System

Abstract

To provide a system capable of providing quick and appropriate responses to website visitors.SOLUTION: A system in an embodiment includes a responding unit, a detailed information providing unit, an inquiry support unit, a purchasing support unit, an estimation unit, and an analysis result providing unit. The responding unit responds to questions from website visitors. The detailed information providing unit provides details of the product or service specified by the visitor to the visitors. The inquiry support unit provides guidance or solutions to the inquiries of the visitor. The purchasing support unit supports visitors in purchasing products, booking services, and making appointments. The estimation unit estimates the interests of the visitor based on the information of the visitor. The analysis result providing unit analyzes feedback or opinions from the visitors and provides analysis results.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] With conventional technology, it was difficult to provide immediate and appropriate responses to website visitors, making it difficult to improve customer satisfaction.

[0005] The system according to the embodiment aims to provide an immediate and appropriate response to website visitors. [Means for solving the problem]

[0006] The system according to the embodiment includes an answering unit, a detailed information providing unit, an inquiry support unit, a purchase support unit, an estimation unit, and an analysis result providing unit. The answering unit answers questions from visitors of the website. The detailed information providing unit provides the visitor with detailed information about a product or service specified by the visitor. The inquiry support unit provides guidance or solutions to the visitor's inquiries. The purchase support unit supports the visitor in purchasing products, reserving services, and making appointments. The estimation unit estimates the visitor's interests based on the visitor's information. The analysis result providing unit analyzes feedback or opinions from the visitor and provides analysis results. Effect of the Invention

[0007] The system according to the embodiment can provide an immediate and appropriate response to website visitors. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The automatic response system AI assistant according to the embodiment of the present invention is a system that provides a wide range of support to website visitors. This system includes an answering unit that immediately answers questions from visitors. For example, when a visitor asks, "What are your business hours?", the answering unit immediately responds, "Business hours are from 9:00 to 18:00." Next, a detailed information providing unit is provided that provides detailed information on products and services desired by visitors in real time. For example, when a visitor asks, "Please tell me the details of this product," the detailed information providing unit provides detailed information such as product specifications, prices, and usage methods. In addition, an inquiry support unit is provided that provides guidance and solutions to inquiries about technical problems and services. For example, when a visitor inquires, "My Internet connection is unstable," the inquiry support unit provides a method for checking the connection and troubleshooting procedures. In addition, the system includes an estimation unit with a lead acquisition function that acquires the visitor's contact information and investigates the visitor's interest in products and services. For example, when a visitor says, "I'm interested in this service," the estimation unit acquires the visitor's contact information and provides information on the service of interest. The system also includes a purchase support unit that recommends products to visitors of an online shop, adds them to a cart, and supports the purchase process. For example, if a visitor asks, "What products do you recommend?", the purchase support section will recommend products based on the visitor's past purchase history and interests, and will support the visitor in adding them to the cart and completing the purchase process. It also provides an appointment setting function that supports the process when a visitor wants to reserve or set up an appointment for a service. For example, if a visitor says, "I'd like to make a reservation for next Tuesday," the appointment setting function will check availability and assist with the reservation process. It has an analysis result provision section that collects feedback and opinions from visitors, analyzes and reports them. For example, if a visitor provides feedback such as "This service was very good," the analysis result provision section collects the feedback and displays it on the dashboard in real time. It also has a multimedia support function that provides responses that incorporate not only text but also multimedia content such as videos, images, and audio.For example, if a visitor asks, "Please tell me how to use this product," the multimedia support function will explain how to use it using videos and images. It also has a real-time learning function that learns the trends and needs of visitors to the website through dialogue with the visitor and provides more appropriate responses based on that. For example, if a visitor frequently asks a specific question, the real-time learning function will learn that trend and improve the response from the next time onwards. Finally, if the inquiry is complex and the AI ​​cannot handle it, it has an escalation support function that escalates the inquiry to a real customer support representative. For example, if a visitor says, "I cannot solve this problem," the escalation support function will transfer the inquiry to a customer support representative who will respond appropriately. This allows the automatic response system AI assistant to provide a wide range of support to website visitors.

[0029] The AI ​​assistant automatic response system according to the embodiment includes an answering unit, a detailed information providing unit, an inquiry support unit, a purchase support unit, an estimation unit, and an analysis result providing unit. The answering unit answers questions from visitors to the website. For example, if a visitor asks, "What are your business hours?", the answering unit immediately responds, "Business hours are from 9:00 to 18:00." The detailed information providing unit provides detailed information about a product or service specified by the visitor. For example, if a visitor asks, "Please tell me the details of this product," the detailed information providing unit provides detailed information such as product specifications, prices, and usage methods. The inquiry support unit provides guidance or solutions to the visitor's inquiries. For example, if a visitor asks, "My Internet connection is unstable," the inquiry support unit provides a method for checking the connection and troubleshooting procedures. The purchase support unit supports the visitor in purchasing products, reserving services, and making appointments. For example, if a visitor asks, "What products do you recommend?", the purchase support unit recommends products based on the visitor's past purchase history and interests, and supports the visitor in adding the products to the cart and completing the purchase procedure. The estimation unit estimates the visitor's interest in a specific target based on the visitor's information. For example, if the visitor says, "I'm interested in this service," the estimation unit obtains the visitor's contact information and provides information about the service of interest. The analysis result providing unit analyzes feedback or opinions from the visitor and provides analysis results. For example, if the visitor provides feedback such as, "This service was very good," the analysis result providing unit collects the feedback and displays it on the dashboard in real time. In this way, the automatic response system AI assistant according to the embodiment can provide a wide range of support to website visitors.

[0030] The answering section answers questions from visitors to the website. For example, if a visitor asks, "What are your business hours?", the answering section immediately responds, "Business hours are from 9:00 to 18:00." The answering section uses natural language processing (NLP) technology to analyze the visitor's question and generate an appropriate answer. Specifically, to understand the intent of the question, morphological analysis and context analysis are performed, and the answer that best suits the content of the question is searched for from a database. Furthermore, the answering section can learn the visitor's past question history and behavioral patterns to provide a more personalized answer. For example, if a visitor has previously asked a question about a specific product, information related to that product is provided preferentially. In addition, the answering section continuously learns to improve the accuracy of answers to visitor questions. For example, the answering section collects feedback from visitors, evaluates the accuracy and satisfaction of the answers, and improves the answering algorithm based on the results. This allows the answering section to quickly and accurately respond to a variety of questions from visitors and improve the user experience of the website.

[0031] The detailed information providing unit provides detailed information on the product or service specified by the visitor. For example, when the visitor asks "Please tell me the details of this product," the detailed information providing unit provides detailed information such as the product specifications, price, and usage. The detailed information providing unit has a rich database on products and services, and quickly provides information in response to the visitor's request. Specifically, the detailed information providing unit centrally manages information such as product specifications, price, usage, user reviews, and related FAQs, and extracts appropriate information for the visitor's question. In addition, the detailed information providing unit can also suggest information on related products and services based on the visitor's interests and concerns. For example, when the visitor shows interest in a specific product, the detailed information providing unit provides information on accessories and optional products related to the product. Furthermore, the detailed information providing unit analyzes the visitor's behavior history and past inquiries to provide more personalized information. As a result, the detailed information providing unit can quickly and accurately provide the information the visitor desires to purchase.

[0032] The inquiry support department provides guidance or solutions to the visitor's inquiries. For example, if a visitor inquires that "the Internet connection is unstable," the inquiry support department provides a method for checking the connection and troubleshooting procedures. The inquiry support department has a rich knowledge base and troubleshooting guides to quickly solve the visitor's problems. Specifically, it accumulates solutions to common problems and troubles in a database and provides appropriate solutions according to the visitor's inquiry. In addition, the inquiry support department can ask additional questions to understand the visitor's problem in more detail. For example, if a visitor states that "the Internet connection is unstable," the inquiry support department can ask "Specifically, in what circumstances does the connection become unstable?" to collect information to identify the cause of the problem. In addition, the inquiry support department also has the function of escalating the visitor's problem to a specialized support team if the visitor's problem is not resolved. This allows the inquiry support department to quickly and effectively solve the visitor's problem and improve customer satisfaction.

[0033] The purchase support department supports visitors in purchasing products, reserving services, and making appointments. For example, if a visitor asks, "What is the recommended product?", the purchase support department recommends products based on the visitor's past purchase history and interests, and supports adding products to the cart and making purchases. The purchase support department analyzes the visitor's purchasing behavior and interests, and suggests optimal products and services. Specifically, it recommends products and services that the visitor may be interested in based on data such as the visitor's past purchase history, browsing history, and search history. In addition, the purchase support department provides support such as adding products to the cart, making payments, and selecting delivery options so that the visitor can make the purchase process smooth. In addition, the purchase support department can provide real-time chat support to resolve any questions or concerns that the visitor may have about the purchase. For example, if a visitor asks, "What is the warranty period for this product?", the purchase support department will immediately respond and resolve the visitor's concerns. This allows the purchase support department to improve the visitor's purchasing experience and contribute to increased sales.

[0034] The estimation unit estimates the visitor's interest in a specific target based on the visitor's information. For example, if the visitor says, "I'm interested in this service," the estimation unit obtains the visitor's contact information and provides information about the service of interest. The estimation unit analyzes the visitor's behavioral data and past inquiries to estimate the visitor's interests. Specifically, based on data such as the visitor's browsing history, search history, and click patterns, the estimation unit identifies products and services that the visitor may be interested in. The estimation unit can also provide related information and offers based on the visitor's interests. For example, if the visitor shows interest in a specific service, the estimation unit provides promotion and discount information related to the service. Furthermore, the estimation unit can continuously learn the visitor's interests and make more accurate estimations. As a result, the estimation unit can provide information according to the visitor's needs and improve the visitor's satisfaction.

[0035] The analysis result providing unit analyzes feedback or opinions from visitors and provides analysis results. For example, if a visitor provides feedback such as "this service was very good," the analysis result providing unit collects the feedback and displays it on a dashboard in real time. The analysis result providing unit collects feedback and opinions from visitors and analyzes them using text mining technology. Specifically, the content of the feedback is classified and positive and negative opinions are extracted. In addition, based on the visitor feedback, it is also possible to identify areas for improvement and areas to be strengthened in the service. Furthermore, the analysis result providing unit displays the analysis results on a dashboard in real time, allowing the administrator to respond quickly. For example, if there is a lot of negative feedback, the cause can be identified and measures to improve the service can be taken quickly. In this way, the analysis result providing unit can effectively utilize the visitor feedback and contribute to improving the quality of the service.

[0036] The automatic response system AI assistant according to the embodiment includes a connection unit that connects the visitor's inquiry to a customer support representative based on the details of the visitor's inquiry. For example, if the visitor says, "I can't solve this problem," the connection unit transfers the inquiry to the customer support representative and takes appropriate action. This allows complex inquiries to be escalated to the customer support representative. Some or all of the above-mentioned processing in the connection unit may be performed, for example, using AI or may be performed without using AI. For example, the connection unit may input the details of the visitor's inquiry to the generation AI and cause the generation AI to execute a process of evaluating the complexity of the inquiry.

[0037] The automatic response system AI assistant according to the embodiment includes a learning unit that learns dialogue with visitors in real time and provides a response based on the visitor's behavioral patterns and requests. For example, if a visitor frequently asks a specific question, the learning unit learns the tendency and improves the response from the next time onwards. This makes it possible to provide a more appropriate response based on the visitor's tendencies and needs. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using AI or may be performed without using AI. For example, the learning unit may input dialogue data with the visitor to a generation AI and cause the generation AI to perform an analysis of the behavioral patterns.

[0038] The detailed information providing unit can provide personalized information based on the visitor's past behavior history. For example, related product information is provided based on products the visitor has viewed in the past. The detailed information providing unit can also provide related service information based on products the visitor has purchased in the past. This makes it possible to provide more personalized information to the visitor. Some or all of the above-mentioned processing in the detailed information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the detailed information providing unit can input the visitor's past behavior history data to the generation AI and cause the generation AI to generate personalized information.

[0039] The analysis result providing unit can display feedback from visitors on the dashboard in real time. For example, if a visitor provides feedback such as "this service was very good," the analysis result providing unit collects the feedback and displays it on the dashboard in real time. This allows feedback from visitors to be checked in real time. Some or all of the above-mentioned processing in the analysis result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis result providing unit can input visitor feedback data to a generation AI and cause the generation AI to generate data for displaying on the dashboard.

[0040] The estimation unit can analyze the visitor's browsing time and page stay time to estimate the interest. For example, if the visitor stays on a particular page for a long time, the estimation unit estimates the interest related to that page. The estimation unit can also analyze the visitor's browsing time and identify topics in which the visitor is interested. This allows the visitor's interest to be estimated more accurately. Some or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI or may be performed without using AI. For example, the estimation unit can input the visitor's browsing data to the generation AI and cause the generation AI to perform interest estimation.

[0041] The answering unit can have a multilingual capability to provide a response based on a language selected by the visitor. For example, if the visitor asks a question in English, the answering unit responds in English. Also, if the visitor asks a question in Japanese, the answering unit can respond in Japanese. This makes it possible to provide responses in multiple languages ​​to the visitor. Some or all of the above-mentioned processing in the answering unit may be performed, for example, using AI or may be performed without using AI. For example, the answering unit can input the visitor's question to a generating AI and have the generating AI execute a response in the selected language.

[0042] The purchase support unit can have a function of predicting and recommending the next purchase based on the visitor's purchase history. For example, it recommends related products based on products the visitor has purchased in the past. The purchase support unit can also recommend products based on specific interests and concerns from the visitor's purchase history. This makes it possible to predict and recommend the next purchase to the visitor. Some or all of the above-mentioned processing in the purchase support unit may be performed, for example, using AI or may be performed without using AI. For example, the purchase support unit can input the visitor's purchase history data into a generation AI and have the generation AI execute a prediction of the next purchase.

[0043] The connection unit can connect the visitor's inquiry to a customer support representative when a combination of the complexity of the visitor's inquiry and the visitor's waiting time satisfies a predetermined condition. For example, if the visitor is kept waiting for a long time, the connection unit escalates the inquiry to a customer support representative. Also, if the inquiry is very complex, the connection unit can connect it to a customer support representative. This allows the visitor's inquiry to be escalated to a customer support representative at an appropriate time. A part or all of the above-mentioned processing in the connection unit may be performed, for example, using AI or may be performed without using AI. For example, the connection unit can input the visitor's waiting time data and the complexity data of the inquiry to the generation AI and cause the generation AI to execute the escalation decision.

[0044] The inquiry support unit can have a function of automatically completing the visitor's input. For example, while the visitor is inputting a question, the inquiry support unit presents appropriate candidates and completes the input. In addition, when the visitor inputs a specific keyword, the inquiry support unit can automatically display related candidates. This can improve the efficiency of inquiries by automatically completing the visitor's input. A part or all of the above-mentioned processing in the inquiry support unit can be performed, for example, using AI or can be performed without using AI. For example, the inquiry support unit can input the visitor's input data to a generation AI and cause the generation AI to generate candidates for auto-completion.

[0045] The connection unit can have a function of managing the schedule of inquiries when visitor inquiries are concentrated in a specific time period. For example, when visitors make many inquiries in a specific time period, the connection unit adjusts the schedule of inquiries and connects them to a customer support representative at an appropriate time. Furthermore, even during peak hours, the connection unit can determine the priority of inquiries and efficiently manage the schedule. This allows efficient schedule management of visitor inquiries. A part or all of the above-mentioned processing in the connection unit may be performed, for example, using AI, or may be performed without using AI. For example, the connection unit can input visitor inquiry data to the generation AI and cause the generation AI to optimize schedule management.

[0046] When answering, the answering unit can provide a more personalized answer by referring to the user's past question history. For example, based on the content of questions asked by the user in the past, related information can be provided. In addition, it is also possible to provide a solution to a similar problem by referring to a problem that the user has solved in the past. Furthermore, it is also possible to provide an answer based on a specific interest or concern from the user's past question history. This makes it possible to provide a more personalized answer based on the user's past question history. A part or all of the above-mentioned processing in the answering unit may be performed, for example, using AI, or may be performed without using AI. For example, the answering unit can input the user's past question history data to the generation AI and cause the generation AI to generate a personalized answer.

[0047] The answering unit can customize the answer content based on the user's current situation and context when answering. For example, if the user asks a question about the current time zone, the answering unit provides information related to that time zone. In addition, if the user is in a specific location, the answering unit can provide information related to that location. Furthermore, if the user is using a specific device, the answering unit can provide information optimized for that device. This makes it possible to provide a more appropriate answer based on the user's current situation and context. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can input the user's current situation and context data to the generation AI and cause the generation AI to generate a customized answer.

[0048] The answering unit can provide highly relevant information in consideration of the geographical location information of the user when answering. For example, if the user is in a specific city, information related to the city can be provided. Also, if the user is in a specific country, information related to the country can be provided. Furthermore, if the user is in a specific region, information related to the region can be provided. This makes it possible to provide more relevant information based on the geographical location information of the user. A part or all of the above-mentioned processing in the answering unit may be performed, for example, using AI, or may be performed without using AI. For example, the answering unit can input the geographical location information data of the user to the generation AI and cause the generation AI to generate highly relevant information.

[0049] The answering unit can analyze the user's social media activity and provide relevant information when answering. For example, the answering unit can provide relevant answers based on information shared by the user on social media. Also, the answering unit can provide relevant information based on accounts the user follows on social media. Furthermore, the answering unit can provide relevant answers based on topics in which the user has shown interest on social media. This makes it possible to provide more relevant information based on the user's social media activity. Some or all of the above-mentioned processing in the answering unit can be performed, for example, using AI or can be performed without using AI. For example, the answering unit can input the user's social media activity data into the generation AI and cause the generation AI to generate relevant information.

[0050] The detailed information providing unit can provide more personalized information by referring to the user's past behavior history when providing the detailed information. For example, related product information can be provided based on products the user has viewed in the past. Also, related service information can be provided based on products the user has purchased in the past. Furthermore, information based on specific interests and concerns can be provided from the user's past behavior history. This makes it possible to provide more personalized information based on the user's past behavior history. A part or all of the above-mentioned processing in the detailed information providing unit may be performed, for example, using AI or may be performed without using AI. For example, the detailed information providing unit can input the user's past behavior history data to the generation AI and cause the generation AI to generate personalized information.

[0051] The detailed information providing unit can customize information based on the user's current field of interest when providing the detailed information. For example, information related to a product in which the user is currently interested can be provided. Information related to a service in which the user is currently interested can also be provided. Furthermore, information related to a topic in which the user is currently paying attention can also be provided. This makes it possible to provide more appropriate information based on the user's current field of interest. A part or all of the above-mentioned processing in the detailed information providing unit may be performed, for example, using AI or may be performed without using AI. For example, the detailed information providing unit can input the user's current field of interest data to the generation AI and cause the generation AI to generate customized information.

[0052] The detailed information providing unit can provide highly relevant information in consideration of the geographical location information of the user when providing the detailed information. For example, if the user is in a specific city, product information related to the city can be provided. Also, if the user is in a specific country, service information related to the country can be provided. Furthermore, if the user is in a specific region, information related to the region can be provided. This makes it possible to provide more relevant information based on the geographical location information of the user. A part or all of the above-mentioned processing in the detailed information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the detailed information providing unit can input the geographical location information data of the user to the generation AI and cause the generation AI to generate highly relevant information.

[0053] The detailed information providing unit can analyze the user's social media activities and provide related information when providing the detailed information. For example, related product information can be provided based on information shared by the user on social media. Also, related service information can be provided based on accounts the user follows on social media. Furthermore, related information can be provided based on topics in which the user shows interest on social media. This makes it possible to provide more relevant information based on the user's social media activities. A part or all of the above-mentioned processing in the detailed information providing unit can be performed, for example, using AI or can be performed without using AI. For example, the detailed information providing unit can input the user's social media activity data to the generation AI and cause the generation AI to generate related information.

[0054] The inquiry support unit can provide more personalized support by referring to the user's past inquiry history during inquiry support. For example, based on the content of the user's past inquiries, related support can be provided. Also, by referring to problems the user has solved in the past, a solution to a similar problem can be provided. Furthermore, support based on specific interests and concerns can be provided from the user's past inquiry history. This makes it possible to provide more personalized support based on the user's past inquiry history. Part or all of the above-mentioned processing in the inquiry support unit may be performed, for example, using AI, or may be performed without using AI. For example, the inquiry support unit can input the user's past inquiry history data into the generation AI and cause the generation AI to generate personalized support.

[0055] The inquiry support unit can customize the support content based on the user's current situation and context during the inquiry support. For example, if the user makes an inquiry about the current time period, the inquiry support unit provides support related to that time period. Also, if the user is in a specific location, support related to that location can be provided. Furthermore, if the user is using a specific device, support optimized for that device can be provided. This makes it possible to provide more appropriate support based on the user's current situation and context. Some or all of the above-mentioned processing in the inquiry support unit may be performed using, for example, AI, or may be performed without using AI. For example, the inquiry support unit can input the user's current situation and context data into the generation AI and cause the generation AI to generate customized support.

[0056] The inquiry support unit can provide highly relevant support in consideration of the geographical location information of the user during the inquiry support. For example, if the user is in a specific city, support related to the city can be provided. Also, if the user is in a specific country, support related to the country can be provided. Furthermore, if the user is in a specific region, support related to the region can be provided. This makes it possible to provide more relevant support based on the geographical location information of the user. A part or all of the above-mentioned processing in the inquiry support unit may be performed, for example, using AI, or may be performed without using AI. For example, the inquiry support unit can input the geographical location information data of the user to the generation AI and cause the generation AI to generate highly relevant support.

[0057] The inquiry support unit can analyze the user's social media activities and provide relevant support during the inquiry support. For example, the inquiry support unit can provide relevant support based on information shared by the user on social media. The inquiry support unit can also provide relevant support based on accounts the user follows on social media. Furthermore, the inquiry support unit can provide relevant support based on topics in which the user shows interest on social media. This makes it possible to provide more relevant support based on the user's social media activities. Some or all of the above-mentioned processing in the inquiry support unit can be performed, for example, using AI or can be performed without using AI. For example, the inquiry support unit can input the user's social media activity data into the generation AI and cause the generation AI to generate related support.

[0058] The purchase support unit can provide more personalized support by referring to the user's past purchase history during purchase support. For example, based on products purchased by the user in the past, related products are recommended. Also, support based on specific interests and concerns can be provided from the user's past purchase history. Furthermore, related support can be provided by referring to the usage status of products purchased by the user in the past. This makes it possible to provide more personalized support based on the user's past purchase history. Part or all of the above-mentioned processing in the purchase support unit may be performed, for example, using AI or may be performed without using AI. For example, the purchase support unit can input the user's past purchase history data into the generation AI and cause the generation AI to generate personalized support.

[0059] The purchase support unit can customize the support content based on the user's current situation and context during purchase support. For example, if the user is requesting purchase support related to the current time period, the purchase support unit provides information related to that time period. In addition, if the user is in a specific location, purchase support related to that location can be provided. Furthermore, if the user is using a specific device, purchase support optimized for that device can be provided. This makes it possible to provide more appropriate support based on the user's current situation and context. Some or all of the above-mentioned processing in the purchase support unit may be performed using, for example, AI, or may be performed without using AI. For example, the purchase support unit can input the user's current situation and context data into the generation AI and cause the generation AI to generate customized support.

[0060] The purchase support unit can provide highly relevant support during purchase support by taking into account the geographic location information of the user. For example, if the user is in a specific city, product information related to the city can be provided. Also, if the user is in a specific country, product information related to the country can be provided. Furthermore, if the user is in a specific region, product information related to the region can be provided. This makes it possible to provide more relevant support based on the geographic location information of the user. A part or all of the above-mentioned processing in the purchase support unit may be performed, for example, using AI, or may be performed without using AI. For example, the purchase support unit can input the geographic location information data of the user to the generation AI and cause the generation AI to generate highly relevant support.

[0061] The purchase support unit can analyze the user's social media activities and provide relevant support during purchase support. For example, the purchase support unit can provide relevant product information based on information shared by the user on social media. The purchase support unit can also provide relevant product information based on accounts the user follows on social media. Furthermore, the purchase support unit can provide relevant product information based on topics in which the user has shown interest on social media. This makes it possible to provide more relevant support based on the user's social media activities. Some or all of the above-mentioned processing in the purchase support unit can be performed, for example, using AI or without AI. For example, the purchase support unit can input the user's social media activity data into a generation AI and have the generation AI execute the generation of related support.

[0062] The estimation unit can perform more accurate estimation by referring to the user's past behavioral history at the time of estimation. For example, the interest is estimated based on the page the user viewed in the past. The interest can also be estimated based on the product the user purchased in the past. Furthermore, specific interests and concerns can be estimated from the user's past behavioral history. This allows more accurate estimation to be performed based on the user's past behavioral history. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input the user's past behavioral history data to the generation AI and cause the generation AI to perform accurate estimation.

[0063] The estimation unit can customize the estimation content based on the user's current situation and context at the time of estimation. For example, the estimation unit estimates the user's interests based on information about the user's current time zone. In addition, if the user is in a specific location, the estimation unit can estimate the user's interests based on information related to the location. In addition, if the user is using a specific device, the estimation unit can estimate the user's interests based on information optimized for the device. This allows more appropriate estimation to be performed based on the user's current situation and context. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input the user's current situation and context data to the generation AI and cause the generation AI to perform a customized estimation.

[0064] The estimation unit can perform highly relevant estimation by taking into account the geographical location information of the user at the time of estimation. For example, if the user is in a specific city, the interest is estimated based on information related to the city. Also, if the user is in a specific country, the interest can be estimated based on information related to the country. Furthermore, if the user is in a specific region, the interest can be estimated based on information related to the region. This allows more relevant estimation to be performed based on the geographical location information of the user. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input the geographical location information data of the user to the generation AI and cause the generation AI to perform a highly relevant estimation.

[0065] The estimation unit can analyze the user's social media activity and make relevant inferences at the time of estimation. For example, the estimation unit estimates interests based on information shared by the user on social media. The estimation unit can also estimate interests based on accounts the user follows on social media. Furthermore, the estimation unit can also estimate interests based on topics in which the user has shown interest on social media. This allows more relevant inferences to be made based on the user's social media activity. Some or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI or may be performed without using AI. For example, the estimation unit can input the user's social media activity data to the generation AI and cause the generation AI to perform the relevant inferences.

[0066] When providing the analysis result, the analysis result providing unit can provide a more personalized result by referring to the user's past feedback history. For example, based on the feedback provided by the user in the past, the analysis result providing unit can provide a related analysis result. Also, based on the user's past feedback history, a result based on a specific interest or concern can be provided. Furthermore, based on the user's past feedback history, a related result can be provided by referring to the content of the feedback provided by the user in the past. This makes it possible to provide a more personalized result based on the user's past feedback history. A part or all of the above-mentioned processing in the analysis result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis result providing unit can input the user's past feedback history data to the generation AI and cause the generation AI to generate a personalized result.

[0067] The analysis result providing unit can customize the results based on the user's current field of interest when providing the analysis result. For example, the analysis result providing unit can provide analysis results related to topics in which the user is currently interested. The analysis result providing unit can also provide analysis results related to products in which the user is currently interested. Furthermore, the analysis result providing unit can provide analysis results related to services in which the user is currently paying attention. This makes it possible to provide more appropriate results based on the user's current field of interest. Some or all of the above-mentioned processing in the analysis result providing unit can be performed, for example, using AI or can be performed without using AI. For example, the analysis result providing unit can input the user's current field of interest data to the generation AI and cause the generation AI to generate customized results.

[0068] When providing the analysis results, the analysis result providing unit can provide highly relevant results by taking into account the geographical location information of the user. For example, if the user is in a specific city, the analysis result related to the city can be provided. Also, if the user is in a specific country, the analysis result related to the country can be provided. Furthermore, if the user is in a specific region, the analysis result related to the region can be provided. This makes it possible to provide more relevant results based on the geographical location information of the user. A part or all of the above-mentioned processing in the analysis result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis result providing unit can input the geographical location information data of the user to the generation AI and cause the generation AI to generate highly relevant results.

[0069] The analysis result providing unit can analyze the user's social media activity and provide related results when providing the analysis result. For example, the analysis result providing unit can provide related analysis results based on information shared by the user on social media. Also, the analysis result providing unit can provide related analysis results based on accounts the user follows on social media. Furthermore, the analysis result providing unit can provide related analysis results based on topics in which the user shows interest on social media. This makes it possible to provide more relevant results based on the user's social media activity. Some or all of the above-mentioned processing in the analysis result providing unit can be performed, for example, using AI or can be performed without using AI. For example, the analysis result providing unit can input the user's social media activity data to the generation AI and cause the generation AI to generate related results.

[0070] At the time of connection, the connection unit can provide a more personalized connection by referring to the user's past inquiry history. For example, the connection unit can connect to a related customer support representative based on the content of the user's past inquiries. Also, the connection unit can connect to a representative who is familiar with a specific problem from the user's past inquiry history. Furthermore, the connection unit can connect to a representative who provides support for a similar problem by referring to a problem that the user has solved in the past. This makes it possible to provide a more personalized connection based on the user's past inquiry history. Part or all of the above-mentioned processing in the connection unit may be performed, for example, using AI or may be performed without using AI. For example, the connection unit can input the user's past inquiry history data to the generation AI and cause the generation AI to generate a personalized connection.

[0071] At the time of connection, the connection unit can customize the connection content based on the user's current situation and context. For example, if the user is making an inquiry about the current time period, the connection unit can connect to a person related to that time period. Also, if the user is in a specific location, the connection unit can connect to a person related to that location. Furthermore, if the user is using a specific device, the connection unit can connect to a person who provides support optimized for that device. This makes it possible to provide a more appropriate connection based on the user's current situation and context. Some or all of the above-mentioned processing in the connection unit may be performed using, for example, AI, or may be performed without using AI. For example, the connection unit can input the user's current situation and context data to the generation AI and cause the generation AI to generate a customized connection.

[0072] The connection unit can provide a highly relevant connection in consideration of the geographical location information of the user at the time of connection. For example, if the user is in a specific city, the connection unit can connect to a person related to the city. Also, if the user is in a specific country, the connection unit can connect to a person related to the country. Furthermore, if the user is in a specific region, the connection unit can connect to a person related to the region. This makes it possible to provide a more relevant connection based on the geographical location information of the user. A part or all of the above-mentioned processing in the connection unit may be performed, for example, using AI or may be performed without using AI. For example, the connection unit can input the geographical location information data of the user to the generation AI and cause the generation AI to generate a highly relevant connection.

[0073] At the time of connection, the connection unit can analyze the user's social media activity and provide relevant connections. For example, the connection unit can connect to relevant personnel based on information shared by the user on social media. The connection unit can also connect to relevant personnel based on accounts the user follows on social media. Furthermore, the connection unit can connect to relevant personnel based on topics in which the user has shown interest on social media. This makes it possible to provide more relevant connections based on the user's social media activity. Some or all of the above-mentioned processing in the connection unit may be performed, for example, using AI or may be performed without using AI. For example, the connection unit can input the user's social media activity data to the generation AI and cause the generation AI to generate relevant connections.

[0074] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. For example, an optimal learning algorithm is selected based on past learning data. Also, a specific pattern can be extracted from the past learning data to optimize the learning algorithm. Furthermore, the accuracy of the learning algorithm can be improved by analyzing the past learning data. This makes it possible to optimize the learning algorithm based on the past learning data. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input past learning data to a generation AI and cause the generation AI to optimize the learning algorithm.

[0075] The learning unit can customize the learning content based on the user's current situation and context during learning. For example, the learning content is customized based on information about the user's current time zone. In addition, when the user is in a specific location, the learning content can be customized based on information related to the location. Furthermore, when the user is using a specific device, the learning content can be customized based on information optimized for that device. This allows more appropriate learning based on the user's current situation and context. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the user's current situation and context data to the generation AI and cause the generation AI to generate customized learning content.

[0076] During learning, the learning unit can learn highly relevant data taking into account the geographical location information of the user. For example, if the user is in a specific city, data related to the city is learned. Also, if the user is in a specific country, data related to the country can be learned. Furthermore, if the user is in a specific region, data related to the region can be learned. This allows learning to be performed with more relevant data based on the geographical location information of the user. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the geographical location information data of the user to the generation AI and cause the generation AI to execute learning of highly relevant data.

[0077] During learning, the learning unit can analyze the user's social media activities and learn related data. For example, the learning unit learns related data based on information shared by the user on social media. Also, the learning unit can learn related data based on accounts the user follows on social media. Furthermore, the learning unit can learn related data based on topics in which the user shows interest on social media. This allows learning to be performed with more relevant data based on the user's social media activities. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using AI or may be performed without using AI. For example, the learning unit can input the user's social media activity data to the generation AI and cause the generation AI to execute learning of related data.

[0078] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0079] The automated response system AI assistant can be equipped with a prediction unit that analyzes the visitor's behavioral patterns and predicts the action the visitor is likely to take next. For example, if the visitor frequently views a particular product page, the prediction unit can recommend the purchase of that product. Also, if the visitor repeatedly searches for information about a particular service, the prediction unit can provide detailed information about that service. Furthermore, if the visitor frequently accesses the site during a particular time period, the prediction unit can provide promotional information related to that time period. This allows for more appropriate support to be provided based on the visitor's behavioral patterns.

[0080] The automated response system AI assistant can be equipped with a purchase prediction unit that analyzes the visitor's past purchase history and predicts the product the visitor is likely to purchase next. For example, if the visitor has purchased a product of a particular brand in the past, the purchase prediction unit can recommend new products of that brand. Also, if the visitor has purchased products of a particular category in the past, the purchase prediction unit can recommend related products of that category. Furthermore, if the visitor has purchased products in a particular price range in the past, the purchase prediction unit can recommend products in that price range. This makes it possible to recommend more appropriate products based on the visitor's purchase history.

[0081] The automated response system AI assistant may include a needs prediction unit that predicts the visitor's needs based on the visitor's current situation and context. For example, if the visitor is searching for information about a particular event, the needs prediction unit may provide information related to that event. Also, if the visitor is searching for products related to a particular season, the needs prediction unit may recommend products related to that season. Furthermore, if the visitor is using a particular device, the needs prediction unit may provide information optimized for that device. This allows for more appropriate support to be provided based on the visitor's current situation and context.

[0082] The automated response system AI assistant may include a feedback prediction unit that analyzes the visitor's past feedback and predicts the feedback that the visitor is likely to provide next. For example, if the visitor has provided positive feedback in the past, the feedback prediction unit predicts that the visitor will provide positive feedback next time. Also, if the visitor has provided neutral feedback in the past, the feedback prediction unit may predict that the visitor will provide neutral feedback next time. Furthermore, if the visitor has provided negative feedback in the past, the feedback prediction unit may predict that the visitor will provide negative feedback next time. This makes it possible to provide more appropriate support based on the visitor's past feedback.

[0083] The automated response system AI assistant can be equipped with a behavioral prediction unit that predicts the visitor's behavior based on the visitor's current situation and context. For example, if the visitor frequently visits during a certain time period, the behavioral prediction unit can provide information related to that time period. Also, if the visitor is in a certain location, the behavioral prediction unit can provide information related to that location. Furthermore, if the visitor is using a specific device, the behavioral prediction unit can provide information optimized for that device. This allows for more appropriate support to be provided based on the visitor's current situation and context.

[0084] The process flow of the first embodiment will be briefly described below.

[0085] Step 1: The answerer responds to questions from visitors to the website. For example, if a visitor asks, "What are your business hours?", the answerer immediately responds, "Business hours are from 9:00 to 18:00." Step 2: The detailed information providing section provides detailed information about the product or service specified by the visitor. For example, if the visitor asks "Please tell me the details of this product," the detailed information providing section provides detailed information such as product specifications, prices, and usage methods. Step 3: The customer support department provides guidance or a solution to the visitor's inquiry. For example, if a visitor inquires about "unstable Internet connection," the customer support department provides a method to check the connection and troubleshooting steps. Step 4: The purchasing support department assists the visitor in purchasing products, booking services, and making appointments. For example, if a visitor asks, "What products do you recommend?", the purchasing support department will recommend products based on the visitor's past purchase history and interests, and help them add products to their cart and complete the purchase. Step 5: The estimation unit estimates the visitor's interest in a particular subject based on the visitor's information. For example, if the visitor says, "I'm interested in this service," the estimation unit obtains the visitor's contact information and provides information about the service of interest. Step 6: The analysis result providing unit analyzes the feedback or opinions from the visitors and provides the analysis result. For example, if the visitor provides feedback such as "This service was very good," the analysis result providing unit collects the feedback and displays it on the dashboard in real time.

[0086] (Example 2) The automatic response system AI assistant according to the embodiment of the present invention is a system that provides a wide range of support to website visitors. This system includes an answering unit that immediately answers questions from visitors. For example, when a visitor asks, "What are your business hours?", the answering unit immediately responds, "Business hours are from 9:00 to 18:00." Next, a detailed information providing unit is provided that provides detailed information on products and services desired by visitors in real time. For example, when a visitor asks, "Please tell me the details of this product," the detailed information providing unit provides detailed information such as product specifications, prices, and usage methods. In addition, an inquiry support unit is provided that provides guidance and solutions to inquiries about technical problems and services. For example, when a visitor inquires, "My Internet connection is unstable," the inquiry support unit provides a method for checking the connection and troubleshooting procedures. In addition, the system includes an estimation unit with a lead acquisition function that acquires the visitor's contact information and investigates the visitor's interest in products and services. For example, when a visitor says, "I'm interested in this service," the estimation unit acquires the visitor's contact information and provides information on the service of interest. The system also includes a purchase support unit that recommends products to visitors of an online shop, adds them to a cart, and supports the purchase process. For example, if a visitor asks, "What products do you recommend?", the purchase support section will recommend products based on the visitor's past purchase history and interests, and will support the visitor in adding them to the cart and completing the purchase process. It also provides an appointment setting function that supports the process when a visitor wants to reserve or set up an appointment for a service. For example, if a visitor says, "I'd like to make a reservation for next Tuesday," the appointment setting function will check availability and assist with the reservation process. It has an analysis result provision section that collects feedback and opinions from visitors, analyzes and reports them. For example, if a visitor provides feedback such as "This service was very good," the analysis result provision section collects the feedback and displays it on the dashboard in real time. It also has a multimedia support function that provides responses that incorporate not only text but also multimedia content such as videos, images, and audio.For example, if a visitor asks, "Please tell me how to use this product," the multimedia support function will explain how to use it using videos and images. It also has a real-time learning function that learns the trends and needs of visitors to the website through dialogue with the visitor and provides more appropriate responses based on that. For example, if a visitor frequently asks a specific question, the real-time learning function will learn that trend and improve the response from the next time onwards. Finally, if the inquiry is complex and the AI ​​cannot handle it, it has an escalation support function that escalates the inquiry to a real customer support representative. For example, if a visitor says, "I cannot solve this problem," the escalation support function will transfer the inquiry to a customer support representative who will respond appropriately. This allows the automatic response system AI assistant to provide a wide range of support to website visitors.

[0087] The AI ​​assistant automatic response system according to the embodiment includes an answering unit, a detailed information providing unit, an inquiry support unit, a purchase support unit, an estimation unit, and an analysis result providing unit. The answering unit answers questions from visitors to the website. For example, if a visitor asks, "What are your business hours?", the answering unit immediately responds, "Business hours are from 9:00 to 18:00." The detailed information providing unit provides detailed information about a product or service specified by the visitor. For example, if a visitor asks, "Please tell me the details of this product," the detailed information providing unit provides detailed information such as product specifications, prices, and usage methods. The inquiry support unit provides guidance or solutions to the visitor's inquiries. For example, if a visitor asks, "My Internet connection is unstable," the inquiry support unit provides a method for checking the connection and troubleshooting procedures. The purchase support unit supports the visitor in purchasing products, reserving services, and making appointments. For example, if a visitor asks, "What products do you recommend?", the purchase support unit recommends products based on the visitor's past purchase history and interests, and supports the visitor in adding the products to the cart and completing the purchase procedure. The estimation unit estimates the visitor's interest in a specific target based on the visitor's information. For example, if the visitor says, "I'm interested in this service," the estimation unit obtains the visitor's contact information and provides information about the service of interest. The analysis result providing unit analyzes feedback or opinions from the visitor and provides analysis results. For example, if the visitor provides feedback such as, "This service was very good," the analysis result providing unit collects the feedback and displays it on the dashboard in real time. In this way, the automatic response system AI assistant according to the embodiment can provide a wide range of support to website visitors.

[0088] The answering section answers questions from visitors to the website. For example, if a visitor asks, "What are your business hours?", the answering section immediately responds, "Business hours are from 9:00 to 18:00." The answering section uses natural language processing (NLP) technology to analyze the visitor's question and generate an appropriate answer. Specifically, to understand the intent of the question, morphological analysis and context analysis are performed, and the answer that best suits the content of the question is searched for from a database. Furthermore, the answering section can learn the visitor's past question history and behavioral patterns to provide a more personalized answer. For example, if a visitor has previously asked a question about a specific product, information related to that product is provided preferentially. In addition, the answering section continuously learns to improve the accuracy of answers to visitor questions. For example, the answering section collects feedback from visitors, evaluates the accuracy and satisfaction of the answers, and improves the answering algorithm based on the results. This allows the answering section to quickly and accurately respond to a variety of questions from visitors and improve the user experience of the website.

[0089] The detailed information providing unit provides detailed information on the product or service specified by the visitor. For example, when the visitor asks "Please tell me the details of this product," the detailed information providing unit provides detailed information such as the product specifications, price, and usage. The detailed information providing unit has a rich database on products and services, and quickly provides information in response to the visitor's request. Specifically, the detailed information providing unit centrally manages information such as product specifications, price, usage, user reviews, and related FAQs, and extracts appropriate information for the visitor's question. In addition, the detailed information providing unit can also suggest information on related products and services based on the visitor's interests and concerns. For example, when the visitor shows interest in a specific product, the detailed information providing unit provides information on accessories and optional products related to the product. Furthermore, the detailed information providing unit analyzes the visitor's behavior history and past inquiries to provide more personalized information. As a result, the detailed information providing unit can quickly and accurately provide the information the visitor desires to purchase.

[0090] The inquiry support department provides guidance or solutions to the visitor's inquiries. For example, if a visitor inquires that "the Internet connection is unstable," the inquiry support department provides a method for checking the connection and troubleshooting procedures. The inquiry support department has a rich knowledge base and troubleshooting guides to quickly solve the visitor's problems. Specifically, it accumulates solutions to common problems and troubles in a database and provides appropriate solutions according to the visitor's inquiry. In addition, the inquiry support department can ask additional questions to understand the visitor's problem in more detail. For example, if a visitor states that "the Internet connection is unstable," the inquiry support department can ask "Specifically, in what circumstances does the connection become unstable?" to collect information to identify the cause of the problem. In addition, the inquiry support department also has the function of escalating the visitor's problem to a specialized support team if the visitor's problem is not resolved. This allows the inquiry support department to quickly and effectively solve the visitor's problem and improve customer satisfaction.

[0091] The purchase support department supports visitors in purchasing products, reserving services, and making appointments. For example, if a visitor asks, "What is the recommended product?", the purchase support department recommends products based on the visitor's past purchase history and interests, and supports adding products to the cart and making purchases. The purchase support department analyzes the visitor's purchasing behavior and interests, and suggests optimal products and services. Specifically, it recommends products and services that the visitor may be interested in based on data such as the visitor's past purchase history, browsing history, and search history. In addition, the purchase support department provides support such as adding products to the cart, making payments, and selecting delivery options so that the visitor can make the purchase process smooth. In addition, the purchase support department can provide real-time chat support to resolve any questions or concerns that the visitor may have about the purchase. For example, if a visitor asks, "What is the warranty period for this product?", the purchase support department will immediately respond and resolve the visitor's concerns. This allows the purchase support department to improve the visitor's purchasing experience and contribute to increased sales.

[0092] The estimation unit estimates the visitor's interest in a specific target based on the visitor's information. For example, if the visitor says, "I'm interested in this service," the estimation unit obtains the visitor's contact information and provides information about the service of interest. The estimation unit analyzes the visitor's behavioral data and past inquiries to estimate the visitor's interests. Specifically, based on data such as the visitor's browsing history, search history, and click patterns, the estimation unit identifies products and services that the visitor may be interested in. The estimation unit can also provide related information and offers based on the visitor's interests. For example, if the visitor shows interest in a specific service, the estimation unit provides promotion and discount information related to the service. Furthermore, the estimation unit can continuously learn the visitor's interests and make more accurate estimations. As a result, the estimation unit can provide information according to the visitor's needs and improve the visitor's satisfaction.

[0093] The analysis result providing unit analyzes feedback or opinions from visitors and provides analysis results. For example, if a visitor provides feedback such as "this service was very good," the analysis result providing unit collects the feedback and displays it on a dashboard in real time. The analysis result providing unit collects feedback and opinions from visitors and analyzes them using text mining technology. Specifically, the content of the feedback is classified and positive and negative opinions are extracted. In addition, based on the visitor feedback, it is also possible to identify areas for improvement and areas to be strengthened in the service. Furthermore, the analysis result providing unit displays the analysis results on a dashboard in real time, allowing the administrator to respond quickly. For example, if there is a lot of negative feedback, the cause can be identified and measures to improve the service can be taken quickly. In this way, the analysis result providing unit can effectively utilize the visitor feedback and contribute to improving the quality of the service.

[0094] The automatic response system AI assistant according to the embodiment includes a connection unit that connects the visitor's inquiry to a customer support representative based on the details of the visitor's inquiry. For example, if the visitor says, "I can't solve this problem," the connection unit transfers the inquiry to the customer support representative and takes appropriate action. This allows complex inquiries to be escalated to the customer support representative. Some or all of the above-mentioned processing in the connection unit may be performed, for example, using AI or may be performed without using AI. For example, the connection unit may input the details of the visitor's inquiry to the generation AI and cause the generation AI to execute a process of evaluating the complexity of the inquiry.

[0095] The automatic response system AI assistant according to the embodiment includes a learning unit that learns dialogue with visitors in real time and provides a response based on the visitor's behavioral patterns and requests. For example, if a visitor frequently asks a specific question, the learning unit learns the tendency and improves the response from the next time onwards. This makes it possible to provide a more appropriate response based on the visitor's tendencies and needs. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using AI or may be performed without using AI. For example, the learning unit may input dialogue data with the visitor to a generation AI and cause the generation AI to perform an analysis of the behavioral patterns.

[0096] The detailed information providing unit can provide personalized information based on the visitor's past behavior history. For example, related product information is provided based on products the visitor has viewed in the past. The detailed information providing unit can also provide related service information based on products the visitor has purchased in the past. This makes it possible to provide more personalized information to the visitor. Some or all of the above-mentioned processing in the detailed information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the detailed information providing unit can input the visitor's past behavior history data to the generation AI and cause the generation AI to generate personalized information.

[0097] The analysis result providing unit can display feedback from visitors on the dashboard in real time. For example, if a visitor provides feedback such as "this service was very good," the analysis result providing unit collects the feedback and displays it on the dashboard in real time. This allows feedback from visitors to be checked in real time. Some or all of the above-mentioned processing in the analysis result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis result providing unit can input visitor feedback data to a generation AI and cause the generation AI to generate data for displaying on the dashboard.

[0098] The estimation unit can analyze the visitor's browsing time and page stay time to estimate the interest. For example, if the visitor stays on a particular page for a long time, the estimation unit estimates the interest related to that page. The estimation unit can also analyze the visitor's browsing time and identify topics in which the visitor is interested. This allows the visitor's interest to be estimated more accurately. Some or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI or may be performed without using AI. For example, the estimation unit can input the visitor's browsing data to the generation AI and cause the generation AI to perform interest estimation.

[0099] The answering unit can have a multilingual capability to provide a response based on a language selected by the visitor. For example, if the visitor asks a question in English, the answering unit responds in English. Also, if the visitor asks a question in Japanese, the answering unit can respond in Japanese. This makes it possible to provide responses in multiple languages ​​to the visitor. Some or all of the above-mentioned processing in the answering unit may be performed, for example, using AI or may be performed without using AI. For example, the answering unit can input the visitor's question to a generating AI and have the generating AI execute a response in the selected language.

[0100] The purchase support unit can have a function of predicting and recommending the next purchase based on the visitor's purchase history. For example, it recommends related products based on products the visitor has purchased in the past. The purchase support unit can also recommend products based on specific interests and concerns from the visitor's purchase history. This makes it possible to predict and recommend the next purchase to the visitor. Some or all of the above-mentioned processing in the purchase support unit may be performed, for example, using AI or may be performed without using AI. For example, the purchase support unit can input the visitor's purchase history data into a generation AI and have the generation AI execute a prediction of the next purchase.

[0101] The connection unit can connect the visitor's inquiry to a customer support representative when a combination of the complexity of the visitor's inquiry and the visitor's waiting time satisfies a predetermined condition. For example, if the visitor is kept waiting for a long time, the connection unit escalates the inquiry to a customer support representative. Also, if the inquiry is very complex, the connection unit can connect it to a customer support representative. This allows the visitor's inquiry to be escalated to a customer support representative at an appropriate time. A part or all of the above-mentioned processing in the connection unit may be performed, for example, using AI or may be performed without using AI. For example, the connection unit can input the visitor's waiting time data and the complexity data of the inquiry to the generation AI and cause the generation AI to execute the escalation decision.

[0102] The inquiry support unit can have a function of automatically completing the visitor's input. For example, while the visitor is inputting a question, the inquiry support unit presents appropriate candidates and completes the input. In addition, when the visitor inputs a specific keyword, the inquiry support unit can automatically display related candidates. This can improve the efficiency of inquiries by automatically completing the visitor's input. A part or all of the above-mentioned processing in the inquiry support unit can be performed, for example, using AI or can be performed without using AI. For example, the inquiry support unit can input the visitor's input data to a generation AI and cause the generation AI to generate candidates for auto-completion.

[0103] The connection unit can have a function of managing the schedule of inquiries when visitor inquiries are concentrated in a specific time period. For example, when visitors make many inquiries in a specific time period, the connection unit adjusts the schedule of inquiries and connects them to a customer support representative at an appropriate time. Furthermore, even during peak hours, the connection unit can determine the priority of inquiries and efficiently manage the schedule. This allows efficient schedule management of visitor inquiries. A part or all of the above-mentioned processing in the connection unit may be performed, for example, using AI, or may be performed without using AI. For example, the connection unit can input visitor inquiry data to the generation AI and cause the generation AI to optimize schedule management.

[0104] The answering unit can estimate the user's emotions and adjust the tone and expression of the answer based on the estimated user's emotions. For example, if the user is stressed, the answering unit can respond in a gentle tone and use expressions that give a sense of security. Also, if the user is relaxed, the answering unit can respond in a casual tone and use friendly expressions. Furthermore, if the user is in a hurry, the answering unit can respond in a quick and concise tone to provide the necessary information in a short time. This makes it possible to provide an answer in an appropriate tone and expression according to the user's emotions. The estimation of emotions is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the answering unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the answering unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the tone and expression.

[0105] When answering, the answering unit can provide a more personalized answer by referring to the user's past question history. For example, based on the content of questions asked by the user in the past, related information can be provided. In addition, it is also possible to provide a solution to a similar problem by referring to a problem that the user has solved in the past. Furthermore, it is also possible to provide an answer based on a specific interest or concern from the user's past question history. This makes it possible to provide a more personalized answer based on the user's past question history. A part or all of the above-mentioned processing in the answering unit may be performed, for example, using AI, or may be performed without using AI. For example, the answering unit can input the user's past question history data to the generation AI and cause the generation AI to generate a personalized answer.

[0106] The answering unit can customize the answer content based on the user's current situation and context when answering. For example, if the user asks a question about the current time zone, the answering unit provides information related to that time zone. In addition, if the user is in a specific location, the answering unit can provide information related to that location. Furthermore, if the user is using a specific device, the answering unit can provide information optimized for that device. This makes it possible to provide a more appropriate answer based on the user's current situation and context. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can input the user's current situation and context data to the generation AI and cause the generation AI to generate a customized answer.

[0107] The answering unit can estimate the user's emotions and determine the priority of the answers based on the estimated user's emotions. For example, if the user has an urgent question, the answering unit processes the question with the highest priority. Also, if the user is relaxed, the answering unit can process the question with the same priority as other questions. Furthermore, if the user is stressed, the answering unit can process the question with priority and respond quickly. This allows for a faster and more appropriate response by determining the priority of answers according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the answering unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the answering unit can input the user's emotion data to the generation AI and have the generation AI execute the determination of the priority.

[0108] The answering unit can provide highly relevant information in consideration of the geographical location information of the user when answering. For example, if the user is in a specific city, information related to the city can be provided. Also, if the user is in a specific country, information related to the country can be provided. Furthermore, if the user is in a specific region, information related to the region can be provided. This makes it possible to provide more relevant information based on the geographical location information of the user. A part or all of the above-mentioned processing in the answering unit may be performed, for example, using AI, or may be performed without using AI. For example, the answering unit can input the geographical location information data of the user to the generation AI and cause the generation AI to generate highly relevant information.

[0109] The answering unit can analyze the user's social media activity and provide relevant information when answering. For example, the answering unit can provide relevant answers based on information shared by the user on social media. Also, the answering unit can provide relevant information based on accounts the user follows on social media. Furthermore, the answering unit can provide relevant answers based on topics in which the user has shown interest on social media. This makes it possible to provide more relevant information based on the user's social media activity. Some or all of the above-mentioned processing in the answering unit can be performed, for example, using AI or can be performed without using AI. For example, the answering unit can input the user's social media activity data into the generation AI and cause the generation AI to generate relevant information.

[0110] The detailed information providing unit can estimate the user's emotion and adjust the information presentation method based on the estimated user's emotion. For example, when the user is stressed, the detailed information providing unit provides concise and easy-to-understand information. In addition, when the user is relaxed, the detailed information providing unit can also provide detailed information. Furthermore, when the user is in a hurry, the detailed information providing unit can also provide information that covers the main points. This makes it possible to present information in an appropriate manner according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the detailed information providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detailed information providing unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the information presentation method.

[0111] The detailed information providing unit can provide more personalized information by referring to the user's past behavior history when providing the detailed information. For example, related product information can be provided based on products the user has viewed in the past. Also, related service information can be provided based on products the user has purchased in the past. Furthermore, information based on specific interests and concerns can be provided from the user's past behavior history. This makes it possible to provide more personalized information based on the user's past behavior history. A part or all of the above-mentioned processing in the detailed information providing unit may be performed, for example, using AI or may be performed without using AI. For example, the detailed information providing unit can input the user's past behavior history data to the generation AI and cause the generation AI to generate personalized information.

[0112] The detailed information providing unit can customize information based on the user's current field of interest when providing the detailed information. For example, information related to a product in which the user is currently interested can be provided. Information related to a service in which the user is currently interested can also be provided. Furthermore, information related to a topic in which the user is currently paying attention can also be provided. This makes it possible to provide more appropriate information based on the user's current field of interest. A part or all of the above-mentioned processing in the detailed information providing unit may be performed, for example, using AI or may be performed without using AI. For example, the detailed information providing unit can input the user's current field of interest data to the generation AI and cause the generation AI to generate customized information.

[0113] The detailed information providing unit can estimate the user's emotion and determine the priority of information based on the estimated user's emotion. For example, when the user requires urgent information, the detailed information providing unit provides the information with the highest priority. In addition, when the user is relaxed, the detailed information providing unit can provide the information with the same priority as other information. Furthermore, when the user is stressed, the detailed information providing unit can provide the information with priority and respond quickly. This enables a faster and more appropriate response by determining the priority of information according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the detailed information providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detailed information providing unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority.

[0114] The detailed information providing unit can provide highly relevant information in consideration of the geographical location information of the user when providing the detailed information. For example, if the user is in a specific city, product information related to the city can be provided. Also, if the user is in a specific country, service information related to the country can be provided. Furthermore, if the user is in a specific region, information related to the region can be provided. This makes it possible to provide more relevant information based on the geographical location information of the user. A part or all of the above-mentioned processing in the detailed information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the detailed information providing unit can input the geographical location information data of the user to the generation AI and cause the generation AI to generate highly relevant information.

[0115] The detailed information providing unit can analyze the user's social media activities and provide related information when providing the detailed information. For example, related product information can be provided based on information shared by the user on social media. Also, related service information can be provided based on accounts the user follows on social media. Furthermore, related information can be provided based on topics in which the user shows interest on social media. This makes it possible to provide more relevant information based on the user's social media activities. A part or all of the above-mentioned processing in the detailed information providing unit can be performed, for example, using AI or can be performed without using AI. For example, the detailed information providing unit can input the user's social media activity data to the generation AI and cause the generation AI to generate related information.

[0116] The inquiry support unit can estimate the user's emotions and adjust the tone and expression of support based on the estimated user's emotions. For example, if the user is stressed, the inquiry support unit can respond in a gentle tone and use expressions that give a sense of security. Also, if the user is relaxed, the inquiry support unit can respond in a casual tone and use friendly expressions. Furthermore, if the user is in a hurry, the inquiry support unit can respond in a quick and concise tone and provide the necessary information in a short time. This makes it possible to provide support in an appropriate tone and expression according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the inquiry support unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the inquiry support unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the tone and expression.

[0117] The inquiry support unit can provide more personalized support by referring to the user's past inquiry history during inquiry support. For example, based on the content of the user's past inquiries, related support can be provided. Also, by referring to problems the user has solved in the past, a solution to a similar problem can be provided. Furthermore, support based on specific interests and concerns can be provided from the user's past inquiry history. This makes it possible to provide more personalized support based on the user's past inquiry history. Part or all of the above-mentioned processing in the inquiry support unit may be performed, for example, using AI, or may be performed without using AI. For example, the inquiry support unit can input the user's past inquiry history data into the generation AI and cause the generation AI to generate personalized support.

[0118] The inquiry support unit can customize the support content based on the user's current situation and context during the inquiry support. For example, if the user makes an inquiry about the current time period, the inquiry support unit provides support related to that time period. Also, if the user is in a specific location, support related to that location can be provided. Furthermore, if the user is using a specific device, support optimized for that device can be provided. This makes it possible to provide more appropriate support based on the user's current situation and context. Some or all of the above-mentioned processing in the inquiry support unit may be performed using, for example, AI, or may be performed without using AI. For example, the inquiry support unit can input the user's current situation and context data into the generation AI and cause the generation AI to generate customized support.

[0119] The inquiry support unit can estimate the user's emotions and determine the priority of support based on the estimated user's emotions. For example, if the user makes an urgent inquiry, the inquiry support unit processes the inquiry with the highest priority. Also, if the user is relaxed, the inquiry support unit can process the inquiry with the same priority as other inquiries. Furthermore, if the user is stressed, the inquiry support unit can process the inquiry with priority and respond quickly. This allows for a faster and more appropriate response by determining the priority of support according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the inquiry support unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the inquiry support unit can input the user's emotion data to the generation AI and have the generation AI execute the determination of the priority.

[0120] The inquiry support unit can provide highly relevant support in consideration of the geographical location information of the user during the inquiry support. For example, if the user is in a specific city, support related to the city can be provided. Also, if the user is in a specific country, support related to the country can be provided. Furthermore, if the user is in a specific region, support related to the region can be provided. This makes it possible to provide more relevant support based on the geographical location information of the user. A part or all of the above-mentioned processing in the inquiry support unit may be performed, for example, using AI, or may be performed without using AI. For example, the inquiry support unit can input the geographical location information data of the user to the generation AI and cause the generation AI to generate highly relevant support.

[0121] The inquiry support unit can analyze the user's social media activities and provide relevant support during the inquiry support. For example, the inquiry support unit can provide relevant support based on information shared by the user on social media. The inquiry support unit can also provide relevant support based on accounts the user follows on social media. Furthermore, the inquiry support unit can provide relevant support based on topics in which the user shows interest on social media. This makes it possible to provide more relevant support based on the user's social media activities. Some or all of the above-mentioned processing in the inquiry support unit can be performed, for example, using AI or can be performed without using AI. For example, the inquiry support unit can input the user's social media activity data into the generation AI and cause the generation AI to generate related support.

[0122] The purchase support unit can estimate the user's emotions and adjust the tone and expression of the purchase support based on the estimated user's emotions. For example, if the user is stressed, the purchase support unit can respond in a gentle tone and use expressions that give a sense of security. Also, if the user is relaxed, the purchase support unit can respond in a casual tone and use friendly expressions. Furthermore, if the user is in a hurry, the purchase support unit can respond in a quick and concise tone and provide the necessary information in a short time. This makes it possible to provide purchase support in an appropriate tone and expression according to the user's emotions. The estimation of emotions is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the purchase support unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the purchase support unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the tone and expression.

[0123] The purchase support unit can provide more personalized support by referring to the user's past purchase history during purchase support. For example, based on products purchased by the user in the past, related products are recommended. Also, support based on specific interests and concerns can be provided from the user's past purchase history. Furthermore, related support can be provided by referring to the usage status of products purchased by the user in the past. This makes it possible to provide more personalized support based on the user's past purchase history. Part or all of the above-mentioned processing in the purchase support unit may be performed, for example, using AI or may be performed without using AI. For example, the purchase support unit can input the user's past purchase history data into the generation AI and cause the generation AI to generate personalized support.

[0124] The purchase support unit can customize the support content based on the user's current situation and context during purchase support. For example, if the user is requesting purchase support related to the current time period, the purchase support unit provides information related to that time period. In addition, if the user is in a specific location, purchase support related to that location can be provided. Furthermore, if the user is using a specific device, purchase support optimized for that device can be provided. This makes it possible to provide more appropriate support based on the user's current situation and context. Some or all of the above-mentioned processing in the purchase support unit may be performed using, for example, AI, or may be performed without using AI. For example, the purchase support unit can input the user's current situation and context data into the generation AI and cause the generation AI to generate customized support.

[0125] The purchase support unit can estimate the user's emotions and determine the priority of purchase support based on the estimated user's emotions. For example, if the user requires urgent purchase support, the purchase support unit processes that support with the highest priority. Also, if the user is relaxed, the purchase support unit can process that support with the same priority as other supports. Furthermore, if the user is stressed, the purchase support unit can process that support with priority and respond quickly. This allows for faster and more appropriate response by determining the priority of purchase support according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the purchase support unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the purchase support unit can input the user's emotion data into the generation AI and have the generation AI execute the determination of the priority.

[0126] The purchase support unit can provide highly relevant support during purchase support by taking into account the geographic location information of the user. For example, if the user is in a specific city, product information related to the city can be provided. Also, if the user is in a specific country, product information related to the country can be provided. Furthermore, if the user is in a specific region, product information related to the region can be provided. This makes it possible to provide more relevant support based on the geographic location information of the user. A part or all of the above-mentioned processing in the purchase support unit may be performed, for example, using AI, or may be performed without using AI. For example, the purchase support unit can input the geographic location information data of the user to the generation AI and cause the generation AI to generate highly relevant support.

[0127] The purchase support unit can analyze the user's social media activities and provide relevant support during purchase support. For example, the purchase support unit can provide relevant product information based on information shared by the user on social media. The purchase support unit can also provide relevant product information based on accounts the user follows on social media. Furthermore, the purchase support unit can provide relevant product information based on topics in which the user has shown interest on social media. This makes it possible to provide more relevant support based on the user's social media activities. Some or all of the above-mentioned processing in the purchase support unit can be performed, for example, using AI or without AI. For example, the purchase support unit can input the user's social media activity data into a generation AI and have the generation AI execute the generation of related support.

[0128] The estimation unit can estimate the user's emotion and adjust the interest estimation method based on the estimated user's emotion. For example, when the user is relaxed, the estimation unit estimates the interest based on detailed information. Also, when the user is in a hurry, the estimation unit can estimate the interest based on concise information. Furthermore, when the user is excited, the estimation unit can estimate the interest based on visually stimulating information. This makes it possible to estimate the interest in an appropriate manner according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the estimation method.

[0129] The estimation unit can perform more accurate estimation by referring to the user's past behavioral history at the time of estimation. For example, the interest is estimated based on the page the user viewed in the past. The interest can also be estimated based on the product the user purchased in the past. Furthermore, specific interests and concerns can be estimated from the user's past behavioral history. This allows more accurate estimation to be performed based on the user's past behavioral history. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input the user's past behavioral history data to the generation AI and cause the generation AI to perform accurate estimation.

[0130] The estimation unit can customize the estimation content based on the user's current situation and context at the time of estimation. For example, the estimation unit estimates the user's interests based on information about the user's current time zone. In addition, if the user is in a specific location, the estimation unit can estimate the user's interests based on information related to the location. In addition, if the user is using a specific device, the estimation unit can estimate the user's interests based on information optimized for the device. This allows more appropriate estimation to be performed based on the user's current situation and context. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input the user's current situation and context data to the generation AI and cause the generation AI to perform a customized estimation.

[0131] The estimation unit can estimate the user's emotion and determine the priority of estimation based on the estimated user's emotion. For example, when the user is seeking urgent information, the estimation unit estimates the information with the highest priority. In addition, when the user is relaxed, the estimation unit can estimate the information with the same priority as other information. Furthermore, when the user is stressed, the estimation unit can estimate the information with priority and respond quickly. This enables a quicker and more appropriate response by determining the priority of estimation according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority.

[0132] The estimation unit can perform highly relevant estimation by taking into account the geographical location information of the user at the time of estimation. For example, if the user is in a specific city, the interest is estimated based on information related to the city. Also, if the user is in a specific country, the interest can be estimated based on information related to the country. Furthermore, if the user is in a specific region, the interest can be estimated based on information related to the region. This allows more relevant estimation to be performed based on the geographical location information of the user. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input the geographical location information data of the user to the generation AI and cause the generation AI to perform a highly relevant estimation.

[0133] The estimation unit can analyze the user's social media activity and make relevant inferences at the time of estimation. For example, the estimation unit estimates interests based on information shared by the user on social media. The estimation unit can also estimate interests based on accounts the user follows on social media. Furthermore, the estimation unit can also estimate interests based on topics in which the user has shown interest on social media. This allows more relevant inferences to be made based on the user's social media activity. Some or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI or may be performed without using AI. For example, the estimation unit can input the user's social media activity data to the generation AI and cause the generation AI to perform the relevant inferences.

[0134] The analysis result providing unit can estimate the user's emotion and adjust the presentation method of the analysis result based on the estimated user's emotion. For example, when the user is stressed, the analysis result providing unit provides a concise and easy-to-understand result. In addition, when the user is relaxed, the analysis result providing unit can also provide a detailed result. Furthermore, when the user is in a hurry, the analysis result providing unit can also provide a result that covers the main points. This makes it possible to present the analysis result in an appropriate manner according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis result providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis result providing unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the presentation method.

[0135] When providing the analysis result, the analysis result providing unit can provide a more personalized result by referring to the user's past feedback history. For example, based on the feedback provided by the user in the past, the analysis result providing unit can provide a related analysis result. Also, based on the user's past feedback history, a result based on a specific interest or concern can be provided. Furthermore, based on the user's past feedback history, a related result can be provided by referring to the content of the feedback provided by the user in the past. This makes it possible to provide a more personalized result based on the user's past feedback history. A part or all of the above-mentioned processing in the analysis result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis result providing unit can input the user's past feedback history data to the generation AI and cause the generation AI to generate a personalized result.

[0136] The analysis result providing unit can customize the results based on the user's current field of interest when providing the analysis result. For example, the analysis result providing unit can provide analysis results related to topics in which the user is currently interested. The analysis result providing unit can also provide analysis results related to products in which the user is currently interested. Furthermore, the analysis result providing unit can provide analysis results related to services in which the user is currently paying attention. This makes it possible to provide more appropriate results based on the user's current field of interest. Some or all of the above-mentioned processing in the analysis result providing unit can be performed, for example, using AI or can be performed without using AI. For example, the analysis result providing unit can input the user's current field of interest data to the generation AI and cause the generation AI to generate customized results.

[0137] The analysis result providing unit can estimate the user's emotion and determine the priority of the analysis results based on the estimated user's emotion. For example, if the user requires an urgent analysis result, the analysis result providing unit provides the result with the highest priority. In addition, if the user is relaxed, the analysis result providing unit can provide the result with the same priority as other results. Furthermore, if the user is stressed, the analysis result providing unit can provide the result with priority and respond quickly. This enables a faster and more appropriate response by determining the priority of the analysis results according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis result providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis result providing unit can input the user's emotion data to the generation AI and cause the generation AI to determine the priority.

[0138] When providing the analysis results, the analysis result providing unit can provide highly relevant results by taking into account the geographical location information of the user. For example, if the user is in a specific city, the analysis result related to the city can be provided. Also, if the user is in a specific country, the analysis result related to the country can be provided. Furthermore, if the user is in a specific region, the analysis result related to the region can be provided. This makes it possible to provide more relevant results based on the geographical location information of the user. A part or all of the above-mentioned processing in the analysis result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis result providing unit can input the geographical location information data of the user to the generation AI and cause the generation AI to generate highly relevant results.

[0139] The analysis result providing unit can analyze the user's social media activity and provide related results when providing the analysis result. For example, the analysis result providing unit can provide related analysis results based on information shared by the user on social media. Also, the analysis result providing unit can provide related analysis results based on accounts the user follows on social media. Furthermore, the analysis result providing unit can provide related analysis results based on topics in which the user shows interest on social media. This makes it possible to provide more relevant results based on the user's social media activity. Some or all of the above-mentioned processing in the analysis result providing unit can be performed, for example, using AI or can be performed without using AI. For example, the analysis result providing unit can input the user's social media activity data to the generation AI and cause the generation AI to generate related results.

[0140] The connection unit can estimate the user's emotion and adjust the timing and method of connection based on the estimated user's emotion. For example, if the user is feeling stressed, the connection unit can quickly connect to a customer support representative. Also, if the user is relaxed, the connection unit can connect at a normal timing. Furthermore, if the user is in a hurry, the connection unit can connect in the shortest time. This makes it possible to provide a connection at an appropriate timing and method according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the connection unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the connection unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the timing and method.

[0141] At the time of connection, the connection unit can provide a more personalized connection by referring to the user's past inquiry history. For example, the connection unit can connect to a related customer support representative based on the content of the user's past inquiries. Also, the connection unit can connect to a representative who is familiar with a specific problem from the user's past inquiry history. Furthermore, the connection unit can connect to a representative who provides support for a similar problem by referring to a problem that the user has solved in the past. This makes it possible to provide a more personalized connection based on the user's past inquiry history. Part or all of the above-mentioned processing in the connection unit may be performed, for example, using AI or may be performed without using AI. For example, the connection unit can input the user's past inquiry history data to the generation AI and cause the generation AI to generate a personalized connection.

[0142] At the time of connection, the connection unit can customize the connection content based on the user's current situation and context. For example, if the user is making an inquiry about the current time period, the connection unit can connect to a person related to that time period. Also, if the user is in a specific location, the connection unit can connect to a person related to that location. Furthermore, if the user is using a specific device, the connection unit can connect to a person who provides support optimized for that device. This makes it possible to provide a more appropriate connection based on the user's current situation and context. Some or all of the above-mentioned processing in the connection unit may be performed using, for example, AI, or may be performed without using AI. For example, the connection unit can input the user's current situation and context data to the generation AI and cause the generation AI to generate a customized connection.

[0143] The connection unit can estimate the user's emotion and determine the priority of the connection based on the estimated user's emotion. For example, if the user makes an urgent inquiry, the connection unit processes the inquiry with the highest priority. Also, if the user is relaxed, the connection unit can process the inquiry with the same priority as other inquiries. Furthermore, if the user is stressed, the connection unit can process the inquiry with priority and respond quickly. This allows for a faster and more appropriate response by determining the priority of the connection according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the connection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the connection unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority.

[0144] The connection unit can provide a highly relevant connection in consideration of the geographical location information of the user at the time of connection. For example, if the user is in a specific city, the connection unit can connect to a person related to the city. Also, if the user is in a specific country, the connection unit can connect to a person related to the country. Furthermore, if the user is in a specific region, the connection unit can connect to a person related to the region. This makes it possible to provide a more relevant connection based on the geographical location information of the user. A part or all of the above-mentioned processing in the connection unit may be performed, for example, using AI or may be performed without using AI. For example, the connection unit can input the geographical location information data of the user to the generation AI and cause the generation AI to generate a highly relevant connection.

[0145] At the time of connection, the connection unit can analyze the user's social media activity and provide relevant connections. For example, the connection unit can connect to relevant personnel based on information shared by the user on social media. The connection unit can also connect to relevant personnel based on accounts the user follows on social media. Furthermore, the connection unit can connect to relevant personnel based on topics in which the user has shown interest on social media. This makes it possible to provide more relevant connections based on the user's social media activity. Some or all of the above-mentioned processing in the connection unit may be performed, for example, using AI or may be performed without using AI. For example, the connection unit can input the user's social media activity data to the generation AI and cause the generation AI to generate relevant connections.

[0146] The learning unit can estimate the user's emotion and select learning data based on the estimated user's emotion. For example, when the user is relaxed, the learning unit can learn based on detailed data. Also, when the user is in a hurry, the learning unit can also learn based on concise data. Furthermore, when the user is excited, the learning unit can also learn based on visually stimulating data. This allows learning to be performed with appropriate data according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's emotion data to the generation AI and cause the generation AI to select the learning data.

[0147] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. For example, an optimal learning algorithm is selected based on past learning data. Also, a specific pattern can be extracted from the past learning data to optimize the learning algorithm. Furthermore, the accuracy of the learning algorithm can be improved by analyzing the past learning data. This makes it possible to optimize the learning algorithm based on the past learning data. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input past learning data to a generation AI and cause the generation AI to optimize the learning algorithm.

[0148] The learning unit can customize the learning content based on the user's current situation and context during learning. For example, the learning content is customized based on information about the user's current time zone. In addition, when the user is in a specific location, the learning content can be customized based on information related to the location. Furthermore, when the user is using a specific device, the learning content can be customized based on information optimized for that device. This allows more appropriate learning based on the user's current situation and context. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the user's current situation and context data to the generation AI and cause the generation AI to generate customized learning content.

[0149] The learning unit can estimate the user's emotion and adjust the frequency of learning based on the estimated user's emotion. For example, when the user is relaxed, the learning unit can learn frequently. Also, when the user is in a hurry, the learning unit can reduce the frequency of learning. Furthermore, when the user is excited, the learning unit can adjust the frequency of learning. This allows for more effective learning by adjusting the frequency of learning according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the learning unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the learning frequency.

[0150] During learning, the learning unit can learn highly relevant data taking into account the geographical location information of the user. For example, if the user is in a specific city, data related to the city is learned. Also, if the user is in a specific country, data related to the country can be learned. Furthermore, if the user is in a specific region, data related to the region can be learned. This allows learning to be performed with more relevant data based on the geographical location information of the user. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the geographical location information data of the user to the generation AI and cause the generation AI to execute learning of highly relevant data.

[0151] During learning, the learning unit can analyze the user's social media activities and learn related data. For example, the learning unit learns related data based on information shared by the user on social media. Also, the learning unit can learn related data based on accounts the user follows on social media. Furthermore, the learning unit can learn related data based on topics in which the user shows interest on social media. This allows learning to be performed with more relevant data based on the user's social media activities. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using AI or may be performed without using AI. For example, the learning unit can input the user's social media activity data to the generation AI and cause the generation AI to execute learning of related data.

[0152] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0153] The automated response system AI assistant can be equipped with a prediction unit that analyzes the visitor's behavioral patterns and predicts the action the visitor is likely to take next. For example, if the visitor frequently views a particular product page, the prediction unit can recommend the purchase of that product. Also, if the visitor repeatedly searches for information about a particular service, the prediction unit can provide detailed information about that service. Furthermore, if the visitor frequently accesses the site during a particular time period, the prediction unit can provide promotional information related to that time period. This allows for more appropriate support to be provided based on the visitor's behavioral patterns.

[0154] The automatic response system AI assistant may include a stress evaluation unit that estimates the visitor's emotions and evaluates the visitor's stress level based on the estimated emotions. For example, if the visitor frequently receives error messages, the stress evaluation unit may evaluate the visitor's stress level as high. In addition, if the visitor stays on the same page for a long time, the stress evaluation unit may evaluate the visitor's stress level as medium. Furthermore, if the visitor browses many pages in a short time, the stress evaluation unit may evaluate the visitor's stress level as low. This makes it possible to provide appropriate support according to the visitor's stress level.

[0155] The automated response system AI assistant can be equipped with a purchase prediction unit that analyzes the visitor's past purchase history and predicts the product the visitor is likely to purchase next. For example, if the visitor has purchased a product of a particular brand in the past, the purchase prediction unit can recommend new products of that brand. Also, if the visitor has purchased products of a particular category in the past, the purchase prediction unit can recommend related products of that category. Furthermore, if the visitor has purchased products in a particular price range in the past, the purchase prediction unit can recommend products in that price range. This makes it possible to recommend more appropriate products based on the visitor's purchase history.

[0156] The automatic response system AI assistant may include a satisfaction evaluation unit that estimates the visitor's emotions and evaluates the visitor's satisfaction level based on the estimated emotions. For example, if the visitor provides positive feedback, the satisfaction evaluation unit may evaluate the visitor's satisfaction level as high. Also, if the visitor provides neutral feedback, the satisfaction evaluation unit may evaluate the visitor's satisfaction level as medium. Furthermore, if the visitor provides negative feedback, the satisfaction evaluation unit may evaluate the visitor's satisfaction level as low. This makes it possible to provide appropriate support according to the visitor's satisfaction level.

[0157] The automated response system AI assistant may include a needs prediction unit that predicts the visitor's needs based on the visitor's current situation and context. For example, if the visitor is searching for information about a particular event, the needs prediction unit may provide information related to that event. Also, if the visitor is searching for products related to a particular season, the needs prediction unit may recommend products related to that season. Furthermore, if the visitor is using a particular device, the needs prediction unit may provide information optimized for that device. This allows for more appropriate support to be provided based on the visitor's current situation and context.

[0158] The automatic response system AI assistant may include an engagement evaluation unit that estimates the visitor's emotions and evaluates the visitor's engagement level based on the estimated emotions. For example, if the visitor is actively asking questions, the engagement evaluation unit may evaluate the visitor's engagement level as high. Also, if the visitor is viewing information with a neutral attitude, the engagement evaluation unit may evaluate the visitor's engagement level as medium. Furthermore, if the visitor is viewing information with a passive attitude, the engagement evaluation unit may evaluate the visitor's engagement level as low. This makes it possible to provide appropriate support according to the visitor's engagement level.

[0159] The automated response system AI assistant may include a feedback prediction unit that analyzes the visitor's past feedback and predicts the feedback that the visitor is likely to provide next. For example, if the visitor has provided positive feedback in the past, the feedback prediction unit predicts that the visitor will provide positive feedback next time. Also, if the visitor has provided neutral feedback in the past, the feedback prediction unit may predict that the visitor will provide neutral feedback next time. Furthermore, if the visitor has provided negative feedback in the past, the feedback prediction unit may predict that the visitor will provide negative feedback next time. This makes it possible to provide more appropriate support based on the visitor's past feedback.

[0160] The automatic response system AI assistant may include a purchasing willingness evaluation unit that estimates the visitor's emotions and evaluates the visitor's purchasing willingness based on the estimated emotions. For example, if the visitor is excited, the purchasing willingness evaluation unit may evaluate the visitor's purchasing willingness as high. Also, if the visitor is viewing products with a neutral attitude, the purchasing willingness evaluation unit may evaluate the visitor's purchasing willingness as medium. Furthermore, if the visitor is viewing products with a passive attitude, the purchasing willingness evaluation unit may evaluate the visitor's purchasing willingness as low. This makes it possible to provide appropriate support according to the visitor's purchasing willingness.

[0161] The automated response system AI assistant can be equipped with a behavioral prediction unit that predicts the visitor's behavior based on the visitor's current situation and context. For example, if the visitor frequently visits during a certain time period, the behavioral prediction unit can provide information related to that time period. Also, if the visitor is in a certain location, the behavioral prediction unit can provide information related to that location. Furthermore, if the visitor is using a specific device, the behavioral prediction unit can provide information optimized for that device. This allows for more appropriate support to be provided based on the visitor's current situation and context.

[0162] The automatic response system AI assistant may include a repeat rate evaluation unit that estimates the visitor's emotions and evaluates the visitor's repeat rate based on the estimated emotions. For example, if the visitor shows positive emotions, the repeat rate evaluation unit may evaluate the visitor's repeat rate as high. Also, if the visitor shows neutral emotions, the repeat rate evaluation unit may evaluate the visitor's repeat rate as medium. Furthermore, if the visitor shows negative emotions, the repeat rate evaluation unit may evaluate the visitor's repeat rate as low. This makes it possible to provide appropriate support according to the visitor's repeat rate.

[0163] The process flow of the second embodiment will be briefly described below.

[0164] Step 1: The answerer responds to questions from website visitors. For example, if a visitor asks, "What are your business hours?", the answerer immediately responds, "Business hours are from 9:00 to 18:00." Step 2: The detailed information providing section provides detailed information about the product or service specified by the visitor. For example, if the visitor asks, "Please tell me the details of this product," the detailed information providing section provides detailed information such as product specifications, prices, and usage methods. Step 3: The customer support department provides guidance or a solution to the visitor's inquiry. For example, if a visitor inquires that their Internet connection is unstable, the customer support department will provide them with a method to check the connection or a troubleshooting procedure. Step 4: The purchasing support department assists the visitor in purchasing products, booking services, and making appointments. For example, if a visitor asks, "What products do you recommend?", the purchasing support department will recommend products based on the visitor's past purchase history and interests, and help them add products to their cart and complete the purchase. Step 5: The estimation unit estimates the visitor's interest in a particular subject based on the visitor's information. For example, if the visitor says, "I'm interested in this service," the estimation unit obtains the visitor's contact information and provides information about the service of interest. Step 6: The analysis result providing unit analyzes the feedback or opinions from the visitors and provides the analysis result. For example, if the visitor provides feedback such as "This service was very good," the analysis result providing unit collects the feedback and displays it on the dashboard in real time.

[0165] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0166] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0167] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0168] For example, the answering unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the detailed information providing unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the inquiry support unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the purchase support unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the estimation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the analysis result providing unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the connection unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0169] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0170] 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.

[0171] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] 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.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0176] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0177] 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.

[0178] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0179] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0180] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0181] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0182] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0183] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0184] For example, the answering unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the detailed information providing unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the inquiry support unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the purchase support unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the estimation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the analysis result providing unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the connection unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various modifications are possible.

[0185] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0186] 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.

[0187] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0188] 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.

[0189] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0190] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0191] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0192] 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.

[0193] 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.

[0194] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0195] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0196] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0197] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0198] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0199] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0200] For example, the answering unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the detailed information providing unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the inquiry support unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the purchase support unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the estimation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the analysis result providing unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the connection unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the learning unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various modifications are possible.

[0201] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0202] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0203] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0204] 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.

[0205] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0206] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0207] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0208] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0209] 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.

[0210] 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.

[0211] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0212] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0213] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0214] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0215] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0216] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0217] For example, the answering unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the detailed information providing unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the inquiry support unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the purchase support unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the estimation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the analysis result providing unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the connection unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the learning unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0218] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0219] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0220] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0221] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0222] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0223] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0224] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0225] 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.

[0226] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0227] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0228] 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.

[0229] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0230] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0231] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0232] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0233] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0234] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0235] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0236] (Appendix 1) an answering section for answering questions from website visitors; a detailed information providing unit for providing detailed information of a product or service designated by the visitor to the visitor; a support section for providing guidance or solutions to the visitor's inquiries; a purchase support department that provides support for product purchases, service reservations, and appointments to the visitors; an estimation unit that estimates an interest of the visitor based on the information of the visitor; and an analysis result providing unit that analyzes feedback or opinions from the visitors and provides analysis results. A system characterized by: (Appendix 2) a connection unit for connecting the visitor's inquiry to a customer support representative based on details of the visitor's inquiry. 2. The system of claim 1, (Appendix 3) A learning unit that learns interactions with the visitor in real time and provides responses based on the visitor's behavioral patterns and requirements. 2. The system of claim 1, (Appendix 4) The detailed information providing unit is Providing personalized information based on the visitor's past behavior 2. The system of claim 1, (Appendix 5) The analysis result providing unit is Display real-time feedback from said visitors on a dashboard 2. The system of claim 1, (Appendix 6) The estimation unit is Analyzing the visitor's browsing time and time on page to infer their interests 2. The system of claim 1, (Appendix 7) The answering section: Provides multilingual capabilities that provide responses based on the visitor's language of choice 2. The system of claim 1, (Appendix 8) The purchasing support department: The function of predicting and recommending the next purchase based on the visitor's purchase history is provided. 2. The system of claim 1, (Appendix 9) The connection portion is If a combination of the complexity of the visitor's inquiry and the wait time of the visitor satisfies a predetermined condition, the visitor's inquiry is connected to the customer support representative. 3. The system of claim 2, (Appendix 10) The inquiry support department: Equipped with a function to automatically complete the visitor's input 2. The system of claim 1, (Appendix 11) The connection portion is When inquiries from the visitors are concentrated in a specific time period, the function of managing the inquiries on a schedule is provided. 3. The system of claim 2, (Appendix 12) The answering section: Infer user sentiment and adjust the tone and wording of responses based on the inferred sentiment 2. The system of claim 1, (Appendix 13) The answering section: When answering a question, the system references the user's previous question history to provide a more personalized answer. 2. The system of claim 1, (Appendix 14) The answering section: Customize answers based on the user's current situation and context when answering 2. The system of claim 1, (Appendix 15) The answering section: Infer user sentiment and prioritize answers based on the inferred sentiment 2. The system of claim 1, (Appendix 16) The answering section: When answering, it takes into account the user's geographic location to provide more relevant information 2. The system of claim 1, (Appendix 17) The answering section: When you respond, analyze your social media activity and provide you with relevant information 2. The system of claim 1, (Appendix 18) The detailed information providing unit Estimate user emotions and adjust the way information is presented based on the estimated user emotions 2. The system of claim 1, (Appendix 19) The detailed information providing unit When providing detailed information, the system refers to the user's past behavioral history to provide more personalized information. 2. The system of claim 1, (Appendix 20) The detailed information providing unit When you provide your details, tailor the information to you based on your current interests 2. The system of claim 1, (Appendix 21) The detailed information providing unit Estimate user emotions and prioritize information based on the estimated user emotions 2. The system of claim 1, (Appendix 22) The detailed information providing unit When providing detailed information, the system takes into account the user's geographic location to provide more relevant information. 2. The system of claim 1, (Appendix 23) The detailed information providing unit When you provide your details, we analyze your social media activity and provide you with relevant information 2. The system of claim 1, (Appendix 24) The inquiry support department: Infer user emotions and adjust the tone and expression of support based on the inferred user emotions 2. The system of claim 1, (Appendix 25) The inquiry support department: When supporting inquiries, provide more personalized support by referencing the user's past inquiry history 2. The system of claim 1, (Appendix 26) The inquiry support department: When supporting a case, tailor the support experience based on the user's current situation and context 2. The system of claim 1, (Appendix 27) The inquiry support department: Estimate user's emotions and determine priority of support based on the estimated user's emotions 2. The system of claim 1, (Appendix 28) The inquiry support department: When supporting enquiries, provide more relevant support by taking into account the user's geographic location 2. The system of claim 1, (Appendix 29) The inquiry support department: Analyze your social media activity and provide relevant support when you contact us 2. The system of claim 1, (Appendix 30) The purchasing support department: Infer user sentiment and adjust the tone and language of purchase support based on the inferred user sentiment 2. The system of claim 1, (Appendix 31) The purchasing support department: When providing purchase support, provide more personalized support by referencing the user's past purchase history 2. The system of claim 1, (Appendix 32) The purchasing support department: During purchase support, tailor support based on the user's current situation and context 2. The system of claim 1, (Appendix 33) The purchasing support department: Estimate user sentiment and prioritize purchase support based on the estimated user sentiment 2. The system of claim 1, (Appendix 34) The purchasing support department: Provide relevant support during purchases by taking into account the user's geographic location 2. The system of claim 1, (Appendix 35) The purchasing support department: Analyze users' social media activity and provide relevant support when making purchases 2. The system of claim 1, (Appendix 36) The estimation unit is To estimate a user's emotion and adjust an interest estimation method based on the estimated user's emotion. 2. The system of claim 1, (Appendix 37) The estimation unit is When making an estimation, the system refers to the user's past behavior history to make a more accurate estimation. 2. The system of claim 1, (Appendix 38) The estimation unit is When making an estimate, customize the estimate based on the user's current situation and context 2. The system of claim 1, (Appendix 39) The estimation unit is To estimate a user's emotion and determine a priority of estimations based on the estimated user's emotion. 2. The system of claim 1, (Appendix 40) The estimation unit is During estimation, the geographic location of the user is taken into account to make more relevant estimations. 2. The system of claim 1, (Appendix 41) The estimation unit is At the time of inference, the social media activity of the user is analyzed and relevant inferences are made. 2. The system of claim 1, (Appendix 42) The analysis result providing unit is Infer user sentiment and adjust the presentation of analysis results based on the inferred user sentiment 2. The system of claim 1, (Appendix 43) The analysis result providing unit is When providing analysis results, the system refers to the user's past feedback history to provide more personalized results. 2. The system of claim 1, (Appendix 44) The analysis result providing unit is When providing analysis results, customize the results based on the user's current areas of interest 2. The system of claim 1, (Appendix 45) The analysis result providing unit is Infer user sentiment and prioritize analysis results based on the inferred user sentiment 2. The system of claim 1, (Appendix 46) The analysis result providing unit is When providing analysis results, the geographic location of the user is taken into account to provide more relevant results. 2. The system of claim 1, (Appendix 47) The analysis result providing unit is When providing analytics, analyze your social media activity and provide you with relevant results 2. The system of claim 1, (Appendix 48) The connection portion is Estimate the user's emotions and adjust the timing and method of connection based on the estimated user's emotions. 3. The system of claim 2, (Appendix 49) The connection portion is When connecting, reference the user's past contact history to provide a more personalized connection 3. The system of claim 2, (Appendix 50) The connection portion is When connecting, customize the connection experience based on the user's current situation and context 3. The system of claim 2, (Appendix 51) The connection portion is Inferring user emotions and prioritizing connections based on the estimated user emotions 3. The system of claim 2, (Appendix 52) The connection portion is When connecting, it takes into account the user's geographic location to provide more relevant connections 3. The system of claim 2, (Appendix 53) The connection portion is When you connect, analyze your social media activity to provide you with relevant connections 3. The system of claim 2, (Appendix 54) The learning unit is Estimate the user's emotions and select learning data based on the estimated user emotions. 4. The system of claim 3. (Appendix 55) The learning unit is During training, the learning algorithm is optimized by referencing past training data. 4. The system of claim 3. (Appendix 56) The learning unit is Customize learning experiences based on the user's current situation and context as they learn 4. The system of claim 3. (Appendix 57) The learning unit is Infer user emotions and adjust the frequency of learning based on the estimated user emotions. 4. The system of claim 3. (Appendix 58) The learning unit is During training, the system takes into account the user's geographic location to learn more relevant data. 4. The system of claim 3. (Appendix 59) The learning unit is During learning, the system analyzes users' social media activity and learns relevant data. 4. The system of claim 3. [Explanation of symbols]

[0237] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an answering section for answering questions from website visitors; a detailed information providing unit for providing detailed information of a product or service designated by the visitor to the visitor; a support section for providing guidance or solutions to the visitor's inquiries; a purchase support department that provides support for product purchases, service reservations, and appointments to the visitors; an estimation unit that estimates an interest of the visitor based on the information of the visitor; and an analysis result providing unit that analyzes feedback or opinions from the visitors and provides analysis results. A system characterized by:

2. a connection unit for connecting the visitor's inquiry to a customer support representative based on details of the visitor's inquiry.

2. The system of claim 1 .

3. A learning unit that learns interactions with the visitor in real time and provides responses based on the visitor's behavioral patterns and requirements.

2. The system of claim 1 .

4. The detailed information providing unit is Providing personalized information based on the visitor's past behavior 2. The system of claim 1 .

5. The analysis result providing unit is Display real-time feedback from said visitors on a dashboard 2. The system of claim 1 .

6. The estimation unit is Analyzing the visitor's browsing time and time on page to infer their interests 2. The system of claim 1 .

7. The answering section: Provides multilingual capabilities that provide responses based on the visitor's language of choice 2. The system of claim 1 .

8. The purchasing support department: The function of predicting and recommending the next purchase based on the visitor's purchase history is provided.

2. The system of claim 1 .

9. The connection portion is If a combination of the complexity of the visitor's inquiry and the wait time of the visitor satisfies a predetermined condition, the visitor's inquiry is connected to the customer support representative.

3. The system of claim 2.

Images