system

Abstract

The system according to this embodiment aims to alleviate user anxiety during online shopping. [Solution] The system according to the embodiment comprises a data collection unit, an analysis unit, a recommendation unit, a question answering unit, and a chat unit. The data collection unit collects user behavior data. The analysis unit analyzes the data collected by the data collection unit. The recommendation unit recommends products based on the analysis results obtained by the analysis unit. The question answering unit answers user questions. The chat unit conducts real-time chat.

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, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to the description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, the support for reducing the user's anxiety in online shopping is not sufficient, and there is room for improvement.

[0005] The system according to the embodiment aims to reduce the user's anxiety in online shopping.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, an analysis unit, a recommendation unit, a question answering unit, and a chat unit. The data collection unit collects user behavior data. The analysis unit analyzes the data collected by the data collection unit. The recommendation unit recommends products based on the analysis results obtained by the analysis unit. The question answering unit answers user questions. The chat unit conducts real-time chat. [Effects of the Invention]

[0007] The system according to this embodiment can reduce user anxiety during online shopping. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), 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 AI ​​agent system according to an embodiment of the present invention is a system integrated into an online shopping platform to alleviate user anxiety when purchasing products. This AI agent system automatically collects customer reviews and provides reliable information to reduce user anxiety. It also answers user questions in real time through a question-answering system utilizing natural language processing. Furthermore, it features a personalized product recommendation function based on machine learning to suggest the most suitable products to users. Additionally, it provides a chatbot that enables real-time user support, facilitating smooth communication with users. This improves the user's purchasing experience and increases the speed of purchase decisions. For example, the AI ​​agent system sets a new standard for online shopping by providing highly accurate product recommendations based on user behavior data. For instance, if a user shows interest in a particular product, it recommends other related products to increase the user's desire to purchase. It also suggests products best suited to individual users based on their past purchases and browsing history. This allows users to make more informed purchase decisions and improves post-purchase satisfaction. Furthermore, the AI ​​agent system supports trust building among users through community features. Users can purchase products with greater confidence by referring to other users' reviews and Q&A responses. Furthermore, real-time chat allows users to communicate directly with other users, alleviating any anxieties they may have about their purchases. In this way, the AI ​​agent system provides various functions to reduce user anxiety in online shopping and improve the purchase experience. This is expected to lead to increased customer engagement, higher repeat purchase rates, faster purchase decisions, and higher customer satisfaction. For example, improved customer engagement is expected to increase the repeat purchase rate by 20%, and the speed of purchase decisions due to the resolution of user questions is expected to increase by 30%. In addition, a 15% increase in customer satisfaction is expected through real-time support. Thus, the AI ​​agent system can improve the user's purchase experience and increase the speed of purchase decisions.

[0029] The AI ​​agent system according to this embodiment comprises a data collection unit, an analysis unit, a recommendation unit, a question answering unit, and a chat unit. The data collection unit collects user behavior data. For example, the data collection unit collects behavior data such as the user's click history, browsing time, and purchase history. For example, the data collection unit records the user's click history on a website and collects which pages were viewed and for how long. The data collection unit can also record the history of products purchased by the user and collect data such as the date and time of purchase, the products purchased, and the purchase amount. The analysis unit analyzes the data collected by the data collection unit. For example, the analysis unit analyzes the data using statistical analysis or machine learning algorithms to identify the user's interests and preferences. For example, the analysis unit analyzes the user's click history to identify which pages are viewed the most. The analysis unit can also analyze the user's purchase history to identify which product categories are purchased the most. The recommendation unit recommends products based on the analysis results obtained by the analysis unit. For example, the recommendation unit recommends the most suitable products for the user using collaborative filtering or content-based recommendation algorithms. The recommendation unit recommends related products based on the user's past purchases, for example. It can also recommend products that the user might be interested in based on their browsing history. The question answering unit answers user questions using natural language processing. For example, it uses natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis to understand user questions and generate appropriate answers. For example, if a user enters a question about a product, the question answering unit analyzes the question and provides an appropriate answer. It can also analyze questions about the purchase process and provide appropriate answers. The chat unit conducts real-time chats with users. For example, the chat unit uses a chatbot to enable real-time chats with users. For example, if a user enters a question into the chatbot, the chat unit immediately returns an answer. The chat unit can also provide appropriate advice if a user enters a question about a product.As a result, the AI ​​agent system according to this embodiment can improve the user's purchasing experience by collecting and analyzing user behavior data, recommending products, answering questions, and conducting real-time chats.

[0030] The data collection unit collects user behavior data. For example, it collects behavioral data such as user click history, browsing time, and purchase history. Specifically, it records user click history on websites and collects data on which pages were viewed and for how long. This includes detailed data such as which links users clicked, how long they stayed on each page, and what content they showed interest in. The data collection unit can also record the history of products purchased by users, collecting data such as purchase date and time, purchased items, and purchase amount. This allows for a detailed understanding of user purchasing behavior and consumption trends. Furthermore, the data collection unit can also collect technical data such as user device information, the IP address from which the user accessed the site, and the type of browser and operating system used. This provides foundational data for more accurate analysis of user behavior patterns. The collected data is stored in a secure database and encrypted using appropriate encryption technology to protect privacy. The data collection unit can collect this data in real time and provide it quickly to the analysis unit and other system components. This allows the data collection unit to efficiently and effectively collect user behavior data and improve the overall system performance.

[0031] The analysis unit analyzes the data collected by the data collection unit. For example, the analysis unit uses statistical analysis and machine learning algorithms to analyze the data and identify user interests. Specifically, it analyzes user click history to identify which pages are viewed most frequently. This involves using metrics such as page views, time spent on the page, and click-through rate to identify content of high user interest. The analysis unit can also analyze user purchase history to identify which product categories are most frequently purchased. This involves using metrics such as purchase frequency, purchase amount, and repeat purchase rate to analyze user purchasing trends. Furthermore, the analysis unit can use machine learning algorithms to extract patterns and trends from user behavior data and predict future behavior. For example, it can use clustering algorithms to identify user groups with similar behavioral patterns and develop optimal marketing strategies for each group. It can also use deep learning to predict user interests with high accuracy and provide personalized content and products. This allows the analysis unit to quickly and accurately analyze collected data and identify user interests. Furthermore, the analysis unit can utilize historical data and statistical information to evaluate long-term trends and risks, and formulate future countermeasures. This allows the analysis unit to not only grasp the situation in real time but also to formulate long-term strategies, thereby improving the reliability and effectiveness of the entire system.

[0032] The recommendation unit recommends products based on the analysis results obtained by the analysis unit. The recommendation unit uses methods such as collaborative filtering and content-based recommendation algorithms to recommend the most suitable products to users. Specifically, it uses collaborative filtering to recommend products relevant to the user based on data from other users with similar interests and purchase history. This involves analyzing the user's past purchase and browsing history to recommend products purchased and content viewed by other users. It also uses content-based recommendation algorithms to recommend products with similar characteristics based on the features of products and content the user has shown interest in in the past. This involves analyzing information such as product categories, attributes, and keywords to identify products that match the user's interests. Furthermore, the recommendation unit can respond to changes in user interests and preferences based on real-time updated data. For example, it can instantly update recommendations based on products or content the user has newly shown interest in. The recommendation unit can also collect user feedback to continuously improve the accuracy of its recommendation algorithms. This involves collecting data such as whether the user purchased the recommended products, and evaluations and comments on the recommendations, to evaluate the algorithm's performance. This allows the recommendation unit to recommend the most suitable products to users and improve the purchasing experience.

[0033] The question-answering unit uses natural language processing to answer user questions. For example, it uses natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis to understand user questions and generate appropriate answers. Specifically, if a user enters a question about a product, the unit analyzes the question and provides appropriate answers regarding product details, specifications, and usage. This involves referencing product databases and FAQ databases, extracting relevant information, and generating answers. Furthermore, if a user enters a question about the purchase process, the unit analyzes the question and provides appropriate answers regarding the purchase procedure, payment methods, and shipping information. In addition, the question-answering unit can use machine learning algorithms to understand the intent and context of user questions, enabling more natural dialogue. For example, even if a user enters an ambiguous question, it can generate an appropriate answer based on past dialogue history and relevant information. The question-answering unit can also collect user feedback and continuously improve the accuracy and quality of its answers. This involves providing a function for users to input ratings and comments on the provided answers, and evaluating the algorithm's performance based on this data. This allows the question-answering unit to answer user questions quickly and accurately, improving the purchase experience.

[0034] The chat function provides real-time chat with users. For example, it uses a chatbot to achieve real-time chat with users. Specifically, when a user enters a question into the chatbot, it immediately provides an answer. This is achieved using natural language processing technology to understand the user's question and generate an appropriate response. The chat function can also provide appropriate advice when a user enters a question about a product. This includes advice on how to choose, use, and maintain the product. Furthermore, the chat function can collect user feedback to continuously improve the accuracy and quality of the chatbot's responses. This involves providing a function for users to input ratings and comments on their interactions with the chatbot, and evaluating the algorithm's performance based on this data. In addition, the chat function can save the user's conversation history and refer to past conversations to achieve more consistent interactions. As a result, the chat function can provide quick and appropriate support through real-time chat with users, improving the purchasing experience.

[0035] The data collection unit can collect users' purchase history and browsing history. For example, the data collection unit can collect users' purchase history, such as purchase date and time, purchased items, and purchase amount. The data collection unit can also collect users' browsing history, such as pages viewed, viewing time, and viewing frequency. By collecting users' purchase and browsing history, more accurate data analysis becomes possible. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input users' purchase history and browsing history into a generating AI and have the generating AI perform the data collection.

[0036] The analysis unit can analyze the collected data and identify the user's interests and preferences. For example, the analysis unit can analyze the collected data using statistical analysis or machine learning algorithms. For example, the analysis unit can analyze the user's click history to identify which pages are viewed the most. The analysis unit can also analyze the user's purchase history to identify which product categories are purchased the most. This allows for more appropriate product recommendations by identifying the user's interests and preferences. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the collected data into a generating AI and have the generating AI identify the user's interests and preferences.

[0037] The recommendation system can recommend products based on identified interests. For example, it can use collaborative filtering or content-based recommendation algorithms to recommend the most suitable products to the user. For example, it can recommend related products based on the user's past purchases. It can also recommend products that the user might be interested in based on their browsing history. This allows for increased user purchasing intent by recommending products based on the user's interests. Some or all of the above processes in the recommendation system may be performed using AI, or not. For example, the recommendation system can input data for recommending products based on identified interests into a generating AI, and have the generating AI perform product recommendations.

[0038] The question-answering unit can answer user questions using natural language processing. For example, the question-answering unit uses natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis to understand user questions and generate appropriate answers. For instance, if a user inputs a question about a product, the question-answering unit analyzes the question and provides an appropriate answer. Furthermore, if a user inputs a question about the purchase procedure, the question-answering unit can analyze the question and provide an appropriate answer. This allows for quick and accurate answers to user questions by utilizing natural language processing. Some or all of the above-described processes in the question-answering unit may be performed using AI, or without AI. For example, the question-answering unit can input a user's question into a generating AI and have the generating AI generate an answer to the question.

[0039] The chat function can conduct real-time chats with users. For example, the chat function can use a chatbot to achieve real-time chats with users. For example, when a user enters a question into the chatbot, the chat function can immediately provide an answer. The chat function can also provide appropriate advice when a user enters a question about a product. In this way, users' doubts and concerns can be resolved immediately through real-time chat. Some or all of the above processes in the chat function may be performed using AI, for example, or without AI. For example, the chat function can input the content of the chat with the user into a generating AI and have the generating AI execute the real-time chat.

[0040] The data collection unit can analyze the user's past purchase and browsing history and select the optimal data collection method. For example, the data collection unit can prioritize collecting product categories that the user has frequently purchased in the past. For example, the data collection unit can also focus on collecting data about products that the user has viewed in the past but did not purchase. For example, the data collection unit can collect data related to specific seasons or events from the user's past purchase history. This allows the optimal data collection method to be selected by analyzing the user's past purchase and browsing history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's past purchase and browsing history into a generating AI and have the generating AI select the optimal data collection method.

[0041] The data collection unit can filter data based on the user's current areas of interest and behavioral patterns during data collection. For example, the data collection unit can prioritize collecting data related to product categories that the user is currently interested in. The data collection unit can also adjust the data collected at specific times based on the user's behavioral patterns. The data collection unit can also collect only highly relevant data based on the user's current areas of interest. This allows for the collection of highly relevant data by filtering the data based on the user's current areas of interest and behavioral patterns. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's current areas of interest and behavioral patterns into a generating AI and have the generating AI perform data filtering.

[0042] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, the data collection unit can prioritize the collection of product information related to the area where the user is currently located. The data collection unit can also, for example, collect data on popular products in a specific region based on the user's geographical location information. The data collection unit can also, for example, collect region-specific promotional information based on the user's location information. This allows for the priority collection of highly relevant data by considering the user's geographical location information. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location information into a generating AI and have the generating AI perform the collection of highly relevant data.

[0043] The data collection unit can analyze the user's social media activity and collect relevant data during data collection. For example, the data collection unit can collect data about products mentioned by the user on social media. The data collection unit can also collect data related to product categories the user is interested in from the user's social media activity. The data collection unit can also collect data about products that the user's followers and friends on social media are interested in. In this way, relevant data can be collected by analyzing the user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's social media activity into a generating AI and have the generating AI perform the collection of relevant data.

[0044] The analysis unit can adjust the level of detail of the analysis based on the importance of the collected data during the analysis. For example, the analysis unit can perform a detailed analysis on data with high importance. For example, the analysis unit can also perform a simplified analysis on data with low importance. The analysis unit can also determine the priority of the analysis according to the importance of the data. This allows for efficient data analysis by adjusting the level of detail of the analysis based on the importance of the collected data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the importance of the collected data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0045] The analysis unit can apply different analysis algorithms depending on the data category during analysis. For example, the analysis unit can apply a sentiment analysis algorithm to product reviews. For example, the analysis unit can also apply a purchase pattern analysis algorithm to purchase history. For example, the analysis unit can also apply an interest analysis algorithm to browsing history. By applying different analysis algorithms depending on the data category, more accurate analysis results can be obtained. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the data category into a generating AI and have the generating AI execute the application of different analysis algorithms.

[0046] The analysis unit can determine the priority of analysis based on the data collection timing during analysis. For example, the analysis unit may prioritize the analysis of the most recent data. The analysis unit may also prioritize the most recent data while referring to past data. The analysis unit may also dynamically adjust the priority of analysis according to the data collection timing. This allows for the prioritization of analysis of the most recent data by determining the priority of analysis based on the data collection timing. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the data collection timing into a generating AI and have the generating AI determine the priority of analysis.

[0047] The analysis unit can adjust the order of analysis based on the relevance of the data during analysis. For example, the analysis unit may prioritize the analysis of highly relevant data. For example, the analysis unit may postpone the analysis of less relevant data. The analysis unit can also dynamically adjust the order of analysis according to the relevance of the data. This enables efficient data analysis by adjusting the order of analysis based on the relevance of the data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the relevance of the data into a generating AI and have the generating AI perform the adjustment of the order of analysis.

[0048] The recommendation unit can adjust the level of detail of recommendations based on the importance of the products. For example, the recommendation unit provides detailed recommendation information for highly important products. For example, the recommendation unit can also provide simplified recommendation information for less important products. The recommendation unit can also dynamically adjust the level of detail of recommendations according to the importance of the products. This allows the recommendation unit to provide the most suitable recommendation information for the user by adjusting the level of detail of recommendations based on the importance of the products. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the importance of the products into a generating AI and have the generating AI perform the adjustment of the level of detail of recommendations.

[0049] The recommendation system can apply different recommendation algorithms depending on the product category during the recommendation process. For example, for electronic devices, the recommendation system might apply a recommendation algorithm that emphasizes technical features. For fashion items, the recommendation system might also apply a recommendation algorithm that emphasizes trends. For food products, the recommendation system might also apply a recommendation algorithm that emphasizes health consciousness. By applying different recommendation algorithms depending on the product category, more accurate recommendations become possible. Some or all of the above processing in the recommendation system may be performed using AI, for example, or without AI. For example, the recommendation system can input the product category into a generating AI and have the generating AI apply different recommendation algorithms.

[0050] The recommendation system can determine the priority of recommendations based on the product submission timing. For example, the recommendation system may prioritize recommending new products. The recommendation system can also recommend seasonal products at the appropriate time. The recommendation system can also dynamically adjust the recommendation priority according to the product submission timing. This allows the system to recommend products to users at the optimal time by determining the recommendation priority based on the product submission timing. Some or all of the above processes in the recommendation system may be performed using AI, for example, or not using AI. For example, the recommendation system can input the product submission timing into a generating AI and have the generating AI determine the recommendation priority.

[0051] The recommendation unit can adjust the order of recommendations based on the relevance of the products. For example, the recommendation unit may prioritize recommending highly relevant products. For example, it may also postpone recommending less relevant products. The recommendation unit can also dynamically adjust the order of recommendations based on the relevance of the products. This allows the recommendation unit to recommend products in the optimal order for the user by adjusting the order of recommendations based on the relevance of the products. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the relevance of products into a generating AI and have the generating AI perform the adjustment of the recommendation order.

[0052] The question-answering unit can provide the most appropriate answer by referring to the user's past question history when answering a question. For example, the question-answering unit can provide relevant answers based on the content of questions the user has asked in the past. For example, the question-answering unit can also prioritize providing answers to frequently asked questions from the user's past question history. For example, the question-answering unit can analyze the user's past question history and provide the most appropriate answer. This allows the unit to provide the most appropriate answer by referring to the user's past question history. Some or all of the above processing in the question-answering unit may be performed using AI, for example, or without AI. For example, the question-answering unit can input the user's past question history into a generating AI and have the generating AI perform the task of providing the most appropriate answer.

[0053] The question-answering unit can customize the content of its answers based on the user's current areas of interest when answering questions. For example, the question-answering unit can provide answers related to product categories that the user is currently interested in. The question-answering unit can also provide answers that contain highly relevant information based on the user's current areas of interest. The question-answering unit can also dynamically adjust the content of its answers according to the user's current areas of interest. This allows the system to provide the user with the most suitable answers by customizing the content of its answers based on the user's current areas of interest. Some or all of the above processing in the question-answering unit may be performed using AI, for example, or without AI. For example, the question-answering unit can input the user's current areas of interest into a generating AI and have the generating AI customize the content of its answers.

[0054] The question-answering unit can provide the most relevant answer by considering the user's geographical location when answering a question. For example, the question-answering unit can provide an answer that includes information relevant to the area where the user is currently located. For example, the question-answering unit can also provide an answer that includes region-specific promotional information based on the user's geographical location. For example, the question-answering unit can provide an answer that includes region-specific information based on the user's location. This allows the system to provide highly relevant answers by considering the user's geographical location. Some or all of the above processing in the question-answering unit may be performed using AI, for example, or without AI. For example, the question-answering unit can input the user's geographical location information into a generating AI and have the generating AI perform the task of providing the most relevant answer.

[0055] The question-answering unit can analyze the user's social media activity and provide relevant answers when answering questions. For example, the question-answering unit can provide answers related to what the user has mentioned on social media. For example, the question-answering unit can also provide answers related to topics the user has shown interest in based on their social media activity. For example, the question-answering unit can provide answers related to topics that the user's followers or friends on social media have shown interest in. In this way, relevant answers can be provided by analyzing the user's social media activity. Some or all of the above processing in the question-answering unit may be performed using AI, for example, or without AI. For example, the question-answering unit can input the user's social media activity into a generating AI and have the generating AI perform the task of providing relevant answers.

[0056] The chat function can provide optimal communication by referring to the user's past chat history during a chat. For example, the chat function can provide relevant information based on what the user has mentioned in past chats. For example, the chat function can also prioritize providing answers to frequently asked questions based on the user's past chat history. For example, the chat function can analyze the user's past chat history to provide optimal communication. This allows the chat function to provide relevant and optimal communication by referring to the user's past chat history. Some or all of the above processing in the chat function may be performed using AI, for example, or not using AI. For example, the chat function can input the user's past chat history into a generating AI and have the generating AI perform the task of providing optimal communication.

[0057] The chat function can customize the chat content based on the user's current areas of interest during a chat. For example, the chat function can provide information related to product categories that the user is currently interested in. The chat function can also initiate a chat that includes highly relevant information based on the user's current areas of interest. The chat function can also dynamically adjust the chat content according to the user's current areas of interest. This allows the chat function to provide the user with the most relevant information by customizing the chat content based on the user's current areas of interest. Some or all of the above processing in the chat function may be performed using AI, for example, or without AI. For example, the chat function can input the user's current areas of interest into a generating AI and have the generating AI customize the chat content.

[0058] The chat function can provide optimal communication during a chat, taking into account the user's geographical location. For example, the chat function can provide chats that include information relevant to the user's current location. For example, the chat function can also provide chats that include region-specific promotional information based on the user's geographical location. For example, the chat function can provide chats that include region-specific information based on the user's location. This allows for the provision of highly relevant communication by considering the user's geographical location. Some or all of the above processing in the chat function may be performed using AI, for example, or without AI. For example, the chat function can input the user's geographical location information into a generating AI and have the generating AI perform the task of providing optimal communication.

[0059] The chat unit can analyze the user's social media activity during a chat and provide relevant chat content. For example, the chat unit can provide information related to what the user has mentioned on social media. For example, the chat unit can also provide chats that include information related to topics the user has shown interest in, based on the user's social media activity. For example, the chat unit can also provide chats that include information related to topics that the user's followers and friends on social media have shown interest in. In this way, relevant chat content can be provided by analyzing the user's social media activity. Some or all of the above processing in the chat unit may be performed using AI, for example, or without AI. For example, the chat unit can input the user's social media activity into a generating AI and have the generating AI provide relevant chat content.

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

[0061] The AI ​​agent system can also include a trust rating unit that evaluates the user's level of trust in specific brands and manufacturers based on their purchase history. This unit, for example, analyzes reviews and ratings of products the user has previously purchased to calculate a level of trust in those brands and manufacturers. The unit can, for example, prioritize recommending brands and manufacturers that the user has given high ratings to. It can also adjust recommendations to avoid brands and manufacturers that the user has given low ratings to. This enables product recommendations based on user trust levels, thereby improving user satisfaction.

[0062] The AI ​​agent system can also include a seasonal event recommendation unit that prioritizes recommending products related to specific seasons or events based on the user's purchase and browsing history. For example, the seasonal event recommendation unit could analyze products the user has purchased during the Christmas season in the past and recommend similar seasonal products. Alternatively, it could prioritize recommending summer-related products based on products the user has purchased during the summer. Furthermore, the seasonal event recommendation unit could recommend products related to similar events (e.g., birthdays or anniversaries) based on the user's purchase history of products related to those events. This enables product recommendations tailored to the user's season and events, thereby increasing their purchasing intent.

[0063] The AI ​​agent system can also include a price monitoring unit that monitors price fluctuations of specific products based on the user's purchase and browsing history, and notifies the user of the optimal purchase timing. For example, the price monitoring unit analyzes price fluctuations of products the user has previously purchased and notifies the user when the price drops. The price monitoring unit can also notify the user in real time if the price of a product the user is interested in drops. Furthermore, the price monitoring unit can collect sales information for specific products and notify the user. This allows the user to purchase products at the optimal time, improving cost performance.

[0064] The AI ​​agent system can also include an inventory monitoring unit that monitors the stock status of specific products based on the user's purchase and browsing history, and notifies the user when stock levels become low. For example, the inventory monitoring unit monitors the stock status of products the user has previously purchased and notifies the user when stock levels become low. The inventory monitoring unit can also notify the user in real time if the stock of a product the user is interested in becomes low. Furthermore, the inventory monitoring unit can collect restock information for specific products and notify the user. This allows users to purchase products before stock levels become low, preventing them from missing out on purchase opportunities.

[0065] The AI ​​agent system can also include a review analysis unit that analyzes reviews and ratings of specific products based on the user's purchase and browsing history, providing highly reliable information. For example, the review analysis unit can analyze reviews of products the user has previously purchased and extract highly reliable reviews. It can also analyze reviews of products the user is interested in and provide highly reliable information. Furthermore, the review analysis unit can analyze ratings of specific products and provide information beneficial to the user. This allows users to make purchase decisions based on reliable information, thereby improving post-purchase satisfaction.

[0066] The AI ​​agent system can also include a quality evaluation unit that evaluates the quality of specific products based on the user's purchase and browsing history, and prioritizes recommending high-quality products. For example, the quality evaluation unit can analyze the quality of products the user has previously purchased and extract high-quality products. It can also analyze the quality of products the user has shown interest in and prioritize recommending high-quality products. Furthermore, the quality evaluation unit can evaluate the quality of specific products and provide the user with useful information. This allows users to purchase high-quality products and improve their post-purchase satisfaction.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The data collection unit collects user behavior data. The data collection unit collects behavioral data such as user click history, browsing time, and purchase history. For example, the data collection unit records a user's click history on a website and collects data on which pages were viewed and for how long. The data collection unit can also record the history of products purchased by users and collect data such as the date and time of purchase, the products purchased, and the purchase amount. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the data using, for example, statistical analysis and machine learning algorithms to identify user interests and preferences. For example, the analysis unit analyzes user click history to identify which pages are viewed the most. The analysis unit can also analyze user purchase history to identify which product categories are purchased the most. Step 3: The recommendation unit recommends products based on the analysis results obtained by the analysis unit. The recommendation unit recommends the most suitable products for the user, for example, using collaborative filtering or content-based recommendation algorithms. The recommendation unit recommends related products based on products the user has purchased in the past. The recommendation unit can also recommend products that the user might be interested in based on their browsing history. Step 4: The question answering unit uses natural language processing to answer the user's questions. The question answering unit uses natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis to understand the user's questions and generate appropriate answers. For example, if the user enters a question about a product, the question answering unit will analyze the question and provide an appropriate answer. The question answering unit can also analyze a question if the user enters a question about the purchase procedure and provide an appropriate answer. Step 5: The chat unit conducts real-time chats with users. The chat unit achieves real-time chats with users, for example, by using a chatbot. For example, when a user enters a question into the chatbot, the chat unit will immediately provide an answer. The chat unit can also provide appropriate advice when a user enters a question about a product.

[0069] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is a system integrated into an online shopping platform to alleviate user anxiety when purchasing products. This AI agent system automatically collects customer reviews and provides reliable information to reduce user anxiety. It also answers user questions in real time through a question-answering system utilizing natural language processing. Furthermore, it features a personalized product recommendation function based on machine learning to suggest the most suitable products to users. Additionally, it provides a chatbot that enables real-time user support, facilitating smooth communication with users. This improves the user's purchasing experience and increases the speed of purchase decisions. For example, the AI ​​agent system sets a new standard for online shopping by providing highly accurate product recommendations based on user behavior data. For instance, if a user shows interest in a particular product, it recommends other related products to increase the user's desire to purchase. It also suggests products best suited to individual users based on their past purchases and browsing history. This allows users to make more informed purchase decisions and improves post-purchase satisfaction. Furthermore, the AI ​​agent system supports trust building among users through community features. Users can purchase products with greater confidence by referring to other users' reviews and Q&A responses. Furthermore, real-time chat allows users to communicate directly with other users, alleviating any anxieties they may have about their purchases. In this way, the AI ​​agent system provides various functions to reduce user anxiety in online shopping and improve the purchase experience. This is expected to lead to increased customer engagement, higher repeat purchase rates, faster purchase decisions, and higher customer satisfaction. For example, improved customer engagement is expected to increase the repeat purchase rate by 20%, and the speed of purchase decisions due to the resolution of user questions is expected to increase by 30%. In addition, a 15% increase in customer satisfaction is expected through real-time support. Thus, the AI ​​agent system can improve the user's purchase experience and increase the speed of purchase decisions.

[0070] The AI ​​agent system according to this embodiment comprises a data collection unit, an analysis unit, a recommendation unit, a question answering unit, and a chat unit. The data collection unit collects user behavior data. For example, the data collection unit collects behavior data such as the user's click history, browsing time, and purchase history. For example, the data collection unit records the user's click history on a website and collects which pages were viewed and for how long. The data collection unit can also record the history of products purchased by the user and collect data such as the date and time of purchase, the products purchased, and the purchase amount. The analysis unit analyzes the data collected by the data collection unit. For example, the analysis unit analyzes the data using statistical analysis or machine learning algorithms to identify the user's interests and preferences. For example, the analysis unit analyzes the user's click history to identify which pages are viewed the most. The analysis unit can also analyze the user's purchase history to identify which product categories are purchased the most. The recommendation unit recommends products based on the analysis results obtained by the analysis unit. For example, the recommendation unit recommends the most suitable products for the user using collaborative filtering or content-based recommendation algorithms. The recommendation unit recommends related products based on the user's past purchases, for example. It can also recommend products that the user might be interested in based on their browsing history. The question answering unit answers user questions using natural language processing. For example, it uses natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis to understand user questions and generate appropriate answers. For example, if a user enters a question about a product, the question answering unit analyzes the question and provides an appropriate answer. It can also analyze questions about the purchase process and provide appropriate answers. The chat unit conducts real-time chats with users. For example, the chat unit uses a chatbot to enable real-time chats with users. For example, if a user enters a question into the chatbot, the chat unit immediately returns an answer. The chat unit can also provide appropriate advice if a user enters a question about a product.As a result, the AI ​​agent system according to this embodiment can improve the user's purchasing experience by collecting and analyzing user behavior data, recommending products, answering questions, and conducting real-time chats.

[0071] The data collection unit collects user behavior data. For example, it collects behavioral data such as user click history, browsing time, and purchase history. Specifically, it records user click history on websites and collects data on which pages were viewed and for how long. This includes detailed data such as which links users clicked, how long they stayed on each page, and what content they showed interest in. The data collection unit can also record the history of products purchased by users, collecting data such as purchase date and time, purchased items, and purchase amount. This allows for a detailed understanding of user purchasing behavior and consumption trends. Furthermore, the data collection unit can also collect technical data such as user device information, the IP address from which the user accessed the site, and the type of browser and operating system used. This provides foundational data for more accurate analysis of user behavior patterns. The collected data is stored in a secure database and encrypted using appropriate encryption technology to protect privacy. The data collection unit can collect this data in real time and provide it quickly to the analysis unit and other system components. This allows the data collection unit to efficiently and effectively collect user behavior data and improve the overall system performance.

[0072] The analysis unit analyzes the data collected by the data collection unit. For example, the analysis unit uses statistical analysis and machine learning algorithms to analyze the data and identify user interests. Specifically, it analyzes user click history to identify which pages are viewed most frequently. This involves using metrics such as page views, time spent on the page, and click-through rate to identify content of high user interest. The analysis unit can also analyze user purchase history to identify which product categories are most frequently purchased. This involves using metrics such as purchase frequency, purchase amount, and repeat purchase rate to analyze user purchasing trends. Furthermore, the analysis unit can use machine learning algorithms to extract patterns and trends from user behavior data and predict future behavior. For example, it can use clustering algorithms to identify user groups with similar behavioral patterns and develop optimal marketing strategies for each group. It can also use deep learning to predict user interests with high accuracy and provide personalized content and products. This allows the analysis unit to quickly and accurately analyze collected data and identify user interests. Furthermore, the analysis unit can utilize historical data and statistical information to evaluate long-term trends and risks, and formulate future countermeasures. This allows the analysis unit to not only grasp the situation in real time but also to formulate long-term strategies, thereby improving the reliability and effectiveness of the entire system.

[0073] The recommendation unit recommends products based on the analysis results obtained by the analysis unit. The recommendation unit uses methods such as collaborative filtering and content-based recommendation algorithms to recommend the most suitable products to users. Specifically, it uses collaborative filtering to recommend products relevant to the user based on data from other users with similar interests and purchase history. This involves analyzing the user's past purchase and browsing history to recommend products purchased and content viewed by other users. It also uses content-based recommendation algorithms to recommend products with similar characteristics based on the features of products and content the user has shown interest in in the past. This involves analyzing information such as product categories, attributes, and keywords to identify products that match the user's interests. Furthermore, the recommendation unit can respond to changes in user interests and preferences based on real-time updated data. For example, it can instantly update recommendations based on products or content the user has newly shown interest in. The recommendation unit can also collect user feedback to continuously improve the accuracy of its recommendation algorithms. This involves collecting data such as whether the user purchased the recommended products, and evaluations and comments on the recommendations, to evaluate the algorithm's performance. This allows the recommendation unit to recommend the most suitable products to users and improve the purchasing experience.

[0074] The question-answering unit uses natural language processing to answer user questions. For example, it uses natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis to understand user questions and generate appropriate answers. Specifically, if a user enters a question about a product, the unit analyzes the question and provides appropriate answers regarding product details, specifications, and usage. This involves referencing product databases and FAQ databases, extracting relevant information, and generating answers. Furthermore, if a user enters a question about the purchase process, the unit analyzes the question and provides appropriate answers regarding the purchase procedure, payment methods, and shipping information. In addition, the question-answering unit can use machine learning algorithms to understand the intent and context of user questions, enabling more natural dialogue. For example, even if a user enters an ambiguous question, it can generate an appropriate answer based on past dialogue history and relevant information. The question-answering unit can also collect user feedback and continuously improve the accuracy and quality of its answers. This involves providing a function for users to input ratings and comments on the provided answers, and evaluating the algorithm's performance based on this data. This allows the question-answering unit to answer user questions quickly and accurately, improving the purchase experience.

[0075] The chat function provides real-time chat with users. For example, it uses a chatbot to achieve real-time chat with users. Specifically, when a user enters a question into the chatbot, it immediately provides an answer. This is achieved using natural language processing technology to understand the user's question and generate an appropriate response. The chat function can also provide appropriate advice when a user enters a question about a product. This includes advice on how to choose, use, and maintain the product. Furthermore, the chat function can collect user feedback to continuously improve the accuracy and quality of the chatbot's responses. This involves providing a function for users to input ratings and comments on their interactions with the chatbot, and evaluating the algorithm's performance based on this data. In addition, the chat function can save the user's conversation history and refer to past conversations to achieve more consistent interactions. As a result, the chat function can provide quick and appropriate support through real-time chat with users, improving the purchasing experience.

[0076] The data collection unit can collect users' purchase history and browsing history. For example, the data collection unit can collect users' purchase history, such as purchase date and time, purchased items, and purchase amount. The data collection unit can also collect users' browsing history, such as pages viewed, viewing time, and viewing frequency. By collecting users' purchase and browsing history, more accurate data analysis becomes possible. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input users' purchase history and browsing history into a generating AI and have the generating AI perform the data collection.

[0077] The analysis unit can analyze the collected data and identify the user's interests and preferences. For example, the analysis unit can analyze the collected data using statistical analysis or machine learning algorithms. For example, the analysis unit can analyze the user's click history to identify which pages are viewed the most. The analysis unit can also analyze the user's purchase history to identify which product categories are purchased the most. This allows for more appropriate product recommendations by identifying the user's interests and preferences. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the collected data into a generating AI and have the generating AI identify the user's interests and preferences.

[0078] The recommendation system can recommend products based on identified interests. For example, it can use collaborative filtering or content-based recommendation algorithms to recommend the most suitable products to the user. For example, it can recommend related products based on the user's past purchases. It can also recommend products that the user might be interested in based on their browsing history. This allows for increased user purchasing intent by recommending products based on the user's interests. Some or all of the above processes in the recommendation system may be performed using AI, or not. For example, the recommendation system can input data for recommending products based on identified interests into a generating AI, and have the generating AI perform product recommendations.

[0079] The question-answering unit can answer user questions using natural language processing. For example, the question-answering unit uses natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis to understand user questions and generate appropriate answers. For instance, if a user inputs a question about a product, the question-answering unit analyzes the question and provides an appropriate answer. Furthermore, if a user inputs a question about the purchase procedure, the question-answering unit can analyze the question and provide an appropriate answer. This allows for quick and accurate answers to user questions by utilizing natural language processing. Some or all of the above-described processes in the question-answering unit may be performed using AI, or without AI. For example, the question-answering unit can input a user's question into a generating AI and have the generating AI generate an answer to the question.

[0080] The chat function can conduct real-time chats with users. For example, the chat function can use a chatbot to achieve real-time chats with users. For example, when a user enters a question into the chatbot, the chat function can immediately provide an answer. The chat function can also provide appropriate advice when a user enters a question about a product. In this way, users' doubts and concerns can be resolved immediately through real-time chat. Some or all of the above processes in the chat function may be performed using AI, for example, or without AI. For example, the chat function can input the content of the chat with the user into a generating AI and have the generating AI execute the real-time chat.

[0081] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, if the user is stressed, the data collection unit can reduce the frequency of data collection to alleviate the user's burden. For example, if the user is relaxed, the data collection unit can increase the frequency of data collection to collect more detailed data. For example, if the user is in a hurry, the data collection unit can collect data quickly and only the minimum necessary data. This reduces the user's burden by adjusting the timing of data 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into the generative AI and have the generative AI adjust the timing of data collection.

[0082] The data collection unit can analyze the user's past purchase and browsing history and select the optimal data collection method. For example, the data collection unit can prioritize collecting product categories that the user has frequently purchased in the past. For example, the data collection unit can also focus on collecting data about products that the user has viewed in the past but did not purchase. For example, the data collection unit can collect data related to specific seasons or events from the user's past purchase history. This allows the optimal data collection method to be selected by analyzing the user's past purchase and browsing history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's past purchase and browsing history into a generating AI and have the generating AI select the optimal data collection method.

[0083] The data collection unit can filter data based on the user's current areas of interest and behavioral patterns during data collection. For example, the data collection unit can prioritize collecting data related to product categories that the user is currently interested in. The data collection unit can also adjust the data collected at specific times based on the user's behavioral patterns. The data collection unit can also collect only highly relevant data based on the user's current areas of interest. This allows for the collection of highly relevant data by filtering the data based on the user's current areas of interest and behavioral patterns. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's current areas of interest and behavioral patterns into a generating AI and have the generating AI perform data filtering.

[0084] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated emotions. For example, if the user is stressed, the data collection unit will prioritize collecting only high-priority data. If the user is relaxed, the data collection unit may also prioritize collecting detailed data. If the user is in a hurry, the data collection unit may also prioritize collecting data that can be collected quickly. This allows for the priority collection of important data by determining the priority of data to collect 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 data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI determine the priority of the data.

[0085] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, the data collection unit can prioritize the collection of product information related to the area where the user is currently located. The data collection unit can also, for example, collect data on popular products in a specific region based on the user's geographical location information. The data collection unit can also, for example, collect region-specific promotional information based on the user's location information. This allows for the priority collection of highly relevant data by considering the user's geographical location information. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location information into a generating AI and have the generating AI perform the collection of highly relevant data.

[0086] The data collection unit can analyze the user's social media activity and collect relevant data during data collection. For example, the data collection unit can collect data about products mentioned by the user on social media. The data collection unit can also collect data related to product categories the user is interested in from the user's social media activity. The data collection unit can also collect data about products that the user's followers and friends on social media are interested in. In this way, relevant data can be collected by analyzing the user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's social media activity into a generating AI and have the generating AI perform the collection of relevant data.

[0087] The analysis unit can estimate the user's emotions and adjust the data analysis method based on the estimated user emotions. For example, if the user is stressed, the analysis unit can apply a simple analysis method and provide results quickly. For example, if the user is relaxed, the analysis unit can also apply a detailed analysis method to provide deeper insights. For example, if the user is in a hurry, the analysis unit can also apply an analysis method that provides results quickly. In this way, by adjusting the data analysis method according to the user's emotions, it is possible to provide analysis results that are appropriate for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the data analysis method.

[0088] The analysis unit can adjust the level of detail of the analysis based on the importance of the collected data during the analysis. For example, the analysis unit can perform a detailed analysis on data with high importance. For example, the analysis unit can also perform a simplified analysis on data with low importance. The analysis unit can also determine the priority of the analysis according to the importance of the data. This allows for efficient data analysis by adjusting the level of detail of the analysis based on the importance of the collected data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the importance of the collected data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0089] The analysis unit can apply different analysis algorithms depending on the data category during analysis. For example, the analysis unit can apply a sentiment analysis algorithm to product reviews. For example, the analysis unit can also apply a purchase pattern analysis algorithm to purchase history. For example, the analysis unit can also apply an interest analysis algorithm to browsing history. By applying different analysis algorithms depending on the data category, more accurate analysis results can be obtained. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the data category into a generating AI and have the generating AI execute the application of different analysis algorithms.

[0090] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is stressed, the analysis unit can provide a simple and highly visible display method. For example, if the user is relaxed, the analysis unit can also provide a display method that includes detailed information. For example, if the user is in a hurry, the analysis unit can also provide a display method that gets straight to the point. By adjusting the display method of the analysis results according to the user's emotions, it becomes possible to provide a display that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's emotion data into the generative AI and have the generative AI adjust the display method of the analysis results.

[0091] The analysis unit can determine the priority of analysis based on the data collection timing during analysis. For example, the analysis unit may prioritize the analysis of the most recent data. The analysis unit may also prioritize the most recent data while referring to past data. The analysis unit may also dynamically adjust the priority of analysis according to the data collection timing. This allows for the prioritization of analysis of the most recent data by determining the priority of analysis based on the data collection timing. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the data collection timing into a generating AI and have the generating AI determine the priority of analysis.

[0092] The analysis unit can adjust the order of analysis based on the relevance of the data during analysis. For example, the analysis unit may prioritize the analysis of highly relevant data. For example, the analysis unit may postpone the analysis of less relevant data. The analysis unit can also dynamically adjust the order of analysis according to the relevance of the data. This enables efficient data analysis by adjusting the order of analysis based on the relevance of the data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the relevance of the data into a generating AI and have the generating AI perform the adjustment of the order of analysis.

[0093] The recommendation section can estimate the user's emotions and adjust the way recommendations are presented based on those emotions. For example, if the user is stressed, the recommendation section can provide simple and easy-to-understand recommendations. If the user is relaxed, the recommendation section can also provide recommendations that include detailed information. If the user is in a hurry, the recommendation section can provide concise recommendations. By adjusting the way recommendations are presented according to the user's emotions, recommendations that are easy for the user to understand become possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recommendation section may be performed using AI or not. For example, the recommendation section can input user emotion data into a generative AI and have the generative AI adjust the way recommendations are presented.

[0094] The recommendation unit can adjust the level of detail of recommendations based on the importance of the products. For example, the recommendation unit provides detailed recommendation information for highly important products. For example, the recommendation unit can also provide simplified recommendation information for less important products. The recommendation unit can also dynamically adjust the level of detail of recommendations according to the importance of the products. This allows the recommendation unit to provide the most suitable recommendation information for the user by adjusting the level of detail of recommendations based on the importance of the products. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the importance of the products into a generating AI and have the generating AI perform the adjustment of the level of detail of recommendations.

[0095] The recommendation system can apply different recommendation algorithms depending on the product category during the recommendation process. For example, for electronic devices, the recommendation system might apply a recommendation algorithm that emphasizes technical features. For fashion items, the recommendation system might also apply a recommendation algorithm that emphasizes trends. For food products, the recommendation system might also apply a recommendation algorithm that emphasizes health consciousness. By applying different recommendation algorithms depending on the product category, more accurate recommendations become possible. Some or all of the above processing in the recommendation system may be performed using AI, for example, or without AI. For example, the recommendation system can input the product category into a generating AI and have the generating AI apply different recommendation algorithms.

[0096] The recommendation section can estimate the user's emotions and adjust the length of recommendations based on the estimated emotions. For example, if the user is stressed, the recommendation section will provide short, concise recommendations. If the user is relaxed, the recommendation section may provide longer recommendations with more detailed explanations. If the user is in a hurry, the recommendation section may provide short recommendations that can be quickly understood. By adjusting the length of recommendations according to the user's emotions, the recommendation section can provide the most suitable recommendation information for the user. 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 recommendation section may be performed using AI or not. For example, the recommendation section can input user emotion data into a generative AI and have the generative AI adjust the length of recommendations.

[0097] The recommendation system can determine the priority of recommendations based on the product submission timing. For example, the recommendation system may prioritize recommending new products. The recommendation system can also recommend seasonal products at the appropriate time. The recommendation system can also dynamically adjust the recommendation priority according to the product submission timing. This allows the system to recommend products to users at the optimal time by determining the recommendation priority based on the product submission timing. Some or all of the above processes in the recommendation system may be performed using AI, for example, or not using AI. For example, the recommendation system can input the product submission timing into a generating AI and have the generating AI determine the recommendation priority.

[0098] The recommendation unit can adjust the order of recommendations based on the relevance of the products. For example, the recommendation unit may prioritize recommending highly relevant products. For example, it may also postpone recommending less relevant products. The recommendation unit can also dynamically adjust the order of recommendations based on the relevance of the products. This allows the recommendation unit to recommend products in the optimal order for the user by adjusting the order of recommendations based on the relevance of the products. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the relevance of products into a generating AI and have the generating AI perform the adjustment of the recommendation order.

[0099] The question-answering unit can estimate the user's emotions and adjust its question-answering method based on the estimated emotions. For example, if the user is stressed, the question-answering unit can provide a concise and quick answer. For example, if the user is relaxed, the question-answering unit can provide an answer that includes a detailed explanation. For example, if the user is in a hurry, the question-answering unit can provide a concise answer. In this way, by adjusting the question-answering method according to the user's emotions, the system can provide the user with the most appropriate answer. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the question-answering unit may be performed using AI, for example, or not using AI. For example, the question-answering unit can input user emotion data into the generative AI and have the generative AI adjust the question-answering method.

[0100] The question-answering unit can provide the most appropriate answer by referring to the user's past question history when answering a question. For example, the question-answering unit can provide relevant answers based on the content of questions the user has asked in the past. For example, the question-answering unit can also prioritize providing answers to frequently asked questions from the user's past question history. For example, the question-answering unit can analyze the user's past question history and provide the most appropriate answer. This allows the unit to provide the most appropriate answer by referring to the user's past question history. Some or all of the above processing in the question-answering unit may be performed using AI, for example, or without AI. For example, the question-answering unit can input the user's past question history into a generating AI and have the generating AI perform the task of providing the most appropriate answer.

[0101] The question-answering unit can customize the content of its answers based on the user's current areas of interest when answering questions. For example, the question-answering unit can provide answers related to product categories that the user is currently interested in. The question-answering unit can also provide answers that contain highly relevant information based on the user's current areas of interest. The question-answering unit can also dynamically adjust the content of its answers according to the user's current areas of interest. This allows the system to provide the user with the most suitable answers by customizing the content of its answers based on the user's current areas of interest. Some or all of the above processing in the question-answering unit may be performed using AI, for example, or without AI. For example, the question-answering unit can input the user's current areas of interest into a generating AI and have the generating AI customize the content of its answers.

[0102] The question-answering unit can estimate the user's emotions and determine the priority of question-answering based on the estimated emotions. For example, if the user is stressed, the question-answering unit can provide a quick answer. For example, if the user is relaxed, the question-answering unit can also provide a detailed answer. For example, if the user is in a hurry, the question-answering unit can prioritize providing a concise answer. By determining the priority of question-answering according to the user's emotions, the system can provide answers at the optimal time for the user. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the question-answering unit may be performed using AI or not. For example, the question-answering unit can input user emotion data into a generative AI and have the generative AI determine the priority of question-answering.

[0103] The question-answering unit can provide the most relevant answer by considering the user's geographical location when answering a question. For example, the question-answering unit can provide an answer that includes information relevant to the area where the user is currently located. For example, the question-answering unit can also provide an answer that includes region-specific promotional information based on the user's geographical location. For example, the question-answering unit can provide an answer that includes region-specific information based on the user's location. This allows the system to provide highly relevant answers by considering the user's geographical location. Some or all of the above processing in the question-answering unit may be performed using AI, for example, or without AI. For example, the question-answering unit can input the user's geographical location information into a generating AI and have the generating AI perform the task of providing the most relevant answer.

[0104] The question-answering unit can analyze the user's social media activity and provide relevant answers when answering questions. For example, the question-answering unit can provide answers related to what the user has mentioned on social media. For example, the question-answering unit can also provide answers related to topics the user has shown interest in based on their social media activity. For example, the question-answering unit can provide answers related to topics that the user's followers or friends on social media have shown interest in. In this way, relevant answers can be provided by analyzing the user's social media activity. Some or all of the above processing in the question-answering unit may be performed using AI, for example, or without AI. For example, the question-answering unit can input the user's social media activity into a generating AI and have the generating AI perform the task of providing relevant answers.

[0105] The chat unit can estimate the user's emotions and adjust its chat style based on those emotions. For example, if the user is stressed, the chat unit will chat in a calm tone. If the user is relaxed, the chat unit can also chat in a friendly tone. If the user is in a hurry, the chat unit can also chat quickly and concisely. By adjusting the chat style according to the user's emotions, the system can provide optimal communication for the user. 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-described processes in the chat unit may be performed using AI or not. For example, the chat unit can input user emotion data into a generative AI and have the generative AI adjust the chat style.

[0106] The chat function can provide optimal communication by referring to the user's past chat history during a chat. For example, the chat function can provide relevant information based on what the user has mentioned in past chats. For example, the chat function can also prioritize providing answers to frequently asked questions based on the user's past chat history. For example, the chat function can analyze the user's past chat history to provide optimal communication. This allows the chat function to provide relevant and optimal communication by referring to the user's past chat history. Some or all of the above processing in the chat function may be performed using AI, for example, or not using AI. For example, the chat function can input the user's past chat history into a generating AI and have the generating AI perform the task of providing optimal communication.

[0107] The chat function can customize the chat content based on the user's current areas of interest during a chat. For example, the chat function can provide information related to product categories that the user is currently interested in. The chat function can also initiate a chat that includes highly relevant information based on the user's current areas of interest. The chat function can also dynamically adjust the chat content according to the user's current areas of interest. This allows the chat function to provide the user with the most relevant information by customizing the chat content based on the user's current areas of interest. Some or all of the above processing in the chat function may be performed using AI, for example, or without AI. For example, the chat function can input the user's current areas of interest into a generating AI and have the generating AI customize the chat content.

[0108] The chat unit can estimate the user's emotions and prioritize chats based on those emotions. For example, if the user is stressed, the chat unit can start a chat quickly. If the user is relaxed, the chat unit can also provide a chat with more detailed information. If the user is in a hurry, the chat unit can prioritize providing a concise chat. By prioritizing chats according to the user's emotions, communication can be provided at the optimal time for the user. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the chat unit may be performed using AI or not. For example, the chat unit can input user emotion data into a generative AI and have the generative AI determine the priority of chats.

[0109] The chat function can provide optimal communication during a chat, taking into account the user's geographical location. For example, the chat function can provide chats that include information relevant to the user's current location. For example, the chat function can also provide chats that include region-specific promotional information based on the user's geographical location. For example, the chat function can provide chats that include region-specific information based on the user's location. This allows for the provision of highly relevant communication by considering the user's geographical location. Some or all of the above processing in the chat function may be performed using AI, for example, or without AI. For example, the chat function can input the user's geographical location information into a generating AI and have the generating AI perform the task of providing optimal communication.

[0110] The chat unit can analyze the user's social media activity during a chat and provide relevant chat content. For example, the chat unit can provide information related to what the user has mentioned on social media. For example, the chat unit can also provide chats that include information related to topics the user has shown interest in, based on the user's social media activity. For example, the chat unit can also provide chats that include information related to topics that the user's followers and friends on social media have shown interest in. In this way, relevant chat content can be provided by analyzing the user's social media activity. Some or all of the above processing in the chat unit may be performed using AI, for example, or without AI. For example, the chat unit can input the user's social media activity into a generating AI and have the generating AI provide relevant chat content.

[0111] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0112] The AI ​​agent system can also include a trust rating unit that evaluates the user's level of trust in specific brands and manufacturers based on their purchase history. This unit, for example, analyzes reviews and ratings of products the user has previously purchased to calculate a level of trust in those brands and manufacturers. The unit can, for example, prioritize recommending brands and manufacturers that the user has given high ratings to. It can also adjust recommendations to avoid brands and manufacturers that the user has given low ratings to. This enables product recommendations based on user trust levels, thereby improving user satisfaction.

[0113] The AI ​​agent system can also include a seasonal event recommendation unit that prioritizes recommending products related to specific seasons or events based on the user's purchase and browsing history. For example, the seasonal event recommendation unit could analyze products the user has purchased during the Christmas season in the past and recommend similar seasonal products. Alternatively, it could prioritize recommending summer-related products based on products the user has purchased during the summer. Furthermore, the seasonal event recommendation unit could recommend products related to similar events (e.g., birthdays or anniversaries) based on the user's purchase history of products related to those events. This enables product recommendations tailored to the user's season and events, thereby increasing their purchasing intent.

[0114] The AI ​​agent system may also include a support adjustment unit that estimates the user's emotions and adjusts the method of support based on those emotions. For example, if the user is stressed, the support adjustment unit may provide concise and quick support. If the user is relaxed, the support adjustment unit may also provide support that includes detailed explanations. Furthermore, if the user is in a hurry, the support adjustment unit may prioritize providing concise support. This enables support that is tailored to the user's emotions, thereby improving user satisfaction.

[0115] The AI ​​agent system can also include a price monitoring unit that monitors price fluctuations of specific products based on the user's purchase and browsing history, and notifies the user of the optimal purchase timing. For example, the price monitoring unit analyzes price fluctuations of products the user has previously purchased and notifies the user when the price drops. The price monitoring unit can also notify the user in real time if the price of a product the user is interested in drops. Furthermore, the price monitoring unit can collect sales information for specific products and notify the user. This allows the user to purchase products at the optimal time, improving cost performance.

[0116] The AI ​​agent system may also include an explanation adjustment unit that estimates the user's emotions and adjusts the way product descriptions are presented to the user based on the estimated emotions. For example, if the user is stressed, the explanation adjustment unit may provide a concise and visually appealing product description. If the user is relaxed, for example, the explanation adjustment unit may also provide a product description that includes detailed information. Furthermore, if the user is in a hurry, the explanation adjustment unit may prioritize providing a product description that gets straight to the point. This enables product descriptions that are tailored to the user's emotions, thereby deepening the user's understanding.

[0117] The AI ​​agent system can also include an inventory monitoring unit that monitors the stock status of specific products based on the user's purchase and browsing history, and notifies the user when stock levels become low. For example, the inventory monitoring unit monitors the stock status of products the user has previously purchased and notifies the user when stock levels become low. The inventory monitoring unit can also notify the user in real time if the stock of a product the user is interested in becomes low. Furthermore, the inventory monitoring unit can collect restock information for specific products and notify the user. This allows users to purchase products before stock levels become low, preventing them from missing out on purchase opportunities.

[0118] The AI ​​agent system can also include a timing adjustment unit that estimates the user's emotions and adjusts the timing of product recommendations based on those emotions. For example, if the user is stressed, the timing adjustment unit can reduce the frequency of product recommendations to lessen the user's burden. If the user is relaxed, the timing adjustment unit can increase the frequency of product recommendations and provide more detailed information. Furthermore, if the user is in a hurry, the timing adjustment unit can provide product recommendations that can be quickly understood. This enables product recommendations to be timed according to the user's emotions, thereby increasing the user's willingness to purchase.

[0119] The AI ​​agent system can also include a review analysis unit that analyzes reviews and ratings of specific products based on the user's purchase and browsing history, providing highly reliable information. For example, the review analysis unit can analyze reviews of products the user has previously purchased and extract highly reliable reviews. It can also analyze reviews of products the user is interested in and provide highly reliable information. Furthermore, the review analysis unit can analyze ratings of specific products and provide information beneficial to the user. This allows users to make purchase decisions based on reliable information, thereby improving post-purchase satisfaction.

[0120] The AI ​​agent system may also include a chat support adjustment unit that estimates the user's emotions and adjusts the chat support method based on the estimated emotions. For example, if the user is stressed, the chat support adjustment unit will provide chat support in a calm tone. If the user is relaxed, the chat support adjustment unit may also provide chat support in a friendly tone. Furthermore, if the user is in a hurry, the chat support adjustment unit can provide quick and concise chat support. This enables chat support that is tailored to the user's emotions, thereby improving user satisfaction.

[0121] The AI ​​agent system can also include a quality evaluation unit that evaluates the quality of specific products based on the user's purchase and browsing history, and prioritizes recommending high-quality products. For example, the quality evaluation unit can analyze the quality of products the user has previously purchased and extract high-quality products. It can also analyze the quality of products the user has shown interest in and prioritize recommending high-quality products. Furthermore, the quality evaluation unit can evaluate the quality of specific products and provide the user with useful information. This allows users to purchase high-quality products and improve their post-purchase satisfaction.

[0122] The following briefly describes the processing flow for example form 2.

[0123] Step 1: The data collection unit collects user behavior data. The data collection unit collects behavioral data such as user click history, browsing time, and purchase history. For example, the data collection unit records a user's click history on a website and collects data on which pages were viewed and for how long. The data collection unit can also record the history of products purchased by users and collect data such as the date and time of purchase, the products purchased, and the purchase amount. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the data using, for example, statistical analysis and machine learning algorithms to identify user interests and preferences. For example, the analysis unit analyzes user click history to identify which pages are viewed the most. The analysis unit can also analyze user purchase history to identify which product categories are purchased the most. Step 3: The recommendation unit recommends products based on the analysis results obtained by the analysis unit. The recommendation unit recommends the most suitable products for the user, for example, using collaborative filtering or content-based recommendation algorithms. The recommendation unit recommends related products based on products the user has purchased in the past. The recommendation unit can also recommend products that the user might be interested in based on their browsing history. Step 4: The question answering unit uses natural language processing to answer the user's questions. The question answering unit uses natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis to understand the user's questions and generate appropriate answers. For example, if the user enters a question about a product, the question answering unit will analyze the question and provide an appropriate answer. The question answering unit can also analyze a question if the user enters a question about the purchase procedure and provide an appropriate answer. Step 5: The chat unit conducts real-time chats with users. The chat unit achieves real-time chats with users, for example, by using a chatbot. For example, when a user enters a question into the chatbot, the chat unit will immediately provide an answer. The chat unit can also provide appropriate advice when a user enters a question about a product.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] Each of the multiple elements described above, including the data collection unit, analysis unit, recommendation unit, question answering unit, and chat unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data collection unit collects the user's click history and browsing time by the control unit 46A of the smart device 14, and the purchase history by the identification processing unit 290 of the data processing unit 12. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the collected data. The recommendation unit is implemented in the identification processing unit 290 of the data processing unit 12 and recommends products based on the analysis results. The question answering unit is implemented in the identification processing unit 46A of the smart device 14 and answers the user's questions using natural language processing. The chat unit is implemented in the identification processing unit 46A of the smart device 14 and conducts real-time chat with the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0128] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] Each of the multiple elements described above, including the data collection unit, analysis unit, recommendation unit, question answering unit, and chat unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit collects the user's click history and browsing time by the control unit 46A of the smart glasses 214, and the purchase history by the identification processing unit 290 of the data processing unit 12. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the collected data. The recommendation unit is implemented in the identification processing unit 290 of the data processing unit 12 and recommends products based on the analysis results. The question answering unit is implemented in the identification processing unit 46A of the smart glasses 214 and answers the user's questions using natural language processing. The chat unit is implemented in the identification processing unit 46A of the smart glasses 214 and conducts real-time chat with the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0144] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] Each of the multiple elements described above, including the data collection unit, analysis unit, recommendation unit, question answering unit, and chat unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data collection unit collects the user's click history and browsing time by the control unit 46A of the headset terminal 314, and the purchase history by the identification processing unit 290 of the data processing unit 12. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the collected data. The recommendation unit is implemented in the identification processing unit 290 of the data processing unit 12 and recommends products based on the analysis results. The question answering unit is implemented in the identification processing unit 46A of the headset terminal 314 and answers the user's questions using natural language processing. The chat unit is implemented in the identification processing unit 46A of the headset terminal 314 and conducts real-time chat with the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0160] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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).

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.).

[0173] 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.

[0174] 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.

[0175] 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.

[0176] Each of the multiple elements described above, including the data collection unit, analysis unit, recommendation unit, question answering unit, and chat unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the data collection unit collects the user's click history and browsing time by the control unit 46A of the robot 414, and the purchase history by the identification processing unit 290 of the data processing unit 12. The analysis unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and analyzes the collected data. The recommendation unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and recommends products based on the analysis results. The question answering unit is implemented by, for example, the control unit 46A of the robot 414 and answers the user's questions using natural language processing. The chat unit is implemented by, for example, the control unit 46A of the robot 414 and conducts real-time chat with the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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."

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] (Note 1) A data collection unit that collects user behavior data, An analysis unit analyzes the data collected by the aforementioned collection unit, A recommendation unit recommends products based on the analysis results obtained by the aforementioned analysis unit, A question answering unit that answers user questions, It includes a chat section for real-time chat. A system characterized by the following features. (Note 2) The aforementioned collection unit is Collects users' purchase and browsing history. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, The collected data is analyzed to identify the user's interests and preferences. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned recommendation department, Recommend products based on identified interests and preferences. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned question answering unit is Use natural language processing to answer user questions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned chat section is, Conduct real-time chat with users The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Analyze users' past purchase and browsing history to select the most suitable data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting data, filtering is performed based on the user's current areas of interest and behavioral patterns. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting data, the system prioritizes the collection of highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is During data collection, the system analyzes users' social media activity and collects relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, We estimate the user's emotions and adjust the data analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the collected data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, the priority of the analysis is determined based on when the data was collected. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, adjust the order of analysis based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned recommendation department, It estimates the user's emotions and adjusts the way recommendations are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned recommendation department, When making recommendations, adjust the level of detail based on the importance of the product. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned recommendation department, When making recommendations, different recommendation algorithms are applied depending on the product category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned recommendation department, It estimates the user's sentiment and adjusts the length of recommendations based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned recommendation department, When making a recommendation, we will prioritize recommendations based on when the product was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned recommendation department, When making recommendations, the order of recommendations is adjusted based on the relevance of the products. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned question answering unit is It estimates the user's emotions and adjusts the question-answering method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned question answering unit is When answering questions, the system provides the most appropriate answer by referring to the user's past question history. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned question answering unit is When answering questions, customize the content of the answers based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned question answering unit is The system estimates the user's emotions and prioritizes question responses based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned question answering unit is When answering questions, the system takes the user's geographical location into consideration to provide the most appropriate answer. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned question answering unit is When answering questions, the system analyzes the user's social media activity to provide relevant answers. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned chat section is, It estimates the user's emotions and adjusts the chat method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned chat section is, During chats, the system provides optimal communication by referencing the user's past chat history. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned chat section is, During a chat, the chat content is customized based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned chat section is, It estimates the user's emotions and prioritizes chats based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned chat section is, When chatting, we provide optimal communication by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned chat section is, During chats, the system analyzes the user's social media activity and provides relevant chat content. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0196] 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. A data collection unit that collects user behavior data, An analysis unit analyzes the data collected by the aforementioned collection unit, A recommendation unit recommends products based on the analysis results obtained by the aforementioned analysis unit, A question answering unit that answers user questions, It includes a chat section for real-time chat. A system characterized by the following features.

2. The aforementioned collection unit is Collects users' purchase and browsing history. The system according to feature 1.

3. The aforementioned analysis unit, The collected data is analyzed to identify the user's interests and preferences. The system according to feature 1.

4. The aforementioned recommendation department, Recommend products based on identified interests and preferences. The system according to feature 1.

5. The aforementioned question answering unit is Use natural language processing to answer user questions. The system according to feature 1.

6. The aforementioned chat section is, Conduct real-time chat with users The system according to feature 1.

7. The aforementioned collection unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is Analyze users' past purchase and browsing history to select the most suitable data collection method. The system according to feature 1.

9. The aforementioned collection unit is When collecting data, filtering is performed based on the user's current areas of interest and behavioral patterns. The system according to feature 1.

10. The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system according to feature 1.

Images