System

Abstract

An object of a system according to an embodiment is to improve the efficiency of inquiry handling.SOLUTION: A system according to an embodiment includes an inquiry reception unit, a response generation unit, a classification unit, and a prioritization unit. The inquiry reception unit receives an inquiry from a user. The response generation unit generates a response to the inquiry received by the inquiry reception unit. The classification unit classifies the inquiry content based on the response generated by the response generation unit. The prioritizing unit prioritizes the queries classified by the classifying unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques do not efficiently handle inquiries, and there is room for improvement.

[0005] The system according to the embodiment aims to improve the efficiency of inquiries. [Means for solving the problem]

[0006] The system according to the embodiment includes an inquiry reception unit, a response generation unit, a classification unit, and a prioritization unit. The inquiry reception unit receives inquiries from users. The response generation unit generates responses to the inquiries received by the inquiry reception unit. The classification unit classifies the inquiry content based on the responses generated by the response generation unit. The prioritization unit prioritizes the inquiries classified by the classification unit. [Effects of the Invention]

[0007] The system according to the embodiment can improve the efficiency of responding to inquiries. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

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

[0028] (Example 1) An inquiry response system according to an embodiment of the present invention is a system that aims to enable easier and simpler communication between both the inquiry sender and the inquiry recipient. This system utilizes generative AI to automatically respond to inquiries in natural language, categorize and prioritize inquiry content, automatically follow up, manage and analyze inquiry history, and support multiple languages. This allows the inquiry response system to enable easier and simpler communication between both the inquiry sender and the inquiry recipient. For example, users can easily send inquiries and receive prompt and appropriate responses. Furthermore, the inquiry recipient can also respond more efficiently by automating the categorization, prioritization, and follow-up of inquiries.

[0029] An inquiry response system according to an embodiment includes an inquiry reception unit, a response generation unit, a classification unit, and a prioritization unit. The inquiry reception unit receives inquiries from users. For example, it can receive inquiries in text format. It can also receive inquiries via voice input. It can also receive inquiries including images and videos. The response generation unit generates a response to the inquiry received by the inquiry reception unit. For example, the generation AI generates an appropriate response to the user's inquiry using natural language processing technology. The generation AI can also generate a template-based response. Furthermore, the generation AI can generate a personalized response by referring to the user's past inquiry history. The classification unit classifies the inquiry content based on the response generated by the response generation unit. For example, the generation AI classifies the inquiry content by category. The generation AI can also determine the urgency of the inquiry content and prioritize high-priority inquiries. Furthermore, the generation AI can perform more precise classification by taking into account background information of the inquiry content. The prioritization unit prioritizes the inquiries classified by the classification unit. For example, the generation AI prioritizes inquiries based on the urgency and importance of the inquiry content. The generation AI can also prioritize inquiries from specific users by taking into account user attribute information. Furthermore, the generation AI can classify inquiry content in real time and dynamically change priorities. As a result, the inquiry response system according to the embodiment automates processes from inquiry reception to response generation, classification, and prioritization, thereby achieving efficient inquiry response. For example, the inquiry response system can quickly process inquiries from users and provide appropriate responses. Furthermore, the inquiry response system can prioritize important inquiries by classifying and prioritizing the inquiry content. Furthermore, the inquiry response system can perform more precise classification and prioritization by taking into account background information of the inquiry content.

[0030] The response generation unit can refer to the inquiry history and generate a personalized response. For example, the generation AI in the response generation unit analyzes the user's past inquiry history and generates a personalized answer based on past responses to similar inquiries. For example, it provides the current inventory status based on the inventory status of a product the user has previously inquired about. The response generation unit also refers to the user's past inquiry history, finds specific patterns and trends, and customizes the response based on them. For example, it provides more detailed information on topics the user frequently inquires about. The response generation unit also learns the user's past inquiry history and generates a personalized response. For example, it provides new information related to the user's previous inquiry. This enables more appropriate responses by generating personalized responses based on the user's past inquiry history.

[0031] The response generation unit can generate a response taking into account the user's current situation and environment. For example, the generation AI in the response generation unit obtains the user's location information and customizes the response based on that information. For example, if the user is in a specific area, the response generation unit provides the inventory status of stores in that area. The response generation unit also generates a response taking into account the user's time of day. For example, if an inquiry is made at night, the response generation unit provides information about the next day's business hours. The response generation unit also analyzes the user's current situation and environment and generates a response based on that. For example, if the user is on the move, the response generation unit provides information about the nearest store. This allows for a more appropriate response by generating a response that takes into account the user's current situation and environment.

[0032] The inquiry reception unit can accept inquiries via voice input, and the response generation unit can generate a voice response based on the voice input. For example, the inquiry reception unit records what a user dictates with a microphone and converts it into text data using voice recognition technology. For example, voice recognition software automatically analyzes the voice and saves it as text. The inquiry reception unit also creates a system that recognizes what a user dictates in real time and displays it as text data. For example, the text is displayed on a screen simultaneously with the voice input. The inquiry reception unit also uses the voice input to convert what the user dictates into text and saves the text data as an answer. For example, it performs high-precision text conversion using voice recognition technology. The response generation unit, for example, uses a generation AI to analyze the voice input and convert the natural language inquiry into text to generate a response. For example, when a user asks, "Is the product in stock?" via voice, it provides a voice answer. The response generation unit also uses voice recognition technology to analyze the user's voice input, and the generation AI generates an appropriate response. For example, when a user makes a voice inquiry, it provides a detailed voice explanation. The response generation unit also constructs a system in which the generation AI analyzes voice input and generates a voice response. For example, when a user makes a voice inquiry, a real-time voice response is provided. This improves user convenience by generating a voice response to a voice-input inquiry.

[0033] The response generation unit can automatically attach related images and videos when generating a response. For example, the response generation unit uses a generation AI to analyze the content of an inquiry and automatically attach related images and videos to generate a response. For example, if an inquiry is made about product stock status, images of the product and an explanatory video are attached. The response generation unit also uses the generation AI to automatically search for related visual content in response to a user inquiry and attach it to the response. For example, if an inquiry is made about how to use a product, a video on how to use it is attached. The response generation unit also builds a system in which related images and videos are automatically attached when the generation AI generates a response. For example, if a user inquires about the details of a specific product, a promotional video for that product is attached. This allows the automatic attachment of related images and videos to provide more visual information to the user.

[0034] The classification unit can perform more precise classification by taking into account background information of the inquiry content. For example, the generation AI analyzes the background information of the inquiry content and performs classification and prioritization by taking into account past trouble history. For example, if a similar trouble has occurred in the past, that inquiry will be processed with priority. The classification unit also builds a system in which the generation AI performs precise classification and prioritization based on the background information of the inquiry content. For example, it refers to past trouble history and processes inquiries with a high level of urgency with priority. The classification unit also analyzes the background information of the inquiry content by the generation AI and performs classification and prioritization by taking into account past trouble history. For example, if a particular user frequently reports trouble, it will process that user's inquiries with priority. This enables more precise classification by taking into account the background information of the inquiry content.

[0035] When classifying inquiry content, the classification unit can automatically recognize and appropriately classify industry-specific terminology and slang. The classification unit, for example, builds a system in which a generation AI automatically recognizes industry-specific terminology and slang and appropriately classifies inquiry content. For example, it recognizes and classifies technical terms in the IT industry. The classification unit also analyzes industry-specific terminology and slang contained in the inquiry content, and the generation AI appropriately classifies it. For example, it recognizes and classifies technical terms in the medical industry. The classification unit also allows the generation AI to automatically recognize industry-specific terminology and slang and appropriately classify the inquiry content. For example, it recognizes and classifies slang in the financial industry. This enables more appropriate classification by automatically recognizing industry-specific terminology and slang.

[0036] The classification unit can classify inquiry content in real time and dynamically change priorities. For example, the classification unit builds a system in which a generation AI analyzes inquiry content in real time and classifies and prioritizes it. For example, when a new inquiry is added, the priority is dynamically changed. The classification unit also develops an algorithm that classifies inquiry content in real time and dynamically changes the priority. For example, when a highly urgent inquiry is added, that inquiry is processed with priority. The classification unit also builds a system in which a generation AI analyzes inquiry content in real time and dynamically changes the priority. For example, the priority is adjusted according to the user's situation. This enables faster and more appropriate responses by classifying inquiry content in real time and dynamically changing the priority.

[0037] When classifying query content, the classification unit can refer to other data sources and classify query content into highly relevant categories. For example, the classification unit constructs a system in which the generation AI refers to trend data on social media and classifies query content into highly relevant categories. For example, queries related to current trends are processed with priority. The classification unit also refers to other data sources so that the generation AI appropriately classifies query content. For example, the classifier classifies query content based on data from news sites. The classification unit also analyzes trend data on social media and classifies query content into highly relevant categories. For example, if a specific topic is trending, queries related to that topic are processed with priority. This makes it possible to classify queries into more relevant categories by referring to other data sources.

[0038] The prioritization unit can perform more precise prioritization by taking into account background information about the inquiry content. For example, the prioritization unit uses the generation AI to analyze the background information about the inquiry content and classify and prioritize the inquiries taking into account past trouble history. For example, if a similar trouble has occurred in the past, that inquiry will be handled with priority. The prioritization unit also builds a system in which the generation AI performs precise classification and prioritization based on the background information about the inquiry content. For example, it refers to past trouble history and handles inquiries with higher urgency with priority. The prioritization unit also uses the generation AI to analyze the background information about the inquiry content and classify and prioritize the inquiries taking into account past trouble history. For example, if a specific user frequently reports trouble, it will handle that user's inquiries with priority. This enables more precise prioritization by taking into account the background information of the inquiry content.

[0039] The prioritization unit can automatically recognize industry-specific terminology and slang and appropriately classify inquiry content when classifying inquiry content. The prioritization unit, for example, builds a system in which a generation AI automatically recognizes industry-specific terminology and slang and appropriately classifies inquiry content. For example, it recognizes and classifies IT industry terminology. The prioritization unit also analyzes industry-specific terminology and slang contained in inquiry content, and the generation AI appropriately classifies it. For example, it recognizes and classifies medical industry terminology. The prioritization unit also allows a generation AI to automatically recognize industry-specific terminology and slang and appropriately classify inquiry content. For example, it recognizes and classifies financial industry slang. This automatically recognizes industry-specific terminology and slang, enabling more appropriate classification.

[0040] The prioritization unit can classify inquiry content in real time and dynamically change priorities. For example, the prioritization unit constructs a system in which a generation AI analyzes inquiry content in real time and classifies and prioritizes it. For example, when a new inquiry is added, the priority is dynamically changed. The prioritization unit also develops an algorithm that classifies inquiry content in real time and dynamically changes the priority. For example, when a highly urgent inquiry is added, that inquiry is processed with priority. The prioritization unit also constructs a system in which a generation AI analyzes inquiry content in real time and dynamically changes the priority. For example, the priority is adjusted according to the user's situation. This enables faster and more appropriate responses by classifying inquiry content in real time and dynamically changing the priority.

[0041] When classifying query content, the prioritization unit can refer to other data sources and classify query content into highly relevant categories. For example, the prioritization unit constructs a system in which the generation AI refers to trend data from social media and classifies query content into highly relevant categories. For example, queries related to current trends are processed preferentially. The prioritization unit also refers to other data sources so that the generation AI appropriately classifies query content. For example, the query content is classified based on data from news sites. The prioritization unit also analyzes trend data from social media and classifies query content into highly relevant categories. For example, if a specific topic is trending, queries related to that topic are processed preferentially. This makes it possible to classify queries into more relevant categories by referring to other data sources.

[0042] The response generation unit can optimize the timing of follow-ups based on the user's behavioral patterns. In the response generation unit, for example, the generation AI analyzes the user's behavioral patterns and determines the optimal timing of follow-ups. For example, follow-ups are performed during times when the user frequently accesses the site. In addition, the response generation unit optimizes the timing of follow-ups based on the user's past behavioral data. For example, if the user is active on a specific day of the week, follow-ups are performed on that day. In addition, the response generation unit analyzes the user's behavioral patterns in real time and determines the optimal timing of follow-ups. For example, follow-ups are performed if the user has not been active recently. This enables more effective follow-ups by optimizing the timing of follow-ups based on the user's behavioral patterns.

[0043] When performing follow-up, the response generation unit can refer to the user's past response history and perform personalized follow-up. For example, the response generation unit uses a generation AI to analyze the user's past response history and perform personalized follow-up. For example, it may provide new information related to content that the user has previously inquired about. The response generation unit also customizes the content of the follow-up based on the user's past response history. For example, it may provide a new solution related to a problem that the user has previously solved. The response generation unit also builds a system in which the generation AI refers to the user's past response history and performs personalized follow-up. For example, it may provide the latest information on a product that the user has previously inquired about. This makes it possible to perform more personalized follow-up by referring to the user's past response history.

[0044] The response generation unit can send follow-up content via multiple media. The response generation unit, for example, builds a system in which a generation AI generates follow-up content and sends it via multiple media. For example, the follow-up is performed using email, SMS, and app notification. The response generation unit also has the generation AI send the follow-up content via an appropriate medium depending on the user's preferences. For example, if the user prefers email, the follow-up is performed via email. The response generation unit also has the generation AI send the follow-up content via multiple media so that the user can receive the follow-up in the most accessible way. For example, the response generation unit sends app notification and SMS simultaneously. In this way, by sending the follow-up via multiple media, the user can receive the follow-up in the most accessible way.

[0045] The response generation unit can automatically attach related documents and links when performing a follow-up. For example, the response generation unit builds a system in which the generation AI automatically attaches related documents and links when generating the content of a follow-up. For example, it attaches links to product manuals and FAQ pages. The response generation unit also searches for related documents and links according to the content of a user's inquiry and attaches them to the follow-up. For example, it attaches documents containing solutions to technical problems. The response generation unit also automatically attaches related documents and links when the generation AI performs a follow-up. For example, it attaches a link containing detailed information about a product that the user inquired about. In this way, by automatically attaching related documents and links, it is possible to provide the user with more detailed information.

[0046] The inquiry history management unit can analyze the inquiry history in chronological order and identify long-term trends. For example, the inquiry history management unit builds a system in which a generation AI analyzes the inquiry history in chronological order and identifies long-term trends. For example, it identifies a trend of increasing inquiries about a specific product. The inquiry history management unit also analyzes the inquiry history in chronological order and the generation AI identifies long-term trends. For example, it identifies seasonal inquiry patterns. The inquiry history management unit also analyzes the inquiry history in chronological order and identifies long-term trends. For example, it identifies a trend of increasing inquiries about a specific problem. In this way, by analyzing the inquiry history in chronological order, long-term trends can be identified, enabling more effective responses.

[0047] When analyzing the inquiry history, the inquiry history management unit takes into account user attribute information and can identify trends by attribute. For example, the inquiry history management unit builds a system in which a generation AI analyzes user attribute information and identifies trends by attribute based on the inquiry history. For example, it identifies topics that are frequently inquired about by a specific age group. The inquiry history management unit also takes into account user attribute information and the generation AI analyzes the inquiry history and identifies trends by attribute. For example, it identifies differences in inquiries based on gender. The inquiry history management unit also takes into account user attribute information and the generation AI analyzes user attribute information and identifies trends by attribute based on the inquiry history. For example, it identifies topics that are frequently inquired about by users in a specific region. In this way, by taking user attribute information into account, trends by attribute can be identified and more effective responses can be made.

[0048] The inquiry history management unit can integrate inquiry history with other data sources and perform comprehensive analysis. For example, the inquiry history management unit builds a system in which a generation AI integrates inquiry history and sales data to perform comprehensive analysis. For example, it analyzes the relationship between product sales figures and the number of inquiries. The inquiry history management unit also integrates inquiry history with other data sources and the generation AI performs comprehensive analysis. For example, it integrates marketing data and inquiry history for analysis. The inquiry history management unit also integrates inquiry history with other data sources and the generation AI performs comprehensive analysis. For example, it integrates customer satisfaction data and inquiry history for analysis. This makes it possible to perform comprehensive analysis by integrating inquiry history with other data sources.

[0049] When analyzing the inquiry history, the inquiry history management unit can simultaneously analyze inquiries in different languages ​​and identify global trends. The inquiry history management unit, for example, builds a system in which a generation AI analyzes inquiries in different languages ​​and identifies global trends. For example, queries in English and Japanese are analyzed simultaneously to identify trends. The inquiry history management unit also analyzes inquiries in different languages ​​and the generation AI identifies global trends. For example, query content in multiple languages ​​is integrated and analyzed. The inquiry history management unit also analyzes inquiries in different languages ​​simultaneously and identifies global trends. For example, it identifies a trend of an increase in inquiries about a particular topic in multiple languages. In this way, by simultaneously analyzing queries in different languages, global trends can be identified and more effective responses can be made.

[0050] The response generation unit can automatically translate the query content into multiple languages ​​and generate a response that takes into account the nuances in each language. The response generation unit, for example, builds a system in which a generation AI automatically translates the query content into multiple languages ​​and generates a response that takes into account the nuances in each language. For example, the response generation unit automatically translates the query content into multiple languages ​​and the generation AI ... an appropriate response in German. This enables more appropriate responses by automatically translating the query content into multiple languages ​​and generating a response that takes into account the nuances in each language.

[0051] The response generation unit can generate responses that take into account regional culture and customs when providing multilingual support. For example, the response generation unit builds a system in which, when the generation AI provides multilingual support, it generates responses that take into account regional culture and customs. For example, it generates responses that take into account Japanese culture. The response generation unit also generates responses that take into account regional culture and customs when the generation AI provides multilingual support. For example, it generates responses that take into account American culture. The response generation unit also generates responses that take into account regional culture and customs when the generation AI provides multilingual support. For example, it generates responses that take into account Indian culture. This enables more appropriate responses by generating responses that take into account regional culture and customs.

[0052] The response generation unit realizes multilingual support through voice input and can generate voice responses. The response generation unit, for example, builds a system in which a generation AI analyzes voice input and generates voice responses in multiple languages. For example, voice input in English is converted into a voice response in Japanese. The response generation unit also uses voice recognition technology to have the generation AI analyze the voice input and generate voice responses in multiple languages. For example, voice input in French is converted into a voice response in English. The response generation unit also uses the generation AI to analyze the voice input and generate voice responses in multiple languages. For example, voice input in Spanish is converted into a voice response in German. This realizes multilingual support through voice input and generates voice responses, enabling more appropriate responses.

[0053] The response generation unit can automatically attach related images and videos when providing multilingual support, thereby providing visual information. For example, the response generation unit builds a system in which, when the generation AI provides multilingual support, it automatically attaches related images and videos to generate responses. For example, an explanatory video in Japanese is attached to an inquiry in English. The response generation unit also allows the generation AI to automatically search for related images and videos according to the inquiry content and attach them to the response. For example, an explanatory image in English is attached to an inquiry in French. The response generation unit also automatically attaches related images and videos when the generation AI provides multilingual support. For example, an explanatory video in German is attached to an inquiry in Spanish. This makes it possible to provide visual information by automatically attaching related images and videos when providing multilingual support.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The inquiry response system can further analyze the user's behavioral history and optimize responses based on the behavioral patterns. For example, it can analyze what time of day the user has made inquiries in the past and provide a response tailored to that time of day. Also, if the user is using a specific device, it can generate a response optimized for that device. Furthermore, it can analyze what topics the user has been interested in in the past and provide information related to those topics preferentially. This allows for more personalized responses by providing responses based on the user's behavioral patterns.

[0056] The inquiry response system can also link with a user's social media account and generate responses by analyzing their social media activity. For example, if a user mentions a particular product on social media, the system can provide the latest information about that product. Or, if a user discusses a particular issue on social media, the system can provide solutions related to that issue. Furthermore, the system can provide relevant information based on the interests and concerns expressed by the user through their social media activity. This allows for more appropriate responses by taking into account social media activity.

[0057] The inquiry response system can also analyze the user's health data and generate a response based on their health status. For example, if a user is using a health app, the system can analyze that data to provide health advice. If a user inquires about a specific health problem, the system can provide the latest research results and treatments related to that problem. It can also provide preventative advice based on the user's health data. This allows for more appropriate responses based on the user's health status.

[0058] The inquiry response system can also analyze a user's purchasing history and generate a response based on their purchasing patterns. For example, it can suggest related products based on information about products the user has purchased in the past. Also, if a user frequently purchases products from a specific category, it can provide the latest information related to that category. Furthermore, it can provide information about the stock status and price fluctuations of specific products based on the user's purchasing history. This allows for more personalized responses by providing responses based on the user's purchasing patterns.

[0059] The inquiry response system can also analyze the user's location information and generate a response based on that location information. For example, if the user is in a specific area, the system can provide the inventory status and business hours of stores in that area. If the user is traveling, the system can also provide tourist information and transportation information for the user's destination. Furthermore, the system can provide information on the nearest service locations and events based on the user's location information. This allows for more appropriate responses by providing responses based on the user's location information.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The inquiry reception unit receives an inquiry from a user. For example, the inquiry may be in text format, voice input, or may include an image or video. Step 2: The response generation unit generates a response to the inquiry received by the inquiry reception unit. For example, the generation AI can generate an appropriate response using natural language processing technology, and can generate template-based responses or personalized responses that refer to the user's past inquiry history. Step 3: The classification unit classifies the inquiry content based on the response generated by the response generation unit. For example, the generation AI can classify the inquiry content by category, determine the urgency, and prioritize inquiries with high priority. It can also perform more precise classification by taking into account the background information of the inquiry content. Step 4: The prioritization unit prioritizes the inquiries classified by the classification unit. For example, the generation AI can prioritize inquiries based on the urgency and importance of the inquiry content, and prioritize inquiries from specific users by taking into account their attribute information. It can also classify inquiry content in real time and dynamically change priorities.

[0062] (Example 2) An inquiry response system according to an embodiment of the present invention is a system that aims to enable easier and simpler communication between both the inquiry sender and the inquiry recipient. This system utilizes generative AI to automatically respond to inquiries in natural language, categorize and prioritize inquiry content, automatically follow up, manage and analyze inquiry history, and support multiple languages. This allows the inquiry response system to enable easier and simpler communication between both the inquiry sender and the inquiry recipient. For example, users can easily send inquiries and receive prompt and appropriate responses. Furthermore, the inquiry recipient can also respond more efficiently by automating the categorization, prioritization, and follow-up of inquiries.

[0063] An inquiry response system according to an embodiment includes an inquiry reception unit, a response generation unit, a classification unit, and a prioritization unit. The inquiry reception unit receives inquiries from users. For example, it can receive inquiries in text format. It can also receive inquiries via voice input. It can also receive inquiries including images and videos. The response generation unit generates a response to the inquiry received by the inquiry reception unit. For example, the generation AI generates an appropriate response to the user's inquiry using natural language processing technology. The generation AI can also generate a template-based response. Furthermore, the generation AI can generate a personalized response by referring to the user's past inquiry history. The classification unit classifies the inquiry content based on the response generated by the response generation unit. For example, the generation AI classifies the inquiry content by category. The generation AI can also determine the urgency of the inquiry content and prioritize high-priority inquiries. Furthermore, the generation AI can perform more precise classification by taking into account background information of the inquiry content. The prioritization unit prioritizes the inquiries classified by the classification unit. For example, the generation AI prioritizes inquiries based on the urgency and importance of the inquiry content. The generation AI can also prioritize inquiries from specific users by taking into account user attribute information. Furthermore, the generation AI can classify inquiry content in real time and dynamically change priorities. As a result, the inquiry response system according to the embodiment automates processes from inquiry reception to response generation, classification, and prioritization, thereby achieving efficient inquiry response. For example, the inquiry response system can quickly process inquiries from users and provide appropriate responses. Furthermore, the inquiry response system can prioritize important inquiries by classifying and prioritizing the inquiry content. Furthermore, the inquiry response system can perform more precise classification and prioritization by taking into account background information of the inquiry content.

[0064] The response generation unit can refer to the inquiry history and generate a personalized response. For example, the generation AI in the response generation unit analyzes the user's past inquiry history and generates a personalized answer based on past responses to similar inquiries. For example, it provides the current inventory status based on the inventory status of a product the user has previously inquired about. The response generation unit also refers to the user's past inquiry history, finds specific patterns and trends, and customizes the response based on them. For example, it provides more detailed information on topics the user frequently inquires about. The response generation unit also learns the user's past inquiry history and generates a personalized response. For example, it provides new information related to the user's previous inquiry. This enables more appropriate responses by generating personalized responses based on the user's past inquiry history.

[0065] The response generation unit can generate a response taking into account the user's current situation and environment. For example, the generation AI in the response generation unit obtains the user's location information and customizes the response based on that information. For example, if the user is in a specific area, the response generation unit provides the inventory status of stores in that area. The response generation unit also generates a response taking into account the user's time of day. For example, if an inquiry is made at night, the response generation unit provides information about the next day's business hours. The response generation unit also analyzes the user's current situation and environment and generates a response based on that. For example, if the user is on the move, the response generation unit provides information about the nearest store. This allows for a more appropriate response by generating a response that takes into account the user's current situation and environment.

[0066] The response generation unit can use the emotion estimation function to analyze the user's emotional state and generate a response that corresponds to that emotion. For example, the response generation unit uses a generation AI to estimate the emotion from the user's input and generate a response that corresponds to that emotion. For example, if the user expresses dissatisfaction, the response generation unit provides an apology and a solution. The response generation unit also uses the emotion estimation function to analyze the user's emotional state in real time and customize the response. For example, if the user is happy, the response generation unit provides more positive information. The response generation unit also uses a generation AI to analyze the user's emotional state and generate a response that corresponds to the emotion. For example, if the user is confused, the response generation unit provides a more detailed explanation. This enables a more appropriate response by analyzing the user's emotional state and generating a response that corresponds to the emotion.

[0067] The inquiry reception unit can accept inquiries via voice input, and the response generation unit can generate a voice response based on the voice input. For example, the inquiry reception unit records what a user dictates with a microphone and converts it into text data using voice recognition technology. For example, voice recognition software automatically analyzes the voice and saves it as text. The inquiry reception unit also creates a system that recognizes what a user dictates in real time and displays it as text data. For example, the text is displayed on a screen simultaneously with the voice input. The inquiry reception unit also uses the voice input to convert what the user dictates into text and saves the text data as an answer. For example, it performs high-precision text conversion using voice recognition technology. The response generation unit, for example, uses a generation AI to analyze the voice input and convert the natural language inquiry into text to generate a response. For example, when a user asks, "Is the product in stock?" via voice, it provides a voice answer. The response generation unit also uses voice recognition technology to analyze the user's voice input, and the generation AI generates an appropriate response. For example, when a user makes a voice inquiry, it provides a detailed voice explanation. The response generation unit also constructs a system in which the generation AI analyzes voice input and generates a voice response. For example, when a user makes a voice inquiry, a real-time voice response is provided. This improves user convenience by generating a voice response to a voice-input inquiry.

[0068] The response generation unit can automatically attach related images and videos when generating a response. For example, the response generation unit uses a generation AI to analyze the content of an inquiry and automatically attach related images and videos to generate a response. For example, if an inquiry is made about product stock status, images of the product and an explanatory video are attached. The response generation unit also uses the generation AI to automatically search for related visual content in response to a user inquiry and attach it to the response. For example, if an inquiry is made about how to use a product, a video on how to use it is attached. The response generation unit also builds a system in which related images and videos are automatically attached when the generation AI generates a response. For example, if a user inquires about the details of a specific product, a promotional video for that product is attached. This allows the automatic attachment of related images and videos to provide more visual information to the user.

[0069] The response generation unit can use the emotion estimation function to analyze the emotion a user feels when entering a query in real time and generate a response that elicits positive emotions. For example, the response generation unit uses the emotion estimation function to analyze the emotion a user feels when entering a query in real time and generate a response that elicits positive emotions. For example, if the user is feeling anxious, it provides a response that gives a sense of security. The response generation unit also uses a generation AI to analyze the user's emotional state in real time and generate a response that elicits positive emotions. For example, if the user is confused, it provides a clear and concise explanation. The response generation unit also uses the emotion estimation function to build a system that analyzes the user's emotions in real time and generates a response that elicits positive emotions. For example, if the user is feeling angry, it provides an apology and a solution. This improves user satisfaction by analyzing the user's emotions in real time and generating a response that elicits positive emotions.

[0070] The classification unit can perform more precise classification by taking into account background information of the inquiry content. For example, the generation AI analyzes the background information of the inquiry content and performs classification and prioritization by taking into account past trouble history. For example, if a similar trouble has occurred in the past, that inquiry will be processed with priority. The classification unit also builds a system in which the generation AI performs precise classification and prioritization based on the background information of the inquiry content. For example, it refers to past trouble history and processes inquiries with a high level of urgency with priority. The classification unit also analyzes the background information of the inquiry content by the generation AI and performs classification and prioritization by taking into account past trouble history. For example, if a particular user frequently reports trouble, it will process that user's inquiries with priority. This enables more precise classification by taking into account the background information of the inquiry content.

[0071] When classifying inquiry content, the classification unit can automatically recognize and appropriately classify industry-specific terminology and slang. The classification unit, for example, builds a system in which a generation AI automatically recognizes industry-specific terminology and slang and appropriately classifies inquiry content. For example, it recognizes and classifies technical terms in the IT industry. The classification unit also analyzes industry-specific terminology and slang contained in the inquiry content, and the generation AI appropriately classifies it. For example, it recognizes and classifies technical terms in the medical industry. The classification unit also allows the generation AI to automatically recognize industry-specific terminology and slang and appropriately classify the inquiry content. For example, it recognizes and classifies slang in the financial industry. This enables more appropriate classification by automatically recognizing industry-specific terminology and slang.

[0072] The classification unit can use the emotion estimation function to analyze the user's emotional state and prioritize processing inquiries with high emotional urgency. The classification unit, for example, uses the emotion estimation function to analyze the user's emotional state and build a system that prioritizes processing inquiries with high emotional urgency. For example, if the user is feeling strong anxiety, the classification unit prioritizes processing those inquiries. The classification unit also uses the generation AI to analyze the user's emotional state in real time and prioritizes processing those inquiries with high emotional urgency. For example, if the user is feeling angry, the classification unit responds to those inquiries quickly. The classification unit also uses the emotion estimation function to analyze the user's emotional state and prioritize processing those inquiries with high emotional urgency. For example, if the user is confused, the classification unit prioritizes processing those inquiries. This enables a quick response by analyzing the user's emotional state and prioritizing processing those inquiries with high emotional urgency.

[0073] The classification unit can classify inquiry content in real time and dynamically change priorities. For example, the classification unit builds a system in which a generation AI analyzes inquiry content in real time and classifies and prioritizes it. For example, when a new inquiry is added, the priority is dynamically changed. The classification unit also develops an algorithm that classifies inquiry content in real time and dynamically changes the priority. For example, when a highly urgent inquiry is added, that inquiry is processed with priority. The classification unit also builds a system in which a generation AI analyzes inquiry content in real time and dynamically changes the priority. For example, the priority is adjusted according to the user's situation. This enables faster and more appropriate responses by classifying inquiry content in real time and dynamically changing the priority.

[0074] When classifying query content, the classification unit can refer to other data sources and classify query content into highly relevant categories. For example, the classification unit constructs a system in which the generation AI refers to trend data on social media and classifies query content into highly relevant categories. For example, queries related to current trends are processed with priority. The classification unit also refers to other data sources so that the generation AI appropriately classifies query content. For example, the classifier classifies query content based on data from news sites. The classification unit also analyzes trend data on social media and classifies query content into highly relevant categories. For example, if a specific topic is trending, queries related to that topic are processed with priority. This makes it possible to classify queries into more relevant categories by referring to other data sources.

[0075] The classification unit can use the emotion estimation function to analyze the emotion of a user when entering a query in real time and prioritize queries based on the emotion. The classification unit, for example, uses the emotion estimation function to analyze the emotion of a user when entering a query in real time and build a system that prioritizes queries based on the emotion. For example, if a user is feeling strong anxiety, the query is processed with priority. The classification unit also uses the generation AI to analyze the user's emotional state in real time and prioritize queries based on the emotion. For example, if a user is feeling angry, the query is quickly responded to. The classification unit also uses the emotion estimation function to analyze the user's emotional state and prioritize queries based on the emotion. For example, if the user is confused, the query is processed with priority. This enables faster and more appropriate responses by analyzing the user's emotion in real time and prioritizing queries based on the emotion.

[0076] The prioritization unit can perform more precise prioritization by taking into account background information about the inquiry content. For example, the prioritization unit uses the generation AI to analyze the background information about the inquiry content and classify and prioritize the inquiries taking into account past trouble history. For example, if a similar trouble has occurred in the past, that inquiry will be handled with priority. The prioritization unit also builds a system in which the generation AI performs precise classification and prioritization based on the background information about the inquiry content. For example, it refers to past trouble history and handles inquiries with higher urgency with priority. The prioritization unit also uses the generation AI to analyze the background information about the inquiry content and classify and prioritize the inquiries taking into account past trouble history. For example, if a specific user frequently reports trouble, it will handle that user's inquiries with priority. This enables more precise prioritization by taking into account the background information of the inquiry content.

[0077] The prioritization unit can automatically recognize industry-specific terminology and slang and appropriately classify inquiry content when classifying inquiry content. The prioritization unit, for example, builds a system in which a generation AI automatically recognizes industry-specific terminology and slang and appropriately classifies inquiry content. For example, it recognizes and classifies IT industry terminology. The prioritization unit also analyzes industry-specific terminology and slang contained in inquiry content, and the generation AI appropriately classifies it. For example, it recognizes and classifies medical industry terminology. The prioritization unit also allows a generation AI to automatically recognize industry-specific terminology and slang and appropriately classify inquiry content. For example, it recognizes and classifies financial industry slang. This automatically recognizes industry-specific terminology and slang, enabling more appropriate classification.

[0078] The prioritization unit can use the emotion estimation function to analyze the user's emotional state and prioritize inquiries with high emotional urgency. The prioritization unit, for example, uses the emotion estimation function to analyze the user's emotional state and build a system that prioritizes inquiries with high emotional urgency. For example, if the user is feeling strong anxiety, the prioritization unit prioritizes processing those inquiries. In addition, the prioritization unit uses the generation AI to analyze the user's emotional state in real time and prioritizes processing those inquiries with high emotional urgency. For example, if the user is feeling angry, the prioritization unit responds quickly. In addition, the prioritization unit uses the emotion estimation function to analyze the user's emotional state and prioritizes processing those inquiries with high emotional urgency. For example, if the user is confused, the prioritization unit prioritizes processing those inquiries. This enables a quick response by analyzing the user's emotional state and prioritizing processing those inquiries with high emotional urgency.

[0079] The prioritization unit can classify inquiry content in real time and dynamically change priorities. For example, the prioritization unit constructs a system in which a generation AI analyzes inquiry content in real time and classifies and prioritizes it. For example, when a new inquiry is added, the priority is dynamically changed. The prioritization unit also develops an algorithm that classifies inquiry content in real time and dynamically changes the priority. For example, when a highly urgent inquiry is added, that inquiry is processed with priority. The prioritization unit also constructs a system in which a generation AI analyzes inquiry content in real time and dynamically changes the priority. For example, the priority is adjusted according to the user's situation. This enables faster and more appropriate responses by classifying inquiry content in real time and dynamically changing the priority.

[0080] When classifying query content, the prioritization unit can refer to other data sources and classify query content into highly relevant categories. For example, the prioritization unit constructs a system in which the generation AI refers to trend data from social media and classifies query content into highly relevant categories. For example, queries related to current trends are processed preferentially. The prioritization unit also refers to other data sources so that the generation AI appropriately classifies query content. For example, the query content is classified based on data from news sites. The prioritization unit also analyzes trend data from social media and classifies query content into highly relevant categories. For example, if a specific topic is trending, queries related to that topic are processed preferentially. This makes it possible to classify queries into more relevant categories by referring to other data sources.

[0081] The prioritization unit can use the emotion estimation function to analyze the emotion of a user when entering a query in real time and prioritize queries based on the emotion. The prioritization unit, for example, uses the emotion estimation function to analyze the emotion of a user when entering a query in real time and builds a system that prioritizes queries based on the emotion. For example, if a user is feeling strong anxiety, the query is processed with priority. The prioritization unit also uses the generation AI to analyze the user's emotional state in real time and prioritize queries based on the emotion. For example, if a user is feeling angry, the query is handled quickly. The prioritization unit also uses the emotion estimation function to analyze the user's emotional state and prioritize queries based on the emotion. For example, if the user is confused, the query is handled with priority. This enables faster and more appropriate responses by analyzing the user's emotion in real time and prioritizing queries based on the emotion.

[0082] The response generation unit can optimize the timing of follow-ups based on the user's behavioral patterns. In the response generation unit, for example, the generation AI analyzes the user's behavioral patterns and determines the optimal timing of follow-ups. For example, follow-ups are performed during times when the user frequently accesses the site. In addition, the response generation unit optimizes the timing of follow-ups based on the user's past behavioral data. For example, if the user is active on a specific day of the week, follow-ups are performed on that day. In addition, the response generation unit analyzes the user's behavioral patterns in real time and determines the optimal timing of follow-ups. For example, follow-ups are performed if the user has not been active recently. This enables more effective follow-ups by optimizing the timing of follow-ups based on the user's behavioral patterns.

[0083] When performing follow-up, the response generation unit can refer to the user's past response history and perform personalized follow-up. For example, the response generation unit uses a generation AI to analyze the user's past response history and perform personalized follow-up. For example, it may provide new information related to content that the user has previously inquired about. The response generation unit also customizes the content of the follow-up based on the user's past response history. For example, it may provide a new solution related to a problem that the user has previously solved. The response generation unit also builds a system in which the generation AI refers to the user's past response history and performs personalized follow-up. For example, it may provide the latest information on a product that the user has previously inquired about. This makes it possible to perform more personalized follow-up by referring to the user's past response history.

[0084] The response generation unit can use the emotion estimation function to analyze the user's emotional state and perform follow-up according to the emotion. The response generation unit, for example, uses the emotion estimation function to build a system that analyzes the user's emotional state and performs follow-up according to the emotion. For example, if the user is feeling anxious, a follow-up that provides a sense of security is performed. The response generation unit also uses a generation AI to analyze the user's emotional state in real time and perform follow-up according to the emotion. For example, if the user is happy, more positive information is provided. The response generation unit also uses the emotion estimation function to analyze the user's emotional state and perform follow-up according to the emotion. For example, if the user is confused, a more detailed explanation is provided. This allows for a more appropriate response by analyzing the user's emotional state and performing follow-up according to the emotion.

[0085] The response generation unit can send follow-up content via multiple media. The response generation unit, for example, builds a system in which a generation AI generates follow-up content and sends it via multiple media. For example, the follow-up is performed using email, SMS, and app notification. The response generation unit also has the generation AI send the follow-up content via an appropriate medium depending on the user's preferences. For example, if the user prefers email, the follow-up is performed via email. The response generation unit also has the generation AI send the follow-up content via multiple media so that the user can receive the follow-up in the most accessible way. For example, the response generation unit sends app notification and SMS simultaneously. In this way, by sending the follow-up via multiple media, the user can receive the follow-up in the most accessible way.

[0086] The response generation unit can automatically attach related documents and links when performing a follow-up. For example, the response generation unit builds a system in which the generation AI automatically attaches related documents and links when generating the content of a follow-up. For example, it attaches links to product manuals and FAQ pages. The response generation unit also searches for related documents and links according to the content of a user's inquiry and attaches them to the follow-up. For example, it attaches documents containing solutions to technical problems. The response generation unit also automatically attaches related documents and links when the generation AI performs a follow-up. For example, it attaches a link containing detailed information about a product that the user inquired about. In this way, by automatically attaching related documents and links, it is possible to provide the user with more detailed information.

[0087] The response generation unit uses the emotion estimation function to analyze the emotions of the user when receiving a follow-up in real time and can perform follow-up based on the emotions. The response generation unit, for example, uses the emotion estimation function to analyze the emotions of the user when receiving a follow-up in real time and builds a system that performs follow-up based on emotions. For example, if the user is feeling anxious, a follow-up that gives a sense of security is performed. The response generation unit also uses the generation AI to analyze the user's emotional state in real time and perform follow-up based on emotions. For example, if the user is happy, more positive information is provided. The response generation unit also uses the emotion estimation function to analyze the user's emotional state and perform follow-up based on emotions. For example, if the user is confused, a more detailed explanation is provided. This allows for a more appropriate response by analyzing the user's emotions in real time and performing follow-up based on emotions.

[0088] The inquiry history management unit can analyze the inquiry history in chronological order and identify long-term trends. For example, the inquiry history management unit builds a system in which a generation AI analyzes the inquiry history in chronological order and identifies long-term trends. For example, it identifies a trend of increasing inquiries about a specific product. The inquiry history management unit also analyzes the inquiry history in chronological order and the generation AI identifies long-term trends. For example, it identifies seasonal inquiry patterns. The inquiry history management unit also analyzes the inquiry history in chronological order and identifies long-term trends. For example, it identifies a trend of increasing inquiries about a specific problem. In this way, by analyzing the inquiry history in chronological order, long-term trends can be identified, enabling more effective responses.

[0089] When analyzing the inquiry history, the inquiry history management unit takes into account user attribute information and can identify trends by attribute. For example, the inquiry history management unit builds a system in which a generation AI analyzes user attribute information and identifies trends by attribute based on the inquiry history. For example, it identifies topics that are frequently inquired about by a specific age group. The inquiry history management unit also takes into account user attribute information and the generation AI analyzes the inquiry history and identifies trends by attribute. For example, it identifies differences in inquiries based on gender. The inquiry history management unit also takes into account user attribute information and the generation AI analyzes user attribute information and identifies trends by attribute based on the inquiry history. For example, it identifies topics that are frequently inquired about by users in a specific region. In this way, by taking user attribute information into account, trends by attribute can be identified and more effective responses can be made.

[0090] The inquiry history management unit can use the emotion estimation function to analyze emotions contained in the inquiry history and identify emotional trends. The inquiry history management unit, for example, uses the emotion estimation function to build a system that analyzes emotions contained in the inquiry history and identifies emotional trends. For example, it identifies a trend of increasing user dissatisfaction. The inquiry history management unit also uses a generation AI to analyze the inquiry history and identify emotional trends. For example, it identifies a trend of increasing positive emotions toward a specific topic. The inquiry history management unit also uses the emotion estimation function to analyze emotions contained in the inquiry history and identify emotional trends. For example, it identifies a trend of user emotions changing with the seasons. In this way, by analyzing the emotions contained in the inquiry history, emotional trends can be identified and more effective responses can be made.

[0091] The inquiry history management unit can integrate inquiry history with other data sources and perform comprehensive analysis. For example, the inquiry history management unit builds a system in which a generation AI integrates inquiry history and sales data to perform comprehensive analysis. For example, it analyzes the relationship between product sales figures and the number of inquiries. The inquiry history management unit also integrates inquiry history with other data sources and the generation AI performs comprehensive analysis. For example, it integrates marketing data and inquiry history for analysis. The inquiry history management unit also integrates inquiry history with other data sources and the generation AI performs comprehensive analysis. For example, it integrates customer satisfaction data and inquiry history for analysis. This makes it possible to perform comprehensive analysis by integrating inquiry history with other data sources.

[0092] When analyzing the inquiry history, the inquiry history management unit can simultaneously analyze inquiries in different languages ​​and identify global trends. The inquiry history management unit, for example, builds a system in which a generation AI analyzes inquiries in different languages ​​and identifies global trends. For example, queries in English and Japanese are analyzed simultaneously to identify trends. The inquiry history management unit also analyzes inquiries in different languages ​​and the generation AI identifies global trends. For example, query content in multiple languages ​​is integrated and analyzed. The inquiry history management unit also analyzes inquiries in different languages ​​simultaneously and identifies global trends. For example, it identifies a trend of an increase in inquiries about a particular topic in multiple languages. In this way, by simultaneously analyzing queries in different languages, global trends can be identified and more effective responses can be made.

[0093] The inquiry history management unit can use the emotion estimation function to analyze emotions contained in the inquiry history in real time and provide emotion-based insights. The inquiry history management unit, for example, uses the emotion estimation function to analyze emotions contained in the inquiry history in real time and build a system that provides emotion-based insights. For example, if user dissatisfaction is increasing, the cause is identified. The inquiry history management unit also uses a generation AI to analyze the inquiry history in real time and provide emotion-based insights. For example, if positive emotions toward a specific topic are increasing, the cause is identified. The inquiry history management unit also uses the emotion estimation function to analyze emotions contained in the inquiry history in real time and provide emotion-based insights. For example, if user emotions change with the seasons, the trend is identified. As a result, by analyzing emotions contained in the inquiry history in real time, emotion-based insights can be provided, enabling more effective responses.

[0094] The response generation unit can automatically translate the query content into multiple languages ​​and generate a response that takes into account the nuances in each language. The response generation unit, for example, builds a system in which a generation AI automatically translates the query content into multiple languages ​​and generates a response that takes into account the nuances in each language. For example, the response generation unit automatically translates the query content into multiple languages ​​and the generation AI ... an appropriate response in German. This enables more appropriate responses by automatically translating the query content into multiple languages ​​and generating a response that takes into account the nuances in each language.

[0095] The response generation unit can generate responses that take into account regional culture and customs when providing multilingual support. For example, the response generation unit builds a system in which, when the generation AI provides multilingual support, it generates responses that take into account regional culture and customs. For example, it generates responses that take into account Japanese culture. The response generation unit also generates responses that take into account regional culture and customs when the generation AI provides multilingual support. For example, it generates responses that take into account American culture. The response generation unit also generates responses that take into account regional culture and customs when the generation AI provides multilingual support. For example, it generates responses that take into account Indian culture. This enables more appropriate responses by generating responses that take into account regional culture and customs.

[0096] The response generation unit can use the emotion estimation function to analyze emotional expressions in different languages ​​and generate a response according to the emotion. The response generation unit, for example, uses the emotion estimation function to build a system that analyzes emotional expressions in different languages ​​and generates a response according to the emotion. For example, it analyzes emotional expressions in English and generates an appropriate response. The response generation unit also uses a generation AI to analyze emotional expressions in different languages ​​and generate a response according to the emotion. For example, it analyzes emotional expressions in French and generates an appropriate response. The response generation unit also uses the emotion estimation function to analyze emotional expressions in different languages ​​and generate a response according to the emotion. For example, it analyzes emotional expressions in Spanish and generates an appropriate response. This enables more appropriate responses by analyzing emotional expressions in different languages ​​and generating a response according to the emotion.

[0097] The response generation unit realizes multilingual support through voice input and can generate voice responses. The response generation unit, for example, builds a system in which a generation AI analyzes voice input and generates voice responses in multiple languages. For example, voice input in English is converted into a voice response in Japanese. The response generation unit also uses voice recognition technology to have the generation AI analyze the voice input and generate voice responses in multiple languages. For example, voice input in French is converted into a voice response in English. The response generation unit also uses the generation AI to analyze the voice input and generate voice responses in multiple languages. For example, voice input in Spanish is converted into a voice response in German. This realizes multilingual support through voice input and generates voice responses, enabling more appropriate responses.

[0098] The response generation unit can automatically attach related images and videos when providing multilingual support, thereby providing visual information. For example, the response generation unit builds a system in which, when the generation AI provides multilingual support, it automatically attaches related images and videos to generate responses. For example, an explanatory video in Japanese is attached to an inquiry in English. The response generation unit also allows the generation AI to automatically search for related images and videos according to the inquiry content and attach them to the response. For example, an explanatory image in English is attached to an inquiry in French. The response generation unit also automatically attaches related images and videos when the generation AI provides multilingual support. For example, an explanatory video in German is attached to an inquiry in Spanish. This makes it possible to provide visual information by automatically attaching related images and videos when providing multilingual support.

[0099] The response generation unit can use the emotion estimation function to analyze emotional expressions in different languages ​​in real time and generate multilingual responses based on the emotions. The response generation unit, for example, uses the emotion estimation function to build a system that analyzes emotional expressions in different languages ​​in real time and generates multilingual responses based on the emotions. For example, it analyzes emotional expressions in English and generates an appropriate response. The response generation unit also uses a generation AI to analyze emotional expressions in different languages ​​in real time and generate multilingual responses based on the emotions. For example, it analyzes emotional expressions in French and generates an appropriate response. The response generation unit also uses the emotion estimation function to analyze emotional expressions in different languages ​​in real time and generate multilingual responses based on the emotions. For example, it analyzes emotional expressions in Spanish and generates an appropriate response. This enables more appropriate responses by analyzing emotional expressions in different languages ​​in real time and generating multilingual responses based on the emotions.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The inquiry response system can further analyze the user's behavioral history and optimize responses based on the behavioral patterns. For example, it can analyze what time of day the user has made inquiries in the past and provide a response tailored to that time of day. Also, if the user is using a specific device, it can generate a response optimized for that device. Furthermore, it can analyze what topics the user has been interested in in the past and provide information related to those topics preferentially. This allows for more personalized responses by providing responses based on the user's behavioral patterns.

[0102] The inquiry response system can also link with a user's social media account and generate responses by analyzing their social media activity. For example, if a user mentions a particular product on social media, the system can provide the latest information about that product. Or, if a user discusses a particular issue on social media, the system can provide solutions related to that issue. Furthermore, the system can provide relevant information based on the interests and concerns expressed by the user through their social media activity. This allows for more appropriate responses by taking into account social media activity.

[0103] The inquiry response system can also analyze the user's health data and generate a response based on their health status. For example, if a user is using a health app, the system can analyze that data to provide health advice. If a user inquires about a specific health problem, the system can provide the latest research results and treatments related to that problem. It can also provide preventative advice based on the user's health data. This allows for more appropriate responses based on the user's health status.

[0104] The inquiry response system can also analyze a user's purchasing history and generate a response based on their purchasing patterns. For example, it can suggest related products based on information about products the user has purchased in the past. Also, if a user frequently purchases products from a specific category, it can provide the latest information related to that category. Furthermore, it can provide information about the stock status and price fluctuations of specific products based on the user's purchasing history. This allows for more personalized responses by providing responses based on the user's purchasing patterns.

[0105] The inquiry response system can also analyze the user's location information and generate a response based on that location information. For example, if the user is in a specific area, the system can provide the inventory status and business hours of stores in that area. If the user is traveling, the system can also provide tourist information and transportation information for the user's destination. Furthermore, the system can provide information on the nearest service locations and events based on the user's location information. This allows for more appropriate responses by providing responses based on the user's location information.

[0106] The inquiry response system can also analyze the user's emotional state and generate a response based on the emotion. For example, if the user is feeling anxious, it can provide a reassuring response. If the user is happy, it can provide more positive information. If the user is confused, it can provide a more detailed explanation. This allows for more appropriate responses based on the user's emotional state.

[0107] The inquiry response system can also analyze the user's emotional state in real time and provide follow-up based on the user's emotions. For example, if the user is feeling anxious, the system can provide reassurance through follow-up. If the user is happy, the system can provide more positive information. If the user is confused, the system can provide a more detailed explanation. This allows for more appropriate responses by providing follow-up based on the user's emotional state.

[0108] The inquiry response system can further analyze the emotional state of the user and prioritize inquiries based on the emotion. For example, if the user is feeling very anxious, the inquiry can be handled with priority. Also, if the user is feeling angry, the inquiry can be handled quickly. Furthermore, if the user is confused, the inquiry can be handled with priority. Thus, by prioritizing based on the emotional state of the user, a quick response is possible.

[0109] The inquiry response system can also analyze the user's emotional state and provide insights based on the user's emotions. For example, if user dissatisfaction is increasing, the system can identify the cause. Also, if positive emotions toward a particular topic are increasing, the system can identify the factors behind this. Furthermore, if user emotions change with the seasons, the system can identify these trends. This allows for more effective responses by providing insights based on the user's emotional state.

[0110] The inquiry response system can further analyze the emotional state of the user and generate a multilingual response based on the emotion. For example, the system can analyze emotional expressions in English and generate an appropriate response. It can also analyze emotional expressions in French and generate an appropriate response. It can also analyze emotional expressions in Spanish and generate an appropriate response. This allows for more appropriate responses by analyzing emotional expressions in different languages ​​and generating multilingual responses based on the emotion.

[0111] The processing flow of the second embodiment will be briefly explained below.

[0112] Step 1: The inquiry reception unit receives an inquiry from a user. For example, the inquiry may be in text format, voice input, or may include an image or video. Step 2: The response generation unit generates a response to the inquiry received by the inquiry reception unit. For example, the generation AI can generate an appropriate response using natural language processing technology, and can generate template-based responses or personalized responses that refer to the user's past inquiry history. Step 3: The classification unit classifies the inquiry content based on the response generated by the response generation unit. For example, the generation AI can classify the inquiry content by category, determine the urgency, and prioritize inquiries with high priority. It can also perform more precise classification by taking into account the background information of the inquiry content. Step 4: The prioritization unit prioritizes the inquiries classified by the classification unit. For example, the generation AI can prioritize inquiries based on the urgency and importance of the inquiry content, and prioritize inquiries from specific users by taking into account their attribute information. It can also classify inquiry content in real time and dynamically change priorities.

[0113] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0116] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0117] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0118] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0124] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0126] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0127] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0128] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0133] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0138] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0141] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0142] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0150] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0153] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0154] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0157] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0163] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0164] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0165] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0166] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0167] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0169] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0170] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0171] 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.

[0172] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0173] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0174] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0175] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0176] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0177] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0178] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0179] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0180] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an inquiry reception unit that receives inquiries from users; a response generation unit that generates a response to the inquiry received by the inquiry reception unit; a classification unit that classifies the inquiry content based on the response generated by the response generation unit; a prioritization unit that prioritizes the queries classified by the classification unit. A system characterized by:

2. The response generation unit Referencing the inquiry history and generating a personalized response 2. The system of claim 1.

3. The response generation unit Generate responses taking into account the user's current situation and environment 2. The system of claim 1.

4. The response generation unit Analyzing the emotional state of the user and generating a response according to the emotion.

2. The system of claim 1.

5. The inquiry reception unit Accepts inquiries via voice input, The response generation unit Generate a voice response based on the voice input 2. The system of claim 1.

Images