above-described processes in the escalation unit may be performed using AI, for example, or without using AI.

[0053] The escalation unit can select the optimal escalation method by considering the user's device information during escalation. For example, if the user is using a smartphone, the escalation unit can provide a mobile-friendly escalation method. For example, the escalation unit can acquire device information and provide an escalation method optimized for smartphones. The escalation unit can also provide an escalation method optimized for larger screens if the user is using a tablet. For example, the escalation unit can acquire device information and provide an escalation method optimized for tablets. The escalation unit can also provide an escalation method that includes detailed information if the user is using a desktop. For example, the escalation unit can acquire device information and provide an escalation method optimized for desktops. In this way, the escalation unit can provide the optimal escalation method by considering device information. Some or all of the above processing in the escalation unit may be performed using AI, for example, or without using AI.

[0054] The multilingual support unit can select the optimal response method by referring to the user's past inquiry history when providing multilingual support. For example, the multilingual support unit can propose the optimal response method based on the language the user has used in the past. For example, the multilingual support unit can retrieve past inquiry history from a database and propose the most suitable method for current multilingual support. The multilingual support unit can also select the most efficient response method from the user's past inquiry history. For example, the multilingual support unit can analyze past inquiry history and select the optimal response method. The multilingual support unit can also prioritize providing the language the user has preferred to use in the past. For example, the multilingual support unit prioritizes the language the user has preferred to use based on past inquiry history. In this way, the multilingual support unit can select the optimal response method by referring to past inquiry history. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without using AI.

[0055] The multilingual support unit can select the optimal support method by considering the user's geographical location information when providing multilingual support. For example, if the user is in a specific region, the multilingual support unit will prioritize supporting the language associated with that region. For example, the multilingual support unit will acquire geographical location information and prioritize supporting the language associated with that region. Furthermore, if the user is in a different region, the multilingual support unit can customize the multilingual support based on the characteristics of that region. For example, the multilingual support unit will acquire geographical location information and adjust the support method based on the characteristics of that region. Also, if the user is on the move, the multilingual support unit can update the multilingual support in real time based on the user's current location. For example, the multilingual support unit will acquire geographical location information in real time and update the support method based on the user's current location. In this way, the multilingual support unit can provide optimal multilingual support by considering geographical location information. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without using AI.

[0056] The troubleshooting unit can select the optimal solution by referring to the user's past trouble history during troubleshooting. For example, the troubleshooting unit can propose the optimal solution based on troubles the user has experienced in the past. For example, the troubleshooting unit can retrieve past trouble history from a database and propose the optimal solution for the current trouble. The troubleshooting unit can also select the most efficient solution from the user's past trouble history. For example, the troubleshooting unit can analyze past trouble history and select the optimal solution. The troubleshooting unit can also prioritize providing solutions that the user has preferred to use in the past. For example, the troubleshooting unit prioritizes methods that the user has preferred to use based on past trouble history. In this way, the troubleshooting unit can select the optimal solution by referring to past trouble history. Some or all of the above processes in the troubleshooting unit may be performed using AI, for example, or without using AI.

[0057] The troubleshooting unit can select the optimal solution by considering the user's device information during troubleshooting. For example, if the user is using a smartphone, the troubleshooting unit can provide a mobile-friendly solution. For example, the troubleshooting unit can acquire device information and provide a solution optimized for smartphones. The troubleshooting unit can also provide a solution optimized for larger screens if the user is using a tablet. For example, the troubleshooting unit can acquire device information and provide a solution optimized for tablets. The troubleshooting unit can also provide a solution with detailed information if the user is using a desktop. For example, the troubleshooting unit can acquire device information and provide a solution optimized for desktops. In this way, the troubleshooting unit can provide the optimal solution by considering device information. Some or all of the above processing in the troubleshooting unit may be performed using AI, for example, or without using AI.

[0058] The advice unit can select the most appropriate advice by referring to the user's past behavior history when providing advice. For example, the advice unit can provide the most appropriate advice based on the advice the user has received in the past. For example, the advice unit can retrieve past behavior history from a database and propose the most appropriate method for the current advice. The advice unit can also select the most efficient advice from the user's past behavior history. For example, the advice unit can analyze past behavior history and select the most appropriate advice. The advice unit can also prioritize providing advice that the user has preferred to receive in the past. For example, the advice unit prioritizes advice that the user preferred to receive based on past behavior history. In this way, the advice unit can select the most appropriate advice by referring to past behavior history. Some or all of the above processes in the advice unit may be performed using AI, for example, or without using AI.

[0059] The advice unit can select the most appropriate advice by considering the user's geographical location when providing advice. For example, if the user is in a specific region, the advice unit will prioritize providing advice relevant to that region. For example, the advice unit will acquire geographical location information and prioritize providing advice relevant to that region. The advice unit can also customize advice based on the characteristics of different regions if the user is in a different region. For example, the advice unit will acquire geographical location information and adjust the advice based on the characteristics of that region. The advice unit can also update advice in real time based on the user's current location if the user is on the move. For example, the advice unit will acquire geographical location information in real time and update the advice based on the current location. In this way, the advice unit can provide the most appropriate advice by considering geographical location information. Some or all of the above processing in the advice unit may be performed using AI, for example, or without using AI.

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

[0061] The analysis unit can improve analysis accuracy by referring to the user's past inquiry history when analyzing text, images, and audio. For example, the analysis unit can refer to text messages previously sent by the user and provide analysis results for similar inquiries. For instance, the analysis unit retrieves past inquiry history from a database and compares it with the current inquiry. The analysis unit can also check if similar problems are occurring based on images previously sent by the user. For example, the analysis unit analyzes past image data and compares it with the current image. The analysis unit can also analyze audio messages previously sent by the user and provide answers to similar inquiries. For example, the analysis unit analyzes past audio data and compares it with the current audio. In this way, the analysis unit improves analysis accuracy by referring to past inquiry history.

[0062] The analysis unit can apply different analysis algorithms depending on the category of the query content during analysis. For example, the analysis unit applies a natural language processing algorithm to text-based queries. For instance, it analyzes the meaning of text using morphological analysis and contextual analysis. The analysis unit can also apply an image recognition algorithm to image-based queries. For example, it analyzes the content of images using object detection and image classification algorithms. Furthermore, the analysis unit can apply a speech recognition algorithm to speech-based queries. For example, it converts speech to text using a speech recognition algorithm and then performs text analysis. This allows the analysis unit to apply the most appropriate analysis algorithm for the query content, thereby improving analysis accuracy.

[0063] The analysis unit can customize the analysis results by taking into account the user's geographical location information during analysis. For example, if the user is in a specific region, the analysis unit will prioritize analyzing information related to that region. For instance, the analysis unit will acquire geographical location information and prioritize analyzing data related to that region. Furthermore, if the user is in a different region, the analysis unit can also customize the analysis results based on the characteristics of that region. For example, the analysis unit will acquire geographical location information and adjust the analysis results based on the characteristics of that region. Additionally, if the user is on the move, the analysis unit can update the analysis results in real time based on their current location. For example, the analysis unit will acquire geographical location information in real time and update the analysis results based on their current location. This allows the analysis unit to provide more appropriate analysis results by considering geographical location information.

[0064] The reception department can select the optimal reception method by referring to the user's past inquiry history at the time of reception. For example, the reception department can propose the optimal method based on the reception methods the user has used in the past. For example, the reception department can retrieve past inquiry history from the database and propose the most suitable method for the current inquiry. The reception department can also select the most efficient reception method from the user's past inquiry history. For example, the reception department can analyze past inquiry history and select the optimal reception method. The reception department can also prioritize providing the reception method that the user has preferred to use in the past. For example, the reception department prioritizes the method that the user preferred to use based on past inquiry history. In this way, the reception department can select the optimal reception method by referring to past inquiry history.

[0065] The reception desk can select the optimal reception method by considering the user's device information at the time of reception. For example, if the user is using a smartphone, the reception desk can provide a mobile-friendly reception method. For example, the reception desk can acquire device information and provide a reception method optimized for smartphones. Also, if the user is using a tablet, the reception desk can provide a reception method optimized for larger screens. For example, the reception desk can acquire device information and provide a reception method optimized for tablets. Furthermore, if the user is using a desktop, the reception desk can provide a reception method that includes detailed information. For example, the reception desk can acquire device information and provide a reception method optimized for desktops. In this way, the reception desk can provide the optimal reception method by considering the device information.

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

[0067] Step 1: The analysis unit analyzes text, images, and audio. For example, the analysis unit uses natural language processing techniques to perform text analysis. For example, the analysis unit uses morphological analysis to analyze the meaning of text. The analysis unit also uses image recognition techniques to perform image analysis. For example, the analysis unit uses an object detection algorithm to identify objects in an image. The analysis unit also uses speech recognition techniques to perform audio analysis. For example, the analysis unit uses a speech recognition algorithm to convert audio into text. Step 2: The reception desk receives inquiries. The reception desk can receive inquiries in the form of text, images, and audio. For example, the reception desk can receive text messages. The reception desk can also receive image files. The reception desk can also receive audio messages. Step 3: The generation unit generates an answer based on the results analyzed by the analysis unit. The generation unit generates an answer using, for example, a generation AI. For example, the generation unit generates an answer in natural language using a text generation AI. The generation unit can also generate an image-based answer using an image generation AI. The generation unit can also generate an audio-based answer using an audio generation AI. Step 4: The sentiment analysis unit performs real-time sentiment analysis. The sentiment analysis unit can, for example, analyze a user's text message to estimate their emotions. For example, the sentiment analysis unit extracts emotions from text using natural language processing techniques. The sentiment analysis unit can also analyze a user's voice message to estimate their emotions. For example, the sentiment analysis unit extracts emotions from voice using voice analysis techniques. The sentiment analysis unit can also analyze a user's image to estimate their emotions. For example, the sentiment analysis unit extracts emotions from facial expressions using image analysis techniques. Step 5: The escalation unit escalates based on the emotional state detected by the emotion analysis unit. For example, if the user is feeling frustrated, the escalation unit will escalate to a specialized support team. For example, if the emotion analysis unit detects frustration, the escalation unit will immediately notify the support team. The escalation unit can also quickly escalate if the user requires urgent support. For example, if the emotion analysis unit detects an urgent emotional state, the escalation unit will immediately notify the support team.

[0068] (Example of form 2) The chatbot system according to an embodiment of the present invention is an advanced chatbot that utilizes multimodal AI capable of analyzing text, images, and audio to respond to inquiries from merchants 24 / 7. This chatbot system provides rapid and efficient support to merchants, improving merchant satisfaction and ultimately promoting increased transaction volume and commissions. It also includes a real-time sentiment analysis function to detect the user's emotional state and quickly escalate the issue to a specialized support team. For example, it responds to inquiries from merchants using multimodal AI capable of analyzing text, images, and audio. For instance, if a merchant makes a text-based inquiry, the generating AI uses natural language processing technology to provide an accurate and rapid response. If an image is sent, the generating AI analyzes the image and suggests the optimal QR code placement based on, for example, a store layout image. Furthermore, if a voice message is sent, the generating AI converts the voice into text and provides a response similar to the text analysis. Next, the chatbot is multilingual, supporting not only Japanese but also multiple other languages. This enhances support for foreign owners and staff. For example, the generating AI responds quickly and accurately to inquiries in multiple languages ​​such as English and Chinese. Furthermore, the chatbot is equipped with advanced FAQ functionality, not only providing instant answers to frequently asked questions but also learning from past inquiry history to offer more accurate support. For example, if a similar inquiry has been made in the past, it can quickly provide an answer based on that history. It also has troubleshooting capabilities, automatically detecting problems such as payment issues and system errors and suggesting solutions. It can also escalate issues to a specialized support team if necessary. For example, if a payment error occurs, the generated AI will identify the cause and suggest a solution. In addition, the chatbot analyzes merchant transaction data and provides specific advice to improve sales. For example, it can improve sales by suggesting that campaigns be run during specific time periods. Finally, a real-time sentiment analysis function detects the user's emotional state and quickly escalates to a specialized support team if the customer is feeling frustrated.This will further enhance the customer experience and dramatically improve the speed of problem resolution. This multimodal AI chatbot will be a powerful tool to strengthen merchant support and drive increased transaction volume and commissions. By providing fast and accurate support, it will improve merchant satisfaction and ultimately contribute to business growth. In addition, real-time sentiment analysis capabilities will further enhance the customer experience and dramatically improve the speed of problem resolution. As a result, the chatbot system will provide fast and efficient support to merchants, improve merchant satisfaction, and ultimately drive increased transaction volume and commissions.

[0069] The chatbot system according to this embodiment comprises an analysis unit, a reception unit, a generation unit, an emotion analysis unit, and an escalation unit. The analysis unit analyzes text, images, and audio. The analysis unit uses, for example, natural language processing technology to perform text analysis. For example, the analysis unit uses morphological analysis to analyze the meaning of text. The analysis unit also uses image recognition technology to perform image analysis. For example, the analysis unit uses an object detection algorithm to identify objects in an image. The analysis unit also uses speech recognition technology to perform audio analysis. For example, the analysis unit uses a speech recognition algorithm to convert audio into text. The reception unit receives inquiries. The reception unit can receive inquiries in the form of text, images, and audio. For example, the reception unit can receive text messages. The reception unit can also receive image files. The reception unit can also receive audio messages. The generation unit generates responses based on the results analyzed by the analysis unit. The generation unit generates responses using, for example, a generation AI. For example, the generation unit generates responses in natural language using a text generation AI. The generation unit can also generate image-based responses using image generation AI. The generation unit can also generate voice-based responses using voice generation AI. The sentiment analysis unit performs real-time sentiment analysis. For example, the sentiment analysis unit estimates emotions by analyzing a user's text messages. For example, the sentiment analysis unit extracts emotions from text using natural language processing technology. The sentiment analysis unit can also estimate emotions by analyzing a user's voice messages. For example, the sentiment analysis unit extracts emotions from voice using voice analysis technology. The sentiment analysis unit can also estimate emotions by analyzing a user's images. For example, the sentiment analysis unit extracts emotions from facial expressions using image analysis technology. The escalation unit performs escalation based on the emotional state detected by the sentiment analysis unit. For example, if a user is feeling frustrated, the escalation unit escalates the issue to a specialized support team. For example, if the sentiment analysis unit detects frustration, the escalation unit immediately notifies the support team.Furthermore, the escalation unit can quickly escalate a user's case if they require urgent support. For example, if the sentiment analysis unit detects an urgent emotional state, the escalation unit immediately notifies the support team. As a result, the chatbot system according to this embodiment can provide fast and efficient support by analyzing text, images, and audio, performing real-time sentiment analysis, and escalating as needed.

[0070] The analysis unit analyzes text, images, and audio. For example, the analysis unit uses natural language processing technology to perform text analysis. Specifically, it uses morphological analysis to analyze the meaning of text and understand its context and intent. Morphological analysis is a technology that divides text into words and identifies the part of speech and meaning of each word. This allows for accurate understanding of user inquiries and appropriate responses. The analysis unit also uses image recognition technology to perform image analysis. For example, it uses an object detection algorithm to identify objects in an image and recognize their type and location. An object detection algorithm is a technology that identifies specific patterns and features in an image and classifies objects based on them. This allows for the extraction of necessary information from images sent by users and enables appropriate responses. Furthermore, the analysis unit uses speech recognition technology to perform audio analysis. For example, it uses a speech recognition algorithm to convert audio into text and analyze that text. A speech recognition algorithm is a technology that analyzes audio signals and identifies phonemes and words. This allows for accurate understanding of content and appropriate responses even when users make inquiries by voice. The analysis unit combines these technologies to analyze diverse data such as text, images, and audio, enabling a comprehensive understanding of user inquiries.

[0071] The reception department receives inquiries. The reception department can receive inquiries in the form of text, images, and audio. Specifically, it provides an interface for receiving text messages and receives text entered by users. It also provides an interface for receiving image files and receives images uploaded by users. Furthermore, it provides an interface for receiving audio messages and receives audio recorded by users. Through these interfaces, the reception department can receive a variety of inquiries from users. For example, if a user sends a text message, the reception department receives the message and sends it to the analysis department. If a user uploads an image, the reception department receives the image and sends it to the analysis department. If a user records and sends an audio message, the reception department receives the audio and sends it to the analysis department. This allows the reception department to quickly and accurately receive inquiries from users and forward them to the analysis department.

[0072] The generation unit generates answers based on the results analyzed by the analysis unit. The generation unit generates answers using, for example, generation AI. Specifically, it generates answers in natural language using text generation AI. Text generation AI is a technology that generates appropriate answers based on the user's inquiry and the analysis results. For example, if a user asks about how to use a product, the generation unit generates an answer that includes specific procedures and advice. The generation unit can also generate image-based answers using image generation AI. For example, if a user sends an image of a faulty part of a product, the generation unit analyzes the image and generates and provides images of repair methods and replacement parts. Furthermore, the generation unit can also generate voice-based answers using voice generation AI. For example, if a user makes an inquiry by voice, the generation unit generates a voice response to that inquiry and provides it to the user. By combining these technologies, the generation unit can generate the optimal answer to the user's inquiry and provide it quickly and accurately.

[0073] The sentiment analysis unit performs real-time sentiment analysis. For example, the sentiment analysis unit estimates emotions by analyzing a user's text messages. Specifically, it extracts emotions from text using natural language processing technology. Natural language processing technology is a technique that analyzes the emotional meaning of words and phrases in text and estimates the user's emotional state. For example, if a user uses words that express dissatisfaction or anger, the sentiment analysis unit detects that emotion and takes an appropriate response. The sentiment analysis unit can also estimate emotions by analyzing a user's voice messages. Specifically, it extracts emotions from voice using voice analysis technology. Voice analysis technology is a technique that analyzes the characteristics of a voice signal and estimates the user's emotional state. For example, it analyzes the tone, pitch, and speed of the user's voice to determine whether the user is tense or relaxed. Furthermore, the sentiment analysis unit can also estimate emotions by analyzing a user's image. Specifically, it extracts emotions from facial expressions using image analysis technology. Image analysis technology is a technique that analyzes facial expressions, eye movements, mouth shapes, etc., and estimates the user's emotional state. For example, if a user is smiling, the emotion analysis unit detects that emotion and takes appropriate action. By combining these technologies, the emotion analysis unit can comprehensively understand the user's emotional state and take appropriate action in real time.

[0074] The escalation unit performs escalation based on the emotional state detected by the emotion analysis unit. For example, if a user is feeling frustrated, the escalation unit will escalate the issue to a specialized support team. Specifically, if the emotion analysis unit detects user frustration, the escalation unit immediately notifies the support team and requests assistance. The support team can understand the user's inquiry and emotional state and provide appropriate support. The escalation unit can also quickly escalate if the user requires urgent support. Specifically, if the emotion analysis unit detects an urgent emotional state of the user, the escalation unit immediately notifies the support team and requests prompt assistance. The support team can understand the user's urgent inquiry and emotional state and provide prompt and appropriate support. Through these functions, the escalation unit can provide appropriate support according to the user's emotional state and offer fast and efficient support. As a result, the chatbot system according to this embodiment can provide fast and efficient support by analyzing text, images, and audio, performing real-time emotion analysis, and escalating as needed.

[0075] The multilingual support unit provides multilingual support. The multilingual support unit supports multiple languages, such as English, Japanese, and Chinese. The multilingual support unit translates text using, for example, generative AI. For example, the multilingual support unit translates English text into Japanese using text generation AI. Furthermore, the multilingual support unit can translate speech using speech recognition technology. For example, the multilingual support unit converts English speech into Japanese text using speech recognition technology, and then converts it back into Japanese speech using generative AI. Additionally, the multilingual support unit can translate text within images using image recognition technology. For example, the multilingual support unit detects English text within an image using image recognition technology and translates it into Japanese using generative AI. This allows the multilingual support unit to enhance support for foreign owners and staff.

[0076] The troubleshooting department performs troubleshooting. For example, the troubleshooting department automatically detects problems such as payment issues and system errors. The troubleshooting department identifies the cause of the problem using, for example, generative AI. For example, the troubleshooting department analyzes error messages using text generation AI and identifies the cause. The troubleshooting department can also analyze screenshots of system errors using image recognition technology. For example, the troubleshooting department detects error messages using image recognition technology and identifies the cause using generative AI. The troubleshooting department can also analyze voice messages using speech recognition technology. For example, the troubleshooting department converts voice messages to text using speech recognition technology and identifies the cause using generative AI. Based on the identified cause, the troubleshooting department proposes solutions. For example, the troubleshooting department generates solutions using generative AI. For example, the troubleshooting department generates solutions using text generation AI. The troubleshooting department can also escalate issues to a specialized support team as needed. For example, the troubleshooting department uses generative AI to determine the need for escalation and notifies the support team. This allows the troubleshooting department to automatically detect payment issues and system errors and propose solutions.

[0077] The advisory department provides personalized advice. For example, the advisory department analyzes the transaction data of member stores and provides specific advice for increasing sales. For example, the advisory department analyzes transaction data using generative AI. For example, the advisory department analyzes transaction data using text generation AI and generates advice for increasing sales. The advisory department can also analyze transaction data using image recognition technology. For example, the advisory department analyzes sales data graphs using image recognition technology and generates advice using generative AI. The advisory department can also analyze transaction data using speech recognition technology. For example, the advisory department converts speech data into text using speech recognition technology and generates advice using generative AI. The advisory department can, for example, suggest running campaigns during specific time periods. For example, the advisory department analyzes transaction data and suggests running campaigns during times when sales are low. The advisory department can also suggest promoting specific products. For example, the advisory department analyzes transaction data and suggests promoting products with low sales. This allows the advisory department to analyze transaction data and provide specific advice for increasing sales.

[0078] The analysis unit can estimate the user's emotions and adjust the analysis priority based on the estimated emotions. For example, if the user is feeling frustrated, the analysis unit will prioritize high-priority analyses. For instance, if the analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects frustration, it will prioritize high-priority analyses. The analysis unit can also process data according to the normal analysis procedure if the user is relaxed. For example, if the analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects relaxation, it will follow the normal analysis procedure. The analysis unit can also perform rapid analysis and provide results quickly if the user is in a hurry. For example, if the analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects that the user is in a hurry, it will perform rapid analysis. This allows the analysis unit to provide a more appropriate response by adjusting the analysis priority according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without using AI.

[0079] The analysis unit can improve analysis accuracy by referring to the user's past inquiry history when analyzing text, images, and audio. For example, the analysis unit can refer to text messages previously sent by the user and provide analysis results for similar inquiries. For example, the analysis unit can retrieve past inquiry history from a database and compare it with the current inquiry. The analysis unit can also check if similar problems are occurring based on images previously sent by the user. For example, the analysis unit can analyze past image data and compare it with the current image. The analysis unit can also analyze audio messages previously sent by the user and provide answers to similar inquiries. For example, the analysis unit can analyze past audio data and compare it with the current audio. In this way, the analysis unit improves analysis accuracy by referring to past inquiry history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI.

[0080] The analysis unit can apply different analysis algorithms depending on the category of the query content during analysis. For example, the analysis unit can apply a natural language processing algorithm to text-based queries. For instance, it can analyze the meaning of text using morphological analysis or contextual analysis. The analysis unit can also apply an image recognition algorithm to image-based queries. For example, it can analyze the content of an image using object detection or image classification algorithms. The analysis unit can also apply a speech recognition algorithm to speech-based queries. For example, it can convert speech to text using a speech recognition algorithm and then perform text analysis. This improves the accuracy of the analysis by allowing the analysis unit to apply the most appropriate analysis algorithm for the query content. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI.

[0081] The analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the user is feeling frustrated, the analysis unit can display concise and clear analysis results. For example, if the analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects frustration, it can display concise analysis results. The analysis unit can also display detailed analysis results if the user is relaxed. For example, if the analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects relaxation, it can display detailed analysis results. The analysis unit can also display concise analysis results if the user is in a hurry. For example, if the analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects that the user is in a hurry, it can display concise analysis results. In this way, the analysis unit can provide more appropriate information by adjusting how the analysis results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without using AI.

[0082] The analysis unit can customize the analysis results by taking into account the user's geographical location information during analysis. For example, if the user is in a specific region, the analysis unit will prioritize analyzing information related to that region. For example, the analysis unit will acquire geographical location information and prioritize analyzing data related to that region. The analysis unit can also customize the analysis results based on the characteristics of a different region if the user is in a different region. For example, the analysis unit will acquire geographical location information and adjust the analysis results based on the characteristics of that region. The analysis unit can also update the analysis results in real time based on the user's current location if the user is on the move. For example, the analysis unit will acquire geographical location information in real time and update the analysis results based on the current location. In this way, the analysis unit can provide more appropriate analysis results by taking geographical location information into account. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0083] The analysis unit can analyze users' social media activity during analysis and reflect relevant information in the analysis. For example, the analysis unit can customize the analysis results based on information shared by users on social media. For example, the analysis unit can acquire the content of social media posts and reflect it in the analysis. The analysis unit can also identify interests and concerns from users' social media activity and reflect them in the analysis results. For example, the analysis unit can analyze social media activity data to identify users' interests and concerns. The analysis unit can also include solutions to problems posted by users on social media in the analysis results. For example, the analysis unit can analyze the content of social media posts and provide solutions to problems. In this way, the accuracy of the analysis results is improved by reflecting social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0084] The reception desk can estimate the user's emotions and adjust its response based on those emotions. For example, if the user is feeling frustrated, the reception desk can provide a quick and concise response. For instance, the reception desk can use an emotion estimation algorithm to estimate the user's emotions and, if frustration is detected, provide a quick response. The reception desk can also provide a more detailed explanation if the user is relaxed. For example, the reception desk can use an emotion estimation algorithm to estimate the user's emotions and, if relaxation is detected, provide a detailed explanation. Furthermore, if the user is in a hurry, the reception desk can provide a quick response and offer only the necessary minimum information. For example, the reception desk can use an emotion estimation algorithm to estimate the user's emotions and, if urgency is detected, provide a quick response. This allows the reception desk to provide a more appropriate response by adjusting its response based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-mentioned processes at the reception desk may be performed using AI, for example, or without using AI.

[0085] The reception department can select the optimal reception method by referring to the user's past inquiry history at the time of reception. For example, the reception department can propose the optimal method based on the reception methods the user has used in the past. For example, the reception department can retrieve past inquiry history from the database and propose the most suitable method for the current inquiry. The reception department can also select the most efficient reception method from the user's past inquiry history. For example, the reception department can analyze past inquiry history and select the optimal reception method. The reception department can also prioritize providing reception methods that the user has preferred to use in the past. For example, the reception department prioritizes methods that the user has preferred to use based on past inquiry history. In this way, the reception department can select the optimal reception method by referring to past inquiry history. Some or all of the above processing in the reception department may be performed using AI, for example, or without using AI.

[0086] The reception desk can estimate the user's emotions and determine the priority of service based on the estimated emotions. For example, if the user is feeling frustrated, the reception desk will prioritize their response. For instance, the reception desk can use an emotion estimation algorithm to estimate the user's emotions, and if frustration is detected, it will prioritize their response. The reception desk can also respond to users with normal priority if they are relaxed. For example, the reception desk can use an emotion estimation algorithm to estimate the user's emotions, and if relaxation is detected, it will prioritize their response. The reception desk can also respond quickly if the user is in a hurry. For example, the reception desk can use an emotion estimation algorithm to estimate the user's emotions, and if urgency is detected, it will respond quickly. This allows the reception desk to provide more appropriate service by determining the priority of service according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-mentioned processes at the reception desk may be performed using AI, for example, or without using AI.

[0087] The reception desk can select the optimal reception method at the time of reception, taking into account the user's device information. For example, if the user is using a smartphone, the reception desk can provide a mobile-friendly reception method. For example, the reception desk can acquire device information and provide a reception method optimized for smartphones. The reception desk can also provide a reception method optimized for larger screens if the user is using a tablet. For example, the reception desk can acquire device information and provide a reception method optimized for tablets. The reception desk can also provide a reception method that includes detailed information if the user is using a desktop. For example, the reception desk can acquire device information and provide a reception method optimized for desktops. In this way, the reception desk can provide the optimal reception method by taking device information into consideration. Some or all of the above processing in the reception desk may be performed using AI, for example, or without using AI.

[0088] The generation unit can estimate the user's emotions and adjust the way it expresses its response based on those emotions. For example, if the user is feeling frustrated, the generation unit can generate a concise and clear response. For instance, it can use an emotion estimation algorithm to estimate the user's emotions and, if it detects frustration, generate a concise response. The generation unit can also generate a response with detailed explanations if the user is relaxed. For example, it can use an emotion estimation algorithm to estimate the user's emotions and, if it detects relaxation, generate a detailed response. The generation unit can also generate a response that can be quickly understood if the user is in a hurry. For example, it can use an emotion estimation algorithm to estimate the user's emotions and, if it detects that the user is in a hurry, generate a response that can be quickly understood. This allows the generation unit to provide more appropriate responses by adjusting the way it expresses its response according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without using AI.

[0089] The generation unit can adjust the level of detail in the response based on the importance of the inquiry when generating the response. For example, the generation unit can generate a detailed response for high-importance inquiries. For example, the generation unit can evaluate the importance of the inquiry and generate a detailed response if it is highly important. The generation unit can also generate a concise response for low-importance inquiries. For example, the generation unit can evaluate the importance of the inquiry and generate a concise response if it is not highly important. The generation unit can also adjust the level of detail in the response in stages according to the importance. For example, the generation unit can evaluate the importance of the inquiry and adjust the level of detail in the response according to the importance. This allows the generation unit to provide more appropriate responses by adjusting the level of detail in the response according to the importance of the inquiry. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI.

[0090] The generation unit can apply different generation algorithms depending on the category of the inquiry when generating an answer. For example, the generation unit can apply a natural language generation algorithm to text-based inquiries. For example, the generation unit can generate an answer in natural language using a text generation AI. The generation unit can also apply an image analysis algorithm to image-based inquiries. For example, the generation unit can generate an image-based answer using an image generation AI. The generation unit can also apply a speech generation algorithm to speech-based inquiries. For example, the generation unit can generate a speech-based answer using a speech generation AI. This improves the accuracy of the answer by allowing the generation unit to apply the most appropriate generation algorithm for the inquiry. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without using AI.

[0091] The generation unit can estimate the user's emotions and adjust the length of the response based on the estimated emotions. For example, if the user is feeling frustrated, the generation unit can generate a short, to-the-point response. For example, the generation unit can estimate the user's emotions using an emotion estimation algorithm and, if it detects frustration, generate a short response. The generation unit can also generate a longer response with more detailed explanations if the user is relaxed. For example, the generation unit can estimate the user's emotions using an emotion estimation algorithm and, if it detects relaxation, generate a longer response. The generation unit can also generate a short, easily understandable response if the user is in a hurry. For example, the generation unit can estimate the user's emotions using an emotion estimation algorithm and, if it detects that the user is in a hurry, generate a short response. This allows the generation unit to provide more appropriate responses by adjusting the length of the response according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without using AI.

[0092] The generation unit can determine the priority of responses based on the submission timing of the inquiry when generating responses. For example, the generation unit can generate responses quickly for urgent inquiries. For example, the generation unit evaluates the submission timing and generates a response quickly if the urgency is high. The generation unit can also generate responses with normal priority for regular inquiries. For example, the generation unit evaluates the submission timing and generates a response with normal priority if the urgency is low. The generation unit can also adjust the priority of responses in stages according to the submission timing. For example, the generation unit evaluates the submission timing and adjusts the priority of responses according to the urgency. This allows the generation unit to respond quickly by determining the priority of responses according to the submission timing. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI.

[0093] The generation unit can adjust the order of responses based on the relevance of the queries when generating answers. For example, the generation unit can prioritize generating answers for highly relevant queries. For example, the generation unit can evaluate the relevance of queries and, if highly relevant, prioritize generating answers. The generation unit can also generate answers for less relevant queries in the normal order. For example, the generation unit can evaluate the relevance of queries and, if less relevant, generate answers in the normal order. The generation unit can also adjust the order of responses in stages according to relevance. For example, the generation unit can evaluate the relevance of queries and adjust the order of responses according to relevance. This allows the generation unit to provide more appropriate answers by adjusting the order of responses according to relevance. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI.

[0094] The sentiment analysis unit can estimate the user's emotions and improve the accuracy of the sentiment analysis based on the estimated emotions. For example, the sentiment analysis unit can improve the accuracy of the sentiment analysis by referring to the user's past emotional data. For example, it can retrieve past emotional data from a database and reflect it in the current sentiment analysis. The sentiment analysis unit can also improve the accuracy of the sentiment analysis based on the user's current statements and tone. For example, it can analyze statements and tone and reflect them in the sentiment analysis. Furthermore, the sentiment analysis unit can improve the accuracy of the sentiment analysis by analyzing the user's social media activity. For example, it can analyze social media activity data and reflect it in the sentiment analysis. This allows the sentiment analysis unit to improve the accuracy of the sentiment analysis based on the user's emotions, enabling more accurate sentiment analysis. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the emotion analysis unit may be performed using AI, for example, or without using AI.

[0095] The sentiment analysis unit can improve the accuracy of its analysis by referring to the user's past emotional states during sentiment analysis. For example, the sentiment analysis unit analyzes the user's current emotional state based on emotional data from the user's past experiences. For example, the sentiment analysis unit retrieves past emotional data from a database and incorporates it into the current sentiment analysis. The sentiment analysis unit can also predict the user's current emotional state by referring to the user's past emotional patterns. For example, the sentiment analysis unit analyzes past emotional patterns to predict the current emotional state. The sentiment analysis unit can also identify the user's current emotional state by analyzing their past emotional history. For example, the sentiment analysis unit analyzes their past emotional history to identify the current emotional state. As a result, the sentiment analysis unit improves the accuracy of its sentiment analysis by referring to past emotional states. Some or all of the above processes in the sentiment analysis unit may be performed using AI, for example, or without using AI.

[0096] The sentiment analysis unit can apply different analysis algorithms based on the user's utterances and tone during sentiment analysis. For example, the sentiment analysis unit can apply a natural language processing algorithm based on the user's utterances. For example, the sentiment analysis unit analyzes the utterances and estimates the emotions. The sentiment analysis unit can also apply a speech analysis algorithm based on the user's utterance tone. For example, the sentiment analysis unit analyzes the utterance tone and estimates the emotions. Furthermore, the sentiment analysis unit can combine the user's utterances and tone to apply a complex sentiment analysis algorithm. For example, the sentiment analysis unit analyzes the utterances and tone and estimates the emotions. This improves the accuracy of sentiment analysis by allowing the sentiment analysis unit to apply the most appropriate analysis algorithm according to the utterances and tone. Some or all of the above-described processes in the sentiment analysis unit may be performed using AI, for example, or without AI.

[0097] The emotion analysis unit can estimate the user's emotions and adjust how the emotion analysis results are displayed based on the estimated emotions. For example, if the user is feeling frustrated, the emotion analysis unit can display a concise and clear emotion analysis result. For example, if the emotion analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects frustration, it will display a concise emotion analysis result. The emotion analysis unit can also display a detailed emotion analysis result if the user is relaxed. For example, if the emotion analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects relaxation, it will display a detailed emotion analysis result. The emotion analysis unit can also display a concise emotion analysis result if the user is in a hurry. For example, if the emotion analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects that the user is in a hurry, it will display a concise emotion analysis result. In this way, the emotion analysis unit can provide more appropriate information by adjusting how the emotion analysis results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the sentiment analysis unit may be performed using AI, or not using AI.

[0098] The sentiment analysis unit can customize the analysis results by taking into account the user's geographical location information during sentiment analysis. For example, if the user is in a specific region, the sentiment analysis unit will prioritize analyzing sentiment data related to that region. For example, the sentiment analysis unit will acquire geographical location information and prioritize analyzing data related to that region. The sentiment analysis unit can also customize the sentiment analysis results based on the characteristics of a different region if the user is in a different region. For example, the sentiment analysis unit will acquire geographical location information and adjust the analysis results based on the characteristics of that region. The sentiment analysis unit can also update the sentiment analysis results in real time based on the user's current location if the user is on the move. For example, the sentiment analysis unit will acquire geographical location information in real time and update the analysis results based on the current location. In this way, the sentiment analysis unit can provide more appropriate sentiment analysis results by taking geographical location information into account. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without using AI.

[0099] The sentiment analysis unit can analyze a user's social media activity during sentiment analysis and reflect relevant information in the analysis. For example, the sentiment analysis unit can customize the sentiment analysis results based on information shared by the user on social media. For example, the sentiment analysis unit can acquire the content of social media posts and reflect it in the analysis. The sentiment analysis unit can also identify interests and concerns from the user's social media activity and reflect them in the sentiment analysis results. For example, the sentiment analysis unit can analyze social media activity data to identify the user's interests and concerns. The sentiment analysis unit can also include the user's feelings about issues expressed on social media in the analysis results. For example, the sentiment analysis unit can analyze the content of social media posts and provide feelings about the issues. In this way, the sentiment analysis unit can improve the accuracy of sentiment analysis by reflecting social media activity. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without using AI.

[0100] The escalation unit can estimate the user's emotions and adjust the timing of escalation based on the estimated emotions. For example, if the user is feeling frustrated, the escalation unit can escalate quickly. For example, the escalation unit can estimate the user's emotions using an emotion estimation algorithm and, if it detects frustration, escalate quickly. The escalation unit can also escalate at the normal timing if the user is relaxed. For example, the escalation unit can estimate the user's emotions using an emotion estimation algorithm and, if it detects relaxation, escalate at the normal timing. The escalation unit can also escalate immediately if the user is in a hurry. For example, the escalation unit can estimate the user's emotions using an emotion estimation algorithm and, if it detects that the user is in a hurry, escalate immediately. In this way, the escalation unit can provide a more appropriate response by adjusting the timing of escalation according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the escalation section may be performed using AI, or not using AI.

[0101] The escalation unit can select the optimal escalation method by referring to the user's past inquiry history during escalation. For example, the escalation unit may propose the optimal method based on the methods the user has used to escalate issues in the past. For example, the escalation unit may retrieve past inquiry history from a database and propose the most suitable method for the current escalation. The escalation unit can also select the most efficient escalation method from the user's past inquiry history. For example, the escalation unit may analyze past inquiry history and select the optimal escalation method. The escalation unit may also prioritize providing escalation methods that the user has preferred to use in the past. For example, the escalation unit may prioritize methods that the user has preferred to use based on past inquiry history. In this way, the escalation unit can select the optimal escalation method by referring to past inquiry history. Some or all of the above-described processes in the escalation unit may be performed using AI, for example, or without using AI.

[0102] The escalation unit can estimate the user's emotions and determine the priority of escalation based on the estimated emotions. For example, if the user is feeling frustrated, the escalation unit will prioritize escalation. For example, the escalation unit uses an emotion estimation algorithm to estimate the user's emotions, and if frustration is detected, it will prioritize escalation. The escalation unit can also escalate with the normal priority if the user is relaxed. For example, the escalation unit uses an emotion estimation algorithm to estimate the user's emotions, and if relaxation is detected, it will prioritize escalation. The escalation unit can also escalate quickly if the user is in a hurry. For example, the escalation unit uses an emotion estimation algorithm to estimate the user's emotions, and if urgency is detected, it will quickly escalate. In this way, the escalation unit can provide a more appropriate response by determining the priority of escalation according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generation AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the escalation section may be performed using AI, or not using AI.

[0103] The escalation unit can select the optimal escalation method by considering the user's device information during escalation. For example, if the user is using a smartphone, the escalation unit can provide a mobile-friendly escalation method. For example, the escalation unit can acquire device information and provide an escalation method optimized for smartphones. The escalation unit can also provide an escalation method optimized for larger screens if the user is using a tablet. For example, the escalation unit can acquire device information and provide an escalation method optimized for tablets. The escalation unit can also provide an escalation method that includes detailed information if the user is using a desktop. For example, the escalation unit can acquire device information and provide an escalation method optimized for desktops. In this way, the escalation unit can provide the optimal escalation method by considering device information. Some or all of the above processing in the escalation unit may be performed using AI, for example, or without using AI.

[0104] The multilingual support unit can estimate the user's emotions and adjust the multilingual expression based on the estimated emotions. For example, if the user is feeling frustrated, the multilingual support unit will use concise and clear language. For instance, if the multilingual support unit estimates the user's emotions using an emotion estimation algorithm and detects frustration, it will use concise language. Furthermore, if the user is relaxed, the multilingual support unit can also use language that includes detailed explanations. For example, if the multilingual support unit estimates the user's emotions using an emotion estimation algorithm and detects relaxation, it will use detailed language. Additionally, if the user is in a hurry, the multilingual support unit can use language that can be quickly understood. For example, if the multilingual support unit estimates the user's emotions using an emotion estimation algorithm and detects that the user is in a hurry, it will use language that can be quickly understood. This allows the multilingual support unit to provide more appropriate information by adjusting the multilingual expression according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the multilingual support section may be performed using AI, or not using AI.

[0105] The multilingual support unit can select the optimal response method by referring to the user's past inquiry history when providing multilingual support. For example, the multilingual support unit can propose the optimal response method based on the language the user has used in the past. For example, the multilingual support unit can retrieve past inquiry history from a database and propose the most suitable method for current multilingual support. The multilingual support unit can also select the most efficient response method from the user's past inquiry history. For example, the multilingual support unit can analyze past inquiry history and select the optimal response method. The multilingual support unit can also prioritize providing the language the user has preferred to use in the past. For example, the multilingual support unit prioritizes the language the user has preferred to use based on past inquiry history. In this way, the multilingual support unit can select the optimal response method by referring to past inquiry history. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without using AI.

[0106] The multilingual support unit can estimate the user's emotions and determine the priority of multilingual support based on the estimated emotions. For example, if the user is feeling frustrated, the multilingual support unit will prioritize multilingual support. For example, the multilingual support unit will use an emotion estimation algorithm to estimate the user's emotions, and if frustration is detected, it will prioritize multilingual support. The multilingual support unit can also provide multilingual support with the normal priority if the user is relaxed. For example, the multilingual support unit will use an emotion estimation algorithm to estimate the user's emotions, and if relaxation is detected, it will provide multilingual support with the normal priority. The multilingual support unit can also provide rapid multilingual support if the user is in a hurry. For example, the multilingual support unit will use an emotion estimation algorithm to estimate the user's emotions, and if urgency is detected, it will provide rapid multilingual support. In this way, the multilingual support unit can provide more appropriate support by determining the priority of multilingual support according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the multilingual support section may be performed using AI, or not using AI.

[0107] The multilingual support unit can select the optimal support method by considering the user's geographical location information when providing multilingual support. For example, if the user is in a specific region, the multilingual support unit will prioritize supporting the language associated with that region. For example, the multilingual support unit will acquire geographical location information and prioritize supporting the language associated with that region. Furthermore, if the user is in a different region, the multilingual support unit can customize the multilingual support based on the characteristics of that region. For example, the multilingual support unit will acquire geographical location information and adjust the support method based on the characteristics of that region. Also, if the user is on the move, the multilingual support unit can update the multilingual support in real time based on the user's current location. For example, the multilingual support unit will acquire geographical location information in real time and update the support method based on the user's current location. In this way, the multilingual support unit can provide optimal multilingual support by considering geographical location information. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without using AI.

[0108] The troubleshooting unit can estimate the user's emotions and adjust its troubleshooting methods based on those emotions. For example, if the user is feeling frustrated, the troubleshooting unit can perform quick and concise troubleshooting. For example, it can use an emotion estimation algorithm to estimate the user's emotions and, if frustration is detected, perform quick troubleshooting. The troubleshooting unit can also perform troubleshooting with detailed explanations if the user is relaxed. For example, it can use an emotion estimation algorithm to estimate the user's emotions and, if relaxation is detected, perform detailed troubleshooting. The troubleshooting unit can also provide a quick solution if the user is in a hurry. For example, it can use an emotion estimation algorithm to estimate the user's emotions and, if urgency is detected, provide a quick solution. This allows the troubleshooting unit to provide a more appropriate response by adjusting its troubleshooting methods according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the troubleshooting section may be performed using AI, for example, or without using AI.

[0109] The troubleshooting unit can select the optimal solution by referring to the user's past trouble history during troubleshooting. For example, the troubleshooting unit can propose the optimal solution based on troubles the user has experienced in the past. For example, the troubleshooting unit can retrieve past trouble history from a database and propose the optimal solution for the current trouble. The troubleshooting unit can also select the most efficient solution from the user's past trouble history. For example, the troubleshooting unit can analyze past trouble history and select the optimal solution. The troubleshooting unit can also prioritize providing solutions that the user has preferred to use in the past. For example, the troubleshooting unit prioritizes methods that the user has preferred to use based on past trouble history. In this way, the troubleshooting unit can select the optimal solution by referring to past trouble history. Some or all of the above processes in the troubleshooting unit may be performed using AI, for example, or without using AI.

[0110] The troubleshooting unit can estimate the user's emotions and determine troubleshooting priorities based on those emotions. For example, if the user is feeling frustrated, the troubleshooting unit will prioritize troubleshooting. For instance, it can use an emotion estimation algorithm to estimate the user's emotions, and if frustration is detected, it will prioritize troubleshooting. The troubleshooting unit can also troubleshoot with normal priority if the user is relaxed. For example, it can use an emotion estimation algorithm to estimate the user's emotions, and if relaxation is detected, it will prioritize troubleshooting. The troubleshooting unit can also troubleshoot quickly if the user is in a hurry. For example, it can use an emotion estimation algorithm to estimate the user's emotions, and if urgency is detected, it will quickly troubleshoot. This allows the troubleshooting unit to provide more appropriate responses by determining troubleshooting priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the troubleshooting section may be performed using AI, for example, or without using AI.

[0111] The troubleshooting unit can select the optimal solution by considering the user's device information during troubleshooting. For example, if the user is using a smartphone, the troubleshooting unit can provide a mobile-friendly solution. For example, the troubleshooting unit can acquire device information and provide a solution optimized for smartphones. The troubleshooting unit can also provide a solution optimized for larger screens if the user is using a tablet. For example, the troubleshooting unit can acquire device information and provide a solution optimized for tablets. The troubleshooting unit can also provide a solution with detailed information if the user is using a desktop. For example, the troubleshooting unit can acquire device information and provide a solution optimized for desktops. In this way, the troubleshooting unit can provide the optimal solution by considering device information. Some or all of the above processing in the troubleshooting unit may be performed using AI, for example, or without using AI.

[0112] The advice unit can estimate the user's emotions and adjust the way it expresses advice based on those emotions. For example, if the user is feeling frustrated, the advice unit can provide concise and clear advice. For example, if the advice unit uses an emotion estimation algorithm to estimate the user's emotions and detects frustration, it can provide concise advice. The advice unit can also provide advice with detailed explanations if the user is relaxed. For example, if the advice unit uses an emotion estimation algorithm to estimate the user's emotions and detects relaxation, it can provide detailed advice. The advice unit can also provide advice that can be quickly understood if the user is in a hurry. For example, if the advice unit uses an emotion estimation algorithm to estimate the user's emotions and detects that the user is in a hurry, it can provide advice that can be quickly understood. This allows the advice unit to provide more appropriate information by adjusting the way it expresses advice according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the advice section may be performed using AI, for example, or without using AI.

[0113] The advice unit can select the most appropriate advice by referring to the user's past behavior history when providing advice. For example, the advice unit can provide the most appropriate advice based on the advice the user has received in the past. For example, the advice unit can retrieve past behavior history from a database and propose the most appropriate method for the current advice. The advice unit can also select the most efficient advice from the user's past behavior history. For example, the advice unit can analyze past behavior history and select the most appropriate advice. The advice unit can also prioritize providing advice that the user has preferred to receive in the past. For example, the advice unit prioritizes advice that the user preferred to receive based on past behavior history. In this way, the advice unit can select the most appropriate advice by referring to past behavior history. Some or all of the above processes in the advice unit may be performed using AI, for example, or without using AI.

[0114] The advice unit can estimate the user's emotions and determine the priority of advice based on the estimated emotions. For example, if the user is feeling frustrated, the advice unit will prioritize providing advice. For example, the advice unit can estimate the user's emotions using an emotion estimation algorithm, and if frustration is detected, it will prioritize providing advice. The advice unit can also provide advice with normal priority if the user is relaxed. For example, the advice unit can estimate the user's emotions using an emotion estimation algorithm, and if relaxation is detected, it will prioritize providing advice. The advice unit can also provide advice quickly if the user is in a hurry. For example, the advice unit can estimate the user's emotions using an emotion estimation algorithm, and if urgency is detected, it will provide advice quickly. In this way, the advice unit can provide more appropriate information by determining the priority of advice according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the advice section may be performed using AI, for example, or without using AI.

[0115] The advice unit can select the most appropriate advice by considering the user's geographical location when providing advice. For example, if the user is in a specific region, the advice unit will prioritize providing advice relevant to that region. For example, the advice unit will acquire geographical location information and prioritize providing advice relevant to that region. The advice unit can also customize advice based on the characteristics of different regions if the user is in a different region. For example, the advice unit will acquire geographical location information and adjust the advice based on the characteristics of that region. The advice unit can also update advice in real time based on the user's current location if the user is on the move. For example, the advice unit will acquire geographical location information in real time and update the advice based on the current location. In this way, the advice unit can provide the most appropriate advice by considering geographical location information. Some or all of the above processing in the advice unit may be performed using AI, for example, or without using AI.

[0116] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0117] The analysis unit can estimate the user's emotions and adjust the analysis priority based on the estimated emotions. For example, if the user is feeling frustrated, the analysis unit will prioritize high-priority analyses. For instance, if the analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects frustration, it will prioritize high-priority analyses. The analysis unit can also process data according to the normal analysis procedure if the user is relaxed. For example, if the analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects relaxation, it will follow the normal analysis procedure. Furthermore, if the user is in a hurry, the analysis unit can perform a rapid analysis and provide results quickly. For example, if the analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects that the user is in a hurry, it will perform a rapid analysis. This allows the analysis unit to provide a more appropriate response by adjusting the analysis priority according to the user's emotions.

[0118] The analysis unit can improve analysis accuracy by referring to the user's past inquiry history when analyzing text, images, and audio. For example, the analysis unit can refer to text messages previously sent by the user and provide analysis results for similar inquiries. For instance, the analysis unit retrieves past inquiry history from a database and compares it with the current inquiry. The analysis unit can also check if similar problems are occurring based on images previously sent by the user. For example, the analysis unit analyzes past image data and compares it with the current image. The analysis unit can also analyze audio messages previously sent by the user and provide answers to similar inquiries. For example, the analysis unit analyzes past audio data and compares it with the current audio. In this way, the analysis unit improves analysis accuracy by referring to past inquiry history.

[0119] The analysis unit can apply different analysis algorithms depending on the category of the query content during analysis. For example, the analysis unit applies a natural language processing algorithm to text-based queries. For instance, it analyzes the meaning of text using morphological analysis and contextual analysis. The analysis unit can also apply an image recognition algorithm to image-based queries. For example, it analyzes the content of images using object detection and image classification algorithms. Furthermore, the analysis unit can apply a speech recognition algorithm to speech-based queries. For example, it converts speech to text using a speech recognition algorithm and then performs text analysis. This allows the analysis unit to apply the most appropriate analysis algorithm for the query content, thereby improving analysis accuracy.

[0120] The analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the user is feeling frustrated, the analysis unit can display concise and clear analysis results. For instance, if the analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects frustration, it will display concise analysis results. The analysis unit can also display detailed analysis results if the user is relaxed. For example, if the analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects relaxation, it will display detailed analysis results. The analysis unit can also display concise analysis results if the user is in a hurry. For example, if the analysis unit uses an emotion estimation algorithm to estimate the user's emotions and detects that the user is in a hurry, it will display concise analysis results. In this way, the analysis unit can provide more appropriate information by adjusting how the analysis results are displayed according to the user's emotions.

[0121] The analysis unit can customize the analysis results by taking into account the user's geographical location information during analysis. For example, if the user is in a specific region, the analysis unit will prioritize analyzing information related to that region. For instance, the analysis unit will acquire geographical location information and prioritize analyzing data related to that region. Furthermore, if the user is in a different region, the analysis unit can also customize the analysis results based on the characteristics of that region. For example, the analysis unit will acquire geographical location information and adjust the analysis results based on the characteristics of that region. Additionally, if the user is on the move, the analysis unit can update the analysis results in real time based on their current location. For example, the analysis unit will acquire geographical location information in real time and update the analysis results based on their current location. This allows the analysis unit to provide more appropriate analysis results by considering geographical location information.

[0122] The reception desk can estimate the user's emotions and adjust its response based on those emotions. For example, if the user is feeling frustrated, the reception desk can provide a quick and concise response. For instance, the reception desk can use an emotion estimation algorithm to estimate the user's emotions and, if frustration is detected, provide a quick response. The reception desk can also provide a more detailed explanation if the user is relaxed. For example, the reception desk can use an emotion estimation algorithm to estimate the user's emotions and, if relaxation is detected, provide a detailed explanation. The reception desk can also provide a quick response and offer only the essential information if the user is in a hurry. For example, the reception desk can use an emotion estimation algorithm to estimate the user's emotions and, if urgency is detected, provide a quick response. This allows the reception desk to provide a more appropriate response by adjusting its response based on the user's emotions.

[0123] The reception department can select the optimal reception method by referring to the user's past inquiry history at the time of reception. For example, the reception department can propose the optimal method based on the reception methods the user has used in the past. For example, the reception department can retrieve past inquiry history from the database and propose the most suitable method for the current inquiry. The reception department can also select the most efficient reception method from the user's past inquiry history. For example, the reception department can analyze past inquiry history and select the optimal reception method. The reception department can also prioritize providing the reception method that the user has preferred to use in the past. For example, the reception department prioritizes the method that the user preferred to use based on past inquiry history. In this way, the reception department can select the optimal reception method by referring to past inquiry history.

[0124] The reception desk can estimate the user's emotions and determine the priority of service based on those emotions. For example, if the user is feeling frustrated, the reception desk will prioritize their response. For instance, the reception desk uses an emotion estimation algorithm to estimate the user's emotions, and if frustration is detected, it will prioritize their response. The reception desk can also respond to users who are relaxed with the normal priority. For example, the reception desk uses an emotion estimation algorithm to estimate the user's emotions, and if relaxation is detected, it will respond with the normal priority. The reception desk can also respond quickly if the user is in a hurry. For example, the reception desk uses an emotion estimation algorithm to estimate the user's emotions, and if urgency is detected, it will respond quickly. This allows the reception desk to provide more appropriate service by determining the priority of service according to the user's emotions.

[0125] The reception desk can select the optimal reception method by considering the user's device information at the time of reception. For example, if the user is using a smartphone, the reception desk can provide a mobile-friendly reception method. For example, the reception desk can acquire device information and provide a reception method optimized for smartphones. Also, if the user is using a tablet, the reception desk can provide a reception method optimized for larger screens. For example, the reception desk can acquire device information and provide a reception method optimized for tablets. Furthermore, if the user is using a desktop, the reception desk can provide a reception method that includes detailed information. For example, the reception desk can acquire device information and provide a reception method optimized for desktops. In this way, the reception desk can provide the optimal reception method by considering the device information.

[0126] The generation unit can estimate the user's emotions and adjust the way the response is expressed based on the estimated emotions. For example, if the user is feeling frustrated, the generation unit can generate a concise and clear response. For instance, it can use an emotion estimation algorithm to estimate the user's emotions and, if it detects frustration, generate a concise response. The generation unit can also generate a response with detailed explanations if the user is relaxed. For example, it can use an emotion estimation algorithm to estimate the user's emotions and, if it detects relaxation, generate a detailed response. The generation unit can also generate a response that can be quickly understood if the user is in a hurry. For example, it can use an emotion estimation algorithm to estimate the user's emotions and, if it detects that the user is in a hurry, generate a response that can be quickly understood. In this way, the generation unit can provide more appropriate responses by adjusting the way the response is expressed according to the user's emotions.

[0127] The following briefly describes the processing flow for example form 2.

[0128] Step 1: The analysis unit analyzes text, images, and audio. For example, the analysis unit uses natural language processing techniques to perform text analysis. For example, the analysis unit uses morphological analysis to analyze the meaning of text. The analysis unit also uses image recognition techniques to perform image analysis. For example, the analysis unit uses an object detection algorithm to identify objects in an image. The analysis unit also uses speech recognition techniques to perform audio analysis. For example, the analysis unit uses a speech recognition algorithm to convert audio into text. Step 2: The reception desk receives inquiries. The reception desk can receive inquiries in the form of text, images, and audio. For example, the reception desk can receive text messages. The reception desk can also receive image files. The reception desk can also receive audio messages. Step 3: The generation unit generates an answer based on the results analyzed by the analysis unit. The generation unit generates an answer using, for example, a generation AI. For example, the generation unit generates an answer in natural language using a text generation AI. The generation unit can also generate an image-based answer using an image generation AI. The generation unit can also generate an audio-based answer using an audio generation AI. Step 4: The sentiment analysis unit performs real-time sentiment analysis. The sentiment analysis unit can, for example, analyze a user's text message to estimate their emotions. For example, the sentiment analysis unit extracts emotions from text using natural language processing techniques. The sentiment analysis unit can also analyze a user's voice message to estimate their emotions. For example, the sentiment analysis unit extracts emotions from voice using voice analysis techniques. The sentiment analysis unit can also analyze a user's image to estimate their emotions. For example, the sentiment analysis unit extracts emotions from facial expressions using image analysis techniques. Step 5: The escalation unit escalates based on the emotional state detected by the emotion analysis unit. For example, if the user is feeling frustrated, the escalation unit will escalate to a specialized support team. For example, if the emotion analysis unit detects frustration, the escalation unit will immediately notify the support team. The escalation unit can also quickly escalate if the user requires urgent support. For example, if the emotion analysis unit detects an urgent emotional state, the escalation unit will immediately notify the support team.

[0129] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0130] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0131] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements described above, including the analysis unit, reception unit, generation unit, sentiment analysis unit, escalation unit, multilingual support unit, troubleshooting unit, and advice unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 and the processor 28 of the data processing unit 12. The reception unit is implemented by the reception device 38 of the smart device 14 and the communication I / F 26 of the data processing unit 12. The generation unit is implemented by the processor 46 of the smart device 14 and the specific processing unit 290 of the data processing unit 12. The sentiment analysis unit is implemented by the processor 46 of the smart device 14 and the specific processing unit 290 of the data processing unit 12. The escalation unit is implemented by the processor 46 of the smart device 14 and the specific processing unit 290 of the data processing unit 12. The multilingual support unit is implemented by the processor 46 of the smart device 14 and the specific processing unit 290 of the data processing unit 12. The troubleshooting unit is implemented by the processor 46 of the smart device 14 and the specific processing unit 290 of the data processing unit 12. The advice unit is implemented by the processor 46 of the smart device 14 and the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device and control unit is not limited to the example described above and can be modified in various ways.

[0133] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0134] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0136] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0141] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0142] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0143] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0145] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0147] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] Each of the multiple elements described above, including the analysis unit, reception unit, generation unit, sentiment analysis unit, escalation unit, multilingual support unit, troubleshooting unit, and advice unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 and the processor 28 of the data processing unit 12. The reception unit is implemented by the microphone 238 of the smart glasses 214 and the communication I / F 26 of the data processing unit 12. The generation unit is implemented by the processor 46 of the smart glasses 214 and the specific processing unit 290 of the data processing unit 12. The sentiment analysis unit is implemented by the processor 46 of the smart glasses 214 and the specific processing unit 290 of the data processing unit 12. The escalation unit is implemented by the processor 46 of the smart glasses 214 and the specific processing unit 290 of the data processing unit 12. The multilingual support unit is implemented by the processor 46 of the smart glasses 214 and the specific processing unit 290 of the data processing unit 12. The troubleshooting unit is implemented by the processor 46 of the smart glasses 214 and the specific processing unit 290 of the data processing unit 12. The advice unit is implemented by the processor 46 of the smart glasses 214 and the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device and control unit is not limited to the example described above and can be modified in various ways.

[0149] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0150] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0152] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0153] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0155] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0156] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0157] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0158] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0159] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0160] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0161] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0162] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0163] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0164] Each of the multiple elements described above, including the analysis unit, reception unit, generation unit, sentiment analysis unit, escalation unit, multilingual support unit, troubleshooting unit, and advice unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 and the processor 28 of the data processing unit 12. The reception unit is implemented by the microphone 238 of the headset terminal 314 and the communication I / F 26 of the data processing unit 12. The generation unit is implemented by the processor 46 of the headset terminal 314 and the specific processing unit 290 of the data processing unit 12. The sentiment analysis unit is implemented by the processor 46 of the headset terminal 314 and the specific processing unit 290 of the data processing unit 12. The escalation unit is implemented by the processor 46 of the headset terminal 314 and the specific processing unit 290 of the data processing unit 12. The multilingual support unit is implemented by the processor 46 of the headset terminal 314 and the specific processing unit 290 of the data processing unit 12. The troubleshooting unit is implemented by the processor 46 of the headset terminal 314 and the specific processing unit 290 of the data processing unit 12. The advice unit is implemented by the processor 46 of the headset terminal 314 and the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device and control unit is not limited to the example described above and can be modified in various ways.

[0165] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0166] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0167] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0168] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0169] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0170] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0171] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0172] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0173] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0174] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0175] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0176] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0177] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0178] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0179] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0180] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0181] Each of the multiple elements described above, including the analysis unit, reception unit, generation unit, sentiment analysis unit, escalation unit, multilingual support unit, troubleshooting unit, and advice unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 and the processor 28 of the data processing unit 12. The reception unit is implemented by the microphone 238 of the robot 414 and the communication I / F 26 of the data processing unit 12. The generation unit is implemented by the processor 46 of the robot 414 and the specific processing unit 290 of the data processing unit 12. The sentiment analysis unit is implemented by the processor 46 of the robot 414 and the specific processing unit 290 of the data processing unit 12. The escalation unit is implemented by the processor 46 of the robot 414 and the specific processing unit 290 of the data processing unit 12. The multilingual support unit is implemented by the processor 46 of the robot 414 and the specific processing unit 290 of the data processing unit 12. The troubleshooting unit is implemented by the processor 46 of the robot 414 and the specific processing unit 290 of the data processing unit 12. The advice unit is implemented by the processor 46 of the robot 414 and the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0182] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0183] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0184] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0185] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0186] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0187] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0188] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0189] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0190] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0191] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0192] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0193] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0194] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0195] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0196] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0197] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0198] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0199] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0200] (Note 1) An analysis unit that analyzes text, images, and audio, The reception desk that handles inquiries, A generation unit that generates an answer based on the results of the analysis performed by the analysis unit, The emotion analysis department performs real-time emotion analysis, The system includes an escalation unit that performs escalation based on the emotional state detected by the emotion analysis unit. A system characterized by the following features. (Note 2) It is equipped with a multilingual support unit that handles multiple languages. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a troubleshooting unit for troubleshooting. The system described in Appendix 1, characterized by the features described herein. (Note 4) Equipped with an advisory department that provides personalized advice. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit, It estimates the user's emotions and adjusts the analysis priority based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, When analyzing text, images, and audio, we improve analysis accuracy by referring to the user's past inquiry history. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, During analysis, the analysis results are customized by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, During analysis, the system analyzes users' social media activity and incorporates relevant information into the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is The system estimates the user's emotions and adjusts the receptionist's response based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When a user submits an inquiry, the system will refer to their past inquiry history to select the most appropriate submission method. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is The system estimates the user's emotions and determines the priority of the reception process based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned reception unit is At the time of registration, the optimal registration method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is It estimates the user's emotions and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is When generating an answer, adjust the level of detail in the answer based on the importance of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is When generating responses, different generation algorithms are applied depending on the category of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is It estimates the user's emotions and adjusts the length of the response based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is When generating responses, the priority of responses is determined based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is When generating responses, the order of responses is adjusted based on the relevance of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned emotion analysis unit, It estimates user emotions and improves the accuracy of sentiment analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned emotion analysis unit, When performing sentiment analysis, we improve the accuracy of the analysis by referring to the user's past emotional states. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned emotion analysis unit, During sentiment analysis, different analysis algorithms are applied based on the user's statements and tone. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned emotion analysis unit, It estimates the user's emotions and adjusts how the emotion analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned emotion analysis unit, When performing sentiment analysis, the analysis results are customized by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned emotion analysis unit, During sentiment analysis, the user's social media activity is analyzed, and relevant information is incorporated into the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 27) The escalation unit is, It estimates the user's emotions and adjusts the timing of escalation based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The escalation unit is, During escalation, the system selects the most appropriate escalation method by referring to the user's past inquiry history. The system described in Appendix 1, characterized by the features described herein. (Note 29) The escalation unit is, The system estimates the user's emotions and determines the priority of escalations based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The escalation unit is, During escalation, the optimal escalation method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned multilingual support unit is It estimates the user's emotions and adjusts the multilingual expression based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned multilingual support unit is When providing multilingual support, the system selects the most appropriate response method by referring to the user's past inquiry history. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned multilingual support unit is It estimates user sentiment and determines the priority of multilingual support based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned multilingual support unit is When providing multilingual support, the optimal support method is selected by considering the user's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 35) The troubleshooting unit described above, It estimates the user's emotions and adjusts troubleshooting methods based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 36) The troubleshooting unit described above, During troubleshooting, the system selects the optimal solution by referring to the user's past troubleshooting history. The system described in Appendix 3, characterized by the features described herein. (Note 37) The troubleshooting unit described above, It estimates the user's emotions and prioritizes troubleshooting based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The troubleshooting unit described above, During troubleshooting, the optimal solution is selected by considering the user's device information. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned advice section, It estimates the user's emotions and adjusts the way advice is presented based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned advice section, When providing advice, the system selects the most appropriate advice by referring to the user's past behavioral history. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned advice section, It estimates the user's emotions and prioritizes advice based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned advice section, When providing advice, the system selects the most appropriate advice by taking into account the user's geographical location. The system described in Appendix 4, characterized by the features described herein. [Explanation of symbols]

[0201] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An analysis unit that analyzes text, images, and audio, The reception desk that handles inquiries, A generation unit that generates an answer based on the results of the analysis performed by the analysis unit, The emotion analysis department performs real-time emotion analysis, The system includes an escalation unit that performs escalation based on the emotional state detected by the emotion analysis unit. A system characterized by the following features.

2. It is equipped with a multilingual support unit that handles multiple languages. The system according to feature 1.

3. It includes a troubleshooting unit for troubleshooting. The system according to feature 1.

4. Equipped with an advisory department that provides personalized advice. The system according to feature 1.

5. The aforementioned analysis unit, It estimates the user's emotions and adjusts the analysis priority based on the estimated user emotions. The system according to feature 1.

6. The aforementioned analysis unit, When analyzing text, images, and audio, we improve analysis accuracy by referring to the user's past inquiry history. The system according to feature 1.

7. The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the inquiry. The system according to feature 1.

8. The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system according to feature 1.

9. The aforementioned analysis unit, During analysis, the analysis results are customized by taking into account the user's geographical location. The system according to feature 1.

10. The aforementioned analysis unit, During analysis, the system analyzes users' social media activity and incorporates relevant information into the analysis. The system according to feature 1.

Images