system

Abstract

The system according to this embodiment aims to provide users with the necessary information and facilitate communication so that they can make purchases with confidence. [Solution] The system according to the embodiment comprises a review organization unit, a related product suggestion unit, a Q&A provision unit, and a live chat provision unit. The review organization unit organizes reviews. The related product suggestion unit suggests related products based on the reviews organized by the review organization unit. The Q&A provision unit provides Q&A based on the related products suggested by the related product suggestion unit. The live chat provision unit provides live chat based on the Q&A provided by the Q&A provision unit.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is room for improvement in promoting communication for a user to efficiently obtain necessary information before purchase and purchase with confidence.

[0005] The system according to the embodiment aims to provide necessary information and promote communication so that a user can purchase with confidence.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a review organization unit, a related product suggestion unit, a Q&A provision unit, and a live chat provision unit. The review organization unit organizes reviews. The related product suggestion unit suggests related products based on the reviews organized by the review organization unit. The Q&A provision unit provides Q&A based on the related products suggested by the related product suggestion unit. The live chat provision unit provides live chat based on the Q&A provided by the Q&A provision unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide users with the necessary information and facilitate communication so that they can make purchases with confidence. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The shopping support system according to an embodiment of the present invention is a system that utilizes generative AI to build a community where users can make purchases with peace of mind. This shopping support system uses generative AI to automatically organize and provide reviews and Q&A from other users about the product the user is trying to purchase. Next, the generative AI automatically suggests related products. Furthermore, to promote communication among users, the generative AI provides a Q&A section. It also enables live chat with actual buyers. This makes it easy for users to check reviews and Q&A from other users and find related products. In addition, they can obtain reliable information through live chat with actual buyers, allowing them to make purchases with peace of mind. This realizes a highly reliable shopping experience. For example, the generative AI automatically organizes and provides reviews and Q&A from other users about the product the user is trying to purchase. For example, if a user is looking for reviews about a specific product, the generative AI automatically collects, organizes, and displays reviews related to that product. This makes it easy for users to check the opinions of other users. Next, the generative AI automatically suggests related products. For example, if a user is trying to purchase a specific product, the generative AI suggests other products related to that product. This makes it easier for users to find products that meet their needs. Furthermore, to facilitate communication among users, a generation AI provides a Q&A section. Users can post their questions and receive answers from other users. The generation AI automatically organizes these questions and answers and provides relevant information. For example, if a user wants to know how to use a particular product, the generation AI will automatically collect and display answers to that question. It also enables live chat with actual buyers. Users can chat with other buyers in real time and ask questions directly about product details and user experiences. This allows users to obtain reliable information and make purchases with confidence. This system makes it easy for users to check other users' reviews and Q&A, making it easier to find related products.Furthermore, users can obtain reliable information through live chats with actual buyers, allowing them to purchase with confidence. This results in a trustworthy shopping experience. As a result, the shopping support system can build a community where users can purchase with peace of mind, and facilitate communication among users through reviews, related products, Q&A, and live chat.

[0029] The shopping support system according to this embodiment includes a review organization unit, a related product suggestion unit, a Q&A provision unit, and a live chat provision unit. The review organization unit automatically organizes reviews using a generation AI. For example, if a user is looking for reviews about a specific product, the generation AI automatically collects, organizes, and displays reviews related to that product. The review organization unit can also organize reviews based on review evaluation criteria and organization algorithms. For example, the review organization unit prioritizes displaying highly-rated reviews based on review evaluation criteria. The related product suggestion unit automatically suggests related products using a generation AI. For example, if a user is trying to purchase a specific product, the generation AI suggests other products related to that product. The related product suggestion unit can also suggest related products based on a suggestion algorithm and suggestion criteria. For example, the related product suggestion unit suggests related products based on the user's purchase history and interests. The Q&A provision unit automatically provides Q&A using a generation AI. The Q&A section, for example, uses a generating AI to automatically collect and display answers to questions when a user wants to know how to use a particular product. The Q&A section can also provide Q&A based on question selection criteria and answer delivery methods. For example, it might prioritize displaying the most relevant answers to the user's questions. The live chat section uses a generating AI to automatically provide live chat. For example, the live chat section allows users to chat with other buyers in real time and directly ask questions about product details and user experiences. The live chat section can also provide live chat based on chat initiation conditions and response methods. For example, the live chat section might initiate a live chat when a user is seeking detailed information about a specific product.As a result, the shopping support system according to this embodiment can build a community where users can make purchases with peace of mind, and can promote communication among users through reviews, related products, Q&A, and live chat.

[0030] The review organization section uses generative AI to automatically organize reviews. Specifically, the generative AI utilizes natural language processing technology to automatically collect, organize, and display reviews related to a particular product when a user is searching for reviews about that product. The generative AI can analyze the content of reviews and classify them into positive and negative ratings. For example, the generative AI can extract keywords such as "good," "bad," "recommended," and "dissatisfied" from reviews and classify them based on these keywords. It can also organize reviews based on review evaluation criteria and organization algorithms. For example, the review organization section prioritizes displaying highly-rated reviews based on review evaluation criteria. Furthermore, the generative AI can consider the past review history and ratings of the user who wrote the review in order to evaluate the reliability of the review. This prioritizes displaying reliable reviews, making them easier for users to refer to. The generative AI can also summarize the content of reviews, allowing users to grasp important information in a short amount of time. For example, it can improve user convenience by summarizing long reviews and displaying only the main points. This allows the review organization section to efficiently browse reviews and use them to help users choose products.

[0031] The related products suggestion department uses generative AI to automatically suggest related products. Specifically, the generative AI analyzes the user's purchase history and interests and suggests related products based on that analysis. For example, if a user is about to purchase a specific product, the generative AI will suggest other products related to that product. The generative AI selects the most suitable related products by considering product categories and characteristics, the user's past purchase history, browsing history, etc. It can also suggest related products based on suggestion algorithms and criteria. For example, the generative AI will prioritize suggesting products similar to or in the same category as products the user has previously purchased. Furthermore, the generative AI can analyze the purchase patterns and trends of other users and suggest related products based on that analysis. For example, by suggesting products that other users who purchased the same product also purchased, it can provide related products that are likely to interest the user. In addition, the generative AI can collect user feedback and continuously improve the accuracy of its suggestions. For example, if a user purchases a suggested product, the suggestion algorithm will be adjusted based on that information to provide more accurate suggestions. As a result, the related products suggestion department can efficiently suggest products that users are interested in and improve the shopping experience.

[0032] The Q&A section uses generative AI to automatically provide Q&A. Specifically, the generative AI analyzes user questions, automatically collects the most relevant answers, and displays them. For example, if a user wants to know how to use a particular product, the generative AI will automatically collect and display the answers to that question. The generative AI gathers information from past Q&A databases, product manuals, and relevant forum posts to provide the most relevant answers. It can also provide Q&A based on question selection criteria and answer delivery methods. For example, the generative AI prioritizes displaying the most relevant answers to user questions. Furthermore, the generative AI utilizes natural language processing techniques to understand the intent of user questions and provide appropriate answers. For example, even if a user asks an ambiguous question, the generative AI can analyze its intent and provide an appropriate answer. The generative AI can also collect user feedback and continuously improve the accuracy of its answers. For example, it can evaluate whether users were satisfied with the answers provided and adjust the answer algorithm based on that information. This allows the Q&A section to enable users to obtain information quickly and accurately, improving the shopping experience.

[0033] The department providing live chat will use generative AI to automatically deliver live chat. Specifically, the generative AI will provide an environment where users can chat with other buyers in real time and directly ask questions about product details and usage. The generative AI will analyze user questions and comments and provide appropriate answers and information. It can also provide live chat based on the conditions for starting the live chat and the response method. For example, if a user is asking for detailed information about a particular product, the generative AI will start a live chat to provide that information. The generative AI can refer to past chat history and relevant databases to answer user questions quickly and accurately. Furthermore, the generative AI can collect user feedback and continuously improve the way it responds to chats. For example, it can evaluate whether the user was satisfied with the answers provided and adjust the chat algorithm based on that information. The generative AI can also efficiently handle situations where multiple users are chatting simultaneously. For example, the generative AI will process user questions based on priority and respond quickly to important questions. In this way, the department providing live chat can provide an environment where users can obtain information in real time and improve the shopping experience.

[0034] The review collection unit can collect reviews. For example, the review collection unit might encourage users to post reviews after they have purchased a product. The review collection unit can also collect reviews based on the timing and method of collection. For example, the review collection unit might encourage users to post reviews after they have used a product. This allows users to see the opinions of other users by collecting reviews. Some or all of the above processes in the review collection unit may be performed using AI or not. For example, the review collection unit may use AI to automatically encourage users to post reviews.

[0035] The question collection unit can collect questions. For example, the question collection unit may encourage users to post questions about products. The question collection unit may also collect questions based on the timing and method of collection. For example, the question collection unit may encourage users to post questions after using a product. This allows users to post questions and receive answers from other users. Some or all of the above processes in the question collection unit may be performed using AI or not. For example, the question collection unit may use AI to automatically facilitate user question posting.

[0036] The response collection unit can collect responses. For example, the response collection unit may prompt a user to post responses from other users. The response collection unit may also collect responses based on the timing and method of collection. For example, the response collection unit may prompt a user to post a response after they have posted a question. This allows the user to see responses from other users. Some or all of the above processing in the response collection unit may be performed using AI or not. For example, the response collection unit may use AI to automatically facilitate user response posting.

[0037] The review organization section can automatically organize reviews using generative AI. For example, the generative AI organizes reviews based on review evaluation criteria and organization algorithms. For instance, the generative AI prioritizes displaying highly-rated reviews based on the evaluation criteria. Furthermore, the generative AI can analyze the content of reviews and classify them based on specific keywords. For example, the generative AI extracts frequently occurring keywords from reviews and classifies them into categories. This makes review organization more efficient when using generative AI.

[0038] The related product suggestion function can automatically suggest related products using generative AI. For example, the generative AI suggests related products based on suggestion algorithms and criteria. For instance, the generative AI suggests related products based on the user's purchase history and interests. Furthermore, the generative AI can analyze product ratings and prioritize suggesting highly-rated products. For example, the generative AI prioritizes suggesting products with many positive reviews. This makes the process of suggesting related products more efficient through the use of generative AI.

[0039] The department providing Q&A can automatically provide Q&A using generative AI. For example, the generative AI provides Q&A based on criteria for selecting questions and methods for providing answers. For example, the generative AI prioritizes displaying the most relevant answers to the user's questions. The generative AI can also analyze the content of questions and group similar questions together. For example, the generative AI can group questions about the same product. As a result, using generative AI makes the provision of Q&A more efficient.

[0040] The department providing live chat can use generative AI to automatically provide live chat. For example, the generative AI can provide live chat based on chat initiation conditions and response methods. For instance, the generative AI will start a live chat if the user is seeking detailed information about a specific product. The generative AI can also analyze the chat content and categorize it based on specific keywords. For example, the generative AI can categorize chats about how to use a product. This makes the provision of live chat more efficient by using generative AI.

[0041] The review organization unit can analyze the content of reviews and classify them based on specific keywords. For example, it can extract frequently occurring keywords from reviews and classify them into categories. It can also classify reviews based on keywords related to product features. Furthermore, it can prioritize displaying reviews containing relevant keywords based on user interests. This makes it easier for users to find the information they are looking for by analyzing the content of reviews and classifying them based on specific keywords. Some or all of the above processing in the review organization unit may be performed using or without a generative AI. For example, the review organization unit can input review content data into a generative AI and have the generative AI perform keyword-based classification.

[0042] The review organization unit can evaluate the reliability of reviews and prioritize the display of highly reliable reviews. For example, the review organization unit can analyze the past posting history of the review author to evaluate reliability. It can also evaluate reliability based on the level of detail and specificity of the review content. Furthermore, it can evaluate reliability based on ratings from other users (likes and comments). By prioritizing the display of highly reliable reviews, users can more easily obtain reliable information. The evaluation of review reliability may be performed using a generative AI or not. For example, the review organization unit can input review reliability data into a generative AI and have the generative AI perform the reliability evaluation.

[0043] The review organization unit can analyze the content of reviews and group them based on specific themes. For example, it can group reviews related to product usability. It can also group reviews related to product durability. Furthermore, it can group reviews related to product design. By grouping review content based on specific themes, it makes it easier for users to find the information they are looking for. The analysis of review content may be performed using generative AI or not. For example, the review organization unit can input review content data into a generative AI and have the generative AI perform theme-based grouping.

[0044] The review organization unit can customize how reviews are displayed by considering the attribute information of the review authors. For example, the review organization unit can display reviews based on the age group of the author. It can also display reviews based on the region of the author. Furthermore, it can display reviews based on the purchase history of the author. This allows for the display of reviews that are more relevant to the user by considering the attribute information of the review authors. The consideration of the attribute information of the review authors may be performed using a generation AI or not. For example, the review organization unit can input author attribute information data into a generation AI and have the generation AI perform the customization of the display method.

[0045] The related product suggestion unit can analyze purchase history and suggest related products based on past purchase patterns. For example, it can suggest products similar to those the user has previously purchased. It can also suggest complementary products to those the user has previously purchased. Furthermore, it can suggest related products based on the brands of products the user has previously purchased. This allows the system to suggest products that meet the user's needs by suggesting related products based on past purchase patterns. The purchase history analysis may be performed using generative AI or not. For example, the related product suggestion unit can input purchase history data into a generative AI and have the generative AI perform the purchase pattern analysis.

[0046] The department that suggests related products can analyze the ratings of related products and prioritize suggesting highly-rated products. For example, the department can prioritize suggesting products with many positive reviews. It can also prioritize suggesting products that have received high ratings from other users. Furthermore, it can prioritize suggesting products with a high average rating. By prioritizing highly-rated products, it makes it easier for users to find products that satisfy them. The analysis of related product ratings may be performed using generative AI or without generative AI. For example, the department that suggests related products can input rating data into generative AI and have the generative AI suggest highly-rated products.

[0047] The related product suggestion unit can analyze purchase history and suggest related products based on specific categories. For example, it can suggest related products based on categories the user has previously purchased. It can also suggest related products based on categories the user is interested in. Furthermore, it can suggest related products based on categories the user frequently views. This allows for the suggestion of products that match the user's interests by suggesting related products based on specific categories. The purchase history analysis may be performed using generative AI or without generative AI. For example, the related product suggestion unit can input purchase history data into generative AI and have the generative AI perform category-based suggestions.

[0048] The related product suggestion unit can suggest products that fit the user's budget, taking into account the price range of related products. For example, the related product suggestion unit can estimate the budget from the user's past purchase history and suggest products within that range. Furthermore, the related product suggestion unit can suggest related products based on the budget set by the user. In addition, the related product suggestion unit can analyze the user's purchasing patterns and suggest products that fit the budget. This supports the user's purchasing decision-making by suggesting products that fit their budget. Consideration of price range may be performed using generative AI or without generative AI. For example, the related product suggestion unit can input price data into generative AI and have the generative AI generate suggestions based on the budget.

[0049] The Q&A section can analyze the content of questions and group similar questions together for display. For example, the Q&A section can group questions about the same product. It can also group questions on the same topic. Furthermore, it can group questions on the same problem. By grouping similar questions, it makes it easier for users to find the information they are looking for. The analysis of question content may be performed using generative AI or not. For example, the Q&A section can input question data into a generative AI and have the generative AI perform the grouping of similar questions.

[0050] The Q&A service can evaluate the reliability of answers and prioritize displaying highly reliable answers. For example, the Q&A service can analyze the respondent's past answer history to evaluate reliability. It can also evaluate reliability based on the level of detail and specificity of the answer's content. Furthermore, it can evaluate reliability based on ratings from other users (likes and comments). This makes it easier for users to obtain reliable information by prioritizing the display of highly reliable answers. The evaluation of answer reliability may be performed using a generative AI or not. For example, the Q&A service can input answer data into a generative AI and have the generative AI perform the reliability evaluation.

[0051] The department providing the Q&A can analyze the content of questions and group them based on specific themes. For example, the department can group questions about how to use a product. It can also group questions about troubleshooting products. Furthermore, it can group questions about purchasing products. By grouping Q&A based on specific themes, it makes it easier for users to find the information they are looking for. The analysis of the question content may be performed using generative AI or not. For example, the department providing the Q&A can input question data into a generative AI and have the generative AI perform theme-based grouping.

[0052] The Q&A service can customize how Q&A is displayed by considering the questioner's attribute information. For example, the Q&A service can display Q&A based on the questioner's age group. It can also display Q&A based on the questioner's region. Furthermore, it can display Q&A based on the questioner's purchase history. This allows for the display of more relevant Q&A to the user by considering the questioner's attribute information. The consideration of the questioner's attribute information may be performed using a generation AI or not. For example, the Q&A service can input the questioner's attribute information data into a generation AI and have the generation AI perform the customization of the display method.

[0053] The department providing the live chat service can analyze the chat content and classify it based on specific keywords. For example, the department can classify chats about how to use a product. It can also classify chats about troubleshooting products. Furthermore, it can classify chats about purchasing products. By classifying chat content based on specific keywords, it becomes easier for users to find the information they are looking for. The analysis of the chat content may be performed using generative AI or not. For example, the department providing the live chat service can input chat data into a generative AI and have the generative AI perform classification based on keywords.

[0054] The department providing the live chat service can analyze chat history and suggest appropriate answers based on past chat content. For example, the department can suggest answers to similar questions based on past chat history. Furthermore, the department can suggest information that helps users solve problems based on past chat history. In addition, the department can suggest information based on user interests based on past chat history. This helps users solve problems by suggesting appropriate answers based on past chat content. The analysis of chat history may be performed using generative AI or without generative AI. For example, the department providing the live chat service can input chat history data into a generative AI and have the AI ​​suggest appropriate answers.

[0055] The department providing the live chat service can analyze the chat content and group it based on specific themes. For example, the department can group chats about how to use a product. It can also group chats about troubleshooting a product. Furthermore, it can group chats about purchasing a product. By grouping chat content based on specific themes, it becomes easier for users to find the information they are looking for. The analysis of the chat content may be performed using generative AI or not. For example, the department providing the live chat service can input chat data into a generative AI and have the generative AI perform theme-based grouping.

[0056] A live chat service provider can customize how chats are displayed by considering the attribute information of the chat participants. For example, the service provider can display chats based on the age group of the participants. It can also display chats based on the region of the participants. Furthermore, it can display chats based on the purchase history of the participants. This allows for the display of more relevant chats to users by considering the attribute information of the chat participants. Consideration of participant attribute information may be performed using or without a generative AI. For example, the service provider can input participant attribute data into a generative AI and have the AI ​​perform the customization of the display method.

[0057] The review collection unit can analyze the frequency of review submissions and determine the optimal collection timing. For example, the review collection unit can prompt users to submit reviews immediately after purchasing a product. It can also prompt users to submit reviews after they have used the product. Furthermore, it can prompt users to submit reviews if they are satisfied with the product. By determining the optimal collection timing, reviews can be collected efficiently. The analysis of review submission frequency may be performed using generative AI or without generative AI. For example, the review collection unit can input submission frequency data into generative AI and have the generative AI determine the optimal collection timing.

[0058] The review collection unit can customize its collection method by considering the attribute information of the review writers. For example, the review collection unit can adjust its collection method based on the age group of the writers. It can also adjust its collection method based on the region of the writers. Furthermore, it can adjust its collection method based on the purchase history of the writers. This allows for the collection of more relevant reviews by considering the attribute information of the review writers. The consideration of writer attribute information may be performed using generative AI or not. For example, the review collection unit can input writer attribute information data into a generative AI and have the generative AI perform the customization of the collection method.

[0059] The question collection unit can analyze the frequency of question submissions and determine the optimal timing for collection. For example, the question collection unit can prompt users to submit questions immediately after purchasing a product. It can also prompt users to submit questions after using the product. Furthermore, it can prompt users to submit questions if they are satisfied with the product. By determining the optimal timing for collection, questions can be collected efficiently. The analysis of question submission frequency may be performed using generative AI or not. For example, the question collection unit can input submission frequency data into a generative AI and have the generative AI determine the optimal timing for collection.

[0060] The question collection unit can customize its collection method by considering the questioner's attribute information. For example, the question collection unit can adjust its collection method based on the questioner's age group. It can also adjust its collection method based on the questioner's region. Furthermore, it can adjust its collection method based on the questioner's purchase history. This allows for the collection of more relevant questions by considering the questioner's attribute information. The consideration of the questioner's attribute information may be performed using generative AI or not. For example, the question collection unit can input the questioner's attribute information data into the generative AI and have the generative AI perform the customization of the collection method.

[0061] The unit responsible for collecting responses can analyze the frequency of responses and determine the optimal timing for collection. For example, the unit can prompt users to post responses immediately after they post a question. It can also encourage users to post responses if they are satisfied with the question. Furthermore, it can advise users to refrain from posting responses if they are dissatisfied with the question. By determining the optimal timing for collection, responses can be collected efficiently. The analysis of response posting frequency may be performed using generative AI or without generative AI. For example, the unit responsible for collecting responses can input posting frequency data into a generative AI and have the generative AI determine the optimal timing for collection.

[0062] The unit that collects responses can customize its collection method by taking into account the respondent's attribute information. For example, the unit can adjust the collection method based on the respondent's age group. It can also adjust the collection method based on the respondent's region. Furthermore, it can adjust the collection method based on the respondent's purchase history. This allows for the collection of more relevant responses by considering the respondent's attribute information. The consideration of the respondent's attribute information may be performed using generative AI or not. For example, the unit that collects responses can input the respondent's attribute information data into the generative AI and have the generative AI perform the customization of the collection method.

[0063] The unit that collects responses can analyze the content of the responses and group them based on specific themes. For example, the unit can group responses regarding how to use a product. It can also group responses regarding troubleshooting a product. Furthermore, it can group responses regarding purchasing a product. By grouping responses based on specific themes, it becomes easier for users to find the information they are looking for. The analysis of the content of the responses may be performed using generative AI or not. For example, the unit that collects responses can input the response data into a generative AI and have the generative AI perform theme-based grouping.

[0064] The unit that collects responses can evaluate the reliability of the responses and prioritize collecting highly reliable responses. For example, the unit can analyze the respondent's past response history to evaluate reliability. It can also evaluate reliability based on the level of detail and specificity of the response content. Furthermore, it can evaluate reliability based on ratings from other users (likes and comments). This makes it easier for users to obtain reliable information by prioritizing the collection of highly reliable responses. The evaluation of response reliability may be performed using generative AI or without generative AI. For example, the unit that collects responses can input response data into a generative AI and have the generative AI perform the reliability evaluation.

[0065] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0066] Shopping support systems can analyze a user's purchase history and provide personalized product recommendations based on their preferences. For example, they can suggest similar brands and categories based on the brands and categories of products a user has previously purchased. They can also analyze the trends in products a user frequently buys and suggest new products that match those trends. Furthermore, if a user tends to purchase products related to a particular season or event, they can suggest products that are appropriate for that season or event. This makes it easier for users to find products that suit their preferences, improving the shopping experience.

[0067] The shopping support system can compare a user's purchase history with that of other users and prioritize displaying reviews and ratings from users with similar purchasing patterns. For example, it can display reviews from other users who have purchased the same product as the user in the past. It can also display ratings from other users with similar interests for products the user is interested in. Furthermore, if a user frequently purchases products in a particular category, it can prioritize displaying reviews from other users about products in that category. This allows users to refer to the opinions of other users with similar purchasing patterns and obtain more reliable information.

[0068] A shopping support system can analyze a user's purchase history and suggest complementary products to items they have previously bought. For example, if a user buys a camera, it can suggest lenses and accessories suitable for that camera. If a user buys furniture, it can suggest interior items that match that furniture. Furthermore, if a user buys sports equipment, it can suggest other items related to that sport. This makes it easier for users to find complementary products to make better use of their purchases, improving the shopping experience.

[0069] The shopping support system analyzes the user's purchase history and can suggest products with similar ratings based on the user's past purchases. For example, if a user purchases a highly-rated product, it can suggest other highly-rated products. It can also suggest other products from a specific brand if the user highly rates products from that brand. Furthermore, if a user highly rates products in a specific category, it can suggest other products in that category. This makes it easier for users to find reliable products based on their ratings, improving the shopping experience.

[0070] A shopping support system can analyze a user's purchase history and provide information on how to use and maintain products they have previously purchased. For example, if a user purchases an electronic appliance, the system can provide instructions on how to use and maintain that appliance. Similarly, if a user purchases furniture, it can provide instructions on how to assemble and care for that furniture. Furthermore, if a user purchases sporting goods, it can provide instructions on how to use and store those goods. This allows users to obtain information to use their purchased products more effectively, improving their overall shopping experience.

[0071] The following briefly describes the processing flow for example form 1.

[0072] Step 1: The review organization section automatically organizes reviews using generative AI. For example, if a user is looking for reviews about a specific product, the generative AI automatically collects, organizes, and displays reviews related to that product. It can also organize reviews based on review rating criteria and organization algorithms. For example, it can prioritize displaying highly-rated reviews based on review rating criteria. Step 2: The related product suggestion section automatically suggests related products using generative AI. For example, if a user is trying to purchase a specific product, the generative AI will suggest other products related to that product. It can also suggest related products based on suggestion algorithms and criteria. For example, it can suggest related products based on the user's purchase history and interests. Step 3: The Q&A section automatically provides Q&A using generative AI. For example, if a user wants to know how to use a particular product, the generative AI automatically collects and displays the answer to that question. It can also provide Q&A based on question selection criteria and answer delivery methods. For example, it can prioritize displaying the most relevant answers to the user's question. Step 4: The department providing the live chat automatically provides live chats using generative AI. For example, users can chat with other buyers in real time and ask questions directly about product details and user experiences. It can also provide live chats based on the conditions for starting a chat and how to respond. For example, if a user is seeking detailed information about a specific product, a live chat will be initiated.

[0073] (Example of form 2) The shopping support system according to an embodiment of the present invention is a system that utilizes generative AI to build a community where users can make purchases with peace of mind. This shopping support system uses generative AI to automatically organize and provide reviews and Q&A from other users about the product the user is trying to purchase. Next, the generative AI automatically suggests related products. Furthermore, to promote communication among users, the generative AI provides a Q&A section. It also enables live chat with actual buyers. This makes it easy for users to check reviews and Q&A from other users and find related products. In addition, they can obtain reliable information through live chat with actual buyers, allowing them to make purchases with peace of mind. This realizes a highly reliable shopping experience. For example, the generative AI automatically organizes and provides reviews and Q&A from other users about the product the user is trying to purchase. For example, if a user is looking for reviews about a specific product, the generative AI automatically collects, organizes, and displays reviews related to that product. This makes it easy for users to check the opinions of other users. Next, the generative AI automatically suggests related products. For example, if a user is trying to purchase a specific product, the generative AI suggests other products related to that product. This makes it easier for users to find products that meet their needs. Furthermore, to facilitate communication among users, a generation AI provides a Q&A section. Users can post their questions and receive answers from other users. The generation AI automatically organizes these questions and answers and provides relevant information. For example, if a user wants to know how to use a particular product, the generation AI will automatically collect and display answers to that question. It also enables live chat with actual buyers. Users can chat with other buyers in real time and ask questions directly about product details and user experiences. This allows users to obtain reliable information and make purchases with confidence. This system makes it easy for users to check other users' reviews and Q&A, making it easier to find related products.Furthermore, users can obtain reliable information through live chats with actual buyers, allowing them to purchase with confidence. This results in a trustworthy shopping experience. As a result, the shopping support system can build a community where users can purchase with peace of mind, and facilitate communication among users through reviews, related products, Q&A, and live chat.

[0074] The shopping support system according to this embodiment includes a review organization unit, a related product suggestion unit, a Q&A provision unit, and a live chat provision unit. The review organization unit automatically organizes reviews using a generation AI. For example, if a user is looking for reviews about a specific product, the generation AI automatically collects, organizes, and displays reviews related to that product. The review organization unit can also organize reviews based on review evaluation criteria and organization algorithms. For example, the review organization unit prioritizes displaying highly-rated reviews based on review evaluation criteria. The related product suggestion unit automatically suggests related products using a generation AI. For example, if a user is trying to purchase a specific product, the generation AI suggests other products related to that product. The related product suggestion unit can also suggest related products based on a suggestion algorithm and suggestion criteria. For example, the related product suggestion unit suggests related products based on the user's purchase history and interests. The Q&A provision unit automatically provides Q&A using a generation AI. The Q&A section, for example, uses a generating AI to automatically collect and display answers to questions when a user wants to know how to use a particular product. The Q&A section can also provide Q&A based on question selection criteria and answer delivery methods. For example, it might prioritize displaying the most relevant answers to the user's questions. The live chat section uses a generating AI to automatically provide live chat. For example, the live chat section allows users to chat with other buyers in real time and directly ask questions about product details and user experiences. The live chat section can also provide live chat based on chat initiation conditions and response methods. For example, the live chat section might initiate a live chat when a user is seeking detailed information about a specific product.As a result, the shopping support system according to this embodiment can build a community where users can make purchases with peace of mind, and can promote communication among users through reviews, related products, Q&A, and live chat.

[0075] The review organization section uses generative AI to automatically organize reviews. Specifically, the generative AI utilizes natural language processing technology to automatically collect, organize, and display reviews related to a particular product when a user is searching for reviews about that product. The generative AI can analyze the content of reviews and classify them into positive and negative ratings. For example, the generative AI can extract keywords such as "good," "bad," "recommended," and "dissatisfied" from reviews and classify them based on these keywords. It can also organize reviews based on review evaluation criteria and organization algorithms. For example, the review organization section prioritizes displaying highly-rated reviews based on review evaluation criteria. Furthermore, the generative AI can consider the past review history and ratings of the user who wrote the review in order to evaluate the reliability of the review. This prioritizes displaying reliable reviews, making them easier for users to refer to. The generative AI can also summarize the content of reviews, allowing users to grasp important information in a short amount of time. For example, it can improve user convenience by summarizing long reviews and displaying only the main points. This allows the review organization section to efficiently browse reviews and use them to help users choose products.

[0076] The related products suggestion department uses generative AI to automatically suggest related products. Specifically, the generative AI analyzes the user's purchase history and interests and suggests related products based on that analysis. For example, if a user is about to purchase a specific product, the generative AI will suggest other products related to that product. The generative AI selects the most suitable related products by considering product categories and characteristics, the user's past purchase history, browsing history, etc. It can also suggest related products based on suggestion algorithms and criteria. For example, the generative AI will prioritize suggesting products similar to or in the same category as products the user has previously purchased. Furthermore, the generative AI can analyze the purchase patterns and trends of other users and suggest related products based on that analysis. For example, by suggesting products that other users who purchased the same product also purchased, it can provide related products that are likely to interest the user. In addition, the generative AI can collect user feedback and continuously improve the accuracy of its suggestions. For example, if a user purchases a suggested product, the suggestion algorithm will be adjusted based on that information to provide more accurate suggestions. As a result, the related products suggestion department can efficiently suggest products that users are interested in and improve the shopping experience.

[0077] The Q&A section uses generative AI to automatically provide Q&A. Specifically, the generative AI analyzes user questions, automatically collects the most relevant answers, and displays them. For example, if a user wants to know how to use a particular product, the generative AI will automatically collect and display the answers to that question. The generative AI gathers information from past Q&A databases, product manuals, and relevant forum posts to provide the most relevant answers. It can also provide Q&A based on question selection criteria and answer delivery methods. For example, the generative AI prioritizes displaying the most relevant answers to user questions. Furthermore, the generative AI utilizes natural language processing techniques to understand the intent of user questions and provide appropriate answers. For example, even if a user asks an ambiguous question, the generative AI can analyze its intent and provide an appropriate answer. The generative AI can also collect user feedback and continuously improve the accuracy of its answers. For example, it can evaluate whether users were satisfied with the answers provided and adjust the answer algorithm based on that information. This allows the Q&A section to enable users to obtain information quickly and accurately, improving the shopping experience.

[0078] The department providing live chat will use generative AI to automatically deliver live chat. Specifically, the generative AI will provide an environment where users can chat with other buyers in real time and directly ask questions about product details and usage. The generative AI will analyze user questions and comments and provide appropriate answers and information. It can also provide live chat based on the conditions for starting the live chat and the response method. For example, if a user is asking for detailed information about a particular product, the generative AI will start a live chat to provide that information. The generative AI can refer to past chat history and relevant databases to answer user questions quickly and accurately. Furthermore, the generative AI can collect user feedback and continuously improve the way it responds to chats. For example, it can evaluate whether the user was satisfied with the answers provided and adjust the chat algorithm based on that information. The generative AI can also efficiently handle situations where multiple users are chatting simultaneously. For example, the generative AI will process user questions based on priority and respond quickly to important questions. In this way, the department providing live chat can provide an environment where users can obtain information in real time and improve the shopping experience.

[0079] The review collection unit can collect reviews. For example, the review collection unit might encourage users to post reviews after they have purchased a product. The review collection unit can also collect reviews based on the timing and method of collection. For example, the review collection unit might encourage users to post reviews after they have used a product. This allows users to see the opinions of other users by collecting reviews. Some or all of the above processes in the review collection unit may be performed using AI or not. For example, the review collection unit may use AI to automatically encourage users to post reviews.

[0080] The question collection unit can collect questions. For example, the question collection unit may encourage users to post questions about products. The question collection unit may also collect questions based on the timing and method of collection. For example, the question collection unit may encourage users to post questions after using a product. This allows users to post questions and receive answers from other users. Some or all of the above processes in the question collection unit may be performed using AI or not. For example, the question collection unit may use AI to automatically facilitate user question posting.

[0081] The response collection unit can collect responses. For example, the response collection unit may prompt a user to post responses from other users. The response collection unit may also collect responses based on the timing and method of collection. For example, the response collection unit may prompt a user to post a response after they have posted a question. This allows the user to see responses from other users. Some or all of the above processing in the response collection unit may be performed using AI or not. For example, the response collection unit may use AI to automatically facilitate user response posting.

[0082] The review organization section can automatically organize reviews using generative AI. For example, the generative AI organizes reviews based on review evaluation criteria and organization algorithms. For instance, the generative AI prioritizes displaying highly-rated reviews based on the evaluation criteria. Furthermore, the generative AI can analyze the content of reviews and classify them based on specific keywords. For example, the generative AI extracts frequently occurring keywords from reviews and classifies them into categories. This makes review organization more efficient when using generative AI.

[0083] The related product suggestion function can automatically suggest related products using generative AI. For example, the generative AI suggests related products based on suggestion algorithms and criteria. For instance, the generative AI suggests related products based on the user's purchase history and interests. Furthermore, the generative AI can analyze product ratings and prioritize suggesting highly-rated products. For example, the generative AI prioritizes suggesting products with many positive reviews. This makes the process of suggesting related products more efficient through the use of generative AI.

[0084] The department providing Q&A can automatically provide Q&A using generative AI. For example, the generative AI provides Q&A based on criteria for selecting questions and methods for providing answers. For example, the generative AI prioritizes displaying the most relevant answers to the user's questions. The generative AI can also analyze the content of questions and group similar questions together. For example, the generative AI can group questions about the same product. As a result, using generative AI makes the provision of Q&A more efficient.

[0085] The department providing live chat can use generative AI to automatically provide live chat. For example, the generative AI can provide live chat based on chat initiation conditions and response methods. For instance, the generative AI will start a live chat if the user is seeking detailed information about a specific product. The generative AI can also analyze the chat content and categorize it based on specific keywords. For example, the generative AI can categorize chats about how to use a product. This makes the provision of live chat more efficient by using generative AI.

[0086] The review sorting unit can estimate the user's emotions and adjust the display order of reviews based on the estimated emotions. For example, if the user has positive emotions, the review sorting unit can prioritize displaying positive reviews. It can also prioritize displaying negative reviews if the user has negative emotions. Furthermore, if the user has neutral emotions, the review sorting unit can display balanced reviews. This allows for the display of more appropriate reviews by adjusting the display order of reviews according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review sorting unit may be performed using AI or not. For example, the review sorting unit can input user emotion data into a generative AI and have the generative AI adjust the display order of reviews.

[0087] The review organization unit can analyze the content of reviews and classify them based on specific keywords. For example, it can extract frequently occurring keywords from reviews and classify them into categories. It can also classify reviews based on keywords related to product features. Furthermore, it can prioritize displaying reviews containing relevant keywords based on user interests. This makes it easier for users to find the information they are looking for by analyzing the content of reviews and classifying them based on specific keywords. Some or all of the above processing in the review organization unit may be performed using or without a generative AI. For example, the review organization unit can input review content data into a generative AI and have the generative AI perform keyword-based classification.

[0088] The review organization unit can evaluate the reliability of reviews and prioritize the display of highly reliable reviews. For example, the review organization unit can analyze the past posting history of the review author to evaluate reliability. It can also evaluate reliability based on the level of detail and specificity of the review content. Furthermore, it can evaluate reliability based on ratings from other users (likes and comments). By prioritizing the display of highly reliable reviews, users can more easily obtain reliable information. The evaluation of review reliability may be performed using a generative AI or not. For example, the review organization unit can input review reliability data into a generative AI and have the generative AI perform the reliability evaluation.

[0089] The review sorting unit can estimate the user's sentiment and adjust the importance of reviews based on that estimated sentiment. For example, if the user has a positive sentiment, the sorting unit can increase the importance of positive reviews. It can also increase the importance of negative reviews if the user has a negative sentiment. Furthermore, if the user has a neutral sentiment, the sorting unit can increase the importance of balanced reviews. This allows for the display of more relevant reviews by adjusting the importance of reviews according to the user's sentiment. Sentiment estimation is achieved using a sentiment estimation function, such as a sentiment engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review sorting unit may be performed using AI or not. For example, the review sorting unit can input user sentiment data into a generative AI and have the generative AI adjust the importance of reviews.

[0090] The review organization unit can analyze the content of reviews and group them based on specific themes. For example, it can group reviews related to product usability. It can also group reviews related to product durability. Furthermore, it can group reviews related to product design. By grouping review content based on specific themes, it makes it easier for users to find the information they are looking for. The analysis of review content may be performed using generative AI or not. For example, the review organization unit can input review content data into a generative AI and have the generative AI perform theme-based grouping.

[0091] The review organization unit can customize how reviews are displayed by considering the attribute information of the review authors. For example, the review organization unit can display reviews based on the age group of the author. It can also display reviews based on the region of the author. Furthermore, it can display reviews based on the purchase history of the author. This allows for the display of reviews that are more relevant to the user by considering the attribute information of the review authors. The consideration of the attribute information of the review authors may be performed using a generation AI or not. For example, the review organization unit can input author attribute information data into a generation AI and have the generation AI perform the customization of the display method.

[0092] The related product suggestion unit can estimate the user's emotions and adjust its suggested product method based on those emotions. For example, if the user has positive emotions, the unit can suggest products with many positive reviews. If the user has negative emotions, it can also suggest products with few negative reviews. Furthermore, if the user has neutral emotions, it can suggest products with balanced ratings. By adjusting the suggested product method according to the user's emotions, more appropriate products can be suggested. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the related product suggestion unit may be performed using AI or not. For example, the related product suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the suggestion method.

[0093] The related product suggestion unit can analyze purchase history and suggest related products based on past purchase patterns. For example, it can suggest products similar to those the user has previously purchased. It can also suggest complementary products to those the user has previously purchased. Furthermore, it can suggest related products based on the brands of products the user has previously purchased. This allows the system to suggest products that meet the user's needs by suggesting related products based on past purchase patterns. The purchase history analysis may be performed using generative AI or not. For example, the related product suggestion unit can input purchase history data into a generative AI and have the generative AI perform the purchase pattern analysis.

[0094] The department that suggests related products can analyze the ratings of related products and prioritize suggesting highly-rated products. For example, the department can prioritize suggesting products with many positive reviews. It can also prioritize suggesting products that have received high ratings from other users. Furthermore, it can prioritize suggesting products with a high average rating. By prioritizing highly-rated products, it makes it easier for users to find products that satisfy them. The analysis of related product ratings may be performed using generative AI or without generative AI. For example, the department that suggests related products can input rating data into generative AI and have the generative AI suggest highly-rated products.

[0095] The related products suggestion unit can estimate the user's emotions and adjust the display order of related products based on the estimated emotions. For example, if the user has positive emotions, the related products suggestion unit can display products with many positive reviews at the top. Similarly, if the user has negative emotions, it can display products with few negative reviews at the top. Furthermore, if the user has neutral emotions, it can display products with balanced ratings at the top. This allows for the display of more appropriate products by adjusting the display order of related products according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the related products suggestion unit may be performed using AI or not. For example, the related products suggestion unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the display order.

[0096] The related product suggestion unit can analyze purchase history and suggest related products based on specific categories. For example, it can suggest related products based on categories the user has previously purchased. It can also suggest related products based on categories the user is interested in. Furthermore, it can suggest related products based on categories the user frequently views. This allows for the suggestion of products that match the user's interests by suggesting related products based on specific categories. The purchase history analysis may be performed using generative AI or without generative AI. For example, the related product suggestion unit can input purchase history data into generative AI and have the generative AI perform category-based suggestions.

[0097] The related product suggestion unit can suggest products that fit the user's budget, taking into account the price range of related products. For example, the related product suggestion unit can estimate the budget from the user's past purchase history and suggest products within that range. Furthermore, the related product suggestion unit can suggest related products based on the budget set by the user. In addition, the related product suggestion unit can analyze the user's purchasing patterns and suggest products that fit the budget. This supports the user's purchasing decision-making by suggesting products that fit their budget. Consideration of price range may be performed using generative AI or without generative AI. For example, the related product suggestion unit can input price data into generative AI and have the generative AI generate suggestions based on the budget.

[0098] The Q&A section can estimate the user's emotions and adjust the display method of the Q&A based on the estimated emotions. For example, if the user has positive emotions, the Q&A section can prioritize displaying positive answers. It can also prioritize displaying negative answers if the user has negative emotions. Furthermore, if the user has neutral emotions, the Q&A section can display balanced answers. This allows for the display of more appropriate answers by adjusting the Q&A display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the Q&A section may be performed using AI or not. For example, the Q&A section can input user emotion data into a generative AI and have the generative AI adjust the display method.

[0099] The Q&A section can analyze the content of questions and group similar questions together for display. For example, the Q&A section can group questions about the same product. It can also group questions on the same topic. Furthermore, it can group questions on the same problem. By grouping similar questions, it makes it easier for users to find the information they are looking for. The analysis of question content may be performed using generative AI or not. For example, the Q&A section can input question data into a generative AI and have the generative AI perform the grouping of similar questions.

[0100] The Q&A service can evaluate the reliability of answers and prioritize displaying highly reliable answers. For example, the Q&A service can analyze the respondent's past answer history to evaluate reliability. It can also evaluate reliability based on the level of detail and specificity of the answer's content. Furthermore, it can evaluate reliability based on ratings from other users (likes and comments). This makes it easier for users to obtain reliable information by prioritizing the display of highly reliable answers. The evaluation of answer reliability may be performed using a generative AI or not. For example, the Q&A service can input answer data into a generative AI and have the generative AI perform the reliability evaluation.

[0101] The Q&A section can estimate the user's emotions and adjust the importance of the Q&A based on the estimated emotions. For example, if the user has positive emotions, the Q&A section can increase the importance of positive answers. It can also increase the importance of negative answers if the user has negative emotions. Furthermore, if the user has neutral emotions, the Q&A section can increase the importance of balanced answers. This allows for the display of more appropriate answers by adjusting the importance of Q&A according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the Q&A section may be performed using AI or not. For example, the Q&A section can input user emotion data into a generative AI and have the generative AI perform the importance adjustment.

[0102] The department providing the Q&A can analyze the content of questions and group them based on specific themes. For example, the department can group questions about how to use a product. It can also group questions about troubleshooting products. Furthermore, it can group questions about purchasing products. By grouping Q&A based on specific themes, it makes it easier for users to find the information they are looking for. The analysis of the question content may be performed using generative AI or not. For example, the department providing the Q&A can input question data into a generative AI and have the generative AI perform theme-based grouping.

[0103] The Q&A service can customize how Q&A is displayed by considering the questioner's attribute information. For example, the Q&A service can display Q&A based on the questioner's age group. It can also display Q&A based on the questioner's region. Furthermore, it can display Q&A based on the questioner's purchase history. This allows for the display of more relevant Q&A to the user by considering the questioner's attribute information. The consideration of the questioner's attribute information may be performed using a generation AI or not. For example, the Q&A service can input the questioner's attribute information data into a generation AI and have the generation AI perform the customization of the display method.

[0104] The live chat service provider can estimate the user's emotions and adjust its response based on those emotions. For example, if the user has positive emotions, the live chat service provider can provide a friendly response. If the user has negative emotions, the live chat service provider can provide a polite and careful response. Furthermore, if the user has neutral emotions, the live chat service provider can provide a standard response. By adjusting the live chat response according to the user's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the live chat service provider may be performed using AI or not. For example, the live chat service provider can input user emotion data into a generative AI and have the generative AI adjust the response method.

[0105] The department providing the live chat service can analyze the chat content and classify it based on specific keywords. For example, the department can classify chats about how to use a product. It can also classify chats about troubleshooting products. Furthermore, it can classify chats about purchasing products. By classifying chat content based on specific keywords, it becomes easier for users to find the information they are looking for. The analysis of the chat content may be performed using generative AI or not. For example, the department providing the live chat service can input chat data into a generative AI and have the generative AI perform classification based on keywords.

[0106] The department providing the live chat service can analyze chat history and suggest appropriate answers based on past chat content. For example, the department can suggest answers to similar questions based on past chat history. Furthermore, the department can suggest information that helps users solve problems based on past chat history. In addition, the department can suggest information based on user interests based on past chat history. This helps users solve problems by suggesting appropriate answers based on past chat content. The analysis of chat history may be performed using generative AI or without generative AI. For example, the department providing the live chat service can input chat history data into a generative AI and have the AI ​​suggest appropriate answers.

[0107] The live chat service provider can estimate the user's emotions and determine the priority of the live chat based on the estimated emotions. For example, if a user has an urgent problem, the live chat service provider will prioritize their response. Alternatively, if a user has positive emotions, the live chat service provider can respond with normal priority. Furthermore, if a user has negative emotions, the live chat service provider can respond quickly. This allows for faster responses by prioritizing live chats according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the live chat service provider may be performed using AI or not. For example, the live chat service provider can input user emotion data into a generative AI and have the generative AI determine the priorities.

[0108] The department providing the live chat service can analyze the chat content and group it based on specific themes. For example, the department can group chats about how to use a product. It can also group chats about troubleshooting a product. Furthermore, it can group chats about purchasing a product. By grouping chat content based on specific themes, it becomes easier for users to find the information they are looking for. The analysis of the chat content may be performed using generative AI or not. For example, the department providing the live chat service can input chat data into a generative AI and have the generative AI perform theme-based grouping.

[0109] A live chat service provider can customize how chats are displayed by considering the attribute information of the chat participants. For example, the service provider can display chats based on the age group of the participants. It can also display chats based on the region of the participants. Furthermore, it can display chats based on the purchase history of the participants. This allows for the display of more relevant chats to users by considering the attribute information of the chat participants. Consideration of participant attribute information may be performed using or without a generative AI. For example, the service provider can input participant attribute data into a generative AI and have the AI ​​perform the customization of the display method.

[0110] The review collection unit can estimate the user's sentiment and adjust the review collection method based on the estimated user sentiment. For example, if a user has a positive sentiment, the review collection unit may encourage them to post a review. Conversely, if a user has a negative sentiment, the review collection unit may encourage them to refrain from posting a review. Furthermore, if a user has a neutral sentiment, the review collection unit may encourage them to post a balanced review. This allows for the collection of more appropriate reviews by adjusting the review collection method according to the user's sentiment. Sentiment estimation is achieved using a sentiment estimation function, such as a sentiment engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review collection unit may be performed using AI or not. For example, the review collection unit can input user sentiment data into a generative AI and have the generative AI adjust the collection method.

[0111] The review collection unit can analyze the frequency of review submissions and determine the optimal collection timing. For example, the review collection unit can prompt users to submit reviews immediately after purchasing a product. It can also prompt users to submit reviews after they have used the product. Furthermore, it can prompt users to submit reviews if they are satisfied with the product. By determining the optimal collection timing, reviews can be collected efficiently. The analysis of review submission frequency may be performed using generative AI or without generative AI. For example, the review collection unit can input submission frequency data into generative AI and have the generative AI determine the optimal collection timing.

[0112] The review collection unit can estimate the user's emotions and determine the priority of review collection based on the estimated emotions. For example, if the user has positive emotions, the review collection unit will prioritize collecting reviews. It can also refrain from collecting reviews if the user has negative emotions. Furthermore, if the user has neutral emotions, the review collection unit can prioritize collecting balanced reviews. This allows for the collection of more appropriate reviews by determining the priority of review collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review collection unit may be performed using AI or not. For example, the review collection unit can input user emotion data into a generative AI and have the generative AI determine the collection priority.

[0113] The review collection unit can customize its collection method by considering the attribute information of the review writers. For example, the review collection unit can adjust its collection method based on the age group of the writers. It can also adjust its collection method based on the region of the writers. Furthermore, it can adjust its collection method based on the purchase history of the writers. This allows for the collection of more relevant reviews by considering the attribute information of the review writers. The consideration of writer attribute information may be performed using generative AI or not. For example, the review collection unit can input writer attribute information data into a generative AI and have the generative AI perform the customization of the collection method.

[0114] The question collection unit can estimate the user's emotions and adjust the question collection method based on the estimated emotions. For example, if a user has positive emotions, the question collection unit may encourage them to post questions. Conversely, if a user has negative emotions, the question collection unit may encourage them to refrain from posting questions. Furthermore, if a user has neutral emotions, the question collection unit may encourage them to post balanced questions. This allows for the collection of more appropriate questions by adjusting the question collection method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the question collection unit may be performed using AI or not. For example, the question collection unit can input user emotion data into a generative AI and have the generative AI adjust the collection method.

[0115] The question collection unit can analyze the frequency of question submissions and determine the optimal timing for collection. For example, the question collection unit can prompt users to submit questions immediately after purchasing a product. It can also prompt users to submit questions after using the product. Furthermore, it can prompt users to submit questions if they are satisfied with the product. By determining the optimal timing for collection, questions can be collected efficiently. The analysis of question submission frequency may be performed using generative AI or not. For example, the question collection unit can input submission frequency data into a generative AI and have the generative AI determine the optimal timing for collection.

[0116] The question collection unit can estimate the user's emotions and determine the priority of question collection based on the estimated emotions. For example, if the user has positive emotions, the question collection unit will prioritize collecting questions. Conversely, if the user has negative emotions, the question collection unit may refrain from collecting questions. Furthermore, if the user has neutral emotions, the question collection unit may prioritize collecting balanced questions. This allows for the collection of more appropriate questions by determining the priority of question collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the question collection unit may be performed using AI or not. For example, the question collection unit can input user emotion data into a generative AI and have the generative AI determine the collection priority.

[0117] The question collection unit can customize its collection method by considering the questioner's attribute information. For example, the question collection unit can adjust its collection method based on the questioner's age group. It can also adjust its collection method based on the questioner's region. Furthermore, it can adjust its collection method based on the questioner's purchase history. This allows for the collection of more relevant questions by considering the questioner's attribute information. The consideration of the questioner's attribute information may be performed using generative AI or not. For example, the question collection unit can input the questioner's attribute information data into the generative AI and have the generative AI perform the customization of the collection method.

[0118] The response collection unit can estimate the user's emotions and adjust the response collection method based on the estimated emotions. For example, if a user has positive emotions, the response collection unit may encourage them to submit a response. Conversely, if a user has negative emotions, the response collection unit may encourage them to refrain from submitting a response. Furthermore, if a user has neutral emotions, the response collection unit may encourage them to submit a balanced response. This allows for the collection of more appropriate responses by adjusting the response collection method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response collection unit may be performed using AI or not. For example, the response collection unit can input user emotion data into a generative AI and have the generative AI adjust the collection method.

[0119] The unit responsible for collecting responses can analyze the frequency of responses and determine the optimal timing for collection. For example, the unit can prompt users to post responses immediately after they post a question. It can also encourage users to post responses if they are satisfied with the question. Furthermore, it can advise users to refrain from posting responses if they are dissatisfied with the question. By determining the optimal timing for collection, responses can be collected efficiently. The analysis of response posting frequency may be performed using generative AI or without generative AI. For example, the unit responsible for collecting responses can input posting frequency data into a generative AI and have the generative AI determine the optimal timing for collection.

[0120] The response collection unit can estimate the user's emotions and determine the priority of response collection based on the estimated emotions. For example, if the user has positive emotions, the response collection unit will prioritize collecting responses. It can also refrain from collecting responses if the user has negative emotions. Furthermore, if the user has neutral emotions, the response collection unit can prioritize collecting balanced responses. This allows for the collection of more appropriate responses by determining the priority of response collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response collection unit may be performed using AI or not. For example, the response collection unit can input user emotion data into a generative AI and have the generative AI determine the collection priority.

[0121] The unit that collects responses can customize its collection method by taking into account the respondent's attribute information. For example, the unit can adjust the collection method based on the respondent's age group. It can also adjust the collection method based on the respondent's region. Furthermore, it can adjust the collection method based on the respondent's purchase history. This allows for the collection of more relevant responses by considering the respondent's attribute information. The consideration of the respondent's attribute information may be performed using generative AI or not. For example, the unit that collects responses can input the respondent's attribute information data into the generative AI and have the generative AI perform the customization of the collection method.

[0122] The unit that collects responses can analyze the content of the responses and group them based on specific themes. For example, the unit can group responses regarding how to use a product. It can also group responses regarding troubleshooting a product. Furthermore, it can group responses regarding purchasing a product. By grouping responses based on specific themes, it becomes easier for users to find the information they are looking for. The analysis of the content of the responses may be performed using generative AI or not. For example, the unit that collects responses can input the response data into a generative AI and have the generative AI perform theme-based grouping.

[0123] The unit that collects responses can evaluate the reliability of the responses and prioritize collecting highly reliable responses. For example, the unit can analyze the respondent's past response history to evaluate reliability. It can also evaluate reliability based on the level of detail and specificity of the response content. Furthermore, it can evaluate reliability based on ratings from other users (likes and comments). This makes it easier for users to obtain reliable information by prioritizing the collection of highly reliable responses. The evaluation of response reliability may be performed using generative AI or without generative AI. For example, the unit that collects responses can input response data into a generative AI and have the generative AI perform the reliability evaluation.

[0124] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0125] Shopping support systems can analyze a user's purchase history and provide personalized product recommendations based on their preferences. For example, they can suggest similar brands and categories based on the brands and categories of products a user has previously purchased. They can also analyze the trends in products a user frequently buys and suggest new products that match those trends. Furthermore, if a user tends to purchase products related to a particular season or event, they can suggest products that are appropriate for that season or event. This makes it easier for users to find products that suit their preferences, improving the shopping experience.

[0126] The shopping support system can estimate the user's emotions and adjust the timing of product suggestions based on those emotions. For example, if the user has positive emotions, it will proactively suggest products. If the user has negative emotions, it may refrain from suggesting products or suggest relaxing products. Furthermore, if the user has neutral emotions, it can suggest products at the usual timing. By suggesting products at the appropriate time according to the user's emotions, it can increase the user's willingness to purchase.

[0127] The shopping support system can compare a user's purchase history with that of other users and prioritize displaying reviews and ratings from users with similar purchasing patterns. For example, it can display reviews from other users who have purchased the same product as the user in the past. It can also display ratings from other users with similar interests for products the user is interested in. Furthermore, if a user frequently purchases products in a particular category, it can prioritize displaying reviews from other users about products in that category. This allows users to refer to the opinions of other users with similar purchasing patterns and obtain more reliable information.

[0128] The shopping support system can estimate the user's emotions and customize how reviews are displayed based on those emotions. For example, if a user has positive emotions, positive reviews will be prioritized. Conversely, if a user has negative emotions, negative reviews can be prioritized. Furthermore, if a user has neutral emotions, balanced reviews can be displayed. This allows the system to display appropriate reviews that match the user's emotions, thereby increasing their purchasing intent.

[0129] A shopping support system can analyze a user's purchase history and suggest complementary products to items they have previously bought. For example, if a user buys a camera, it can suggest lenses and accessories suitable for that camera. If a user buys furniture, it can suggest interior items that match that furniture. Furthermore, if a user buys sports equipment, it can suggest other items related to that sport. This makes it easier for users to find complementary products to make better use of their purchases, improving the shopping experience.

[0130] The shopping support system can estimate the user's emotions and adjust its live chat response based on those emotions. For example, if the user has positive emotions, it will respond in a friendly manner. If the user has negative emotions, it can respond politely and carefully. Furthermore, if the user has neutral emotions, it can respond in a standard manner. This allows for more appropriate responses based on the user's emotions, thereby increasing user satisfaction.

[0131] The shopping support system analyzes the user's purchase history and can suggest products with similar ratings based on the user's past purchases. For example, if a user purchases a highly-rated product, it can suggest other highly-rated products. It can also suggest other products from a specific brand if the user highly rates products from that brand. Furthermore, if a user highly rates products in a specific category, it can suggest other products in that category. This makes it easier for users to find reliable products based on their ratings, improving the shopping experience.

[0132] The shopping support system can estimate the user's emotions and adjust the display of Q&A based on those emotions. For example, if the user has positive emotions, positive answers will be displayed preferentially. If the user has negative emotions, negative answers can be displayed preferentially. Furthermore, if the user has neutral emotions, balanced answers can be displayed. This allows the system to effectively resolve the user's questions by displaying appropriate answers that match the user's emotions.

[0133] A shopping support system can analyze a user's purchase history and provide information on how to use and maintain products they have previously purchased. For example, if a user purchases an electronic appliance, the system can provide instructions on how to use and maintain that appliance. Similarly, if a user purchases furniture, it can provide instructions on how to assemble and care for that furniture. Furthermore, if a user purchases sporting goods, it can provide instructions on how to use and store those goods. This allows users to obtain information to use their purchased products more effectively, improving their overall shopping experience.

[0134] The shopping support system can estimate the user's emotions and adjust the importance of reviews based on those emotions. For example, if a user has positive emotions, the importance of positive reviews will be increased. Similarly, if a user has negative emotions, the importance of negative reviews can be increased. Furthermore, if a user has neutral emotions, the importance of balanced reviews can be increased. This allows the system to display appropriate reviews that match the user's emotions, thereby increasing their purchasing intent.

[0135] The following briefly describes the processing flow for example form 2.

[0136] Step 1: The review organization section automatically organizes reviews using generative AI. For example, if a user is looking for reviews about a specific product, the generative AI automatically collects, organizes, and displays reviews related to that product. It can also organize reviews based on review rating criteria and organization algorithms. For example, it can prioritize displaying highly-rated reviews based on review rating criteria. Step 2: The related product suggestion section automatically suggests related products using generative AI. For example, if a user is trying to purchase a specific product, the generative AI will suggest other products related to that product. It can also suggest related products based on suggestion algorithms and criteria. For example, it can suggest related products based on the user's purchase history and interests. Step 3: The Q&A section automatically provides Q&A using generative AI. For example, if a user wants to know how to use a particular product, the generative AI automatically collects and displays the answer to that question. It can also provide Q&A based on question selection criteria and answer delivery methods. For example, it can prioritize displaying the most relevant answers to the user's question. Step 4: The department providing the live chat automatically provides live chats using generative AI. For example, users can chat with other buyers in real time and ask questions directly about product details and user experiences. It can also provide live chats based on the conditions for starting a chat and how to respond. For example, if a user is seeking detailed information about a specific product, a live chat will be initiated.

[0137] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0138] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0139] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements, including the review organization unit, the related product suggestion unit, the Q&A provision unit, and the live chat provision unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the review organization unit is implemented by the control unit 46A of the smart device 14 and automatically organizes reviews using a generation AI. The related product suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically suggests related products using a generation AI. The Q&A provision unit is implemented by the control unit 46A of the smart device 14 and automatically provides Q&A using a generation AI. The live chat provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically provides live chat using a generation AI. The correspondence between each unit and the device or control unit is not limited to the example above and can be changed in various ways.

[0141] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0142] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0143] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0144] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0145] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0147] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0148] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0149] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0150] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0151] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0153] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0154] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0155] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements, including the review organization unit, the related product suggestion unit, the Q&A provision unit, and the live chat provision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the review organization unit is implemented by the control unit 46A of the smart glasses 214 and automatically organizes reviews using a generation AI. The related product suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically suggests related products using a generation AI. The Q&A provision unit is implemented by the control unit 46A of the smart glasses 214 and automatically provides Q&A using a generation AI. The live chat provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically provides live chat using a generation AI. The correspondence between each unit and the device or control unit is not limited to the example above and can be changed in various ways.

[0157] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0158] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0159] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0160] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0161] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0163] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0164] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0165] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0166] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0167] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0168] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0169] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0170] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0171] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0172] Each of the multiple elements, including the review organization unit, the related product suggestion unit, the Q&A provision unit, and the live chat provision unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing unit 12. For example, the review organization unit is implemented by the control unit 46A of the headset terminal 314 and automatically organizes reviews using a generation AI. The related product suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically suggests related products using a generation AI. The Q&A provision unit is implemented by the control unit 46A of the headset terminal 314 and automatically provides Q&A using a generation AI. The live chat provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically provides live chat using a generation AI. The correspondence between each unit and the device or control unit is not limited to the example above and can be changed in various ways.

[0173] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0174] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0175] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0176] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0177] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0178] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0179] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0180] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0181] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0182] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0183] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0184] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0185] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0186] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0187] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0188] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0189] Each of the multiple elements, including the review organization unit, the related product suggestion unit, the Q&A provision unit, and the live chat provision unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the review organization unit is implemented by the control unit 46A of the robot 414 and automatically organizes reviews using a generation AI. The related product suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically suggests related products using a generation AI. The Q&A provision unit is implemented by the control unit 46A of the robot 414 and automatically provides Q&A using a generation AI. The live chat provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically provides live chat using a generation AI. The correspondence between each unit and the device or control unit is not limited to the example above and can be changed in various ways.

[0190] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0191] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0192] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0193] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0194] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0195] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0196] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0197] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0198] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0199] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0200] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0201] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0202] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0203] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0204] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0205] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0206] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0207] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0208] (Note 1) The department that organizes the reviews, A department that proposes related products based on the reviews compiled by the department that compiles the aforementioned reviews, A department that provides Q&A based on the related products proposed by the department that proposes the aforementioned related products, The system comprises a unit that provides live chat based on the Q&A provided by the unit that provides the aforementioned Q&A. A system characterized by the following features. (Note 2) It has a department for collecting reviews. The system described in Appendix 1, characterized by the features described herein. (Note 3) It has a department for collecting questions. The system described in Appendix 1, characterized by the features described herein. (Note 4) It has a department for collecting responses. The system described in Appendix 1, characterized by the features described herein. (Note 5) The section that summarizes the aforementioned review is: AI automatically organizes reviews. The system described in Appendix 1, characterized by the features described herein. (Note 6) The part that proposes the aforementioned related products is, AI automatically suggests related products. The system described in Appendix 1, characterized by the features described herein. (Note 7) The section that provides the aforementioned Q&A is, AI automatically provides Q&A The system described in Appendix 1, characterized by the features described herein. (Note 8) The department that provides the aforementioned live chat is AI automatically provides live chat The system described in Appendix 1, characterized by the features described herein. (Note 9) The section that summarizes the aforementioned review is: It estimates user sentiment and adjusts the display order of reviews based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 10) The section that summarizes the aforementioned review is: Analyze the content of the reviews and categorize them based on specific keywords. The system described in Appendix 1, characterized by the features described herein. (Note 11) The section that summarizes the aforementioned review is: We evaluate the reliability of reviews and prioritize displaying the most reliable reviews. The system described in Appendix 1, characterized by the features described herein. (Note 12) The section that summarizes the aforementioned review is: It estimates user sentiment and adjusts the importance of reviews based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The section that summarizes the aforementioned review is: Analyze the content of the reviews and group them based on specific themes. The system described in Appendix 1, characterized by the features described herein. (Note 14) The section that summarizes the aforementioned review is: Customize how reviews are displayed by taking into account the attributes of the reviewers. The system described in Appendix 1, characterized by the features described herein. (Note 15) The part that proposes the aforementioned related products is, The system estimates the user's emotions and adjusts how related products are suggested based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The part that proposes the aforementioned related products is, We analyze your purchase history and suggest related products based on your past purchase patterns. The system described in Appendix 1, characterized by the features described herein. (Note 17) The part that proposes the aforementioned related products is, We analyze the ratings of related products and prioritize suggesting highly-rated products. The system described in Appendix 1, characterized by the features described herein. (Note 18) The part that proposes the aforementioned related products is, It estimates the user's emotions and adjusts the display order of related products based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The part that proposes the aforementioned related products is, We analyze your purchase history and suggest related products based on specific categories. The system described in Appendix 1, characterized by the features described herein. (Note 20) The part that proposes the aforementioned related products is, We will consider the price range of related products and suggest products that fit the user's budget. The system described in Appendix 1, characterized by the features described herein. (Note 21) The section that provides the aforementioned Q&A is, The system estimates the user's emotions and adjusts the way Q&A is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The section that provides the aforementioned Q&A is, The system analyzes the content of the questions and groups similar questions together for display. The system described in Appendix 1, characterized by the features described herein. (Note 23) The section that provides the aforementioned Q&A is, The system evaluates the reliability of the answers and prioritizes displaying the most reliable answers. The system described in Appendix 1, characterized by the features described herein. (Note 24) The section that provides the aforementioned Q&A is, The system estimates the user's emotions and adjusts the importance of Q&A based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The section that provides the aforementioned Q&A is, Analyze the content of the questions and group the Q&A based on specific themes. The system described in Appendix 1, characterized by the features described herein. (Note 26) The section that provides the aforementioned Q&A is, Customize the display method of Q&A by taking into account the attribute information of the questioner. The system described in Appendix 1, characterized by the features described herein. (Note 27) The department that provides the aforementioned live chat is The system estimates the user's emotions and adjusts the live chat response based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The department that provides the aforementioned live chat is Analyze the chat content and classify it based on specific keywords. The system described in Appendix 1, characterized by the features described herein. (Note 29) The department that provides the aforementioned live chat is It analyzes the chat history and suggests appropriate answers based on past chat content. The system described in Appendix 1, characterized by the features described herein. (Note 30) The department that provides the aforementioned live chat is It estimates the user's emotions and prioritizes live chats based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The department that provides the aforementioned live chat is Analyze the chat content and group it based on specific themes. The system described in Appendix 1, characterized by the features described herein. (Note 32) The department that provides the aforementioned live chat is Customize how the chat is displayed by taking into account the attribute information of the chat participants. The system described in Appendix 1, characterized by the features described herein. (Note 33) The department responsible for collecting the aforementioned reviews is: We estimate user sentiment and adjust how we collect reviews based on that estimated sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 34) The department responsible for collecting the aforementioned reviews is: We analyze the frequency of review submissions to determine the optimal timing for collection. The system described in Appendix 2, characterized by the features described herein. (Note 35) The department responsible for collecting the aforementioned reviews is: The system estimates user sentiment and determines the priority of review collection based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 36) The department responsible for collecting the aforementioned reviews is: Customize the data collection method by considering the attribute information of the review author. The system described in Appendix 2, characterized by the features described herein. (Note 37) The department that collects the aforementioned questions, We estimate the user's emotions and adjust the way we collect questions based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The department that collects the aforementioned questions, We analyze the frequency of question submissions to determine the optimal timing for data collection. The system described in Appendix 3, characterized by the features described herein. (Note 39) The department that collects the aforementioned questions, The system estimates the user's emotions and determines the priority of questions to collect based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The department that collects the aforementioned questions, Customize the data collection method by considering the questioner's attribute information. The system described in Appendix 3, characterized by the features described herein. (Note 41) The department responsible for collecting the aforementioned responses is: We estimate the user's emotions and adjust the method of collecting responses based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 42) The department responsible for collecting the aforementioned responses is: We analyze the frequency of responses submitted to determine the optimal timing for collection. The system described in Appendix 4, characterized by the features described herein. (Note 43) The department responsible for collecting the aforementioned responses is: The system estimates the user's emotions and determines the priority of collecting responses based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 44) The department responsible for collecting the aforementioned responses is: Customize the data collection method by considering the respondents' attribute information. The system described in Appendix 4, characterized by the features described herein. (Note 45) The department responsible for collecting the aforementioned responses is: Analyze the content of the responses and group them based on specific themes. The system described in Appendix 4, characterized by the features described herein. (Note 46) The department responsible for collecting the aforementioned responses is: Evaluate the reliability of the responses and prioritize collecting the most reliable ones. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0209] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The department that organizes the reviews, A department that proposes related products based on the reviews compiled by the department that compiles the aforementioned reviews, A department that provides Q&A based on the related products proposed by the department that proposes the aforementioned related products, The system comprises a unit that provides live chat based on the Q&A provided by the unit that provides the aforementioned Q&A. A system characterized by the following features.

2. It has a department for collecting reviews. The system according to feature 1.

3. It has a department for collecting questions. The system according to feature 1.

4. It has a department for collecting responses. The system according to feature 1.

5. The section that summarizes the aforementioned review is: AI automatically organizes reviews. The system according to feature 1.

6. The part that proposes the aforementioned related products is, AI automatically suggests related products. The system according to feature 1.

7. The section that provides the aforementioned Q&A is, AI automatically provides Q&A. The system according to feature 1.

8. The department that provides the aforementioned live chat is AI automatically provides live chat The system according to feature 1.

9. The section that summarizes the aforementioned review is: It estimates user sentiment and adjusts the display order of reviews based on the estimated user sentiment. The system according to feature 1.

10. The section that summarizes the aforementioned review is: Analyze the content of the reviews and categorize them based on specific keywords. The system according to feature 1.

Images