System

Abstract

An object of a system according to an embodiment is to provide chat support that enables a flexible answer.SOLUTION: A system includes a generation AI, a tag embedding part, an information learning part, a page guide part, and a customer support part. The generation AI generates a flexible answer using the generation AI. The tag embedding unit can be introduced by embedding only one tag. The information learning unit automatically learns information in the site. The page guidance unit performs guidance to a target page. The customer support section performs customer support.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 technology often involves chatbots based on standard phrases or FAQs, which makes it difficult to provide effective customer support because they are unable to respond flexibly.

[0005] The system according to the embodiment aims to provide chat support that allows flexible responses. [Means for solving the problem]

[0006] The system according to the embodiment includes a generation AI, a tag embedding unit, an information learning unit, a page guidance unit, and a customer support unit. The generation AI uses the generation AI to generate flexible answers. The tag embedding unit can be implemented by simply embedding one tag. The information learning unit automatically learns information within the site. The page guidance unit guides users to the desired page. The customer support unit provides customer support. [Effects of the Invention]

[0007] The system according to the embodiment can provide chat support that allows flexible responses. [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) The chat support system according to the embodiment of the present invention uses a generative AI to provide chat support that allows for flexible responses, and is a system that can be easily implemented by simply embedding one tag. This allows the chat support system to improve the user experience of websites and e-commerce sites and reduce the burden on site administrators.

[0029] A chat support system according to an embodiment includes a generation AI, a tag embedding unit, an information learning unit, a page navigation unit, and a customer support unit. The generation AI generates flexible answers. For example, the generation AI generates specific answers to user questions. The generation AI can also generate answers based on information on a website. The generation AI can also analyze user input and generate appropriate answers. The tag embedding unit can be implemented by simply embedding a single tag. For example, by simply adding a specific tag to the website's HTML code, the chatbot automatically learns information on the website and begins a dialogue with the user. The tag embedding unit does not require complex settings or programming, allowing for quick implementation of the chatbot. The information learning unit automatically learns information on the website. For example, the information learning unit analyzes information such as product descriptions, terms of use, and FAQs, and answers user questions based on that information. The information learning unit also eliminates the need for website administrators to manually enter information. The page navigation unit guides users to the desired page. For example, the page navigation unit provides a link to an appropriate page for the user's question. The page navigation unit also enables users to quickly access desired information. The customer support unit provides customer support in an interactive format. For example, the customer support unit responds to user inquiries by guiding them on how to proceed with cancellation procedures and collecting necessary information. The customer support unit also enables users to receive support smoothly. As a result, the chat support system according to the embodiment provides chat support that can provide flexible responses using a generation AI and can be easily implemented by simply embedding one tag. For example, a site administrator can quickly implement a chatbot without the need for complex settings or programming. Furthermore, users can quickly access desired information and receive support smoothly.

[0030] The generation AI can refer to a user's past inquiry history to generate more personalized answers. For example, the generation AI retrieves the user's past inquiry history from a database and generates new answers to similar questions by referring to past answers. For example, if a user has previously asked how to return an item, the generation AI can provide detailed instructions based on that history. The generation AI can also analyze the user's past inquiry history to generate more detailed and specific answers to frequently asked questions. For example, if a user repeatedly asks about the stock status of the same product, the generation AI can provide that product's stock information in real time. The generation AI can also understand the user's preferences and interests based on the user's past inquiry history and generate personalized answers accordingly. For example, if a user is interested in products from a particular brand, the generation AI can prioritize providing information about products from that brand. This allows the generation of more personalized answers based on the user's past inquiry history.

[0031] A generation AI can generate answers to user questions by referencing relevant external resources. For example, a generation AI can automatically search for relevant external resources in response to a user question and generate an answer based on that information. For example, if a user asks for reviews of a specific product, the generation AI can obtain and provide information from an external review site. In response to a user question, the generation AI can also refer to other websites and databases to generate answers based on the latest information. For example, if a user asks for the latest research results on a specific technology, the generation AI can obtain information from a database of related academic papers. In response to a user question, the generation AI can obtain real-time data using an external API and generate an answer based on that data. For example, if a user asks for weather information, the generation AI can obtain and provide the latest weather information from a weather database. This allows answers to be generated by referencing relevant external resources.

[0032] The generation AI can analyze the user's voice input and provide flexible answers in a voice dialogue format. For example, the generation AI analyzes the user's voice input and converts it into text using voice recognition technology. The generation AI then generates an answer based on the text and provides the answer in voice using voice synthesis technology. The generation AI can also analyze the user's voice input in real time and generate an appropriate answer on the spot. For example, if a user asks about the stock status of a product by voice, the AI ​​can immediately provide stock information. The generation AI can also analyze the user's voice tone and speed to provide flexible answers in a voice dialogue format and generate answers in an appropriate tone. For example, if the user is in a hurry, it can provide a quick and concise answer. This makes it possible to provide flexible answers in a voice dialogue format.

[0033] Generative AI can generate answers to user questions that include visual content. For example, generative AI searches for relevant visual content in response to a user's question and incorporates it into the answer. For example, if a user asks how to use a product, it will provide a video showing how to use it. Generative AI can also use image recognition technology to search for relevant images in response to a user's question and include them in the answer. For example, if a user asks about the appearance of a particular product, it will provide an image of that product. In addition, to generate answers that include visual content, generative AI analyzes the content of the user's question and automatically selects and provides appropriate images and videos. For example, if a user asks for a cooking recipe, it will provide images and videos showing the cooking steps. This makes it possible to generate answers that include visual content.

[0034] The tag embedding unit can automatically adapt to the design and theme of a site. For example, when embedding a tag, the tag embedding unit analyzes the CSS stylesheet of the site and automatically adapts the chatbot design. For example, it adjusts the appearance of the chatbot to match the color scheme and font style of the site. Furthermore, when embedding a tag, the tag embedding unit adds a function to analyze the layout of the site and place the chatbot in the optimal position. For example, it places the chatbot in a location where the user's gaze is likely to be drawn. Furthermore, in order to automatically adapt to the design and theme of the site, the tag embedding unit analyzes the HTML structure of the site when embedding a tag and appropriately places the chatbot elements. For example, it adjusts the position of the chatbot to match the header or footer of the site. This allows the tag embedding unit to automatically adapt to the design and theme of the site.

[0035] The tag embedding unit can automatically configure a chatbot that supports multiple languages. For example, when embedding a tag, the tag embedding unit automatically detects the language setting of the site and configures the chatbot in the corresponding language. For example, if a site supports English and Japanese, the chatbot will also support both languages. In addition, the tag embedding unit uses multilingual natural language processing technology in the generation AI to automatically configure a chatbot that supports multiple languages ​​simply by embedding a tag. For example, if a user asks a question in French, the tag embedding unit generates an answer in French. In addition, when embedding a tag, the tag embedding unit analyzes the language setting of the site user and automatically configures the chatbot that supports the most commonly used language. For example, the tag embedding unit identifies the main language based on access analysis data of the site and configures the chatbot in that language. This makes it possible to automatically configure a chatbot that supports multiple languages.

[0036] The tag embedding unit can place the chatbot in the optimal position based on the site's access analysis data. For example, when embedding a tag, the tag embedding unit analyzes the site's access analysis data and places the chatbot in a location where users are likely to look. For example, the chatbot is placed in an area where users frequently click. The tag embedding unit also adds a function to analyze user behavior patterns based on the site's access analysis data and place the chatbot in the optimal position. For example, the chatbot is placed on a page where users stay for a long time. The tag embedding unit also places the chatbot on a page where users have a high dropout rate based on the site's access analysis data. For example, the chatbot is placed on a page where users abandon the purchase process and support is provided. This makes it possible to place the chatbot in the optimal position based on the site's access analysis data.

[0037] The tag embedding unit can automatically integrate the chatbot into the user interface of a site. For example, the tag embedding unit adds a function that allows the chatbot to be automatically integrated into the user interface of a site simply by embedding a tag. For example, it adds a chatbot link to the navigation menu or footer of the site. When embedding a tag, the tag embedding unit also analyzes the user interface of the site and positions the chatbot so that it is integrated naturally. For example, it customizes the chatbot button to match the design of the site. When embedding a tag, the tag embedding unit also analyzes the HTML structure of the site and positions the chatbot in an appropriate position so that the chatbot is automatically integrated into the user interface of the site. For example, it positions the chatbot in the sidebar of the site. This allows the chatbot to be automatically integrated into the user interface of the site.

[0038] The tag embedding unit collects user behavior data on the site in real time and can approach users at the optimal timing. For example, by simply embedding a tag, the tag embedding unit allows a chatbot to collect user behavior data on the site in real time and automatically approach users when they perform a specific action. For example, support is provided when a user adds an item to their cart. The tag embedding unit also allows the chatbot to collect user behavior data in real time and automatically approach users when they are unsure about something on the site. For example, help is provided when a user stays on a particular page for a long time. The tag embedding unit also allows the chatbot to analyze user behavior data and proactively approach users at the optimal timing. For example, a reminder is sent when a user aborts the purchase process. This allows the chatbot to collect user behavior data on the site in real time and approach users at the optimal timing.

[0039] When learning information within a site, the information learning unit evaluates the reliability of the information and prioritizes the use of highly reliable information. For example, when the generation AI learns information within a site, the information learning unit uses an algorithm that evaluates the reliability of information to prioritize the use of highly reliable information. For example, the information learning unit prioritizes learning information from official information sources and highly reliable databases. Furthermore, when learning information within a site, the information learning unit analyzes the source of the information and update frequency to evaluate the reliability of the information and prioritizes the use of highly reliable information. For example, it prioritizes learning official documents that are updated frequently. Furthermore, when the generation AI learns information within a site, the information learning unit evaluates the reliability of the information based on user feedback and prioritizes the use of highly reliable information. For example, it prioritizes learning information that has received high ratings from users. This allows the generation AI to prioritize the use of highly reliable information when learning information within a site.

[0040] When learning information within a site, the information learning unit takes into account how often the information is updated, allowing the latest information to be used preferentially. For example, when the generation AI learns information within a site, the information learning unit introduces an algorithm that analyzes how often the information is updated and prioritizes the use of the latest information. For example, it prioritizes learning news articles and blog posts that are updated frequently. In addition, when learning information within a site, the information learning unit analyzes the update history of the information and prioritizes the use of the latest information. For example, it prioritizes learning recently updated product descriptions and terms of use. In addition, when the generation AI learns information within a site, the information learning unit takes into account how often the information is updated and adds a function to automatically filter out old information. For example, it excludes information that has not been updated for a certain period of time. This allows the latest information to be used preferentially when learning information within a site.

[0041] When learning information within a site, the information learning unit evaluates the relevance of the information and prioritizes the use of highly relevant information. For example, when the generation AI learns information within a site, the information learning unit uses an algorithm to evaluate the relevance of information and prioritizes the use of highly relevant information. For example, it prioritizes learning information that is directly related to the user's question. Furthermore, when learning information within a site, the information learning unit analyzes the keywords and topics of the information to evaluate the relevance of the information and prioritizes the use of highly relevant information. For example, it prioritizes learning information related to the description of a specific product. Furthermore, when the generation AI learns information within a site, the information learning unit evaluates the relevance of the information based on user behavior data and prioritizes the use of highly relevant information. For example, it prioritizes learning information on pages that the user frequently accesses. This allows the generation AI to prioritize the use of highly relevant information when learning information within a site.

[0042] The information learning unit can also integrate information from different data sources. For example, when the generation AI learns information within a site, the information learning unit integrates information from social media to generate answers to user questions that reflect the latest trends and opinions. For example, it analyzes posts on Twitter and Facebook. To integrate information from different data sources, the generation AI collects information from news sites and generates answers to user questions that reflect the latest news and events. For example, it analyzes news articles and incorporates them into the answers. When the generation AI learns information within a site, the information learning unit integrates information from external databases and APIs to generate comprehensive answers to user questions. For example, it uses databases of academic papers and government statistical data. This allows information from different data sources to be integrated.

[0043] The information learning unit can improve the accuracy of the information based on user feedback. For example, when the generation AI learns information on a site, the information learning unit collects feedback from users and improves the accuracy of the information based on that feedback. For example, corrections and additional information provided by users are reflected in the learning. The information learning unit also causes the generation AI to periodically update the information on the site based on user feedback, improving the accuracy of the information. For example, information where a user points out an error is corrected and re-learned. The information learning unit also introduces an algorithm that allows the generation AI to analyze user feedback and improve the accuracy of the information. For example, the reliability of the information is reevaluated based on the user's evaluation score and reflected in the learning. This allows the accuracy of the information to be improved based on user feedback.

[0044] The page navigation unit can refer to the user's past behavior history and guide the user to the optimal page. For example, the generation AI retrieves the user's past behavior history from a database and guides the user to the optimal page based on the pages the user frequently visits and content in which the user is interested. For example, it provides a link to a detail page of a product the user previously viewed. The page navigation unit also analyzes the user's past behavior history and guides the user to the optimal page based on pages the user previously visited and keywords searched for. For example, it provides a link to a page where the user can check the stock status of a product they previously searched for. The page navigation unit also identifies the user's interests and concerns based on the user's past behavior history and guides the user to the optimal page accordingly. For example, if the user is interested in products in a specific category, it provides a link to a page in that category. This makes it possible to guide the user to the optimal page based on the user's past behavior history.

[0045] The page guidance unit can analyze the content of the user's current page and guide the user to related pages. For example, the generation AI analyzes the content of the user's current page and guides the user to the most appropriate page based on information related to that page. For example, if the user is viewing a product details page, it provides links to product reviews and related product pages. The page guidance unit also analyzes the content of the current page and guides the user to pages related to the information the user is looking for. For example, if the user is viewing an FAQ page, it provides links to related support pages. The page guidance unit also guides the user to the page the user is likely to visit next based on the content of the user's current page. For example, if the user is in the process of making a purchase, it provides a link to a payment method details page. This makes it possible to guide the user to related pages based on the content of the user's current page.

[0046] The page navigation unit can analyze the user's voice input and guide the user to the desired page in a voice-interactive format. For example, the page navigation unit uses a generation AI to analyze the user's voice input and convert it into text using voice recognition technology. The generation AI then generates a link to the optimal page based on the text and provides audio guidance using voice synthesis technology. The page navigation unit also analyzes the user's voice input in real time, and the generation AI guides the user to the appropriate page on the spot. For example, if a user asks for product details by voice, a link to the product's details page is provided by voice. To guide the user to the desired page in a voice-interactive format, the generation AI analyzes the user's voice tone and speed and provides guidance in an appropriate tone. For example, if the user is in a hurry, quick and concise guidance is provided. This allows the user to be guided to the desired page in a voice-interactive format.

[0047] The page navigation unit can guide users to pages containing visual content in response to their questions. For example, the generation AI searches for relevant visual content in response to a user's question and provides a link to a page containing that content. For example, if a user asks how to use a product, the page navigation unit provides a link to a page containing a video demonstrating how to use the product. In response to a user's question, the generation AI uses image recognition technology to search for relevant images and provides a link to a page containing the images. For example, if a user asks about the appearance of a specific product, the page navigation unit provides a link to a page containing an image of the product. To guide users to pages containing visual content, the generation AI analyzes the content of the user's question and automatically selects and provides appropriate images or videos. For example, if a user asks about a cooking recipe, the page navigation unit provides a link to a page containing images or videos showing the cooking steps. This allows users to be guided to pages containing visual content.

[0048] The customer support department can provide more personalized support by referencing the user's past support history. For example, the generation AI retrieves the user's past support history from a database and provides new support for similar issues while referring to past responses. For example, if the user has previously completed a return procedure, it provides detailed instructions based on that history. The customer support department also analyzes the user's past support history to provide more detailed and specific support for frequently occurring issues. For example, if a user repeatedly reports a defect with the same product, it provides instructions on how to repair that product. The generation AI also understands the user's preferences and interests based on the user's past support history and provides personalized support accordingly. For example, if a user is interested in products from a particular brand, it will prioritize support for products from that brand. This allows the department to provide more personalized support based on the user's past support history.

[0049] The customer support department can provide support for a user's question by referencing relevant external resources. For example, the generation AI automatically searches for relevant external resources in response to a user's question and provides support based on that information. For example, if a user asks for reviews of a specific product, the generation AI retrieves and provides information from an external review site. In addition, the customer support department can provide support for a user's question by referencing other websites and databases and providing support based on the latest information. For example, if a user asks about the latest research results on a specific technology, the generation AI retrieves information from a database of related academic papers. In addition, the customer support department can provide support for a user's question by using an external API to retrieve real-time data and providing support based on that data. For example, if a user asks about weather information, the generation AI retrieves and provides the latest weather information from a weather database. This allows support to be provided by referencing relevant external resources.

[0050] The customer support department can analyze the user's voice input and provide customer support in a voice dialogue format. For example, in the customer support department, the generation AI analyzes the user's voice input and converts it into text using voice recognition technology. The generation AI then provides support based on the text and provides answers in voice using voice synthesis technology. The customer support department also analyzes the user's voice input in real time, and the generation AI provides appropriate support on the spot. For example, if a user voice-inquires about how to return a product, the AI ​​immediately provides instructions on how to proceed with the return. In addition, in order to provide customer support in a voice dialogue format, the generation AI analyzes the user's voice tone and speed and provides support in an appropriate tone. For example, if the user is in a hurry, it provides quick and concise support. This enables customer support to be provided in a voice dialogue format.

[0051] The customer support department can provide support including visual content in response to a user's question. For example, the generation AI searches for relevant visual content in response to a user's question and provides support including that content. For example, if a user asks how to use a product, a video demonstrating how to use the product is provided. In addition, the customer support department uses image recognition technology to search for relevant images in response to a user's question and provides support including those images. For example, if a user asks about the appearance of a specific product, an image of the product is provided. In addition, in order to provide support including visual content, the generation AI analyzes the content of the user's question and automatically selects and provides appropriate images or videos. For example, if a user asks about a cooking recipe, images or videos showing the cooking steps are provided. This makes it possible to provide support including visual content.

[0052] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0053] The chat support system may further include a behavior analysis unit that analyzes user behavior patterns. The behavior analysis unit, for example, analyzes which pages a user frequently visits on a website and which links they click, and uses this data to understand the user's interests. For example, if a user frequently visits product pages in a particular category, information about products in that category may be provided preferentially. The behavior analysis unit may also predict which page a user is likely to visit next based on the user's behavior patterns, and provide support at the appropriate time. For example, if a user is in the process of making a purchase, it may provide a link to a page with payment method details. The behavior analysis unit may also include a function that automatically approaches a user when they are unsure about a solution on a website based on user behavior data. For example, if a user stays on a particular page for a long time, it may provide help. This allows for analyzing user behavior patterns and providing more personalized support.

[0054] The generation AI can further analyze the user's voice input and provide flexible answers in a voice dialogue format. For example, it analyzes the user's voice input and converts it into text using speech recognition technology. The generation AI then generates an answer based on the text and provides the answer in voice using speech synthesis technology. The generation AI can also analyze the user's voice input in real time and generate an appropriate answer on the spot. For example, if a user asks about the stock status of a product by voice, the AI ​​can immediately provide stock information. The generation AI can also analyze the user's voice tone and speed and generate answers in an appropriate tone to provide flexible answers in a voice dialogue format. For example, if the user is in a hurry, it can provide a quick and concise answer. This allows for flexible answers to be provided in a voice dialogue format.

[0055] Generative AI can also generate answers to user questions that include visual content. For example, it can search for relevant visual content in response to a user's question and incorporate it into the answer. For example, if a user asks how to use a product, it can provide a video showing how to use it. Generative AI can also use image recognition technology to search for relevant images in response to a user's question and include them in the answer. For example, if a user asks about the appearance of a particular product, it can provide an image of that product. In order to generate answers that include visual content, generative AI can analyze the content of the user's question and automatically select and provide appropriate images or videos. For example, if a user asks for a cooking recipe, it can provide images or videos showing the cooking steps. This allows it to generate answers that include visual content.

[0056] The generation AI can also generate answers to user questions by referencing related external resources. For example, it can automatically search for related external resources in response to a user's question and generate an answer based on that information. For example, if a user asks for reviews of a specific product, it can obtain and provide information from an external review site. The generation AI can also refer to other websites and databases to generate answers to user questions based on the latest information. For example, if a user asks for the latest research results on a specific technology, it can obtain information from a database of related academic papers. The generation AI can also obtain real-time data in response to a user's question using an external API and generate an answer based on that data. For example, if a user asks for weather information, it can obtain and provide the latest weather information from a weather database. This allows answers to be generated by referencing related external resources.

[0057] The generation AI can also refer to the user's past inquiry history to generate more personalized answers. For example, it can retrieve the user's past inquiry history from a database and generate new answers to similar questions by referring to past answers. For example, if a user has previously asked about how to return an item, it can provide detailed instructions based on that history. The generation AI can also analyze the user's past inquiry history to generate more detailed and specific answers to frequently asked questions. For example, if a user repeatedly asks about the stock status of the same product, it can provide that product's stock information in real time. The generation AI can also understand the user's preferences and interests based on the user's past inquiry history and generate personalized answers accordingly. For example, if a user is interested in products from a particular brand, it will prioritize providing information about products from that brand. This allows the generation of more personalized answers based on the user's past inquiry history.

[0058] The generation AI can also generate answers to user questions by referencing related external resources. For example, it can automatically search for related external resources in response to a user's question and generate an answer based on that information. For example, if a user asks for reviews of a specific product, it can obtain and provide information from an external review site. The generation AI can also refer to other websites and databases to generate answers to user questions based on the latest information. For example, if a user asks for the latest research results on a specific technology, it can obtain information from a database of related academic papers. The generation AI can also obtain real-time data in response to a user's question using an external API and generate an answer based on that data. For example, if a user asks for weather information, it can obtain and provide the latest weather information from a weather database. This allows answers to be generated by referencing related external resources.

[0059] The generation AI can further analyze the user's voice input and provide flexible answers in a voice dialogue format. For example, it analyzes the user's voice input and converts it into text using speech recognition technology. The generation AI then generates an answer based on the text and provides the answer in voice using speech synthesis technology. The generation AI can also analyze the user's voice input in real time and generate an appropriate answer on the spot. For example, if a user asks about the stock status of a product by voice, the AI ​​can immediately provide stock information. The generation AI can also analyze the user's voice tone and speed and generate answers in an appropriate tone to provide flexible answers in a voice dialogue format. For example, if the user is in a hurry, it can provide a quick and concise answer. This allows for flexible answers to be provided in a voice dialogue format.

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

[0061] Step 1: The generation AI generates flexible answers. For example, the generation AI generates specific answers to user questions. The generation AI can also generate answers based on information on the site. Furthermore, the generation AI can analyze the user's input and generate appropriate answers. Step 2: The tag embedding section can be implemented by simply embedding one tag. For example, by simply adding a specific tag to the HTML code of a site, the chatbot will automatically learn the information on the site and begin interacting with the user. The tag embedding section also allows for quick implementation of the chatbot without the need for complex settings or programming. Step 3: The information learning unit automatically learns information on the site. For example, the information learning unit analyzes information such as product descriptions, terms of use, and FAQs, and uses that information to answer user questions. The information learning unit also saves site administrators the trouble of manually entering information. Step 4: The page navigation unit guides the user to the desired page. For example, the page navigation unit provides a link to the appropriate page for the user's question. The page navigation unit also allows the user to quickly access the desired information. Step 5: The customer support department provides interactive customer support. For example, the customer support department responds to user inquiries by guiding them through cancellation procedures and collecting necessary information. The customer support department also ensures that users can receive support smoothly.

[0062] (Example 2) The chat support system according to the embodiment of the present invention uses a generative AI to provide chat support that allows for flexible responses, and is a system that can be easily implemented by simply embedding one tag. This allows the chat support system to improve the user experience of websites and e-commerce sites and reduce the burden on site administrators.

[0063] A chat support system according to an embodiment includes a generation AI, a tag embedding unit, an information learning unit, a page navigation unit, and a customer support unit. The generation AI generates flexible answers. For example, the generation AI generates specific answers to user questions. The generation AI can also generate answers based on information on a website. The generation AI can also analyze user input and generate appropriate answers. The tag embedding unit can be implemented by simply embedding a single tag. For example, by simply adding a specific tag to the website's HTML code, the chatbot automatically learns information on the website and begins a dialogue with the user. The tag embedding unit does not require complex settings or programming, allowing for quick implementation of the chatbot. The information learning unit automatically learns information on the website. For example, the information learning unit analyzes information such as product descriptions, terms of use, and FAQs, and answers user questions based on that information. The information learning unit also eliminates the need for website administrators to manually enter information. The page navigation unit guides users to the desired page. For example, the page navigation unit provides a link to an appropriate page for the user's question. The page navigation unit also enables users to quickly access desired information. The customer support unit provides customer support in an interactive format. For example, the customer support unit responds to user inquiries by guiding them on how to proceed with cancellation procedures and collecting necessary information. The customer support unit also enables users to receive support smoothly. As a result, the chat support system according to the embodiment provides chat support that can provide flexible responses using a generation AI and can be easily implemented by simply embedding one tag. For example, a site administrator can quickly implement a chatbot without the need for complex settings or programming. Furthermore, users can quickly access desired information and receive support smoothly.

[0064] The generation AI can refer to a user's past inquiry history to generate more personalized answers. For example, the generation AI retrieves the user's past inquiry history from a database and generates new answers to similar questions by referring to past answers. For example, if a user has previously asked how to return an item, the generation AI can provide detailed instructions based on that history. The generation AI can also analyze the user's past inquiry history to generate more detailed and specific answers to frequently asked questions. For example, if a user repeatedly asks about the stock status of the same product, the generation AI can provide that product's stock information in real time. The generation AI can also understand the user's preferences and interests based on the user's past inquiry history and generate personalized answers accordingly. For example, if a user is interested in products from a particular brand, the generation AI can prioritize providing information about products from that brand. This allows the generation of more personalized answers based on the user's past inquiry history.

[0065] The generation AI can infer emotions from the user's input and generate answers in a tone that corresponds to the emotion. For example, the generation AI analyzes the user's input and performs emotion analysis. For example, if the user uses words that express dissatisfaction, the AI ​​infers that emotion and generates an answer in a polite and empathetic tone. The generation AI can also infer emotions from the user's input and generate answers in a friendly and cheerful tone for users with positive emotions. For example, if a user expresses joy, it provides a positive message that corresponds to that emotion. The generation AI also uses its emotion estimation function to generate answers in a relaxing tone if the user is feeling stressed. For example, if the user is confused, it can carefully explain the steps to solving the problem in a calm tone. This makes it possible to generate answers in a tone that corresponds to the user's emotions.

[0066] A generation AI can generate answers to user questions by referencing relevant external resources. For example, a generation AI can automatically search for relevant external resources in response to a user question and generate an answer based on that information. For example, if a user asks for reviews of a specific product, the generation AI can obtain and provide information from an external review site. In response to a user question, the generation AI can also refer to other websites and databases to generate answers based on the latest information. For example, if a user asks for the latest research results on a specific technology, the generation AI can obtain information from a database of related academic papers. In response to a user question, the generation AI can obtain real-time data using an external API and generate an answer based on that data. For example, if a user asks for weather information, the generation AI can obtain and provide the latest weather information from a weather database. This allows answers to be generated by referencing relevant external resources.

[0067] The generation AI can analyze the user's voice input and provide flexible answers in a voice dialogue format. For example, the generation AI analyzes the user's voice input and converts it into text using voice recognition technology. The generation AI then generates an answer based on the text and provides the answer in voice using voice synthesis technology. The generation AI can also analyze the user's voice input in real time and generate an appropriate answer on the spot. For example, if a user asks about the stock status of a product by voice, the AI ​​can immediately provide stock information. The generation AI can also analyze the user's voice tone and speed to provide flexible answers in a voice dialogue format and generate answers in an appropriate tone. For example, if the user is in a hurry, it can provide a quick and concise answer. This makes it possible to provide flexible answers in a voice dialogue format.

[0068] Generative AI can generate answers to user questions that include visual content. For example, generative AI searches for relevant visual content in response to a user's question and incorporates it into the answer. For example, if a user asks how to use a product, it will provide a video showing how to use it. Generative AI can also use image recognition technology to search for relevant images in response to a user's question and include them in the answer. For example, if a user asks about the appearance of a particular product, it will provide an image of that product. In addition, to generate answers that include visual content, generative AI analyzes the content of the user's question and automatically selects and provides appropriate images and videos. For example, if a user asks for a cooking recipe, it will provide images and videos showing the cooking steps. This makes it possible to generate answers that include visual content.

[0069] The generation AI can use the emotion estimation function to generate answers that correspond to the user's emotions. For example, the generation AI uses the emotion estimation function to infer emotions from the user's input and generates answers that correspond to those emotions. For example, if the user expresses dissatisfaction, the generation AI provides problem-solving steps in an empathetic tone. The generation AI also adjusts the tone and content of the answer based on the emotion estimation data to generate answers that correspond to the user's emotions. For example, if the user expresses joy, the generation AI provides a positive message that emphasizes that emotion. The generation AI also uses the emotion estimation function to generate personalized answers that correspond to the user's emotions, improving user satisfaction. For example, if the user is confused, the generation AI provides a polite and easy-to-understand explanation. This makes it possible to generate answers that correspond to the user's emotions.

[0070] The tag embedding unit can automatically adapt to the design and theme of a site. For example, when embedding a tag, the tag embedding unit analyzes the CSS stylesheet of the site and automatically adapts the chatbot design. For example, it adjusts the appearance of the chatbot to match the color scheme and font style of the site. Furthermore, when embedding a tag, the tag embedding unit adds a function to analyze the layout of the site and place the chatbot in the optimal position. For example, it places the chatbot in a location where the user's gaze is likely to be drawn. Furthermore, in order to automatically adapt to the design and theme of the site, the tag embedding unit analyzes the HTML structure of the site when embedding a tag and appropriately places the chatbot elements. For example, it adjusts the position of the chatbot to match the header or footer of the site. This allows the tag embedding unit to automatically adapt to the design and theme of the site.

[0071] The tag embedding unit can automatically configure a chatbot that supports multiple languages. For example, when embedding a tag, the tag embedding unit automatically detects the language setting of the site and configures the chatbot in the corresponding language. For example, if a site supports English and Japanese, the chatbot will also support both languages. In addition, the tag embedding unit uses multilingual natural language processing technology in the generation AI to automatically configure a chatbot that supports multiple languages ​​simply by embedding a tag. For example, if a user asks a question in French, the tag embedding unit generates an answer in French. In addition, when embedding a tag, the tag embedding unit analyzes the language setting of the site user and automatically configures the chatbot that supports the most commonly used language. For example, the tag embedding unit identifies the main language based on access analysis data of the site and configures the chatbot in that language. This makes it possible to automatically configure a chatbot that supports multiple languages.

[0072] The tag embedding unit can place the chatbot in the optimal position based on the site's access analysis data. For example, when embedding a tag, the tag embedding unit analyzes the site's access analysis data and places the chatbot in a location where users are likely to look. For example, the chatbot is placed in an area where users frequently click. The tag embedding unit also adds a function to analyze user behavior patterns based on the site's access analysis data and place the chatbot in the optimal position. For example, the chatbot is placed on a page where users stay for a long time. The tag embedding unit also places the chatbot on a page where users have a high dropout rate based on the site's access analysis data. For example, the chatbot is placed on a page where users abandon the purchase process and support is provided. This makes it possible to place the chatbot in the optimal position based on the site's access analysis data.

[0073] The tag embedding unit can automatically integrate the chatbot into the user interface of a site. For example, the tag embedding unit adds a function that allows the chatbot to be automatically integrated into the user interface of a site simply by embedding a tag. For example, it adds a chatbot link to the navigation menu or footer of the site. When embedding a tag, the tag embedding unit also analyzes the user interface of the site and positions the chatbot so that it is integrated naturally. For example, it customizes the chatbot button to match the design of the site. When embedding a tag, the tag embedding unit also analyzes the HTML structure of the site and positions the chatbot in an appropriate position so that the chatbot is automatically integrated into the user interface of the site. For example, it positions the chatbot in the sidebar of the site. This allows the chatbot to be automatically integrated into the user interface of the site.

[0074] The tag embedding unit collects user behavior data on the site in real time and can approach users at the optimal timing. For example, by simply embedding a tag, the tag embedding unit allows a chatbot to collect user behavior data on the site in real time and automatically approach users when they perform a specific action. For example, support is provided when a user adds an item to their cart. The tag embedding unit also allows the chatbot to collect user behavior data in real time and automatically approach users when they are unsure about something on the site. For example, help is provided when a user stays on a particular page for a long time. The tag embedding unit also allows the chatbot to analyze user behavior data and proactively approach users at the optimal timing. For example, a reminder is sent when a user aborts the purchase process. This allows the chatbot to collect user behavior data on the site in real time and approach users at the optimal timing.

[0075] The tag embedding unit can automatically perform customization according to the user's emotions using the emotion estimation function. For example, when embedding a tag, the tag embedding unit uses the emotion estimation function to analyze the user's emotions and automatically perform customization according to the emotions. For example, if the user is feeling stressed, a design or message that promotes relaxation is displayed. Furthermore, in order to perform customization according to the user's emotions using the emotion estimation function, the tag embedding unit analyzes the user's past behavioral data when embedding tags and automatically performs optimal settings according to the emotions. For example, a design to which the user has previously shown a positive reaction is applied. Furthermore, the tag embedding unit can analyze the user's emotions in real time using the emotion estimation function and perform customization according to the emotions. For example, if the user is feeling happy, a positive message that emphasizes that emotion is displayed. In this way, the emotion estimation function can be used to automatically perform customization according to the user's emotions.

[0076] When learning information within a site, the information learning unit evaluates the reliability of the information and prioritizes the use of highly reliable information. For example, when the generation AI learns information within a site, the information learning unit uses an algorithm that evaluates the reliability of information to prioritize the use of highly reliable information. For example, the information learning unit prioritizes learning information from official information sources and highly reliable databases. Furthermore, when learning information within a site, the information learning unit analyzes the source of the information and update frequency to evaluate the reliability of the information and prioritizes the use of highly reliable information. For example, it prioritizes learning official documents that are updated frequently. Furthermore, when the generation AI learns information within a site, the information learning unit evaluates the reliability of the information based on user feedback and prioritizes the use of highly reliable information. For example, it prioritizes learning information that has received high ratings from users. This allows the generation AI to prioritize the use of highly reliable information when learning information within a site.

[0077] When learning information within a site, the information learning unit takes into account how often the information is updated, allowing the latest information to be used preferentially. For example, when the generation AI learns information within a site, the information learning unit introduces an algorithm that analyzes how often the information is updated and prioritizes the use of the latest information. For example, it prioritizes learning news articles and blog posts that are updated frequently. In addition, when learning information within a site, the information learning unit analyzes the update history of the information and prioritizes the use of the latest information. For example, it prioritizes learning recently updated product descriptions and terms of use. In addition, when the generation AI learns information within a site, the information learning unit takes into account how often the information is updated and adds a function to automatically filter out old information. For example, it excludes information that has not been updated for a certain period of time. This allows the latest information to be used preferentially when learning information within a site.

[0078] When learning information within a site, the information learning unit evaluates the relevance of the information and prioritizes the use of highly relevant information. For example, when the generation AI learns information within a site, the information learning unit uses an algorithm to evaluate the relevance of information and prioritizes the use of highly relevant information. For example, it prioritizes learning information that is directly related to the user's question. Furthermore, when learning information within a site, the information learning unit analyzes the keywords and topics of the information to evaluate the relevance of the information and prioritizes the use of highly relevant information. For example, it prioritizes learning information related to the description of a specific product. Furthermore, when the generation AI learns information within a site, the information learning unit evaluates the relevance of the information based on user behavior data and prioritizes the use of highly relevant information. For example, it prioritizes learning information on pages that the user frequently accesses. This allows the generation AI to prioritize the use of highly relevant information when learning information within a site.

[0079] The information learning unit can also integrate information from different data sources. For example, when the generation AI learns information within a site, the information learning unit integrates information from social media to generate answers to user questions that reflect the latest trends and opinions. For example, it analyzes posts on Twitter and Facebook. To integrate information from different data sources, the generation AI collects information from news sites and generates answers to user questions that reflect the latest news and events. For example, it analyzes news articles and incorporates them into the answers. When the generation AI learns information within a site, the information learning unit integrates information from external databases and APIs to generate comprehensive answers to user questions. For example, it uses databases of academic papers and government statistical data. This allows information from different data sources to be integrated.

[0080] The information learning unit can improve the accuracy of the information based on user feedback. For example, when the generation AI learns information on a site, the information learning unit collects feedback from users and improves the accuracy of the information based on that feedback. For example, corrections and additional information provided by users are reflected in the learning. The information learning unit also causes the generation AI to periodically update the information on the site based on user feedback, improving the accuracy of the information. For example, information where a user points out an error is corrected and re-learned. The information learning unit also introduces an algorithm that allows the generation AI to analyze user feedback and improve the accuracy of the information. For example, the reliability of the information is reevaluated based on the user's evaluation score and reflected in the learning. This allows the accuracy of the information to be improved based on user feedback.

[0081] The information learning unit can use the emotion estimation function to preferentially learn information that corresponds to the user's emotions. For example, to preferentially learn information that corresponds to the user's emotions using the emotion estimation function, the generation AI analyzes the user's emotion score and preferentially learns information that elicits positive emotions. For example, information that makes the user feel happy is preferentially learned. Furthermore, when the generation AI learns information within a site, the information learning unit preferentially learns information that corresponds to the user's emotions based on the emotion estimation data. For example, if the user is feeling stressed, information that is relaxing is preferentially learned. Furthermore, to preferentially learn information that corresponds to the user's emotions using the emotion estimation function, the generation AI analyzes the user's past emotional reactions and learns optimal information that corresponds to the emotion. For example, information to which the user showed a positive reaction is preferentially learned. This allows the emotion estimation function to preferentially learn information that corresponds to the user's emotions.

[0082] The page navigation unit can refer to the user's past behavior history and guide the user to the optimal page. For example, the generation AI retrieves the user's past behavior history from a database and guides the user to the optimal page based on the pages the user frequently visits and content in which the user is interested. For example, it provides a link to a detail page of a product the user previously viewed. The page navigation unit also analyzes the user's past behavior history and guides the user to the optimal page based on pages the user previously visited and keywords searched for. For example, it provides a link to a page where the user can check the stock status of a product they previously searched for. The page navigation unit also identifies the user's interests and concerns based on the user's past behavior history and guides the user to the optimal page accordingly. For example, if the user is interested in products in a specific category, it provides a link to a page in that category. This makes it possible to guide the user to the optimal page based on the user's past behavior history.

[0083] The page guidance unit can analyze the content of the user's current page and guide the user to related pages. For example, the generation AI analyzes the content of the user's current page and guides the user to the most appropriate page based on information related to that page. For example, if the user is viewing a product details page, it provides links to product reviews and related product pages. The page guidance unit also analyzes the content of the current page and guides the user to pages related to the information the user is looking for. For example, if the user is viewing an FAQ page, it provides links to related support pages. The page guidance unit also guides the user to the page the user is likely to visit next based on the content of the user's current page. For example, if the user is in the process of making a purchase, it provides a link to a payment method details page. This makes it possible to guide the user to related pages based on the content of the user's current page.

[0084] The page navigation unit can infer emotions from the user's input and direct the user to a page that corresponds to the emotion. For example, the generation AI analyzes the user's input, infers the user's emotion using an emotion estimation function, and directs the user to a page that corresponds to that emotion. For example, if the user expresses dissatisfaction, it provides a link to a support page for resolving the problem. The page navigation unit also infers emotions from the user's input and directs users with positive emotions to related pages. For example, if the user is excited, it provides a link to a special offer page that will further increase that excitement. The page navigation unit also uses the emotion estimation function to direct the user to a page that corresponds to the user's emotion, and the generation AI selects the optimal page based on the user's emotion score. For example, if the user is confused, it provides a link to a help page with easy-to-understand explanations. This makes it possible to direct the user to a page that corresponds to the user's emotion.

[0085] The page navigation unit can analyze the user's voice input and guide the user to the desired page in a voice-interactive format. For example, the page navigation unit uses a generation AI to analyze the user's voice input and convert it into text using voice recognition technology. The generation AI then generates a link to the optimal page based on the text and provides audio guidance using voice synthesis technology. The page navigation unit also analyzes the user's voice input in real time, and the generation AI guides the user to the appropriate page on the spot. For example, if a user asks for product details by voice, a link to the product's details page is provided by voice. To guide the user to the desired page in a voice-interactive format, the generation AI analyzes the user's voice tone and speed and provides guidance in an appropriate tone. For example, if the user is in a hurry, quick and concise guidance is provided. This allows the user to be guided to the desired page in a voice-interactive format.

[0086] The page navigation unit can guide users to pages containing visual content in response to their questions. For example, the generation AI searches for relevant visual content in response to a user's question and provides a link to a page containing that content. For example, if a user asks how to use a product, the page navigation unit provides a link to a page containing a video demonstrating how to use the product. In response to a user's question, the generation AI uses image recognition technology to search for relevant images and provides a link to a page containing the images. For example, if a user asks about the appearance of a specific product, the page navigation unit provides a link to a page containing an image of the product. To guide users to pages containing visual content, the generation AI analyzes the content of the user's question and automatically selects and provides appropriate images or videos. For example, if a user asks about a cooking recipe, the page navigation unit provides a link to a page containing images or videos showing the cooking steps. This allows users to be guided to pages containing visual content.

[0087] The page navigation unit can use the emotion estimation function to guide the user to a page that corresponds to the user's emotion. For example, the page navigation unit uses the emotion estimation function to infer an emotion from the user's input and guides the user to a page that corresponds to that emotion. For example, if the user expresses dissatisfaction, the page navigation unit provides a link to a support page for resolving the problem. In addition, to guide the user to a page that corresponds to the user's emotion, the generation AI selects the optimal page based on the emotion estimation data. For example, if the user is feeling happy, the page navigation unit provides a link to a page with a positive message that emphasizes that emotion. In addition, the page navigation unit uses the emotion estimation function to guide the user to a personalized page that corresponds to the user's emotion, thereby improving user satisfaction. For example, if the user is confused, the page navigation unit provides a link to a help page with thorough and easy-to-understand explanations. In this way, the emotion estimation function can be used to guide the user to a page that corresponds to the user's emotion.

[0088] The customer support department can provide more personalized support by referencing the user's past support history. For example, the generation AI retrieves the user's past support history from a database and provides new support for similar issues while referring to past responses. For example, if the user has previously completed a return procedure, it provides detailed instructions based on that history. The customer support department also analyzes the user's past support history to provide more detailed and specific support for frequently occurring issues. For example, if a user repeatedly reports a defect with the same product, it provides instructions on how to repair that product. The generation AI also understands the user's preferences and interests based on the user's past support history and provides personalized support accordingly. For example, if a user is interested in products from a particular brand, it will prioritize support for products from that brand. This allows the department to provide more personalized support based on the user's past support history.

[0089] The customer support department can infer emotions from the user's input and provide support in a tone that corresponds to the emotion. For example, in the customer support department, the generation AI analyzes the user's input and performs emotion analysis. For example, if the user uses words that express dissatisfaction, the AI ​​infers that emotion and provides support in a polite and empathetic tone. The customer support department can also infer emotions from the user's input and provide support in a friendly and cheerful tone to users with positive emotions. For example, if a user expresses joy, it provides a positive message that corresponds to that emotion. The customer support department can also use the emotion estimation function to provide support in a relaxing tone if the user is feeling stressed. For example, if the user is confused, it can carefully explain the steps to resolve the problem in a calm tone. This makes it possible to provide support in a tone that corresponds to the user's emotions.

[0090] The customer support department can provide support for a user's question by referencing relevant external resources. For example, the generation AI automatically searches for relevant external resources in response to a user's question and provides support based on that information. For example, if a user asks for reviews of a specific product, the generation AI retrieves and provides information from an external review site. In addition, the customer support department can provide support for a user's question by referencing other websites and databases and providing support based on the latest information. For example, if a user asks about the latest research results on a specific technology, the generation AI retrieves information from a database of related academic papers. In addition, the customer support department can provide support for a user's question by using an external API to retrieve real-time data and providing support based on that data. For example, if a user asks about weather information, the generation AI retrieves and provides the latest weather information from a weather database. This allows support to be provided by referencing relevant external resources.

[0091] The customer support department can analyze the user's voice input and provide customer support in a voice dialogue format. For example, in the customer support department, the generation AI analyzes the user's voice input and converts it into text using voice recognition technology. The generation AI then provides support based on the text and provides answers in voice using voice synthesis technology. The customer support department also analyzes the user's voice input in real time, and the generation AI provides appropriate support on the spot. For example, if a user voice-inquires about how to return a product, the AI ​​immediately provides instructions on how to proceed with the return. In addition, in order to provide customer support in a voice dialogue format, the generation AI analyzes the user's voice tone and speed and provides support in an appropriate tone. For example, if the user is in a hurry, it provides quick and concise support. This enables customer support to be provided in a voice dialogue format.

[0092] The customer support department can provide support including visual content in response to a user's question. For example, the generation AI searches for relevant visual content in response to a user's question and provides support including that content. For example, if a user asks how to use a product, a video demonstrating how to use the product is provided. In addition, the customer support department uses image recognition technology to search for relevant images in response to a user's question and provides support including those images. For example, if a user asks about the appearance of a specific product, an image of the product is provided. In addition, in order to provide support including visual content, the generation AI analyzes the content of the user's question and automatically selects and provides appropriate images or videos. For example, if a user asks about a cooking recipe, images or videos showing the cooking steps are provided. This makes it possible to provide support including visual content.

[0093] The customer support department can use the emotion estimation function to provide support that is appropriate for the user's emotions. For example, the customer support department uses the emotion estimation function to estimate emotions from the user's input and provide support that is appropriate for those emotions. For example, if the user expresses dissatisfaction, the customer support department provides problem-solving steps in an empathetic tone. Furthermore, in order to provide support that is appropriate for the user's emotions, the generation AI adjusts the tone and content of the support based on the emotion estimation data. For example, if the user expresses joy, the customer support department provides a positive message that emphasizes that emotion. Furthermore, the customer support department uses the emotion estimation function to provide personalized support that is appropriate for the user's emotions, thereby improving user satisfaction. For example, if the user is confused, the customer support department provides a polite and easy-to-understand explanation. In this way, the emotion estimation function can be used to provide support that is appropriate for the user's emotions.

[0094] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0095] The chat support system may further include a behavior analysis unit that analyzes user behavior patterns. The behavior analysis unit, for example, analyzes which pages a user frequently visits on a website and which links they click, and uses this data to understand the user's interests. For example, if a user frequently visits product pages in a particular category, information about products in that category may be provided preferentially. The behavior analysis unit may also predict which page a user is likely to visit next based on the user's behavior patterns, and provide support at the appropriate time. For example, if a user is in the process of making a purchase, it may provide a link to a page with payment method details. The behavior analysis unit may also include a function that automatically approaches a user when they are unsure about a solution on a website based on user behavior data. For example, if a user stays on a particular page for a long time, it may provide help. This allows for analyzing user behavior patterns and providing more personalized support.

[0096] The generation AI can further infer emotions from the user's input and generate answers in a tone that corresponds to the emotion. For example, if the user uses words that express dissatisfaction, the AI ​​can infer that emotion and generate an answer in a polite and empathetic tone. The generation AI can also infer emotions from the user's input and generate answers in a friendly and cheerful tone for users with positive emotions. For example, if a user expresses joy, it will provide a positive message that corresponds to that emotion. The generation AI can also use its emotion inference function to generate answers in a relaxing tone if the user is feeling stressed. For example, if the user is confused, it will carefully explain the steps to solving the problem in a calm tone. This makes it possible to generate answers in a tone that corresponds to the user's emotions.

[0097] The generation AI can further analyze the user's voice input and provide flexible answers in a voice dialogue format. For example, it analyzes the user's voice input and converts it into text using speech recognition technology. The generation AI then generates an answer based on the text and provides the answer in voice using speech synthesis technology. The generation AI can also analyze the user's voice input in real time and generate an appropriate answer on the spot. For example, if a user asks about the stock status of a product by voice, the AI ​​can immediately provide stock information. The generation AI can also analyze the user's voice tone and speed and generate answers in an appropriate tone to provide flexible answers in a voice dialogue format. For example, if the user is in a hurry, it can provide a quick and concise answer. This allows for flexible answers to be provided in a voice dialogue format.

[0098] Generative AI can also generate answers to user questions that include visual content. For example, it can search for relevant visual content in response to a user's question and incorporate it into the answer. For example, if a user asks how to use a product, it can provide a video showing how to use it. Generative AI can also use image recognition technology to search for relevant images in response to a user's question and include them in the answer. For example, if a user asks about the appearance of a particular product, it can provide an image of that product. In order to generate answers that include visual content, generative AI can analyze the content of the user's question and automatically select and provide appropriate images or videos. For example, if a user asks for a cooking recipe, it can provide images or videos showing the cooking steps. This allows it to generate answers that include visual content.

[0099] The generation AI can also generate answers to user questions by referencing related external resources. For example, it can automatically search for related external resources in response to a user's question and generate an answer based on that information. For example, if a user asks for reviews of a specific product, it can obtain and provide information from an external review site. The generation AI can also refer to other websites and databases to generate answers to user questions based on the latest information. For example, if a user asks for the latest research results on a specific technology, it can obtain information from a database of related academic papers. The generation AI can also obtain real-time data in response to a user's question using an external API and generate an answer based on that data. For example, if a user asks for weather information, it can obtain and provide the latest weather information from a weather database. This allows answers to be generated by referencing related external resources.

[0100] The generation AI can further infer emotions from the user's input and generate answers in a tone that corresponds to the emotion. For example, if the user uses words that express dissatisfaction, the AI ​​can infer that emotion and generate an answer in a polite and empathetic tone. The generation AI can also infer emotions from the user's input and generate answers in a friendly and cheerful tone for users with positive emotions. For example, if a user expresses joy, it will provide a positive message that corresponds to that emotion. The generation AI can also use its emotion inference function to generate answers in a relaxing tone if the user is feeling stressed. For example, if the user is confused, it will carefully explain the steps to solving the problem in a calm tone. This makes it possible to generate answers in a tone that corresponds to the user's emotions.

[0101] The generation AI can also refer to the user's past inquiry history to generate more personalized answers. For example, it can retrieve the user's past inquiry history from a database and generate new answers to similar questions by referring to past answers. For example, if a user has previously asked about how to return an item, it can provide detailed instructions based on that history. The generation AI can also analyze the user's past inquiry history to generate more detailed and specific answers to frequently asked questions. For example, if a user repeatedly asks about the stock status of the same product, it can provide that product's stock information in real time. The generation AI can also understand the user's preferences and interests based on the user's past inquiry history and generate personalized answers accordingly. For example, if a user is interested in products from a particular brand, it will prioritize providing information about products from that brand. This allows the generation of more personalized answers based on the user's past inquiry history.

[0102] The generation AI can further infer emotions from the user's input and generate answers in a tone that corresponds to the emotion. For example, if the user uses words that express dissatisfaction, the AI ​​can infer that emotion and generate an answer in a polite and empathetic tone. The generation AI can also infer emotions from the user's input and generate answers in a friendly and cheerful tone for users with positive emotions. For example, if a user expresses joy, it will provide a positive message that corresponds to that emotion. The generation AI can also use its emotion inference function to generate answers in a relaxing tone if the user is feeling stressed. For example, if the user is confused, it will carefully explain the steps to solving the problem in a calm tone. This makes it possible to generate answers in a tone that corresponds to the user's emotions.

[0103] The generation AI can also generate answers to user questions by referencing related external resources. For example, it can automatically search for related external resources in response to a user's question and generate an answer based on that information. For example, if a user asks for reviews of a specific product, it can obtain and provide information from an external review site. The generation AI can also refer to other websites and databases to generate answers to user questions based on the latest information. For example, if a user asks for the latest research results on a specific technology, it can obtain information from a database of related academic papers. The generation AI can also obtain real-time data in response to a user's question using an external API and generate an answer based on that data. For example, if a user asks for weather information, it can obtain and provide the latest weather information from a weather database. This allows answers to be generated by referencing related external resources.

[0104] The generation AI can further analyze the user's voice input and provide flexible answers in a voice dialogue format. For example, it analyzes the user's voice input and converts it into text using speech recognition technology. The generation AI then generates an answer based on the text and provides the answer in voice using speech synthesis technology. The generation AI can also analyze the user's voice input in real time and generate an appropriate answer on the spot. For example, if a user asks about the stock status of a product by voice, the AI ​​can immediately provide stock information. The generation AI can also analyze the user's voice tone and speed and generate answers in an appropriate tone to provide flexible answers in a voice dialogue format. For example, if the user is in a hurry, it can provide a quick and concise answer. This allows for flexible answers to be provided in a voice dialogue format.

[0105] The processing flow of the second embodiment will be briefly explained below.

[0106] Step 1: The generation AI generates flexible answers. For example, the generation AI generates specific answers to user questions. The generation AI can also generate answers based on information on the site. Furthermore, the generation AI can analyze the user's input and generate appropriate answers. Step 2: The tag embedding section can be implemented by simply embedding one tag. For example, by simply adding a specific tag to the HTML code of a site, the chatbot will automatically learn the information on the site and begin interacting with the user. The tag embedding section also allows for quick implementation of the chatbot without the need for complex settings or programming. Step 3: The information learning unit automatically learns information on the site. For example, the information learning unit analyzes information such as product descriptions, terms of use, and FAQs, and uses that information to answer user questions. The information learning unit also saves site administrators the trouble of manually entering information. Step 4: The page navigation unit guides the user to the desired page. For example, the page navigation unit provides a link to the appropriate page for the user's question. The page navigation unit also allows the user to quickly access the desired information. Step 5: The customer support department provides interactive customer support. For example, the customer support department responds to user inquiries by guiding them through cancellation procedures and collecting necessary information. The customer support department also ensures that users can receive support smoothly.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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 AI 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.

[0124] 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.

[0125] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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 AI 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.

[0139] 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.

[0140] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0152] 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.

[0153] 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.

[0154] 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 AI 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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."

[0162] 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.

[0163] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0164] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a 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.

[0165] 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.

[0166] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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]

[0174] 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. Generative AI that generates flexible answers using generative AI, A tag embedding section that can be introduced by simply embedding one tag, an information learning unit that automatically learns information within the site; a page navigation unit that guides users to a desired page; A customer support department that performs customer support. A system characterized by:

2. The generated AI is Referencing the user's past inquiry history to generate more personalized responses 2. The system of claim 1.

3. The generated AI is Inferring emotions from user input and generating responses in a tone that matches the emotion 2. The system of claim 1.

4. The generated AI is Generate answers to user questions by referencing relevant external resources 2. The system of claim 1.

5. The generated AI is Analyzes user voice input and provides flexible answers in a voice dialogue format 2. The system of claim 1.

6. The generated AI is Generate answers to user questions, including visual content 2. The system of claim 1.

Images