system

Abstract

The system according to this embodiment aims to maximize advertising effectiveness by analyzing the user's usage history and product information. [Solution] The system according to the embodiment comprises a consumer AI, a sales AI, a conversation unit, and a request unit. The consumer AI analyzes the user's usage history. The sales AI analyzes product information. The conversation unit facilitates conversations between the consumer AI and the sales AI. The request unit requests advertising placement from customers who are estimated to have a high probability of purchasing a product, as identified by the conversation unit.

Description

Technical Field

[0004] ,

[0006] , , , ,

[0005] , , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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 conventional technology, advertisement targeting is not performed with sufficient accuracy, and there is room for improvement in maximizing the advertisement effect.

[0005] The system according to the embodiment analyzes the usage history of the user and the information of the product, and aims to maximize the advertisement effect.

Means for Solving the Problems

[0006] The system according to the embodiment includes a consumer AI, a sales AI, a conversation unit, and a request unit. The consumer AI analyzes the usage history of the user. The sales AI analyzes the information of the product. The conversation unit enables the consumer AI and the sales AI to communicate. The request unit requests advertisement placement to customers who are estimated to have a high probability of purchasing the product found by the conversation unit. [Effects of the Invention]

[0007] The system according to this embodiment can analyze the user's usage history and product information to maximize advertising effectiveness. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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 reverse advertising service according to an embodiment of the present invention is based on a new concept that reverses the conventional advertising model. This reverse advertising service is a system that uses AI to automatically match users with products, and the platform pays the advertising fees. First, the reverse advertising service creates a consumer AI that has been trained on the user's usage history. This consumer AI analyzes the user's interests and preferences based on, for example, their usage history on social media and e-commerce sites. Next, it creates a sales AI that has been trained on products. This sales AI understands the characteristics of products and target customers by collecting product information from the web as well as having the seller write the information. Next, the consumer AI and the sales AI converse to find customers with a high probability of purchasing the product. This conversation is a process in which the AIs compare the user's interests and preferences with the characteristics of the product. For example, if the consumer AI determines that "this user is interested in sports equipment," the sales AI will respond, "this sports equipment is suitable for this user." After that, the product owner is asked to place an advertisement. In this case, the product owner receives compensation as an advertising fee. However, if the product is sold, the reverse advertising service receives an incentive. This system allows those who want to sell products to place advertisements without considering the cost disadvantages. Reverse advertising services use advanced AI to identify highly qualified customers, solving the problem of unknown advertising effectiveness. Furthermore, even without a budget, the platform pays the advertising fees, allowing those who want to sell products to use the service without worrying about cost-effectiveness. In short, reverse advertising services allow those who want to sell products to place advertisements without considering the cost disadvantages.

[0029] The reverse advertising service according to this embodiment comprises a consumer AI, a sales AI, a conversation unit, and a request unit. The consumer AI analyzes the user's usage history. The user's usage history includes, but is not limited to, browsing history, purchase history, and search history. The consumer AI performs the analysis using methods such as data mining, statistical analysis, and machine learning algorithms. The sales AI analyzes product information. The product information includes, but is not limited to, price, specifications, reviews, and stock status. The sales AI performs the analysis based on information provided by the seller and information automatically collected from the web. The conversation unit handles the process of the consumer AI and the sales AI conversing. The conversation unit conducts the conversation using methods such as natural language processing, dialogue systems, and chatbots. The request unit requests advertising placement to customers with a high probability of purchasing a product, as identified by the conversation unit. The request unit requests advertising placement using, for example, an advertising platform and targeting methods. As a result, the reverse advertising service according to this embodiment can analyze the user's usage history and product information, and request advertisements to be placed with customers who are highly likely to purchase the product.

[0030] Consumer AI analyzes users' usage history. This history includes, but is not limited to, browsing history, purchase history, and search history. Consumer AI performs this analysis using methods such as data mining, statistical analysis, and machine learning algorithms. Specifically, it analyzes users' browsing history to identify what products and services they are interested in. For example, it understands user preferences by focusing on categories and specific brands that users frequently browse. By analyzing purchase history, it understands trends in products and services users have purchased in the past and identifies products likely to be repurchased. Furthermore, by analyzing search history, it identifies products and services users are currently interested in, understanding their real-time needs. Consumer AI integrates this data to analyze user behavior patterns and preferences in detail. It uses data mining techniques to extract useful patterns and trends from user behavior data and evaluates the reliability and significance of the data through statistical analysis. Using machine learning algorithms, it predicts future behavior based on user behavior data and builds a foundation for personalized advertising and recommendations. This allows consumer AI to analyze users' usage history in detail and provide information to deliver advertisements and suggestions that are best suited to each individual user.

[0031] Sales AI analyzes product information. This information includes, but is not limited to, price, specifications, reviews, and stock availability. For example, sales AI analyzes information provided by sellers and information automatically collected from the web. Specifically, sales AI analyzes product pricing information and compares prices with competitors to propose the optimal pricing. It also analyzes product specifications to identify the product best suited to the user's needs. For example, it proposes products that meet the requirements of users who prioritize specific functions or performance. Furthermore, it analyzes product review information and evaluates product quality and reliability based on user ratings and feedback. By analyzing the content of reviews using natural language processing technology and understanding trends in positive and negative evaluations, it identifies the product's strengths and weaknesses. It also monitors stock availability in real time and encourages users to purchase at the appropriate time based on information such as out-of-stock items and expected arrival dates. Sales AI integrates this information to build a foundation for making optimal product recommendations to users. By utilizing not only information provided by sellers but also information automatically collected from the web, it can make recommendations that reflect the latest market trends and competitor information. This allows the sales AI to analyze product information in detail and provide information to make optimal product recommendations to users.

[0032] The conversational unit handles the process of conversations between consumer AI and sales AI. The conversational unit uses methods such as natural language processing, dialogue systems, and chatbots for these conversations. Specifically, it generates dialogues to provide optimal product recommendations to users based on user usage history analyzed by the consumer AI and product information analyzed by the sales AI. Using natural language processing technology, it generates appropriate responses to user questions and requests, ensuring smooth dialogue flow. For example, if a user asks about a specific product, the conversational unit provides detailed explanations and reviews based on product information obtained from the sales AI. It also suggests related and recommended products based on the user's preferences and past purchase history. Using a dialogue system, it continuously engages with users to understand their needs and interests in real time. Chatbot technology automates user interactions, providing 24 / 7 support. This allows the conversational unit to generate dialogues that enable the consumer AI and sales AI to collaborate and provide optimal product recommendations, thereby improving user satisfaction. Furthermore, the conversational unit can accumulate user dialogue history and utilize it as data to improve the quality of future conversations. This allows the conversational unit to build a foundation for providing personalized dialogues to users and making optimal product recommendations.

[0033] The requesting department requests advertising placement to customers identified by the conversation department as having a high probability of purchasing a product. The requesting department uses advertising platforms and targeting methods to request advertising placement. Specifically, based on information obtained from the conversation department, the requesting department identifies customers with a high probability of purchasing a product and displays the most suitable advertisements to those customers. By using advertising platforms, personalized advertisements are delivered to specific customer segments to maximize advertising effectiveness. Targeting methods are used to determine the optimal timing and content of advertisements based on customer attributes and behavioral data. For example, advertisements for products and services likely to interest customers are displayed based on their past purchase and browsing history. Furthermore, real-time data analysis allows for dynamic changes to advertisement content in response to changes in customer behavior. This enables the requesting department to deliver effective advertisements to customers with a high probability of purchasing a product, improving the conversion rate of advertisements. In addition, the requesting department can continuously monitor the effectiveness of advertisements and use this information to improve advertising strategies. For example, by analyzing click-through rates and conversion rates and comparing high-performing and low-performing advertisements, the content and delivery methods of advertisements can be optimized. This allows the requesting department to maximize the effectiveness of their advertising and provide the most suitable ads to customers who are most likely to purchase the product.

[0034] The reverse advertising service includes a collection unit that collects user activity history. The collection unit may, for example, collect the user's browsing history. The collection unit may also, for example, collect the user's purchase history. The collection unit may also, for example, collect the user's search history. This allows the consumer AI to perform more accurate analysis by collecting the user's activity history. Activity history includes, but is not limited to, browsing history, purchase history, and search history. Some or all of the processing described above in the collection unit may be performed using, for example, AI, or not using AI. For example, the collection unit may input the user's activity history into an AI model and have the AI ​​perform the collection of activity history.

[0035] The reverse advertising service includes a data collection unit that collects product information. The data collection unit may, for example, collect product price information. The data collection unit may also, for example, collect product specification information. The data collection unit may also, for example, collect product review information. This allows the sales AI to perform more accurate analysis by collecting product information. Product information includes, but is not limited to, price, specifications, reviews, and stock availability. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input product information into an AI model and have the AI ​​perform the collection of product information.

[0036] The reverse advertising service includes a payment unit that pays advertising fees. The payment unit can pay advertising fees, for example, by bank transfer. The payment unit can also pay advertising fees by credit card, for example. The payment unit can also pay advertising fees by electronic money, for example. This allows the payment unit to enable people who want to sell products to place advertisements without considering the cost disadvantages by paying advertising fees. Advertising fees include, but are not limited to, fee structures, payment methods, and discount conditions. Some or all of the above processing in the payment unit may be performed using, for example, AI, or not using AI. For example, the payment unit can input the payment of advertising fees into an AI model and have the AI ​​select the payment method.

[0037] The reverse advertising service includes a management department that manages incentives when a product is sold. The management department manages, for example, the rewards for when a product is sold. The management department may also manage, for example, bonuses for when a product is sold. The management department may also manage, for example, points for when a product is sold. In this way, the management department can properly manage the incentives for the reverse advertising service by managing the incentives for when a product is sold. Incentives include, but are not limited to, rewards, bonuses, and points. Some or all of the above processes in the management department may be performed, for example, using AI or not using AI. For example, the management department can input the incentive management into an AI model and have the AI ​​select the management method.

[0038] Consumer AI can analyze a user's interests and preferences based on their usage history of social media or e-commerce sites. For example, consumer AI can analyze a user's interests and preferences based on their social media browsing history. Consumer AI can also analyze a user's interests and preferences based on their purchase history on e-commerce sites. Consumer AI can also analyze a user's interests and preferences based on their social media search history. This allows consumer AI to perform more accurate analysis by analyzing a user's interests and preferences based on their usage history of social media and e-commerce sites. Interests and preferences include, but are not limited to, hobbies, interests, and purchasing intent. Some or all of the above processing in consumer AI may be performed using AI, for example, or without AI. For example, consumer AI can input social media usage history into an AI model and have the AI ​​perform the analysis of interests and preferences.

[0039] The sales AI can collect product information automatically from the web, in addition to information written by the seller. For example, the sales AI can collect price information for products written by the seller. The sales AI can also automatically collect product specification information from the web. The sales AI can also collect product review information written by the seller. This allows the sales AI to analyze product information more accurately by collecting it automatically from the web in addition to information written by the seller. Product information includes, but is not limited to, price, specifications, reviews, and stock status. Some or all of the above processes in the sales AI may be performed using AI, for example, or not using AI. For example, the sales AI can input product information into an AI model and have the AI ​​perform the collection of product information.

[0040] The conversational unit can perform a process in which the consumer AI and sales AI compare the user's interests and preferences with the characteristics of products. For example, the conversational unit can have the consumer AI identify the user's interests and preferences, and the sales AI provide product information based on those interests. The conversational unit can also have the consumer AI analyze the user's purchase history, and the sales AI provide product information based on that history. For example, the conversational unit can have the consumer AI identify the user's areas of interest, and the sales AI provide product information related to those areas. In this way, the conversational unit can find customers with a high probability of purchasing a product by having the consumer AI and sales AI perform a process in which the user's interests and preferences match the characteristics of products. Interests and preferences include, but are not limited to, hobbies, interests, and purchasing intent. Product characteristics include, but are not limited to, features, design, and price range. Some or all of the above processing in the conversational unit may be performed using AI, for example, or not using AI. For example, the conversational unit can input the conversation between the consumer AI and the sales AI into an AI model and have the AI ​​execute the conversational process.

[0041] Consumer AI can analyze a user's past purchase history and predict changes in their interests and preferences. For example, consumer AI can analyze the categories of products a user has purchased in the past and predict recent purchase trends. Consumer AI can also analyze the price range of products a user has purchased in the past and predict changes in their budget. Consumer AI can also analyze the brands of products a user has purchased in the past and predict changes in their brand preferences. In this way, consumer AI can predict changes in a user's interests and preferences by analyzing their past purchase history. Purchase history includes, but is not limited to, purchase date and time, purchased items, and purchase amount. Changes in interests and preferences include, but are not limited to, past purchase patterns and changes in trends. Some or all of the above processing in consumer AI may be performed using AI, for example, or not using AI. For example, consumer AI can input a user's purchase history data into an AI model and have the AI ​​predict changes in interests and preferences.

[0042] Consumer AI can filter usage history based on the user's lifestyle and areas of interest. For example, if a user is raising children, the consumer AI will prioritize analyzing usage history related to childcare products. If a user is a sports enthusiast, the consumer AI can also prioritize analyzing usage history related to sports equipment. If a user enjoys traveling, the consumer AI can also prioritize analyzing usage history related to travel products. This allows the consumer AI to perform more relevant analysis by filtering based on the user's lifestyle and areas of interest. Lifestyle includes, but is not limited to, family structure, income, and living environment. Areas of interest include, but is not limited to, hobbies, work, and learning. Some or all of the above processing in the consumer AI may be performed using AI, or not using AI. For example, the consumer AI can input user lifestyle data into an AI model and have the AI ​​perform the filtering.

[0043] Consumer AI can prioritize the analysis of highly relevant data by considering the user's geographical location when analyzing usage history. For example, the consumer AI can prioritize the analysis of usage history related to products from stores near the user's current location. The consumer AI can also prioritize the analysis of usage history related to products from stores in areas the user frequently visits. The consumer AI can also prioritize the analysis of usage history related to products from stores in areas the user is traveling to. This allows the consumer AI to analyze more relevant data by considering the user's geographical location. Geographical location information includes, but is not limited to, addresses, GPS data, and regional codes. Some or all of the above processing in the consumer AI may be performed using AI, for example, or without AI. For example, the consumer AI can input the user's geographical location information into an AI model and have the AI ​​perform the analysis of highly relevant data.

[0044] The consumer AI can analyze a user's social media activity and analyze relevant data when analyzing usage history. For example, the consumer AI can prioritize analyzing usage history related to products that a user has "liked" on social media. The consumer AI can also prioritize analyzing usage history related to products that a user has shared on social media. The consumer AI can also prioritize analyzing usage history related to products that a user has commented on on social media. This allows the consumer AI to analyze more relevant data by analyzing the user's social media activity. Social media activity includes, but is not limited to, posts, the number of likes, and the number of followers. Some or all of the above processing in the consumer AI may be performed using AI, for example, or not using AI. For example, the consumer AI can input the user's social media activity data into an AI model and have the AI ​​perform the analysis of the relevant data.

[0045] Sales AI can analyze a product's past sales history and predict the characteristics of target customers. For example, sales AI can identify products popular with a specific age group from past sales data. Sales AI can also identify products popular in a specific region from past sales data. Sales AI can also identify products popular in a specific season from past sales data. This allows sales AI to predict the characteristics of target customers by analyzing a product's past sales history. Sales history includes, but is not limited to, sales date and time, products sold, and sales amount. Characteristics of target customers include, but are not limited to, age, gender, and purchasing behavior. Some or all of the above processing in sales AI may be performed using AI, for example, or not using AI. For example, sales AI can input product sales history data into an AI model and have the AI ​​predict the characteristics of target customers.

[0046] Sales AI can filter product information based on product characteristics and target customers when analyzing product data. For example, sales AI can prioritize providing information on high-priced products to customers who tend to purchase high-priced products. Sales AI can also prioritize providing information on products from a specific brand to customers who prefer that brand. Sales AI can also prioritize providing information on products in a specific category to customers who tend to purchase products in that category. This allows sales AI to perform more relevant analysis by filtering based on product characteristics and target customers. Product characteristics include, but are not limited to, features, design, and price range. Target customers include, but are not limited to, age, gender, and purchasing behavior. Some or all of the above processing in sales AI may be performed using AI, for example, or not using AI. For example, sales AI can input product characteristic data into an AI model and have the AI ​​perform the filtering.

[0047] Sales AI can prioritize the analysis of highly relevant data by considering the geographical distribution of products when analyzing product information. For example, a sales AI can prioritize the analysis of product information that is popular in a particular region. A sales AI can also prioritize the analysis of product information that has a proven sales record in a particular region. A sales AI can also prioritize the analysis of newly launched product information in a particular region. This allows the sales AI to analyze more relevant data by considering the geographical distribution of products. Geographical distribution includes, but is not limited to, regional sales data and population distribution. Some or all of the above processing in sales AI may be performed using AI, for example, or without AI. For example, a sales AI can input geographical distribution data of products into an AI model and have the AI ​​perform the analysis of highly relevant data.

[0048] Sales AI can improve the accuracy of its analysis by referencing relevant market data when analyzing product information. For example, sales AI can prioritize the analysis of popular product information by referencing market trend data. Sales AI can also analyze points of differentiation from competing products by referencing market competitor data. Sales AI can also prioritize the analysis of high-demand product information by referencing market demand data. In this way, sales AI can improve the accuracy of its analysis by referencing relevant market data. Market data includes, but is not limited to, market size, competitor information, and trend data. Some or all of the above processing in sales AI may be performed using AI, for example, or not using AI. For example, sales AI can input market data into an AI model and have the AI ​​perform the improvement of analysis accuracy.

[0049] The conversational unit can improve the accuracy of conversations by considering the interrelationship between the consumer AI and the sales AI during a conversation. For example, the conversational unit can have the consumer AI identify the user's interests, and the sales AI provide product information based on those interests. Alternatively, the conversational unit can have the consumer AI analyze the user's purchase history, and the sales AI provide product information based on that history. The conversational unit can also have the consumer AI identify the user's areas of interest, and the sales AI provide product information related to those areas. In this way, the conversational unit can improve the accuracy of conversations by considering the interrelationship between the consumer AI and the sales AI. This interrelationship includes, but is not limited to, methods of data sharing and collaboration processes. Some or all of the above processing in the conversational unit may be performed using AI, for example, or not using AI. For example, the conversational unit can input data from the consumer AI and the sales AI into an AI model and have the AI ​​perform the conversation accuracy improvement.

[0050] The conversation unit can conduct conversations while considering the user's attribute information. For example, the conversation unit can provide appropriate product information based on the user's age. The conversation unit can also provide appropriate product information based on the user's gender. The conversation unit can also provide appropriate product information based on the user's occupation. This allows the conversation unit to conduct more appropriate conversations by considering the user's attribute information. Attribute information includes, but is not limited to, age, gender, and occupation. Some or all of the above processing in the conversation unit may be performed using, for example, AI, or not using AI. For example, the conversation unit can input the user's attribute information into an AI model and have the AI ​​perform the conversation.

[0051] The conversational unit can conduct conversations while considering the geographical distribution of products. For example, the conversational unit may prioritize providing information on products that are popular in a particular region. The conversational unit may also prioritize providing information on products that have a proven sales record in a particular region. The conversational unit may also prioritize providing information on newly launched products in a particular region. This allows the conversational unit to conduct more appropriate conversations by considering the geographical distribution of products. Geographical distribution includes, but is not limited to, regional sales data and population distribution. Some or all of the processing described above in the conversational unit may be performed using, for example, AI, or not using AI. For example, the conversational unit can input geographical distribution data of products into an AI model and have the AI ​​perform the conversation.

[0052] The conversational unit can improve the accuracy of its conversations by referring to relevant literature during the conversation. For example, the conversational unit can refer to relevant research papers to explain the effects of a product. The conversational unit can also refer to relevant market reports to explain the demand for a product. The conversational unit can also refer to relevant user reviews to explain the evaluation of a product. In this way, the conversational unit can improve the accuracy of its conversations by referring to relevant literature. Literature includes, but is not limited to, academic papers, technical reports, and industry reports. Some or all of the processing described above in the conversational unit may be performed using, for example, AI, or not using AI. For example, the conversational unit can input relevant literature data into an AI model and have the AI ​​perform the task of improving the accuracy of the conversation.

[0053] The requesting department can select the most suitable request method when making an advertising placement request by referring to past request history. For example, the requesting department can select a request method with a high success rate from past request history. The requesting department can also select a request method that is effective for a specific target customer from past request history. The requesting department can also select a request method for a specific product from past request history. In this way, the requesting department can select the most suitable request method by referring to past request history. Request history includes, but is not limited to, past request dates and times, request content, and request results. The most suitable request method includes, but is not limited to, success rate, cost efficiency, and target suitability. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input past request history data into an AI model and have the AI ​​select the most suitable request method.

[0054] The requesting department can customize the content of advertising requests based on the characteristics of the product and the target customers. For example, the requesting department can make detailed advertising requests for high-priced products. For example, the requesting department can make advertising requests that emphasize the characteristics of a specific brand for a particular brand's product. For example, the requesting department can make advertising requests that emphasize the characteristics of a specific category for a particular category of product. This allows the requesting department to make more effective requests by customizing the content of the requests based on the characteristics of the product and the target customers. Product characteristics include, but are not limited to, features, design, and price range. Target customers include, but are not limited to, age, gender, and purchasing behavior. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input product characteristic data into an AI model and have the AI ​​perform the customization of the request content.

[0055] The requesting department can select the most appropriate request method when requesting advertising placement, taking into account the geographical distribution of the product. For example, the requesting department can make a region-specific advertising placement request for a product that is popular in a particular region. For example, the requesting department can also make a region-specific advertising placement request for a product that has a proven sales record in a particular region. For example, the requesting department can also make a region-specific advertising placement request for a newly launched product in a particular region. This allows the requesting department to make more appropriate requests by considering the geographical distribution of the product. Geographical distribution includes, but is not limited to, regional sales data and population distribution. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input geographical distribution data of the product into an AI model and have the AI ​​select the most appropriate request method.

[0056] The requesting department can adjust the content of an advertising request by referring to relevant market data when making an advertising request. For example, the requesting department can refer to market trend data to request advertising for popular products. The requesting department can also refer to market competitor data to request advertising that highlights the differentiating points from competing products. The requesting department can also refer to market demand data to request advertising for products with high demand. In this way, the requesting department can adjust the content of the request by referring to relevant market data. Market data includes, but is not limited to, market size, competitor information, and trend data. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input market data into an AI model and have the AI ​​perform the adjustment of the request content.

[0057] The data collection unit can analyze the user's past usage history and select the optimal data collection method. For example, the data collection unit may prioritize collecting the history of services that the user has frequently used in the past. The data collection unit may also prioritize collecting the history of services that the user has given high ratings to in the past. The data collection unit may also prioritize collecting the history of services that the user has used for extended periods in the past. In this way, the data collection unit can select the optimal data collection method by analyzing the user's past usage history. Usage history includes, but is not limited to, browsing history, purchase history, and search history. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit may input the user's past usage history data into an AI model and have the AI ​​select the optimal data collection method.

[0058] The data collection unit can prioritize the collection of highly relevant history by considering the user's geographical location information when collecting usage history. For example, the data collection unit can prioritize the collection of usage history of stores near the user's current location. The data collection unit can also prioritize the collection of usage history of stores in areas the user frequently visits. The data collection unit can also prioritize the collection of usage history of stores in areas the user is traveling to. In this way, the data collection unit can collect more relevant history by considering the user's geographical location information. Geographical location information includes, but is not limited to, addresses, GPS data, and regional codes. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input the user's geographical location information into an AI model and have the AI ​​perform the collection of highly relevant history.

[0059] The data collection unit can analyze the past sales history of a product and select the optimal data collection method. For example, the data collection unit can prioritize collecting product information popular with a specific age group from past sales data. The data collection unit can also prioritize collecting product information popular in a specific region from past sales data. The data collection unit can also prioritize collecting product information popular in a specific season from past sales data. In this way, the data collection unit can select the optimal data collection method by analyzing the past sales history of a product. Sales history includes, but is not limited to, sales date and time, products sold, and sales amount. Data collection methods include, but are not limited to, data mining, statistical analysis, and machine learning algorithms. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input product sales history data into an AI model and have the AI ​​select the optimal data collection method.

[0060] The data collection unit can prioritize the collection of highly relevant information by considering the geographical distribution of products when collecting product information. For example, the data collection unit can prioritize the collection of product information that is popular in a particular region. The data collection unit can also prioritize the collection of product information that has a proven sales record in a particular region. The data collection unit can also prioritize the collection of product information that has been newly launched in a particular region. In this way, the data collection unit can collect more relevant information by considering the geographical distribution of products. Geographical distribution includes, but is not limited to, regional sales data and population distribution. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input geographical distribution data of products into an AI model and have the AI ​​perform the collection of highly relevant information.

[0061] The payment unit can select the optimal payment method when paying advertising fees by referring to past payment history. For example, the payment unit can select a payment method with a high success rate from past payment history. The payment unit can also select a payment method that is effective for a specific target customer from past payment history. The payment unit can also select a payment method for a specific product from past payment history. In this way, the payment unit can select the optimal payment method by referring to past payment history. Payment history includes, but is not limited to, past payment dates and times, payment details, and payment results. The optimal payment method includes, but is not limited to, success rate, cost efficiency, and target suitability. Some or all of the above processing in the payment unit may be performed using, for example, AI, or not using AI. For example, the payment unit can input past payment history data into an AI model and have the AI ​​select the optimal payment method.

[0062] The payment unit can select the most appropriate payment method when paying advertising fees, taking into account the geographical distribution of the products. For example, the payment unit can provide a region-specific payment method for products that are popular in a particular region. The payment unit can also provide a region-specific payment method for products that have a proven sales record in a particular region. The payment unit can also provide a region-specific payment method for newly launched products in a particular region. This allows the payment unit to make more appropriate payments by considering the geographical distribution of the products. Geographical distribution includes, but is not limited to, regional sales data and population distribution. Some or all of the above processing in the payment unit may be performed using, for example, AI, or not using AI. For example, the payment unit can input geographical distribution data of products into an AI model and have the AI ​​select the most appropriate payment method.

[0063] The management department can select the optimal management method when managing incentives by referring to past management history. For example, the management department can select a management method with a high success rate from past management history. The management department can also select a management method that is effective for a specific target customer from past management history. The management department can also select a management method for a specific product from past management history. In this way, the management department can select the optimal management method by referring to past management history. Management history includes, but is not limited to, past management dates and times, management content, and management results. Optimal management methods include, but are not limited to, success rates, cost efficiency, and target suitability. Some or all of the above processes in the management department may be performed using, for example, AI, or not using AI. For example, the management department can input past management history data into an AI model and have the AI ​​select the optimal management method.

[0064] The management department can select the optimal management method when managing incentives, taking into account the geographical distribution of products. For example, the management department can provide a region-specific management method for products that are popular in a particular region. The management department can also provide a region-specific management method for products that have a proven sales record in a particular region. The management department can also provide a region-specific management method for newly launched products in a particular region. This allows the management department to manage products more appropriately by considering their geographical distribution. Geographical distribution includes, but is not limited to, regional sales data and population distribution. Some or all of the above processing in the management department may be performed using AI, for example, or not. For example, the management department can input geographical distribution data of products into an AI model and have the AI ​​select the optimal management method.

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

[0066] Reverse advertising services can analyze a user's past purchase history and predict future purchasing trends. For example, they can analyze the categories of products a user has purchased in the past and predict the products they are most likely to purchase next. They can also analyze the price range of products a user has purchased in the past and predict changes in their budget. Furthermore, they can analyze the brands of products a user has purchased in the past and predict changes in their brand preferences. In this way, reverse advertising services can analyze a user's past purchase history to predict future purchasing trends and provide more effective advertising. Purchase history includes, but is not limited to, purchase date and time, purchased items, and purchase amount. Predicting purchasing trends can be done using data mining and machine learning algorithms.

[0067] Reverse advertising services can customize ads based on a user's geographical location. For example, ads for products and services from stores near the user's current location can be prioritized. Ads for products and services from stores in areas the user frequently visits can also be displayed. Furthermore, ads for products and services from stores in areas the user is traveling to can be displayed. In this way, reverse advertising services can provide more relevant ads by considering the user's geographical location. Geographical location information includes, but is not limited to, addresses, GPS data, and area codes. Customizing ads based on geographical location can improve the effectiveness of ads by more accurately reflecting user interests and preferences.

[0068] Reverse advertising services can analyze a user's social media activity and display relevant ads. For example, they can prioritize showing ads for products and services that a user has "liked" on social media. They can also show ads for products and services that a user has shared on social media. Furthermore, they can show ads for products and services that a user has commented on on social media. In this way, reverse advertising services can provide more relevant ads by analyzing a user's social media activity. Social media activity includes, but is not limited to, posts, the number of likes, and the number of followers. Customizing ads based on social media activity can more accurately reflect users' interests and preferences, thereby increasing the effectiveness of advertising.

[0069] Reverse advertising services can filter ads based on a user's lifestyle and areas of interest. For example, if a user is raising children, ads for childcare-related products and services can be prioritized. Similarly, if a user is a sports enthusiast, ads for sports equipment and services can be displayed. Furthermore, if a user enjoys traveling, ads for travel-related products and services can be displayed. This allows reverse advertising services to provide more relevant ads by filtering them based on a user's lifestyle and areas of interest. Lifestyle includes, but is not limited to, family structure, income, and living environment. Areas of interest include, but is not limited to, hobbies, work, and studies. Filtering ads based on lifestyle and areas of interest can more accurately reflect a user's interests and thus improve the effectiveness of advertising.

[0070] Reverse advertising services can analyze a user's past usage history and select the most effective way to display ads. For example, they can prioritize displaying ads for services the user has frequently used in the past. They can also display ads for services the user has given high ratings to in the past. Furthermore, they can display ads for services the user has used for extended periods in the past. In this way, reverse advertising services can select the most effective way to display ads by analyzing a user's past usage history and provide more effective advertising. Usage history includes, but is not limited to, browsing history, purchase history, and search history. The selection of the most effective way to display ads can be done using data mining and machine learning algorithms.

[0071] Reverse advertising services can tailor ad content by referencing relevant market data. For example, they can prioritize ads for popular products and services by referencing market trend data. They can also display ads that highlight differentiating points from competing products by referencing market competition data. Furthermore, they can display ads for products and services with high demand by referencing market demand data. In this way, reverse advertising services can tailor ad content by referencing relevant market data and deliver more effective advertising. Market data includes, but is not limited to, market size, competition information, and trend data. Tailoring ad content based on market data can more accurately reflect user interests and preferences, thereby increasing the effectiveness of advertising.

[0072] The following briefly describes the processing flow for example form 1.

[0073] Step 1: The consumer AI analyzes the user's usage history. This history includes, for example, browsing history, purchase history, and search history. The consumer AI performs this analysis using methods such as data mining, statistical analysis, and machine learning algorithms. Step 2: The sales AI analyzes product information. This information includes, for example, price, specifications, reviews, and stock availability. The sales AI performs the analysis based on information provided by the seller and information automatically collected from the web. Step 3: The conversational unit handles the process of the consumer AI and sales AI conversing. The conversational unit uses methods such as natural language processing, dialogue systems, and chatbots to conduct the conversation. Step 4: The requesting department requests advertising placement from customers identified by the conversation department as having a high probability of purchasing the product. The requesting department uses advertising platforms and targeting methods to request advertising placement.

[0074] (Example of form 2) The reverse advertising service according to an embodiment of the present invention is based on a new concept that reverses the conventional advertising model. This reverse advertising service is a system that uses AI to automatically match users with products, and the platform pays the advertising fees. First, the reverse advertising service creates a consumer AI that has been trained on the user's usage history. This consumer AI analyzes the user's interests and preferences based on, for example, their usage history on social media and e-commerce sites. Next, it creates a sales AI that has been trained on products. This sales AI understands the characteristics of products and target customers by collecting product information from the web as well as having the seller write the information. Next, the consumer AI and the sales AI converse to find customers with a high probability of purchasing the product. This conversation is a process in which the AIs compare the user's interests and preferences with the characteristics of the product. For example, if the consumer AI determines that "this user is interested in sports equipment," the sales AI will respond, "this sports equipment is suitable for this user." After that, the product owner is asked to place an advertisement. In this case, the product owner receives compensation as an advertising fee. However, if the product is sold, the reverse advertising service receives an incentive. This system allows those who want to sell products to place advertisements without considering the cost disadvantages. Reverse advertising services use advanced AI to identify highly qualified customers, solving the problem of unknown advertising effectiveness. Furthermore, even without a budget, the platform pays the advertising fees, allowing those who want to sell products to use the service without worrying about cost-effectiveness. In short, reverse advertising services allow those who want to sell products to place advertisements without considering the cost disadvantages.

[0075] The reverse advertising service according to this embodiment comprises a consumer AI, a sales AI, a conversation unit, and a request unit. The consumer AI analyzes the user's usage history. The user's usage history includes, but is not limited to, browsing history, purchase history, and search history. The consumer AI performs the analysis using methods such as data mining, statistical analysis, and machine learning algorithms. The sales AI analyzes product information. The product information includes, but is not limited to, price, specifications, reviews, and stock status. The sales AI performs the analysis based on information provided by the seller and information automatically collected from the web. The conversation unit handles the process of the consumer AI and the sales AI conversing. The conversation unit conducts the conversation using methods such as natural language processing, dialogue systems, and chatbots. The request unit requests advertising placement to customers with a high probability of purchasing a product, as identified by the conversation unit. The request unit requests advertising placement using, for example, an advertising platform and targeting methods. As a result, the reverse advertising service according to this embodiment can analyze the user's usage history and product information, and request advertisements to be placed with customers who are highly likely to purchase the product.

[0076] Consumer AI analyzes users' usage history. This history includes, but is not limited to, browsing history, purchase history, and search history. Consumer AI performs this analysis using methods such as data mining, statistical analysis, and machine learning algorithms. Specifically, it analyzes users' browsing history to identify what products and services they are interested in. For example, it understands user preferences by focusing on categories and specific brands that users frequently browse. By analyzing purchase history, it understands trends in products and services users have purchased in the past and identifies products likely to be repurchased. Furthermore, by analyzing search history, it identifies products and services users are currently interested in, understanding their real-time needs. Consumer AI integrates this data to analyze user behavior patterns and preferences in detail. It uses data mining techniques to extract useful patterns and trends from user behavior data and evaluates the reliability and significance of the data through statistical analysis. Using machine learning algorithms, it predicts future behavior based on user behavior data and builds a foundation for personalized advertising and recommendations. This allows consumer AI to analyze users' usage history in detail and provide information to deliver advertisements and suggestions that are best suited to each individual user.

[0077] Sales AI analyzes product information. This information includes, but is not limited to, price, specifications, reviews, and stock availability. For example, sales AI analyzes information provided by sellers and information automatically collected from the web. Specifically, sales AI analyzes product pricing information and compares prices with competitors to propose the optimal pricing. It also analyzes product specifications to identify the product best suited to the user's needs. For example, it proposes products that meet the requirements of users who prioritize specific functions or performance. Furthermore, it analyzes product review information and evaluates product quality and reliability based on user ratings and feedback. By analyzing the content of reviews using natural language processing technology and understanding trends in positive and negative evaluations, it identifies the product's strengths and weaknesses. It also monitors stock availability in real time and encourages users to purchase at the appropriate time based on information such as out-of-stock items and expected arrival dates. Sales AI integrates this information to build a foundation for making optimal product recommendations to users. By utilizing not only information provided by sellers but also information automatically collected from the web, it can make recommendations that reflect the latest market trends and competitor information. This allows the sales AI to analyze product information in detail and provide information to make optimal product recommendations to users.

[0078] The conversational unit handles the process of conversations between consumer AI and sales AI. The conversational unit uses methods such as natural language processing, dialogue systems, and chatbots for these conversations. Specifically, it generates dialogues to provide optimal product recommendations to users based on user usage history analyzed by the consumer AI and product information analyzed by the sales AI. Using natural language processing technology, it generates appropriate responses to user questions and requests, ensuring smooth dialogue flow. For example, if a user asks about a specific product, the conversational unit provides detailed explanations and reviews based on product information obtained from the sales AI. It also suggests related and recommended products based on the user's preferences and past purchase history. Using a dialogue system, it continuously engages with users to understand their needs and interests in real time. Chatbot technology automates user interactions, providing 24 / 7 support. This allows the conversational unit to generate dialogues that enable the consumer AI and sales AI to collaborate and provide optimal product recommendations, thereby improving user satisfaction. Furthermore, the conversational unit can accumulate user dialogue history and utilize it as data to improve the quality of future conversations. This allows the conversational unit to build a foundation for providing personalized dialogues to users and making optimal product recommendations.

[0079] The requesting department requests advertising placement to customers identified by the conversation department as having a high probability of purchasing a product. The requesting department uses advertising platforms and targeting methods to request advertising placement. Specifically, based on information obtained from the conversation department, the requesting department identifies customers with a high probability of purchasing a product and displays the most suitable advertisements to those customers. By using advertising platforms, personalized advertisements are delivered to specific customer segments to maximize advertising effectiveness. Targeting methods are used to determine the optimal timing and content of advertisements based on customer attributes and behavioral data. For example, advertisements for products and services likely to interest customers are displayed based on their past purchase and browsing history. Furthermore, real-time data analysis allows for dynamic changes to advertisement content in response to changes in customer behavior. This enables the requesting department to deliver effective advertisements to customers with a high probability of purchasing a product, improving the conversion rate of advertisements. In addition, the requesting department can continuously monitor the effectiveness of advertisements and use this information to improve advertising strategies. For example, by analyzing click-through rates and conversion rates and comparing high-performing and low-performing advertisements, the content and delivery methods of advertisements can be optimized. This allows the requesting department to maximize the effectiveness of their advertising and provide the most suitable ads to customers who are most likely to purchase the product.

[0080] The reverse advertising service includes a collection unit that collects user activity history. The collection unit may, for example, collect the user's browsing history. The collection unit may also, for example, collect the user's purchase history. The collection unit may also, for example, collect the user's search history. This allows the consumer AI to perform more accurate analysis by collecting the user's activity history. Activity history includes, but is not limited to, browsing history, purchase history, and search history. Some or all of the processing described above in the collection unit may be performed using, for example, AI, or not using AI. For example, the collection unit may input the user's activity history into an AI model and have the AI ​​perform the collection of activity history.

[0081] The reverse advertising service includes a data collection unit that collects product information. The data collection unit may, for example, collect product price information. The data collection unit may also, for example, collect product specification information. The data collection unit may also, for example, collect product review information. This allows the sales AI to perform more accurate analysis by collecting product information. Product information includes, but is not limited to, price, specifications, reviews, and stock availability. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input product information into an AI model and have the AI ​​perform the collection of product information.

[0082] The reverse advertising service includes a payment unit that pays advertising fees. The payment unit can pay advertising fees, for example, by bank transfer. The payment unit can also pay advertising fees by credit card, for example. The payment unit can also pay advertising fees by electronic money, for example. This allows the payment unit to enable people who want to sell products to place advertisements without considering the cost disadvantages by paying advertising fees. Advertising fees include, but are not limited to, fee structures, payment methods, and discount conditions. Some or all of the above processing in the payment unit may be performed using, for example, AI, or not using AI. For example, the payment unit can input the payment of advertising fees into an AI model and have the AI ​​select the payment method.

[0083] The reverse advertising service includes a management department that manages incentives when a product is sold. The management department manages, for example, the rewards for when a product is sold. The management department may also manage, for example, bonuses for when a product is sold. The management department may also manage, for example, points for when a product is sold. In this way, the management department can properly manage the incentives for the reverse advertising service by managing the incentives for when a product is sold. Incentives include, but are not limited to, rewards, bonuses, and points. Some or all of the above processes in the management department may be performed, for example, using AI or not using AI. For example, the management department can input the incentive management into an AI model and have the AI ​​select the management method.

[0084] Consumer AI can analyze a user's interests and preferences based on their usage history of social media or e-commerce sites. For example, consumer AI can analyze a user's interests and preferences based on their social media browsing history. Consumer AI can also analyze a user's interests and preferences based on their purchase history on e-commerce sites. Consumer AI can also analyze a user's interests and preferences based on their social media search history. This allows consumer AI to perform more accurate analysis by analyzing a user's interests and preferences based on their usage history of social media and e-commerce sites. Interests and preferences include, but are not limited to, hobbies, interests, and purchasing intent. Some or all of the above processing in consumer AI may be performed using AI, for example, or without AI. For example, consumer AI can input social media usage history into an AI model and have the AI ​​perform the analysis of interests and preferences.

[0085] The sales AI can collect product information automatically from the web, in addition to information written by the seller. For example, the sales AI can collect price information for products written by the seller. The sales AI can also automatically collect product specification information from the web. The sales AI can also collect product review information written by the seller. This allows the sales AI to analyze product information more accurately by collecting it automatically from the web in addition to information written by the seller. Product information includes, but is not limited to, price, specifications, reviews, and stock status. Some or all of the above processes in the sales AI may be performed using AI, for example, or not using AI. For example, the sales AI can input product information into an AI model and have the AI ​​perform the collection of product information.

[0086] The conversational unit can perform a process in which the consumer AI and sales AI compare the user's interests and preferences with the characteristics of products. For example, the conversational unit can have the consumer AI identify the user's interests and preferences, and the sales AI provide product information based on those interests. The conversational unit can also have the consumer AI analyze the user's purchase history, and the sales AI provide product information based on that history. For example, the conversational unit can have the consumer AI identify the user's areas of interest, and the sales AI provide product information related to those areas. In this way, the conversational unit can find customers with a high probability of purchasing a product by having the consumer AI and sales AI perform a process in which the user's interests and preferences match the characteristics of products. Interests and preferences include, but are not limited to, hobbies, interests, and purchasing intent. Product characteristics include, but are not limited to, features, design, and price range. Some or all of the above processing in the conversational unit may be performed using AI, for example, or not using AI. For example, the conversational unit can input the conversation between the consumer AI and the sales AI into an AI model and have the AI ​​execute the conversational process.

[0087] The consumer AI can estimate a user's emotions and adjust its analysis of usage history based on the estimated emotions. For example, if a user is stressed, the consumer AI may prioritize analyzing usage history related to relaxing products. If a user is excited, the consumer AI may also prioritize analyzing usage history related to active products. If a user is tired, the consumer AI may also prioritize analyzing usage history related to relaxing products. This allows the consumer AI to perform more appropriate analysis by adjusting its analysis of usage history based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Analysis methods include, but are not limited to, data mining, statistical analysis, and machine learning algorithms. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the consumer AI may be performed using AI, for example, or without AI. For example, consumer AI can input user emotion data into an AI model and have the AI ​​adjust its emotion-based analysis methods.

[0088] Consumer AI can analyze a user's past purchase history and predict changes in their interests and preferences. For example, consumer AI can analyze the categories of products a user has purchased in the past and predict recent purchase trends. Consumer AI can also analyze the price range of products a user has purchased in the past and predict changes in their budget. Consumer AI can also analyze the brands of products a user has purchased in the past and predict changes in their brand preferences. In this way, consumer AI can predict changes in a user's interests and preferences by analyzing their past purchase history. Purchase history includes, but is not limited to, purchase date and time, purchased items, and purchase amount. Changes in interests and preferences include, but are not limited to, past purchase patterns and changes in trends. Some or all of the above processing in consumer AI may be performed using AI, for example, or not using AI. For example, consumer AI can input a user's purchase history data into an AI model and have the AI ​​predict changes in interests and preferences.

[0089] Consumer AI can filter usage history based on the user's lifestyle and areas of interest. For example, if a user is raising children, the consumer AI will prioritize analyzing usage history related to childcare products. If a user is a sports enthusiast, the consumer AI can also prioritize analyzing usage history related to sports equipment. If a user enjoys traveling, the consumer AI can also prioritize analyzing usage history related to travel products. This allows the consumer AI to perform more relevant analysis by filtering based on the user's lifestyle and areas of interest. Lifestyle includes, but is not limited to, family structure, income, and living environment. Areas of interest include, but is not limited to, hobbies, work, and learning. Some or all of the above processing in the consumer AI may be performed using AI, or not using AI. For example, the consumer AI can input user lifestyle data into an AI model and have the AI ​​perform the filtering.

[0090] The consumer AI can estimate the user's emotions and prioritize analysis results based on the estimated emotions. For example, if the user is stressed, the consumer AI will prioritize displaying analysis results related to relaxing products. For example, if the user is excited, the consumer AI may also prioritize displaying analysis results related to active products. For example, if the user is tired, the consumer AI may also prioritize displaying analysis results related to relaxing products. In this way, the consumer AI can provide more appropriate analysis results by prioritizing analysis results based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Prioritization includes, but is not limited to, importance, urgency, and relevance. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the consumer AI may be performed using AI, for example, or without AI. For example, consumer AI can input user emotional data into an AI model and have the AI ​​determine the priority of the analysis results.

[0091] Consumer AI can prioritize the analysis of highly relevant data by considering the user's geographical location when analyzing usage history. For example, the consumer AI can prioritize the analysis of usage history related to products from stores near the user's current location. The consumer AI can also prioritize the analysis of usage history related to products from stores in areas the user frequently visits. The consumer AI can also prioritize the analysis of usage history related to products from stores in areas the user is traveling to. This allows the consumer AI to analyze more relevant data by considering the user's geographical location. Geographical location information includes, but is not limited to, addresses, GPS data, and regional codes. Some or all of the above processing in the consumer AI may be performed using AI, for example, or without AI. For example, the consumer AI can input the user's geographical location information into an AI model and have the AI ​​perform the analysis of highly relevant data.

[0092] The consumer AI can analyze a user's social media activity and analyze relevant data when analyzing usage history. For example, the consumer AI can prioritize analyzing usage history related to products that a user has "liked" on social media. The consumer AI can also prioritize analyzing usage history related to products that a user has shared on social media. The consumer AI can also prioritize analyzing usage history related to products that a user has commented on on social media. This allows the consumer AI to analyze more relevant data by analyzing the user's social media activity. Social media activity includes, but is not limited to, posts, the number of likes, and the number of followers. Some or all of the above processing in the consumer AI may be performed using AI, for example, or not using AI. For example, the consumer AI can input the user's social media activity data into an AI model and have the AI ​​perform the analysis of the relevant data.

[0093] Sales AI can estimate a user's emotions and adjust its product information analysis method based on the estimated emotions. For example, if the user is relaxed, the sales AI can provide detailed product information. If the user is in a hurry, the sales AI can also provide concise product information that gets straight to the point. If the user is excited, the sales AI can also provide visually appealing product information. This allows the sales AI to perform more appropriate analysis by adjusting its product information analysis method based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Analysis methods include, but are not limited to, data mining, statistical analysis, and machine learning algorithms. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the sales AI may be performed using AI, for example, or without AI. For example, a sales AI can input user emotion data into its AI model and have the AI ​​adjust how it analyzes product information.

[0094] Sales AI can analyze a product's past sales history and predict the characteristics of target customers. For example, sales AI can identify products popular with a specific age group from past sales data. Sales AI can also identify products popular in a specific region from past sales data. Sales AI can also identify products popular in a specific season from past sales data. This allows sales AI to predict the characteristics of target customers by analyzing a product's past sales history. Sales history includes, but is not limited to, sales date and time, products sold, and sales amount. Characteristics of target customers include, but are not limited to, age, gender, and purchasing behavior. Some or all of the above processing in sales AI may be performed using AI, for example, or not using AI. For example, sales AI can input product sales history data into an AI model and have the AI ​​predict the characteristics of target customers.

[0095] Sales AI can filter product information based on product characteristics and target customers when analyzing product data. For example, sales AI can prioritize providing information on high-priced products to customers who tend to purchase high-priced products. Sales AI can also prioritize providing information on products from a specific brand to customers who prefer that brand. Sales AI can also prioritize providing information on products in a specific category to customers who tend to purchase products in that category. This allows sales AI to perform more relevant analysis by filtering based on product characteristics and target customers. Product characteristics include, but are not limited to, features, design, and price range. Target customers include, but are not limited to, age, gender, and purchasing behavior. Some or all of the above processing in sales AI may be performed using AI, for example, or not using AI. For example, sales AI can input product characteristic data into an AI model and have the AI ​​perform the filtering.

[0096] Sales AI can estimate a user's emotions and prioritize analysis results based on those emotions. For example, if a user is relaxed, the sales AI might prioritize displaying detailed product information. If a user is in a hurry, the sales AI might prioritize displaying concise product information. If a user is excited, the sales AI might prioritize displaying visually appealing product information. This allows the sales AI to provide more appropriate analysis results by prioritizing them based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Prioritization includes, but is not limited to, importance, urgency, and relevance. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the sales AI may be performed using AI or not using AI. For example, a sales AI can input user sentiment data into an AI model and have the AI ​​determine the priority of the analysis results.

[0097] Sales AI can prioritize the analysis of highly relevant data by considering the geographical distribution of products when analyzing product information. For example, a sales AI can prioritize the analysis of product information that is popular in a particular region. A sales AI can also prioritize the analysis of product information that has a proven sales record in a particular region. A sales AI can also prioritize the analysis of newly launched product information in a particular region. This allows the sales AI to analyze more relevant data by considering the geographical distribution of products. Geographical distribution includes, but is not limited to, regional sales data and population distribution. Some or all of the above processing in sales AI may be performed using AI, for example, or without AI. For example, a sales AI can input geographical distribution data of products into an AI model and have the AI ​​perform the analysis of highly relevant data.

[0098] Sales AI can improve the accuracy of its analysis by referencing relevant market data when analyzing product information. For example, sales AI can prioritize the analysis of popular product information by referencing market trend data. Sales AI can also analyze points of differentiation from competing products by referencing market competitor data. Sales AI can also prioritize the analysis of high-demand product information by referencing market demand data. In this way, sales AI can improve the accuracy of its analysis by referencing relevant market data. Market data includes, but is not limited to, market size, competitor information, and trend data. Some or all of the above processing in sales AI may be performed using AI, for example, or not using AI. For example, sales AI can input market data into an AI model and have the AI ​​perform the improvement of analysis accuracy.

[0099] The conversational unit can estimate the user's emotions and adjust the conversational criteria based on the estimated emotions. For example, if the user is relaxed, the conversational unit will engage in a conversation that includes detailed information. If the user is in a hurry, the conversational unit may engage in a concise conversation that gets straight to the point. If the user is excited, the conversational unit may engage in a conversation that includes visually appealing information. This allows the conversational unit to engage in more appropriate conversations by adjusting the conversational criteria based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Conversational criteria include, but are not limited to, word choice, tone, and topic selection. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the conversational unit may be performed using AI, for example, or without AI. For example, the conversation section can input user emotion data into an AI model and have the AI ​​adjust the criteria for conversation.

[0100] The conversational unit can improve the accuracy of conversations by considering the interrelationship between the consumer AI and the sales AI during a conversation. For example, the conversational unit can have the consumer AI identify the user's interests, and the sales AI provide product information based on those interests. Alternatively, the conversational unit can have the consumer AI analyze the user's purchase history, and the sales AI provide product information based on that history. The conversational unit can also have the consumer AI identify the user's areas of interest, and the sales AI provide product information related to those areas. In this way, the conversational unit can improve the accuracy of conversations by considering the interrelationship between the consumer AI and the sales AI. This interrelationship includes, but is not limited to, methods of data sharing and collaboration processes. Some or all of the above processing in the conversational unit may be performed using AI, for example, or not using AI. For example, the conversational unit can input data from the consumer AI and the sales AI into an AI model and have the AI ​​perform the conversation accuracy improvement.

[0101] The conversation unit can conduct conversations while considering the user's attribute information. For example, the conversation unit can provide appropriate product information based on the user's age. The conversation unit can also provide appropriate product information based on the user's gender. The conversation unit can also provide appropriate product information based on the user's occupation. This allows the conversation unit to conduct more appropriate conversations by considering the user's attribute information. Attribute information includes, but is not limited to, age, gender, and occupation. Some or all of the above processing in the conversation unit may be performed using, for example, AI, or not using AI. For example, the conversation unit can input the user's attribute information into an AI model and have the AI ​​perform the conversation.

[0102] The conversation unit can estimate the user's emotions and adjust the order in which it displays conversation results based on the estimated emotions. For example, if the user is relaxed, the conversation unit may prioritize displaying detailed information. For example, if the user is in a hurry, the conversation unit may prioritize displaying concise information. For example, if the user is excited, the conversation unit may prioritize displaying visually appealing information. This allows the conversation unit to provide more appropriate information by adjusting the order in which it displays conversation results based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. The display order includes, but is not limited to, importance, relevance, and chronological order. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the conversation unit may be performed using AI, for example, or without AI. For example, the conversation section can input user emotion data into an AI model and have the AI ​​adjust the display order.

[0103] The conversational unit can conduct conversations while considering the geographical distribution of products. For example, the conversational unit may prioritize providing information on products that are popular in a particular region. The conversational unit may also prioritize providing information on products that have a proven sales record in a particular region. The conversational unit may also prioritize providing information on newly launched products in a particular region. This allows the conversational unit to conduct more appropriate conversations by considering the geographical distribution of products. Geographical distribution includes, but is not limited to, regional sales data and population distribution. Some or all of the processing described above in the conversational unit may be performed using, for example, AI, or not using AI. For example, the conversational unit can input geographical distribution data of products into an AI model and have the AI ​​perform the conversation.

[0104] The conversational unit can improve the accuracy of its conversations by referring to relevant literature during the conversation. For example, the conversational unit can refer to relevant research papers to explain the effects of a product. The conversational unit can also refer to relevant market reports to explain the demand for a product. The conversational unit can also refer to relevant user reviews to explain the evaluation of a product. In this way, the conversational unit can improve the accuracy of its conversations by referring to relevant literature. Literature includes, but is not limited to, academic papers, technical reports, and industry reports. Some or all of the processing described above in the conversational unit may be performed using, for example, AI, or not using AI. For example, the conversational unit can input relevant literature data into an AI model and have the AI ​​perform the task of improving the accuracy of the conversation.

[0105] The requesting unit can estimate the user's emotions and adjust the method of requesting ad placement based on the estimated user emotions. For example, if the user is relaxed, the requesting unit may make a detailed ad placement request. If the user is in a hurry, the requesting unit may make a concise ad placement request that gets straight to the point. If the user is excited, the requesting unit may make a visually appealing ad placement request. This allows the requesting unit to make more appropriate requests by adjusting the method of requesting ad placement based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Methods of requesting ad placement include, but are not limited to, email, telephone, and online platforms. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the requesting unit may be performed using AI, for example, or without AI. For example, the request department can input user sentiment data into an AI model and have the AI ​​adjust the method of requesting ad placement.

[0106] The requesting department can select the most suitable request method when making an advertising placement request by referring to past request history. For example, the requesting department can select a request method with a high success rate from past request history. The requesting department can also select a request method that is effective for a specific target customer from past request history. The requesting department can also select a request method for a specific product from past request history. In this way, the requesting department can select the most suitable request method by referring to past request history. Request history includes, but is not limited to, past request dates and times, request content, and request results. The most suitable request method includes, but is not limited to, success rate, cost efficiency, and target suitability. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input past request history data into an AI model and have the AI ​​select the most suitable request method.

[0107] The requesting department can customize the content of advertising requests based on the characteristics of the product and the target customers. For example, the requesting department can make detailed advertising requests for high-priced products. For example, the requesting department can make advertising requests that emphasize the characteristics of a specific brand for a particular brand's product. For example, the requesting department can make advertising requests that emphasize the characteristics of a specific category for a particular category of product. This allows the requesting department to make more effective requests by customizing the content of the requests based on the characteristics of the product and the target customers. Product characteristics include, but are not limited to, features, design, and price range. Target customers include, but are not limited to, age, gender, and purchasing behavior. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input product characteristic data into an AI model and have the AI ​​perform the customization of the request content.

[0108] The request unit can estimate the user's emotions and determine the priority of requests based on the estimated emotions. For example, if the user is relaxed, the request unit may prioritize detailed requests. If the user is in a hurry, the request unit may also prioritize concise requests that get straight to the point. If the user is excited, the request unit may also prioritize visually appealing requests. This allows the request unit to make more appropriate requests by prioritizing requests based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Priorities include, but are not limited to, importance, urgency, and relevance. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the request unit may be performed using AI, for example, or without AI. For example, the request department can input user emotion data into an AI model and have the AI ​​determine the priority of requests.

[0109] The requesting department can select the most appropriate request method when requesting advertising placement, taking into account the geographical distribution of the product. For example, the requesting department can make a region-specific advertising placement request for a product that is popular in a particular region. For example, the requesting department can also make a region-specific advertising placement request for a product that has a proven sales record in a particular region. For example, the requesting department can also make a region-specific advertising placement request for a newly launched product in a particular region. This allows the requesting department to make more appropriate requests by considering the geographical distribution of the product. Geographical distribution includes, but is not limited to, regional sales data and population distribution. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input geographical distribution data of the product into an AI model and have the AI ​​select the most appropriate request method.

[0110] The requesting department can adjust the content of an advertising request by referring to relevant market data when making an advertising request. For example, the requesting department can refer to market trend data to request advertising for popular products. The requesting department can also refer to market competitor data to request advertising that highlights the differentiating points from competing products. The requesting department can also refer to market demand data to request advertising for products with high demand. In this way, the requesting department can adjust the content of the request by referring to relevant market data. Market data includes, but is not limited to, market size, competitor information, and trend data. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input market data into an AI model and have the AI ​​perform the adjustment of the request content.

[0111] 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 relaxed, the data collection unit can collect detailed data. For example, if the user is in a hurry, the data collection unit can collect concise data. For example, if the user is excited, the data collection unit can collect visually appealing data. This allows the data collection unit to perform more appropriate data collection by adjusting the timing of data collection based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Data collection timing includes, but is not limited to, time of day, when an event occurs, or at regular intervals. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, 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, for example, or without AI. For example, the data collection unit can input user emotion data into an AI model and have the AI ​​adjust the timing of data collection.

[0112] The data collection unit can analyze the user's past usage history and select the optimal data collection method. For example, the data collection unit may prioritize collecting the history of services that the user has frequently used in the past. The data collection unit may also prioritize collecting the history of services that the user has given high ratings to in the past. The data collection unit may also prioritize collecting the history of services that the user has used for extended periods in the past. In this way, the data collection unit can select the optimal data collection method by analyzing the user's past usage history. Usage history includes, but is not limited to, browsing history, purchase history, and search history. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit may input the user's past usage history data into an AI model and have the AI ​​select the optimal data collection method.

[0113] The data collection unit can estimate the user's emotions and determine the priority of usage history to collect based on the estimated user emotions. For example, if the user is relaxed, the data collection unit may prioritize collecting detailed usage history. For example, if the user is in a hurry, the data collection unit may prioritize collecting concise usage history that gets straight to the point. For example, if the user is excited, the data collection unit may prioritize collecting visually appealing usage history. This allows the data collection unit to perform more appropriate collection by determining the priority of usage history to collect based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Priorities include, but are not limited to, importance, urgency, and relevance. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, 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, for example, or without AI. For example, the data collection unit can input user emotion data into an AI model and have the AI ​​determine priorities.

[0114] The data collection unit can prioritize the collection of highly relevant history by considering the user's geographical location information when collecting usage history. For example, the data collection unit can prioritize the collection of usage history of stores near the user's current location. The data collection unit can also prioritize the collection of usage history of stores in areas the user frequently visits. The data collection unit can also prioritize the collection of usage history of stores in areas the user is traveling to. In this way, the data collection unit can collect more relevant history by considering the user's geographical location information. Geographical location information includes, but is not limited to, addresses, GPS data, and regional codes. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input the user's geographical location information into an AI model and have the AI ​​perform the collection of highly relevant history.

[0115] The data collection unit can estimate the user's emotions and adjust the method of collecting product information based on the estimated user emotions. For example, if the user is relaxed, the data collection unit can collect detailed product information. For example, if the user is in a hurry, the data collection unit can collect concise product information that gets straight to the point. For example, if the user is excited, the data collection unit can collect visually appealing product information. This allows the data collection unit to collect more appropriate information by adjusting the method of collecting product information based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Data collection methods include, but are not limited to, data mining, statistical analysis, and machine learning algorithms. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input user emotion data into an AI model and have the AI ​​adjust the method of collecting product information.

[0116] The data collection unit can analyze the past sales history of a product and select the optimal data collection method. For example, the data collection unit can prioritize collecting product information popular with a specific age group from past sales data. The data collection unit can also prioritize collecting product information popular in a specific region from past sales data. The data collection unit can also prioritize collecting product information popular in a specific season from past sales data. In this way, the data collection unit can select the optimal data collection method by analyzing the past sales history of a product. Sales history includes, but is not limited to, sales date and time, products sold, and sales amount. Data collection methods include, but are not limited to, data mining, statistical analysis, and machine learning algorithms. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input product sales history data into an AI model and have the AI ​​select the optimal data collection method.

[0117] The data collection unit can estimate the user's emotions and determine the priority of product information to collect based on the estimated user emotions. For example, if the user is relaxed, the data collection unit may prioritize collecting detailed product information. For example, if the user is in a hurry, the data collection unit may prioritize collecting concise product information that gets straight to the point. For example, if the user is excited, the data collection unit may prioritize collecting visually appealing product information. This allows the data collection unit to collect more appropriate information by prioritizing product information based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Prioritization includes, but is not limited to, importance, urgency, and relevance. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, 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, for example, or without AI. For example, the data collection unit can input user emotion data into an AI model and have the AI ​​determine the priority of product information.

[0118] The data collection unit can prioritize the collection of highly relevant information by considering the geographical distribution of products when collecting product information. For example, the data collection unit can prioritize the collection of product information that is popular in a particular region. The data collection unit can also prioritize the collection of product information that has a proven sales record in a particular region. The data collection unit can also prioritize the collection of product information that has been newly launched in a particular region. In this way, the data collection unit can collect more relevant information by considering the geographical distribution of products. Geographical distribution includes, but is not limited to, regional sales data and population distribution. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input geographical distribution data of products into an AI model and have the AI ​​perform the collection of highly relevant information.

[0119] The payment unit can estimate the user's emotions and adjust the payment method for advertising fees based on the estimated user emotions. For example, if the user is relaxed, the payment unit may provide a detailed payment method. For example, if the user is in a hurry, the payment unit may provide a concise payment method that gets straight to the point. For example, if the user is excited, the payment unit may provide a visually appealing payment method. This allows the payment unit to make more appropriate payments by adjusting the payment method for advertising fees based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Payment methods include, but are not limited to, bank transfers, credit cards, and electronic money. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the payment unit may be performed using AI or not using AI. For example, the payment unit can input user emotion data into an AI model and have the AI ​​adjust the payment method.

[0120] The payment unit can select the optimal payment method when paying advertising fees by referring to past payment history. For example, the payment unit can select a payment method with a high success rate from past payment history. The payment unit can also select a payment method that is effective for a specific target customer from past payment history. The payment unit can also select a payment method for a specific product from past payment history. In this way, the payment unit can select the optimal payment method by referring to past payment history. Payment history includes, but is not limited to, past payment dates and times, payment details, and payment results. The optimal payment method includes, but is not limited to, success rate, cost efficiency, and target suitability. Some or all of the above processing in the payment unit may be performed using, for example, AI, or not using AI. For example, the payment unit can input past payment history data into an AI model and have the AI ​​select the optimal payment method.

[0121] The payment unit can estimate the user's emotions and determine payment priorities based on the estimated emotions. For example, if the user is relaxed, the payment unit may prioritize detailed payments. If the user is in a hurry, the payment unit may also prioritize concise, to-the-point payments. If the user is excited, the payment unit may also prioritize visually appealing payments. This allows the payment unit to make more appropriate payments by prioritizing payments based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Priorities include, but are not limited to, importance, urgency, and relevance. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the payment unit may be performed using AI, for example, or without AI. For example, the payment unit can input user emotion data into an AI model and have the AI ​​determine payment priorities.

[0122] The payment unit can select the most appropriate payment method when paying advertising fees, taking into account the geographical distribution of the products. For example, the payment unit can provide a region-specific payment method for products that are popular in a particular region. The payment unit can also provide a region-specific payment method for products that have a proven sales record in a particular region. The payment unit can also provide a region-specific payment method for newly launched products in a particular region. This allows the payment unit to make more appropriate payments by considering the geographical distribution of the products. Geographical distribution includes, but is not limited to, regional sales data and population distribution. Some or all of the above processing in the payment unit may be performed using, for example, AI, or not using AI. For example, the payment unit can input geographical distribution data of products into an AI model and have the AI ​​select the most appropriate payment method.

[0123] The management department can estimate the user's emotions and adjust the incentive management method based on the estimated user emotions. For example, if the user is relaxed, the management department can implement detailed incentive management. For example, if the user is in a hurry, the management department can implement concise incentive management that gets straight to the point. For example, if the user is excited, the management department can implement visually appealing incentive management. This allows the management department to provide more appropriate management by adjusting the incentive management method based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Management methods include, but are not limited to, reward calculation methods, bonus awarding criteria, and point management methods. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the management department may be performed using AI, for example, or without AI. For example, the management department can input user emotion data into an AI model and have the AI ​​adjust the incentive management methods.

[0124] The management department can select the optimal management method when managing incentives by referring to past management history. For example, the management department can select a management method with a high success rate from past management history. The management department can also select a management method that is effective for a specific target customer from past management history. The management department can also select a management method for a specific product from past management history. In this way, the management department can select the optimal management method by referring to past management history. Management history includes, but is not limited to, past management dates and times, management content, and management results. Optimal management methods include, but are not limited to, success rates, cost efficiency, and target suitability. Some or all of the above processes in the management department may be performed using, for example, AI, or not using AI. For example, the management department can input past management history data into an AI model and have the AI ​​select the optimal management method.

[0125] The management unit can estimate the user's emotions and determine management priorities based on the estimated emotions. For example, if the user is relaxed, the management unit may prioritize detailed management. If the user is in a hurry, the management unit may also prioritize concise management that gets straight to the point. If the user is excited, the management unit may also prioritize visually appealing management. This allows the management unit to provide more appropriate management by determining management priorities based on the user's emotions. Emotions include, but are not limited to, joy, sadness, excitement, and anger. Priorities include, but are not limited to, importance, urgency, and relevance. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the management unit may be performed using AI, for example, or without AI. For example, the management department can input user sentiment data into an AI model and have the AI ​​determine management priorities.

[0126] The management department can select the optimal management method when managing incentives, taking into account the geographical distribution of products. For example, the management department can provide a region-specific management method for products that are popular in a particular region. The management department can also provide a region-specific management method for products that have a proven sales record in a particular region. The management department can also provide a region-specific management method for newly launched products in a particular region. This allows the management department to manage products more appropriately by considering their geographical distribution. Geographical distribution includes, but is not limited to, regional sales data and population distribution. Some or all of the above processing in the management department may be performed using AI, for example, or not. For example, the management department can input geographical distribution data of products into an AI model and have the AI ​​select the optimal management method.

[0127] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0128] Reverse advertising services can estimate a user's emotions and customize ad content based on those emotions. For example, if a user is stressed, ads for relaxing products and services can be prioritized. If a user is excited, ads for active products and services can be displayed. Furthermore, if a user is sad, ads for mood-boosting products and services can be displayed. In this way, reverse advertising services can provide more effective advertising by customizing ad content based on the user's emotions. Emotion estimation can be done using, for example, emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI and multimodal generation AI. Emotion-based ad customization can improve the effectiveness of advertising because it more accurately reflects the user's interests and concerns.

[0129] Reverse advertising services can analyze a user's past purchase history and predict future purchasing trends. For example, they can analyze the categories of products a user has purchased in the past and predict the products they are most likely to purchase next. They can also analyze the price range of products a user has purchased in the past and predict changes in their budget. Furthermore, they can analyze the brands of products a user has purchased in the past and predict changes in their brand preferences. In this way, reverse advertising services can analyze a user's past purchase history to predict future purchasing trends and provide more effective advertising. Purchase history includes, but is not limited to, purchase date and time, purchased items, and purchase amount. Predicting purchasing trends can be done using data mining and machine learning algorithms.

[0130] Reverse advertising services can customize ads based on a user's geographical location. For example, ads for products and services from stores near the user's current location can be prioritized. Ads for products and services from stores in areas the user frequently visits can also be displayed. Furthermore, ads for products and services from stores in areas the user is traveling to can be displayed. In this way, reverse advertising services can provide more relevant ads by considering the user's geographical location. Geographical location information includes, but is not limited to, addresses, GPS data, and area codes. Customizing ads based on geographical location can improve the effectiveness of ads by more accurately reflecting user interests and preferences.

[0131] Reverse advertising services can analyze a user's social media activity and display relevant ads. For example, they can prioritize showing ads for products and services that a user has "liked" on social media. They can also show ads for products and services that a user has shared on social media. Furthermore, they can show ads for products and services that a user has commented on on social media. In this way, reverse advertising services can provide more relevant ads by analyzing a user's social media activity. Social media activity includes, but is not limited to, posts, the number of likes, and the number of followers. Customizing ads based on social media activity can more accurately reflect users' interests and preferences, thereby increasing the effectiveness of advertising.

[0132] Reverse advertising services can estimate a user's emotions and adjust the timing of ad display based on those emotions. For example, if a user is relaxed, a detailed ad can be displayed. If a user is in a hurry, a concise ad that gets straight to the point can be displayed. Furthermore, if a user is excited, a visually appealing ad can be displayed. In this way, reverse advertising services can provide more effective advertising by adjusting the timing of ad display based on the user's emotions. Emotion estimation can be done using, for example, emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI and multimodal generation AI. Adjusting ad display timing based on emotions can more accurately reflect the user's interests and concerns, thereby improving the effectiveness of advertising.

[0133] Reverse advertising services can filter ads based on a user's lifestyle and areas of interest. For example, if a user is raising children, ads for childcare-related products and services can be prioritized. Similarly, if a user is a sports enthusiast, ads for sports equipment and services can be displayed. Furthermore, if a user enjoys traveling, ads for travel-related products and services can be displayed. This allows reverse advertising services to provide more relevant ads by filtering them based on a user's lifestyle and areas of interest. Lifestyle includes, but is not limited to, family structure, income, and living environment. Areas of interest include, but is not limited to, hobbies, work, and studies. Filtering ads based on lifestyle and areas of interest can more accurately reflect a user's interests and thus improve the effectiveness of advertising.

[0134] Reverse advertising services can estimate a user's emotions and prioritize ads based on those emotions. For example, if a user is relaxed, detailed ads can be prioritized. If a user is in a hurry, concise ads that get straight to the point can be prioritized. Furthermore, if a user is excited, visually appealing ads can be prioritized. In this way, reverse advertising services can provide more effective advertising by prioritizing ads based on user emotions. Emotion estimation can be done using, for example, emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI and multimodal generation AI. Prioritizing ads based on emotions can more accurately reflect user interests and concerns, thereby improving the effectiveness of advertising.

[0135] Reverse advertising services can analyze a user's past usage history and select the most effective way to display ads. For example, they can prioritize displaying ads for services the user has frequently used in the past. They can also display ads for services the user has given high ratings to in the past. Furthermore, they can display ads for services the user has used for extended periods in the past. In this way, reverse advertising services can select the most effective way to display ads by analyzing a user's past usage history and provide more effective advertising. Usage history includes, but is not limited to, browsing history, purchase history, and search history. The selection of the most effective way to display ads can be done using data mining and machine learning algorithms.

[0136] Reverse advertising services can estimate a user's emotions and adjust the order in which ads are displayed based on those emotions. For example, if a user is relaxed, detailed ads can be prioritized. If a user is in a hurry, concise ads that get straight to the point can be prioritized. Furthermore, if a user is excited, visually appealing ads can be prioritized. In this way, reverse advertising services can provide more effective advertising by adjusting the order in which ads are displayed based on the user's emotions. Emotion estimation can be done using, for example, emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI and multimodal generation AI. Adjusting the order in which ads are displayed based on emotions can more accurately reflect the user's interests and concerns, thereby improving the effectiveness of advertising.

[0137] Reverse advertising services can tailor ad content by referencing relevant market data. For example, they can prioritize ads for popular products and services by referencing market trend data. They can also display ads that highlight differentiating points from competing products by referencing market competition data. Furthermore, they can display ads for products and services with high demand by referencing market demand data. In this way, reverse advertising services can tailor ad content by referencing relevant market data and deliver more effective advertising. Market data includes, but is not limited to, market size, competition information, and trend data. Tailoring ad content based on market data can more accurately reflect user interests and preferences, thereby increasing the effectiveness of advertising.

[0138] The following briefly describes the processing flow for example form 2.

[0139] Step 1: The consumer AI analyzes the user's usage history. This history includes, for example, browsing history, purchase history, and search history. The consumer AI performs this analysis using methods such as data mining, statistical analysis, and machine learning algorithms. Step 2: The sales AI analyzes product information. This information includes, for example, price, specifications, reviews, and stock availability. The sales AI performs the analysis based on information provided by the seller and information automatically collected from the web. Step 3: The conversational unit handles the process of the consumer AI and sales AI conversing. The conversational unit uses methods such as natural language processing, dialogue systems, and chatbots to conduct the conversation. Step 4: The requesting department requests advertising placement from customers identified by the conversation department as having a high probability of purchasing the product. The requesting department uses advertising platforms and targeting methods to request advertising placement.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] For example, the consumer AI is implemented by the specific processing unit 290 of the data processing device 12. For example, the sales AI is implemented by the control unit 46A of the smart device 14. For example, the conversation unit is implemented by either the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14. For example, the request unit is implemented by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0144] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0145] 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.

[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 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.

[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 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.

[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 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.

[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 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.

[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 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.

[0159] For example, the consumer AI is implemented by the specific processing unit 290 of the data processing device 12. For example, the sales AI is implemented by the control unit 46A of the smart glasses 214. For example, the conversation unit is implemented by either the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214. For example, the request unit is implemented by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0160] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0161] 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.

[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 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.

[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 (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).

[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] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.).

[0172] 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.

[0173] 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.

[0174] 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.

[0175] For example, the consumer AI is implemented by the specific processing unit 290 of the data processing device 12. For example, the sales AI is implemented by the control unit 46A of the headset terminal 314. For example, the conversation unit is implemented by either the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314. For example, the request unit is implemented by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0176] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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).

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.).

[0189] 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.

[0190] 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.

[0191] 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.

[0192] For example, the consumer AI is implemented by the specific processing unit 290 of the data processing device 12. For example, the sales AI is implemented by the control unit 46A of the robot 414. For example, the conversation unit is implemented by either the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414. For example, the request unit is implemented by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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."

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] (Note 1) Consumer AI that analyzes user usage history, A sales AI that analyzes product information, A conversation unit in which the consumer AI and the sales AI converse, The requesting unit requests advertising placement from customers who are estimated to have a high probability of purchasing the product, as identified by the aforementioned conversation unit. Equipped with A system characterized by the following features. (Note 2) It includes a data collection unit that collects user usage history. The system described in Appendix 1, characterized by the features described herein. (Note 3) It is equipped with a collection unit that collects product information. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a payment section for paying advertising fees. The system described in Appendix 1, characterized by the features described herein. (Note 5) The company has a management department that handles incentives for when products are sold. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned consumer AI, Analyze users' interests and preferences based on their usage history on social media or e-commerce sites. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned sales AI The seller provides product information, and the system also automatically collects information from the web. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned conversation section is, Consumer AI and sales AI perform a process of comparing user interests and preferences with product characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned consumer AI, We estimate the user's emotions and adjust the method of analyzing usage history based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned consumer AI, Analyze users' past purchase history to predict changes in their interests and preferences. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned consumer AI, When analyzing usage history, filtering is performed based on the user's lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned consumer AI, It estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned consumer AI, When analyzing usage history, the system prioritizes analyzing highly relevant data by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned consumer AI, When analyzing usage history, the system analyzes the user's social media activity and related data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned sales AI We estimate the user's emotions and adjust the product information analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned sales AI By analyzing the product's past sales history, we can predict the characteristics of target customers. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned sales AI When analyzing product information, filtering is performed based on product characteristics and target customers. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned sales AI It estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned sales AI When analyzing product information, prioritize analyzing highly relevant data, taking into account the geographical distribution of the products. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned sales AI When analyzing product information, we refer to relevant market data to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned conversation section is, It estimates the user's emotions and adjusts the conversation criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned conversation section is, During conversations, the system improves the accuracy of the conversation by considering the interaction between consumer AI and sales AI. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned conversation section is, When having a conversation, consider the user's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned conversation section is, It estimates the user's emotions and adjusts the order in which conversation results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned conversation section is, When having a conversation, take into account the geographical distribution of the product. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned conversation section is, Referencing relevant literature during conversations improves the accuracy of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned request unit, We estimate user sentiment and adjust the ad placement request method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned request unit, When requesting advertising placement, we will refer to past request history to select the most suitable request method. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned request unit, When requesting advertising placement, customize the request based on the product's characteristics and target customers. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned request unit, It estimates the user's emotions and determines the priority of requests based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned request unit is, When requesting advertising placement, we select the most appropriate method of request considering the geographical distribution of the product. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned request unit, When requesting advertising placement, we adjust the request details by referring to relevant market data. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of collecting usage history based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned collection unit is Analyze the user's past usage history and select the optimal data collection method. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned collection unit is It estimates the user's emotions and determines the priority of usage history to collect based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned collection unit is When collecting usage history, the system prioritizes collecting highly relevant history by considering the user's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 37) The aforementioned collection unit is We estimate the user's emotions and adjust the product information collection method based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned collection unit is Analyze the product's past sales history and select the optimal data collection method. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned collection unit is It estimates the user's emotions and determines the priority of product information to collect based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned collection unit is When collecting product information, prioritize the collection of highly relevant information, taking into account the geographical distribution of the products. The system described in Appendix 3, characterized by the features described herein. (Note 41) The aforementioned payment unit is, We estimate user sentiment and adjust the payment method for ad placements based on the estimated user sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned payment unit is, When paying advertising fees, the system will refer to past payment history to select the most suitable payment method. The system described in Appendix 4, characterized by the features described herein. (Note 43) The aforementioned payment unit is, It estimates the user's emotions and determines payment priorities based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 44) The aforementioned payment unit is, When paying for advertising placement, the most suitable payment method will be selected considering the geographical distribution of the products. The system described in Appendix 4, characterized by the features described herein. (Note 45) The aforementioned management department, We estimate user emotions and adjust incentive management methods based on the estimated user emotions. The system described in Appendix 5, characterized by the features described herein. (Note 46) The aforementioned management department, When managing incentives, refer to past management history to select the optimal management method. The system described in Appendix 5, characterized by the features described herein. (Note 47) The aforementioned management department, It estimates user sentiment and determines management priorities based on the estimated user sentiment. The system described in Appendix 5, characterized by the features described herein. (Note 48) The aforementioned management department, When managing incentives, the optimal management method should be selected considering the geographical distribution of the products. The system described in Appendix 5, characterized by the features described herein. [Explanation of Symbols]

[0212] 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. Consumer AI that analyzes user usage history, A sales AI that analyzes product information, A conversation unit in which the consumer AI and the sales AI converse, The requesting unit requests advertising placement from customers who are estimated to have a high probability of purchasing the product, as identified by the aforementioned conversation unit. Equipped with A system characterized by the following features.

2. It includes a data collection unit that collects user usage history. The system according to feature 1.

3. It is equipped with a collection unit that collects product information. The system according to feature 1.

4. It includes a payment section for paying advertising fees. The system according to feature 1.

5. The company has a management department that handles incentives for when products are sold. The system according to feature 1.

6. The aforementioned consumer AI, Analyze users' interests and preferences based on their usage history on social media or e-commerce sites. The system according to feature 1.

7. The aforementioned sales AI, The seller provides product information, and the system also automatically collects information from the web. The system according to feature 1.

8. The aforementioned conversation section is, Consumer AI and sales AI perform a process of comparing user interests and preferences with product characteristics. The system according to feature 1.

9. The aforementioned consumer AI, We estimate the user's emotions and adjust the method of analyzing usage history based on the estimated user emotions. The system according to feature 1.

10. The aforementioned consumer AI, Analyze users' past purchase history to predict changes in their interests and preferences. The system according to feature 1.

Images