system

Abstract

The system according to this embodiment aims to generate talent that matches the user's preferences and incorporate it into advertising content. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a generation unit, and an integration unit. The collection unit collects user preference data. The analysis unit analyzes the data collected by the collection unit and identifies the characteristics of talent that match the user's preferences. The generation unit generates talent based on the characteristics identified by the analysis unit. The integration unit integrates the talent generated by the generation unit into advertising content.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including 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 prior art, it is difficult to use a talent that suits the preferences of individual users in advertisements, and there is a risk that the advertising effect will decline.

[0005] The system according to the embodiment aims to generate a talent that suits the preferences of the user and incorporate it into the advertisement content.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, and an integration unit. The collection unit collects user preference data. The analysis unit analyzes the data collected by the collection unit and identifies the characteristics of talent that match the user's preferences. The generation unit generates talent based on the characteristics identified by the analysis unit. The integration unit integrates the talent generated by the generation unit into advertising content. [Effects of the Invention]

[0007] The system according to this embodiment can generate talent that matches the user's preferences and incorporate it into advertising content. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An advertising generation system according to an embodiment of the present invention is a system that uses a generation AI to generate talent tailored to each user's preferences and incorporates it into advertising content. The advertising generation system collects user preference data, and the generation AI analyzes this data. Next, the generation AI generates talent tailored to the user's preferences and incorporates that talent into the advertising content. This reduces casting costs and advertising production costs by using different, non-existent talents for each user. In addition, reputation risk is reduced because non-existent talents are used. First, the advertising generation system collects user preference data. At this time, data such as the user's hobbies, interests, and past behavioral history is collected. For example, this includes purchase history on e-commerce sites and content posted on social media. This allows for a detailed understanding of the user's preferences. Next, the generation AI analyzes the collected data in the advertising generation system. Based on the user preference data, the generation AI identifies the characteristics of talent that the user prefers. For example, it can extract characteristics such as specific facial features, hairstyles, and clothing. This provides basic data for generating different talents for each user. The generation AI generates talent that matches the user's preferences based on analysis results. The generated talent does not actually exist, but because it possesses characteristics that users like, it has a high advertising effect. For example, it can generate talent with the facial features, hairstyles, and clothing that users prefer. The advertising generation system incorporates the generated talent into the advertising content. Specifically, it replaces pre-shot talent assets with the talent generated by the generation AI. This allows for the provision of different advertising content for each user. For example, even for the same product, different users can see ads featuring different talents. This mechanism reduces casting costs and lowers advertising production costs. Because talent is generated automatically by the generation AI, high casting costs are unnecessary. Also, because non-existent talent is used, the reputation risk due to talent misconduct is reduced. For example, there is no need to withdraw an ad due to talent misconduct.Furthermore, using different talent for each user can maximize advertising effectiveness. By using talent that matches the user's preferences, the advertisement increases purchase intent, leading to higher click-through rates and conversion rates. For example, displaying an advertisement featuring a talent that a user likes will increase their desire to purchase the product. In this way, by using generative AI to generate talent that matches each user's preferences and incorporating it into advertising content, advertising effectiveness can be maximized, casting costs reduced, and reputational risk mitigated. As a result, the advertising generation system can generate talent that matches the user's preferences and maximize advertising effectiveness.

[0029] The advertising generation system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, and an integration unit. The collection unit collects user preference data. The collection unit can collect data such as purchase history from e-commerce sites and social media posts. The collection unit can also collect data such as the user's hobbies, interests, and past behavioral history. For example, the collection unit collects purchase history from e-commerce sites. The collection unit can also collect social media posts. Furthermore, the collection unit can collect data such as the user's browsing history and survey results. The analysis unit analyzes the data collected by the collection unit and identifies the characteristics of talent that match the user's preferences. The analysis unit can analyze the data using, for example, data mining or machine learning algorithms. Based on the user preference data, the analysis unit can also identify the characteristics of talent that the user likes. For example, the analysis unit extracts characteristics such as specific facial features, hairstyles, and clothing. Based on the user preference data, the analysis unit can also identify the characteristics of talent that the user likes. The generation unit generates talent based on the characteristics identified by the analysis unit. The generation unit can generate talent using, for example, a generation AI. The generation unit can also generate talent with specific facial features such as shape, hairstyle, and clothing. The generation unit can also generate talent that matches the user's preferences using a generation AI. For example, the generation unit generates talent with specific facial features such as shape, hairstyle, and clothing. The generation unit can also generate talent that matches the user's preferences using a generation AI. The embedding unit embeds the talent generated by the generation unit into the advertising content. The embedding unit can, for example, replace the generated talent with pre-recorded talent assets. The embedding unit can also embed the generated talent into the advertising content. For example, the embedding unit can replace the generated talent with pre-recorded talent assets. The embedding unit can also embed the generated talent into the advertising content. As a result, the advertising generation system according to this embodiment can generate talent that matches the user's preferences and maximize advertising effectiveness.

[0030] The data collection unit collects user preference data. For example, it can collect data such as purchase history from e-commerce sites and content from social media posts. Specifically, when collecting purchase history from e-commerce sites, it obtains detailed information about products that users have previously purchased or viewed. This allows the unit to understand what kinds of products users are interested in. When collecting content from social media posts, it analyzes the text, images, videos, and other content posted by users to identify their hobbies and interests. For example, by analyzing hashtags that users frequently use or the content of posts they "like," the unit can more accurately understand user preferences. Furthermore, the data collection unit can also collect data such as user browsing history and survey results. When collecting browsing history, it obtains information about websites visited and pages viewed by users to identify areas and topics that users are interested in. When collecting survey results, it analyzes the content of surveys that users have answered to understand their preferences and opinions. In this way, the data collection unit can collect user preference data from diverse data sources and gain a detailed understanding of users' interests and concerns.

[0031] The analysis unit analyzes the data collected by the collection unit to identify the characteristics of talent that match the user's preferences. The analysis unit can analyze the data using, for example, data mining and machine learning algorithms. Specifically, it uses data mining techniques to extract user preference patterns from the collected data. For example, it identifies the characteristics of products that the user prefers based on information such as the category, brand, and price range of products the user has purchased in the past. It can also use machine learning algorithms to analyze user preference data and identify the characteristics of talent that the user prefers. For example, it can use facial recognition technology to extract features such as the user's preferred face shape, hairstyle, and clothing. Furthermore, it can use text analysis technology to identify the user's hobbies and interests from the content of social media posts. For example, it can analyze keywords and phrases that the user frequently posts to identify topics and themes that the user is interested in. In this way, the analysis unit can analyze the collected data from multiple angles and identify the characteristics of talent that match the user's preferences. Furthermore, the analysis unit can also predict changes and trends in user preferences by utilizing past data and statistical information. This allows the analysis unit to accurately identify the characteristics of talent based on user preferences, thereby improving the accuracy of ad generation.

[0032] The generation unit generates talent based on the features identified by the analysis unit. The generation unit can generate talent using, for example, a generation AI. Specifically, the generation AI uses deep learning technology to generate images of talent with features such as facial shape, hairstyle, and clothing that match the user's preferences. Based on a large amount of pre-trained talent image data, the generation AI can generate images of new talent that match the user's preferences. For example, by providing the user's preferred facial shape, hairstyle, and clothing features as input data, the generation AI generates images of talent with these features. The generation AI can also adjust the talent's facial expressions and poses based on the user's preferences. This allows the generation unit to generate talent that matches the user's preferences with high accuracy. Furthermore, the generation unit also adjusts the generated talent images for application to advertising content. For example, when combining the generated talent images with the background or other elements of an advertisement, it adjusts the color tone, brightness, and contrast to create a natural look. This allows the generation unit to generate talent that matches the user's preferences and prepare them for application to advertising content.

[0033] The integration unit incorporates the talent generated by the generation unit into the advertising content. Specifically, it can replace pre-recorded talent assets with the generated talent. For example, it can replace a talent appearing in a specific scene in an advertising video with the generated talent. The integration unit utilizes video editing software and image processing technology to seamlessly integrate the generated talent's images and videos into the advertising content. For example, when combining the generated talent's images with the advertising background or other elements, it adjusts the color tone, brightness, and contrast to create a natural look. When incorporating the generated talent's videos into the advertising video, it edits them considering scene transitions and the continuity of movement. Furthermore, the integration unit can also add the generated talent's voice and dialogue to the advertising content. For example, it can generate dialogue spoken by the generated talent using speech synthesis technology and incorporate it into the advertising video. This allows the integration unit to seamlessly integrate the generated talent into the advertising content and deliver effective advertisements to users. Furthermore, the integration unit performs a final quality check on the advertising content, verifying that the generated talent aligns with the overall concept and message of the advertisement. This allows the integration unit to incorporate talent that matches user preferences into the advertising content, maximizing advertising effectiveness.

[0034] The data collection unit can collect data such as purchase history from e-commerce sites and social media posts. For example, the data collection unit can collect purchase history from e-commerce sites. The data collection unit can also collect purchase history for products of a specific period or category. The data collection unit can also collect social media posts. The data collection unit can also collect posts for specific keywords or from specific users. The data collection unit can also collect data such as users' hobbies, interests, and past behavioral history. For example, the data collection unit can collect data such as users' browsing history and survey results. This allows the data collection unit to collect detailed user preference data. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input purchase history from e-commerce sites and social media posts into an AI, which can then collect the data.

[0035] The analysis unit can identify the characteristics of talents that users like, based on user preference data. The analysis unit analyzes data using, for example, data mining or machine learning algorithms. The analysis unit can also identify the characteristics of talents that users like, based on user preference data. The analysis unit can extract specific features such as facial shape, hairstyle, and clothing. The analysis unit can also identify the characteristics of talents that users like, based on user preference data. For example, the analysis unit extracts specific features such as facial shape, hairstyle, and clothing. This allows the analysis unit to identify the characteristics of talents that match the user's preferences. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user preference data into AI, and the AI ​​can identify the characteristics of talents.

[0036] The generation unit can generate talents with specific facial features, hairstyles, clothing, and other characteristics. The generation unit can generate talents using, for example, a generation AI. The generation unit can also generate talents with specific facial features, hairstyles, clothing, and other characteristics. The generation unit can also use a generation AI to generate talents that match the user's preferences. For example, the generation unit generates talents with specific facial features, hairstyles, clothing, and other characteristics. The generation unit can also use a generation AI to generate talents that match the user's preferences. This allows the generation unit to generate talents that match the user's preferences. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input user preference data into a generation AI, which can then generate talents.

[0037] The integration unit can replace the generated talent with pre-recorded talent assets. For example, the integration unit can replace the generated talent with pre-recorded talent assets. The integration unit can also integrate the generated talent into advertising content. For example, the integration unit can replace the generated talent with pre-recorded talent assets. The integration unit can also integrate the generated talent into advertising content. This allows the integration unit to provide different advertising content to each user. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can input the generated talent data into AI, and the AI ​​can integrate the talent into advertising content.

[0038] The generation unit can reproduce realistic facial expressions and movements using deep learning technology. For example, the generation unit can reproduce realistic facial expressions and movements using deep learning technology. The generation unit can also generate talent that matches the user's preferences using deep learning technology. For example, the generation unit can generate the facial expressions of talent using a convolutional neural network (CNN). The generation unit can also generate the movements of talent using a generative opposite network (GAN). Furthermore, the generation unit can reproduce realistic facial expressions and movements of talent using deep learning technology. For example, the generation unit can generate the facial expressions of talent using a CNN and generate the movements of talent using a GAN. In this way, the generation unit can enhance the realism of advertisements by reproducing realistic facial expressions and movements. Some or all of the above processing in the generation unit may be performed using a generative AI, or it may be performed without using a generative AI. For example, the generation unit can input talent data generated using deep learning technology into a generative AI, and the generative AI can reproduce the facial expressions and movements of the talent.

[0039] The embedded unit can perform natural synthesis using image processing technology. For example, the embedded unit can perform natural synthesis using image processing technology. The embedded unit can also use image processing technology to naturally integrate the generated talent into the advertising content. For example, the embedded unit can use image synthesis technology to integrate the talent's image into the advertising content. The embedded unit can also use filtering technology to naturally integrate the talent's image into the advertising content. Furthermore, the embedded unit can use edge detection technology to naturally integrate the talent's image into the advertising content. For example, the embedded unit can use image synthesis technology to integrate the talent's image into the advertising content and use filtering technology to make the talent's image appear natural. In this way, the embedded unit can improve the quality of the advertisement by performing natural synthesis. Some or all of the above processing in the embedded unit may be performed using AI or not. For example, the embedded unit can input talent data generated using image processing technology into AI, and the AI ​​can naturally integrate the talent's image into the advertising content.

[0040] The data collection unit can analyze a user's past behavior history and select the optimal data collection method. For example, the data collection unit analyzes a user's past behavior history and selects the optimal data collection method. The data collection unit can also collect data from websites that the user has frequently visited in the past. For example, the data collection unit collects data from websites that the user has frequently visited in the past. The data collection unit can also prioritize the collection of data on relevant products based on a user's past purchase history. For example, the data collection unit prioritizes the collection of data on relevant products based on a user's past purchase history. The data collection unit can also analyze a user's past social media posts and collect data on topics of interest. For example, the data collection unit analyzes a user's past social media posts and collects data on topics of interest. This enables efficient data collection by allowing the data collection unit to select the optimal data collection method based on past behavior history. Some or all of the above-described processes in the data collection unit may be performed using AI or not. For example, the data collection unit can input a user's past behavior history into AI, which can then select the optimal data collection method.

[0041] The data collection unit can filter data based on the user's current interests and trends during data collection. For example, the data collection unit can filter data based on the user's current interests and trends during data collection. The data collection unit can also prioritize the collection of data related to topics the user is currently interested in. For example, the data collection unit prioritizes the collection of data related to topics the user is currently interested in. The data collection unit can also collect data that the user is likely to be interested in based on the latest trend information. For example, the data collection unit collects data that the user is likely to be interested in based on the latest trend information. The data collection unit can also analyze the user's current search history and collect relevant data. For example, the data collection unit analyzes the user's current search history and collects relevant data. This allows the data collection unit to collect highly relevant data by filtering the data based on current interests and trends. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's current interests and trend information into the AI, which can then filter the data.

[0042] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, the data collection unit prioritizes the collection of highly relevant data by considering the user's geographical location information during data collection. The data collection unit can also prioritize the collection of trend information for the area where the user is currently located. For example, the data collection unit prioritizes the collection of trend information for the area where the user is currently located. The data collection unit can also collect relevant data based on the user's past location information. For example, the data collection unit collects relevant data based on the user's past location information. The data collection unit can also prioritize the collection of data related to places the user frequently visits. For example, the data collection unit prioritizes the collection of data related to places the user frequently visits. In this way, the data collection unit can efficiently collect highly relevant data by considering geographical location information. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's geographical location information into AI, and the AI ​​can prioritize the collection of highly relevant data.

[0043] The data collection unit can analyze a user's social media activity and collect relevant data during data collection. For example, the data collection unit can analyze a user's social media activity and collect relevant data during data collection. The data collection unit can also collect data related to topics that a user frequently posts about. For example, the data collection unit can collect data related to topics that a user's followers and friends are interested in. For example, the data collection unit can collect data related to topics that a user's followers and friends are interested in. The data collection unit can also collect data related to topics in online communities that a user participates in. For example, the data collection unit can collect data related to topics in online communities that a user participates in. This allows the data collection unit to efficiently collect data related to a user's interests by analyzing social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input a user's social media activity into an AI, which can then collect relevant data.

[0044] The analysis unit can adjust the level of detail of the analysis based on the importance of the user's preference data during the analysis. For example, the analysis unit can adjust the level of detail of the analysis based on the importance of the user's preference data during the analysis. The analysis unit can also perform detailed analysis on data that the user is particularly interested in. For example, the analysis unit can perform detailed analysis on data that the user is particularly interested in. The analysis unit can also perform concise analysis on data that the user is not very interested in. For example, the analysis unit can perform concise analysis on data that the user is not very interested in. The analysis unit can also determine the priority of the analysis according to the importance of the user's preference data. For example, the analysis unit can determine the priority of the analysis according to the importance of the user's preference data. This enables efficient analysis by allowing the analysis unit to adjust the level of detail of the analysis based on the importance of the preference data. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input user preference data into AI, which can evaluate the importance of the data and adjust the level of detail of the analysis.

[0045] The analysis unit can apply different analysis algorithms depending on the user's preference categories during analysis. For example, the analysis unit can apply different analysis algorithms depending on the user's preference categories during analysis. The analysis unit can also apply an analysis algorithm specialized for music preferences if the user is interested in music. For example, the analysis unit can apply an analysis algorithm specialized for music preferences if the user is interested in sports. For example, the analysis unit can apply an analysis algorithm specialized for sports preferences if the user is interested in sports. The analysis unit can also apply an analysis algorithm specialized for fashion preferences if the user is interested in fashion. For example, the analysis unit can apply an analysis algorithm specialized for fashion preferences if the user is interested in fashion. By applying an analysis algorithm according to the preference category, the analysis unit can perform more accurate analysis. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the user's preference categories into the AI, which can select an appropriate analysis algorithm and perform the analysis.

[0046] The analysis unit can improve the accuracy of its analysis by referring to the user's past preference data during the analysis. For example, the analysis unit can improve the accuracy of its analysis by referring to the user's past preference data during the analysis. The analysis unit can also improve the accuracy of its analysis by predicting the user's current preferences based on the user's past preference data. For example, the analysis unit can improve the accuracy of its analysis by predicting the user's current preferences based on the user's past preference data. The analysis unit can also increase the reliability of its analysis results by referring to the user's past behavior history. For example, the analysis unit can increase the reliability of its analysis results by referring to the user's past behavior history. The analysis unit can also analyze the user's past preference data, grasp trends, and reflect them in the analysis. For example, the analysis unit analyzes the user's past preference data, grasps trends, and reflects them in the analysis. As a result, the analysis unit improves the accuracy of its analysis by referring to past preference data. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input the user's past preference data into the AI, which then analyzes the data to improve the accuracy of the analysis.

[0047] The analysis unit can perform analysis by referring to the user's relevant market data during the analysis process. For example, the analysis unit can perform analysis by referring to the user's relevant market data during the analysis process. The analysis unit can also supplement the analysis results by referring to market data of the market the user is interested in. For example, the analysis unit can supplement the analysis results by referring to market data of the market the user is interested in. The analysis unit can also reflect market trends related to the user's preferences in the analysis. For example, the analysis unit can reflect market trends related to the user's preferences in the analysis. The analysis unit can also perform more accurate analysis by integrating user preference data and market data. For example, the analysis unit can perform more accurate analysis by integrating user preference data and market data. This enables the analysis unit to perform more accurate analysis by referring to relevant market data. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input the user's relevant market data into AI, and the AI ​​can analyze the data and perform the analysis.

[0048] The generation unit can adjust the accuracy of the generation based on the level of detail of the user's preference data during generation. For example, the generation unit adjusts the accuracy of the generation based on the level of detail of the user's preference data during generation. The generation unit can also generate more precise talents if the user's preference data is detailed. For example, the generation unit generates more precise talents if the user's preference data is detailed. The generation unit can also generate talents with basic characteristics if the user's preference data is vague. For example, the generation unit generates talents with basic characteristics if the user's preference data is vague. The generation unit can also adjust the characteristics of the talents it generates according to the level of detail of the user's preference data. For example, the generation unit adjusts the characteristics of the talents it generates according to the level of detail of the user's preference data. In this way, the generation unit can generate more precise talents by adjusting the accuracy of the generation based on the level of detail of the preference data. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the generation unit can input user preference data into the generation AI, which can then evaluate the level of detail in the data and adjust the accuracy of the generation.

[0049] The generation unit can apply different generation algorithms depending on the user's preference categories during generation. For example, the generation unit can apply different generation algorithms depending on the user's preference categories during generation. The generation unit can also apply a generation algorithm specialized for music preferences if the user is interested in music. For example, the generation unit can apply a generation algorithm specialized for music preferences if the user is interested in sports. For example, the generation unit can apply a generation algorithm specialized for sports preferences if the user is interested in sports. The generation unit can also apply a generation algorithm specialized for fashion preferences if the user is interested in fashion. For example, the generation unit can apply a generation algorithm specialized for fashion preferences if the user is interested in fashion. By doing so, the generation unit can generate more accurate talent by applying a generation algorithm according to the preference categories. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the user's preference categories into a generation AI, which can then select an appropriate generation algorithm and generate talent.

[0050] The generation unit can improve the accuracy of generation by referring to the user's past preference data during generation. For example, the generation unit can improve the accuracy of generation by referring to the user's past preference data during generation. The generation unit can also improve the accuracy of generation by predicting the user's current preferences based on the user's past preference data. For example, the generation unit can improve the accuracy of generation by predicting the user's current preferences based on the user's past preference data. The generation unit can also adjust the characteristics of the talents to be generated by referring to the user's past behavior history. For example, the generation unit adjusts the characteristics of the talents to be generated by referring to the user's past behavior history. The generation unit can also analyze the user's past preference data, grasp trends, and reflect them in the generation. For example, the generation unit analyzes the user's past preference data, grasps trends, and reflects them in the generation. As a result, the generation unit improves the accuracy of generation by referring to past preference data. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the generation unit can input the user's past preference data into the generation AI, which then analyzes the data to improve the accuracy of the generation.

[0051] The generation unit can perform generation by referring to the user's relevant market data during generation. For example, the generation unit can perform generation by referring to the user's relevant market data during generation. The generation unit can also adjust the characteristics of the talents it generates by referring to market data that the user is interested in. For example, the generation unit can adjust the characteristics of the talents it generates by referring to market data that the user is interested in. The generation unit can also reflect market trends related to the user's preferences in the generation. For example, the generation unit reflects market trends related to the user's preferences in the generation. The generation unit can also integrate user preference data and market data to perform more accurate generation. For example, the generation unit integrates user preference data and market data to perform more accurate generation. As a result, the generation unit can generate more accurate talents by referring to relevant market data. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the user's relevant market data into a generation AI, which can analyze the data and generate talents.

[0052] The embedding unit can select the optimal embedding method by referring to the user's past ad viewing history during embedding. For example, the embedding unit selects the optimal embedding method by referring to the user's past ad viewing history during embedding. The embedding unit can also embed talent based on the style of ads the user has previously enjoyed watching. For example, the embedding unit embeds talent based on the style of ads the user has previously enjoyed watching. The embedding unit can also analyze the user's past ad viewing history and select the most effective embedding method. For example, the embedding unit analyzes the user's past ad viewing history and selects the most effective embedding method. The embedding unit can also embed talent by referring to the characteristics of ads the user has previously watched. For example, the embedding unit embeds talent by referring to the characteristics of ads the user has previously watched. In this way, the embedding unit can select the optimal embedding method by referring to the past ad viewing history. Some or all of the above processing in the embedding unit may be performed using AI or not. For example, the embedding unit can input the user's past ad viewing history into AI, and the AI ​​can select the optimal embedding method.

[0053] The embedded system can customize the embedding method based on the user's current interests during embedding. For example, the embedded system can customize the embedding method based on the user's current interests during embedding. The embedded system can also embed talent related to topics the user is currently interested in into the ads. For example, the embedded system can embed talent related to topics the user is currently interested in into the ads. The embedded system can also embed relevant talent based on the user's current search history. For example, the embedded system can embed relevant talent based on the user's current search history into the ads. The embedded system can also embed talent related to topics in online communities the user is currently participating in into the ads. For example, the embedded system can embed talent related to topics in online communities the user is currently participating in into the ads. This allows the embedded system to generate more effective ads by customizing the embedding method based on current interests. Some or all of the above processing in the embedded system may be performed using AI or not. For example, the embedded system can input the user's current interests into AI, which can then customize the optimal embedding method.

[0054] The embedding unit can select the optimal embedding method by considering the user's geographical location information during embedding. For example, the embedding unit selects the optimal embedding method by considering the user's geographical location information during embedding. The embedding unit can also embed talent into advertisements based on trend information in the user's current location. For example, the embedding unit embeds talent into advertisements based on trend information in the user's current location. The embedding unit can also embed relevant talent into advertisements by referring to the user's past location information. For example, the embedding unit embeds relevant talent into advertisements by referring to the user's past location information. The embedding unit can also embed talent related to places the user frequently visits into advertisements. For example, the embedding unit embeds talent related to places the user frequently visits into advertisements. In this way, the embedding unit can select the optimal embedding method by considering geographical location information. Some or all of the above processing in the embedding unit may be performed using AI or not. For example, the embedding unit can input the user's geographical location information into AI, and the AI ​​can select the optimal embedding method.

[0055] The embedded unit can analyze the user's social media activity during the embedding process and propose embedding methods. For example, the embedded unit can analyze the user's social media activity during the embedding process and propose embedding methods. The embedded unit can also embed talent related to topics that the user frequently posts about into the advertisement. For example, the embedded unit can embed talent related to topics that the user's followers and friends are interested in into the advertisement. For example, the embedded unit can embed talent related to topics that the user's followers and friends are interested in into the advertisement. The embedded unit can also embed talent related to topics in online communities that the user participates in into the advertisement. For example, the embedded unit can embed talent related to topics in online communities that the user participates in into the advertisement. This allows the embedded unit to propose the optimal embedding method by analyzing social media activity. Some or all of the above processing in the embedded unit may be performed using AI or not. For example, the embedded unit can input the user's social media activity into AI, which can then propose the optimal embedding method.

[0056] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0057] The ad generation system can customize the voices of talents generated based on user preference data. For example, the generation unit can identify the tone and accent of voices preferred by the user and generate voices of talents with those characteristics. Furthermore, the generation unit can adjust the speed and intonation of the talent's voice according to the user's preferences. For instance, if the user prefers a calm voice, the generation unit can generate a talent's voice that speaks slowly in a gentle tone. Conversely, if the user prefers an energetic voice, the generation unit can generate a talent's voice that speaks in a bright and cheerful tone. This allows the ad generation system to generate talent voices that match the user's preferences, further enhancing the effectiveness of the advertisements.

[0058] The ad generation system can customize the actions of the talent generated based on user preference data. For example, the generation unit can identify the actions and gestures that the user prefers and generate actions of talent that possess those characteristics. Furthermore, the generation unit can adjust the speed and rhythm of the talent's actions according to the user's preferences. For example, if the user prefers calm actions, the generation unit can generate talent that perform slow actions. Conversely, if the user prefers lively actions, the generation unit can generate talent that perform energetic actions. In this way, the ad generation system can generate talent actions that match the user's preferences, further enhancing the effectiveness of the advertisements.

[0059] The ad generation system can customize the backgrounds of the talent generated based on user preference data. For example, the generation unit can identify the background style and color scheme preferred by the user and generate backgrounds with those characteristics. Furthermore, the generation unit can adjust the level of detail and atmosphere of the background according to the user's preferences. For instance, if the user prefers a simple background, the generation unit can generate a simple and calm background. Conversely, if the user prefers a vibrant background, the generation unit can generate a colorful and lively background. This allows the ad generation system to generate backgrounds that match the user's preferences, further enhancing the effectiveness of the advertisements.

[0060] The ad generation system can customize the clothing of the talents generated based on user preference data. For example, the generation unit can identify the style and color scheme of clothing preferred by the user and generate clothing for talents that possess those characteristics. Furthermore, the generation unit can adjust the level of detail and accessories of the clothing according to the user's preferences. For instance, if the user prefers casual clothing, the generation unit can generate talents wearing casual and relaxed attire. Similarly, if the user prefers formal clothing, the generation unit can generate talents wearing formal and elegant attire. This allows the ad generation system to generate talent clothing that matches the user's preferences, further enhancing the effectiveness of the advertisements.

[0061] The ad generation system can customize the facial expressions of the talent generated based on user preference data. For example, the generation unit can identify the style and emotion of facial expressions preferred by the user and generate facial expressions of talent with those characteristics. Furthermore, the generation unit can adjust the level of detail and intensity of the facial expressions according to the user's preferences. For example, if the user prefers calm facial expressions, the generation unit can generate talent with calm and gentle facial expressions. Also, if the user prefers cheerful facial expressions, the generation unit can generate talent with bright and energetic facial expressions. In this way, the ad generation system can generate talent facial expressions that match the user's preferences, further enhancing the effectiveness of the advertisements.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The data collection unit collects user preference data. For example, it collects data such as purchase history on e-commerce sites, social media posts, users' hobbies and interests, past behavioral history, browsing history, and survey results. Step 2: The analysis unit analyzes the data collected by the collection unit to identify the characteristics of talent that match the user's preferences. For example, it uses data mining or machine learning algorithms to extract specific features such as facial shape, hairstyle, and clothing. Step 3: The generation unit generates talents based on the features identified by the analysis unit. For example, it uses a generation AI to generate talents with specific facial features such as face shape, hairstyle, and clothing. Step 4: The integration unit integrates the talent generated by the generation unit into the advertising content. For example, it replaces the generated talent with pre-recorded talent assets.

[0064] (Example of form 2) An advertising generation system according to an embodiment of the present invention is a system that uses a generation AI to generate talent tailored to each user's preferences and incorporates it into advertising content. The advertising generation system collects user preference data, and the generation AI analyzes this data. Next, the generation AI generates talent tailored to the user's preferences and incorporates that talent into the advertising content. This reduces casting costs and advertising production costs by using different, non-existent talents for each user. In addition, reputation risk is reduced because non-existent talents are used. First, the advertising generation system collects user preference data. At this time, data such as the user's hobbies, interests, and past behavioral history is collected. For example, this includes purchase history on e-commerce sites and content posted on social media. This allows for a detailed understanding of the user's preferences. Next, the generation AI analyzes the collected data in the advertising generation system. Based on the user preference data, the generation AI identifies the characteristics of talent that the user prefers. For example, it can extract characteristics such as specific facial features, hairstyles, and clothing. This provides basic data for generating different talents for each user. The generation AI generates talent that matches the user's preferences based on analysis results. The generated talent does not actually exist, but because it possesses characteristics that users like, it has a high advertising effect. For example, it can generate talent with the facial features, hairstyles, and clothing that users prefer. The advertising generation system incorporates the generated talent into the advertising content. Specifically, it replaces pre-shot talent assets with the talent generated by the generation AI. This allows for the provision of different advertising content for each user. For example, even for the same product, different users can see ads featuring different talents. This mechanism reduces casting costs and lowers advertising production costs. Because talent is generated automatically by the generation AI, high casting costs are unnecessary. Also, because non-existent talent is used, the reputation risk due to talent misconduct is reduced. For example, there is no need to withdraw an ad due to talent misconduct.Furthermore, using different talent for each user can maximize advertising effectiveness. By using talent that matches the user's preferences, the advertisement increases purchase intent, leading to higher click-through rates and conversion rates. For example, displaying an advertisement featuring a talent that a user likes will increase their desire to purchase the product. In this way, by using generative AI to generate talent that matches each user's preferences and incorporating it into advertising content, advertising effectiveness can be maximized, casting costs reduced, and reputational risk mitigated. As a result, the advertising generation system can generate talent that matches the user's preferences and maximize advertising effectiveness.

[0065] The advertising generation system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, and an integration unit. The collection unit collects user preference data. The collection unit can collect data such as purchase history from e-commerce sites and social media posts. The collection unit can also collect data such as the user's hobbies, interests, and past behavioral history. For example, the collection unit collects purchase history from e-commerce sites. The collection unit can also collect social media posts. Furthermore, the collection unit can collect data such as the user's browsing history and survey results. The analysis unit analyzes the data collected by the collection unit and identifies the characteristics of talent that match the user's preferences. The analysis unit can analyze the data using, for example, data mining or machine learning algorithms. Based on the user preference data, the analysis unit can also identify the characteristics of talent that the user likes. For example, the analysis unit extracts characteristics such as specific facial features, hairstyles, and clothing. Based on the user preference data, the analysis unit can also identify the characteristics of talent that the user likes. The generation unit generates talent based on the characteristics identified by the analysis unit. The generation unit can generate talent using, for example, a generation AI. The generation unit can also generate talent with specific facial features such as shape, hairstyle, and clothing. The generation unit can also generate talent that matches the user's preferences using a generation AI. For example, the generation unit generates talent with specific facial features such as shape, hairstyle, and clothing. The generation unit can also generate talent that matches the user's preferences using a generation AI. The embedding unit embeds the talent generated by the generation unit into the advertising content. The embedding unit can, for example, replace the generated talent with pre-recorded talent assets. The embedding unit can also embed the generated talent into the advertising content. For example, the embedding unit can replace the generated talent with pre-recorded talent assets. The embedding unit can also embed the generated talent into the advertising content. As a result, the advertising generation system according to this embodiment can generate talent that matches the user's preferences and maximize advertising effectiveness.

[0066] The data collection unit collects user preference data. For example, it can collect data such as purchase history from e-commerce sites and content from social media posts. Specifically, when collecting purchase history from e-commerce sites, it obtains detailed information about products that users have previously purchased or viewed. This allows the unit to understand what kinds of products users are interested in. When collecting content from social media posts, it analyzes the text, images, videos, and other content posted by users to identify their hobbies and interests. For example, by analyzing hashtags that users frequently use or the content of posts they "like," the unit can more accurately understand user preferences. Furthermore, the data collection unit can also collect data such as user browsing history and survey results. When collecting browsing history, it obtains information about websites visited and pages viewed by users to identify areas and topics that users are interested in. When collecting survey results, it analyzes the content of surveys that users have answered to understand their preferences and opinions. In this way, the data collection unit can collect user preference data from diverse data sources and gain a detailed understanding of users' interests and concerns.

[0067] The analysis unit analyzes the data collected by the collection unit to identify the characteristics of talent that match the user's preferences. The analysis unit can analyze the data using, for example, data mining and machine learning algorithms. Specifically, it uses data mining techniques to extract user preference patterns from the collected data. For example, it identifies the characteristics of products that the user prefers based on information such as the category, brand, and price range of products the user has purchased in the past. It can also use machine learning algorithms to analyze user preference data and identify the characteristics of talent that the user prefers. For example, it can use facial recognition technology to extract features such as the user's preferred face shape, hairstyle, and clothing. Furthermore, it can use text analysis technology to identify the user's hobbies and interests from the content of social media posts. For example, it can analyze keywords and phrases that the user frequently posts to identify topics and themes that the user is interested in. In this way, the analysis unit can analyze the collected data from multiple angles and identify the characteristics of talent that match the user's preferences. Furthermore, the analysis unit can also predict changes and trends in user preferences by utilizing past data and statistical information. This allows the analysis unit to accurately identify the characteristics of talent based on user preferences, thereby improving the accuracy of ad generation.

[0068] The generation unit generates talent based on the features identified by the analysis unit. The generation unit can generate talent using, for example, a generation AI. Specifically, the generation AI uses deep learning technology to generate images of talent with features such as facial shape, hairstyle, and clothing that match the user's preferences. Based on a large amount of pre-trained talent image data, the generation AI can generate images of new talent that match the user's preferences. For example, by providing the user's preferred facial shape, hairstyle, and clothing features as input data, the generation AI generates images of talent with these features. The generation AI can also adjust the talent's facial expressions and poses based on the user's preferences. This allows the generation unit to generate talent that matches the user's preferences with high accuracy. Furthermore, the generation unit also adjusts the generated talent images for application to advertising content. For example, when combining the generated talent images with the background or other elements of an advertisement, it adjusts the color tone, brightness, and contrast to create a natural look. This allows the generation unit to generate talent that matches the user's preferences and prepare them for application to advertising content.

[0069] The integration unit incorporates the talent generated by the generation unit into the advertising content. Specifically, it can replace pre-recorded talent assets with the generated talent. For example, it can replace a talent appearing in a specific scene in an advertising video with the generated talent. The integration unit utilizes video editing software and image processing technology to seamlessly integrate the generated talent's images and videos into the advertising content. For example, when combining the generated talent's images with the advertising background or other elements, it adjusts the color tone, brightness, and contrast to create a natural look. When incorporating the generated talent's videos into the advertising video, it edits them considering scene transitions and the continuity of movement. Furthermore, the integration unit can also add the generated talent's voice and dialogue to the advertising content. For example, it can generate dialogue spoken by the generated talent using speech synthesis technology and incorporate it into the advertising video. This allows the integration unit to seamlessly integrate the generated talent into the advertising content and deliver effective advertisements to users. Furthermore, the integration unit performs a final quality check on the advertising content, verifying that the generated talent aligns with the overall concept and message of the advertisement. This allows the integration unit to incorporate talent that matches user preferences into the advertising content, maximizing advertising effectiveness.

[0070] The data collection unit can collect data such as purchase history from e-commerce sites and social media posts. For example, the data collection unit can collect purchase history from e-commerce sites. The data collection unit can also collect purchase history for products of a specific period or category. The data collection unit can also collect social media posts. The data collection unit can also collect posts for specific keywords or from specific users. The data collection unit can also collect data such as users' hobbies, interests, and past behavioral history. For example, the data collection unit can collect data such as users' browsing history and survey results. This allows the data collection unit to collect detailed user preference data. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input purchase history from e-commerce sites and social media posts into an AI, which can then collect the data.

[0071] The analysis unit can identify the characteristics of talents that users like, based on user preference data. The analysis unit analyzes data using, for example, data mining or machine learning algorithms. The analysis unit can also identify the characteristics of talents that users like, based on user preference data. The analysis unit can extract specific features such as facial shape, hairstyle, and clothing. The analysis unit can also identify the characteristics of talents that users like, based on user preference data. For example, the analysis unit extracts specific features such as facial shape, hairstyle, and clothing. This allows the analysis unit to identify the characteristics of talents that match the user's preferences. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user preference data into AI, and the AI ​​can identify the characteristics of talents.

[0072] The generation unit can generate talents with specific facial features, hairstyles, clothing, and other characteristics. The generation unit can generate talents using, for example, a generation AI. The generation unit can also generate talents with specific facial features, hairstyles, clothing, and other characteristics. The generation unit can also use a generation AI to generate talents that match the user's preferences. For example, the generation unit generates talents with specific facial features, hairstyles, clothing, and other characteristics. The generation unit can also use a generation AI to generate talents that match the user's preferences. This allows the generation unit to generate talents that match the user's preferences. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input user preference data into a generation AI, which can then generate talents.

[0073] The integration unit can replace the generated talent with pre-recorded talent assets. For example, the integration unit can replace the generated talent with pre-recorded talent assets. The integration unit can also integrate the generated talent into advertising content. For example, the integration unit can replace the generated talent with pre-recorded talent assets. The integration unit can also integrate the generated talent into advertising content. This allows the integration unit to provide different advertising content to each user. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can input the generated talent data into AI, and the AI ​​can integrate the talent into advertising content.

[0074] The generation unit can reproduce realistic facial expressions and movements using deep learning technology. For example, the generation unit can reproduce realistic facial expressions and movements using deep learning technology. The generation unit can also generate talent that matches the user's preferences using deep learning technology. For example, the generation unit can generate the facial expressions of talent using a convolutional neural network (CNN). The generation unit can also generate the movements of talent using a generative opposite network (GAN). Furthermore, the generation unit can reproduce realistic facial expressions and movements of talent using deep learning technology. For example, the generation unit can generate the facial expressions of talent using a CNN and generate the movements of talent using a GAN. In this way, the generation unit can enhance the realism of advertisements by reproducing realistic facial expressions and movements. Some or all of the above processing in the generation unit may be performed using a generative AI, or it may be performed without using a generative AI. For example, the generation unit can input talent data generated using deep learning technology into a generative AI, and the generative AI can reproduce the facial expressions and movements of the talent.

[0075] The embedded unit can perform natural synthesis using image processing technology. For example, the embedded unit can perform natural synthesis using image processing technology. The embedded unit can also use image processing technology to naturally integrate the generated talent into the advertising content. For example, the embedded unit can use image synthesis technology to integrate the talent's image into the advertising content. The embedded unit can also use filtering technology to naturally integrate the talent's image into the advertising content. Furthermore, the embedded unit can use edge detection technology to naturally integrate the talent's image into the advertising content. For example, the embedded unit can use image synthesis technology to integrate the talent's image into the advertising content and use filtering technology to make the talent's image appear natural. In this way, the embedded unit can improve the quality of the advertisement by performing natural synthesis. Some or all of the above processing in the embedded unit may be performed using AI or not. For example, the embedded unit can input talent data generated using image processing technology into AI, and the AI ​​can naturally integrate the talent's image into the advertising content.

[0076] The data collection unit can estimate the user's emotions and adjust the timing of preference data collection based on the estimated emotions. For example, the data collection unit can estimate the user's emotions and adjust the timing of preference data collection based on the estimated emotions. The data collection unit can also estimate the user's emotions and collect preference data when the user is relaxed. For example, the data collection unit collects preference data when the user is relaxed. The data collection unit can also temporarily stop data collection if the user is stressed and resume it later. For example, the data collection unit temporarily stops data collection if the user is stressed and resumes it later. The data collection unit can also collect preference data in real time and immediately send it for analysis if the user is excited. For example, the data collection unit collects preference data in real time and immediately sends it for analysis if the user is excited. This allows the data collection unit to obtain more accurate data by adjusting the timing of data collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the collection unit may be performed using AI or not. For example, the collection unit can input user emotion data into an AI, which can estimate the emotion and adjust the timing of data collection.

[0077] The data collection unit can analyze a user's past behavior history and select the optimal data collection method. For example, the data collection unit analyzes a user's past behavior history and selects the optimal data collection method. The data collection unit can also collect data from websites that the user has frequently visited in the past. For example, the data collection unit collects data from websites that the user has frequently visited in the past. The data collection unit can also prioritize the collection of data on relevant products based on a user's past purchase history. For example, the data collection unit prioritizes the collection of data on relevant products based on a user's past purchase history. The data collection unit can also analyze a user's past social media posts and collect data on topics of interest. For example, the data collection unit analyzes a user's past social media posts and collects data on topics of interest. This enables efficient data collection by allowing the data collection unit to select the optimal data collection method based on past behavior history. Some or all of the above-described processes in the data collection unit may be performed using AI or not. For example, the data collection unit can input a user's past behavior history into AI, which can then select the optimal data collection method.

[0078] The data collection unit can filter data based on the user's current interests and trends during data collection. For example, the data collection unit can filter data based on the user's current interests and trends during data collection. The data collection unit can also prioritize collecting data related to topics the user is currently interested in. For example, the data collection unit prioritizes collecting data related to topics the user is currently interested in. The data collection unit can also collect data that the user is likely to be interested in based on the latest trend information. For example, the data collection unit collects data that the user is likely to be interested in based on the latest trend information. The data collection unit can also analyze the user's current search history and collect relevant data. For example, the data collection unit analyzes the user's current search history and collects relevant data. This allows the data collection unit to collect highly relevant data by filtering data based on current interests and trends. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's current interests and trend information into the AI, which can then filter the data.

[0079] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated emotions. For example, the data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated emotions. The data collection unit can also prioritize the collection of detailed preference data when the user is relaxed. For example, if the user is relaxed, the data collection unit prioritizes the collection of detailed preference data. If the user is stressed, the data collection unit can also prioritize the collection of data that fluctuates in real time when the user is agitated. For example, if the user is agitated, the data collection unit prioritizes the collection of data that fluctuates in real time. This allows the data collection unit to efficiently collect data by prioritizing data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into an AI, which can then estimate the emotion and determine the priority of the data.

[0080] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, the data collection unit prioritizes the collection of highly relevant data by considering the user's geographical location information during data collection. The data collection unit can also prioritize the collection of trend information for the area where the user is currently located. For example, the data collection unit prioritizes the collection of trend information for the area where the user is currently located. The data collection unit can also collect relevant data based on the user's past location information. For example, the data collection unit collects relevant data based on the user's past location information. The data collection unit can also prioritize the collection of data related to places the user frequently visits. For example, the data collection unit prioritizes the collection of data related to places the user frequently visits. In this way, the data collection unit can efficiently collect highly relevant data by considering geographical location information. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's geographical location information into AI, and the AI ​​can prioritize the collection of highly relevant data.

[0081] The data collection unit can analyze the user's social media activity and collect relevant data during data collection. For example, the data collection unit can analyze the user's social media activity and collect relevant data during data collection. The data collection unit can also collect data related to topics that the user frequently posts about. For example, the data collection unit can collect data related to topics that the user's followers and friends are interested in. For example, the data collection unit can collect data related to topics that the user's followers and friends are interested in. The data collection unit can also collect data related to topics in online communities that the user participates in. For example, the data collection unit can collect data related to topics in online communities that the user participates in. This allows the data collection unit to efficiently collect data related to the user's interests by analyzing social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's social media activity into AI, and the AI ​​can collect relevant data.

[0082] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, the analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. The analysis unit can also provide detailed analysis results when the user is relaxed. For example, the analysis unit provides detailed analysis results when the user is relaxed. The analysis unit can also provide concise analysis results when the user is stressed. For example, the analysis unit provides concise analysis results when the user is stressed. The analysis unit can also provide visually appealing analysis results when the user is excited. For example, the analysis unit provides visually appealing analysis results when the user is excited. In this way, the analysis unit can provide more appropriate analysis results by adjusting the presentation of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into the AI, which can then estimate the emotion and adjust the way the analysis is expressed.

[0083] The analysis unit can adjust the level of detail of the analysis based on the importance of the user's preference data during the analysis. For example, the analysis unit can adjust the level of detail of the analysis based on the importance of the user's preference data during the analysis. The analysis unit can also perform detailed analysis on data that the user is particularly interested in. For example, the analysis unit can perform detailed analysis on data that the user is particularly interested in. The analysis unit can also perform concise analysis on data that the user is not very interested in. For example, the analysis unit can perform concise analysis on data that the user is not very interested in. The analysis unit can also determine the priority of the analysis according to the importance of the user's preference data. For example, the analysis unit can determine the priority of the analysis according to the importance of the user's preference data. This enables efficient analysis by allowing the analysis unit to adjust the level of detail of the analysis based on the importance of the preference data. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input user preference data into AI, which can evaluate the importance of the data and adjust the level of detail of the analysis.

[0084] The analysis unit can apply different analysis algorithms depending on the user's preference categories during analysis. For example, the analysis unit can apply different analysis algorithms depending on the user's preference categories during analysis. The analysis unit can also apply an analysis algorithm specialized for music preferences if the user is interested in music. For example, the analysis unit can apply an analysis algorithm specialized for music preferences if the user is interested in sports. For example, the analysis unit can apply an analysis algorithm specialized for sports preferences if the user is interested in sports. The analysis unit can also apply an analysis algorithm specialized for fashion preferences if the user is interested in fashion. For example, the analysis unit can apply an analysis algorithm specialized for fashion preferences if the user is interested in fashion. By applying an analysis algorithm according to the preference category, the analysis unit can perform more accurate analysis. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the user's preference categories into the AI, which can select an appropriate analysis algorithm and perform the analysis.

[0085] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, the analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. The analysis unit can also prioritize detailed analysis when the user is relaxed. For example, the analysis unit prioritizes detailed analysis when the user is relaxed. The analysis unit can also prioritize concise analysis when the user is stressed. For example, the analysis unit prioritizes concise analysis when the user is stressed. The analysis unit can also prioritize real-time fluctuating data analysis when the user is excited. For example, the analysis unit prioritizes real-time fluctuating data analysis when the user is excited. This allows the analysis unit to perform efficient analysis by determining the priority of analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into the AI, which can then estimate the emotion and determine the priority of the analysis.

[0086] The analysis unit can improve the accuracy of its analysis by referring to the user's past preference data during the analysis. For example, the analysis unit can improve the accuracy of its analysis by referring to the user's past preference data during the analysis. The analysis unit can also improve the accuracy of its analysis by predicting the user's current preferences based on the user's past preference data. For example, the analysis unit can improve the accuracy of its analysis by predicting the user's current preferences based on the user's past preference data. The analysis unit can also increase the reliability of its analysis results by referring to the user's past behavior history. For example, the analysis unit can increase the reliability of its analysis results by referring to the user's past behavior history. The analysis unit can also analyze the user's past preference data, grasp trends, and reflect them in the analysis. For example, the analysis unit analyzes the user's past preference data, grasps trends, and reflects them in the analysis. As a result, the analysis unit improves the accuracy of its analysis by referring to past preference data. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input the user's past preference data into the AI, which then analyzes the data to improve the accuracy of the analysis.

[0087] The analysis unit can perform analysis by referring to the user's relevant market data during the analysis process. For example, the analysis unit can perform analysis by referring to the user's relevant market data during the analysis process. The analysis unit can also supplement the analysis results by referring to market data of the market the user is interested in. For example, the analysis unit can supplement the analysis results by referring to market data of the market the user is interested in. The analysis unit can also reflect market trends related to the user's preferences in the analysis. For example, the analysis unit can reflect market trends related to the user's preferences in the analysis. The analysis unit can also perform more accurate analysis by integrating user preference data and market data. For example, the analysis unit can perform more accurate analysis by integrating user preference data and market data. This enables the analysis unit to perform more accurate analysis by referring to relevant market data. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input the user's relevant market data into AI, and the AI ​​can analyze the data and perform the analysis.

[0088] The generation unit can estimate the user's emotions and adjust the characteristics of the talent it generates based on those estimated emotions. For example, the generation unit can estimate the user's emotions and adjust the characteristics of the talent it generates based on those estimated emotions. The generation unit can also generate talent with calm expressions and soft voices when the user is relaxed. For example, the generation unit generates talent with calm expressions and soft voices when the user is relaxed. The generation unit can also generate talent with energetic expressions and bright voices when the user is excited. For example, the generation unit generates talent with energetic expressions and bright voices when the user is excited. The generation unit can also generate talent with calm expressions and calm voices when the user is stressed. For example, the generation unit generates talent with calm expressions and calm voices when the user is stressed. In this way, the generation unit can generate more effective advertisements by adjusting the characteristics of the talent according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generative AI may be a text-generating AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the processing described above in the generation unit may be performed using the generative AI or not. For example, the generation unit can input user emotion data into the generative AI, which can then adjust the characteristics of the talent.

[0089] The generation unit can adjust the accuracy of the generation based on the level of detail of the user's preference data during generation. For example, the generation unit adjusts the accuracy of the generation based on the level of detail of the user's preference data during generation. The generation unit can also generate more precise talents if the user's preference data is detailed. For example, the generation unit generates more precise talents if the user's preference data is detailed. The generation unit can also generate talents with basic characteristics if the user's preference data is vague. For example, the generation unit generates talents with basic characteristics if the user's preference data is vague. The generation unit can also adjust the characteristics of the talents it generates according to the level of detail of the user's preference data. For example, the generation unit adjusts the characteristics of the talents it generates according to the level of detail of the user's preference data. In this way, the generation unit can generate more precise talents by adjusting the accuracy of the generation based on the level of detail of the preference data. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the generation unit can input user preference data into the generation AI, which can then evaluate the level of detail in the data and adjust the accuracy of the generation.

[0090] The generation unit can apply different generation algorithms depending on the user's preference categories during generation. For example, the generation unit can apply different generation algorithms depending on the user's preference categories during generation. The generation unit can also apply a generation algorithm specialized for music preferences if the user is interested in music. For example, the generation unit can apply a generation algorithm specialized for music preferences if the user is interested in sports. For example, the generation unit can apply a generation algorithm specialized for sports preferences if the user is interested in sports. The generation unit can also apply a generation algorithm specialized for fashion preferences if the user is interested in fashion. For example, the generation unit can apply a generation algorithm specialized for fashion preferences if the user is interested in fashion. By doing so, the generation unit can generate more accurate talent by applying a generation algorithm according to the preference categories. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the user's preference categories into a generation AI, which can then select an appropriate generation algorithm and generate talent.

[0091] The generation unit can estimate the user's emotions and determine the priority of the talents to generate based on the estimated emotions. For example, the generation unit can estimate the user's emotions and determine the priority of the talents to generate based on the estimated emotions. The generation unit can also prioritize generating talents with calm expressions if the user is relaxed. For example, if the user is relaxed, the generation unit will prioritize generating talents with calm expressions. The generation unit can also prioritize generating talents with energetic expressions if the user is excited. For example, if the user is excited, the generation unit will prioritize generating talents with energetic expressions. The generation unit can also prioritize generating talents with calm expressions if the user is stressed. For example, if the user is stressed, the generation unit will prioritize generating talents with calm expressions. In this way, the generation unit can generate more effective advertisements by determining the priority of talents according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generative AI may be a text-generating AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the processing described above in the generation unit may be performed using the generative AI or not. For example, the generation unit can input user sentiment data into the generative AI, which can then determine the priority of talents.

[0092] The generation unit can improve the accuracy of generation by referring to the user's past preference data during generation. For example, the generation unit can improve the accuracy of generation by referring to the user's past preference data during generation. The generation unit can also improve the accuracy of generation by predicting the user's current preferences based on the user's past preference data. For example, the generation unit can improve the accuracy of generation by predicting the user's current preferences based on the user's past preference data. The generation unit can also adjust the characteristics of the talents to be generated by referring to the user's past behavior history. For example, the generation unit adjusts the characteristics of the talents to be generated by referring to the user's past behavior history. The generation unit can also analyze the user's past preference data, grasp trends, and reflect them in the generation. For example, the generation unit analyzes the user's past preference data, grasps trends, and reflects them in the generation. As a result, the generation unit improves the accuracy of generation by referring to past preference data. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the generation unit can input the user's past preference data into the generation AI, which then analyzes the data to improve the accuracy of the generation.

[0093] The generation unit can perform generation by referring to the user's relevant market data during generation. For example, the generation unit can perform generation by referring to the user's relevant market data during generation. The generation unit can also adjust the characteristics of the talents it generates by referring to market data that the user is interested in. For example, the generation unit can adjust the characteristics of the talents it generates by referring to market data that the user is interested in. The generation unit can also reflect market trends related to the user's preferences in the generation. For example, the generation unit reflects market trends related to the user's preferences in the generation. The generation unit can also integrate user preference data and market data to perform more accurate generation. For example, the generation unit integrates user preference data and market data to perform more accurate generation. As a result, the generation unit can generate more accurate talents by referring to relevant market data. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the user's relevant market data into a generation AI, which can analyze the data and generate talents.

[0094] The embedded system can estimate the user's emotions and adjust the embedding method based on the estimated emotions. For example, the embedded system can estimate the user's emotions and adjust the embedding method based on the estimated emotions. If the user is relaxed, the embedded system can embed a talent with a calm expression into the ad. For example, if the user is relaxed, the embedded system can embed a talent with a calm expression into the ad. If the user is excited, the embedded system can embed a talent with an energetic expression into the ad. For example, if the user is excited, the embedded system can embed a talent with an energetic expression into the ad. If the user is stressed, the embedded system can embed a talent with a calm expression into the ad. For example, if the user is stressed, the embedded system can embed a talent with a calm expression into the ad. In this way, the embedded system can generate more effective ads by adjusting the embedding method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the above-described processes in the embedded unit may be performed using AI or not. For example, the embedded unit may input user emotion data into the AI, which may estimate the emotion and adjust the embedding method.

[0095] The embedding unit can select the optimal embedding method by referring to the user's past ad viewing history during embedding. For example, the embedding unit selects the optimal embedding method by referring to the user's past ad viewing history during embedding. The embedding unit can also embed talent based on the style of ads the user has previously enjoyed watching. For example, the embedding unit embeds talent based on the style of ads the user has previously enjoyed watching. The embedding unit can also analyze the user's past ad viewing history and select the most effective embedding method. For example, the embedding unit analyzes the user's past ad viewing history and selects the most effective embedding method. The embedding unit can also embed talent by referring to the characteristics of ads the user has previously watched. For example, the embedding unit embeds talent by referring to the characteristics of ads the user has previously watched. In this way, the embedding unit can select the optimal embedding method by referring to the past ad viewing history. Some or all of the above processing in the embedding unit may be performed using AI or not. For example, the embedding unit can input the user's past ad viewing history into AI, and the AI ​​can select the optimal embedding method.

[0096] The embedded system can customize the embedding method based on the user's current interests during embedding. For example, the embedded system can customize the embedding method based on the user's current interests during embedding. The embedded system can also embed talent related to topics the user is currently interested in into the ads. For example, the embedded system can embed talent related to topics the user is currently interested in into the ads. The embedded system can also embed relevant talent based on the user's current search history. For example, the embedded system can embed relevant talent based on the user's current search history into the ads. The embedded system can also embed talent related to topics in online communities the user is currently participating in into the ads. For example, the embedded system can embed talent related to topics in online communities the user is currently participating in into the ads. This allows the embedded system to generate more effective ads by customizing the embedding method based on current interests. Some or all of the above processing in the embedded system may be performed using AI or not. For example, the embedded system can input the user's current interests into AI, which can then customize the optimal embedding method.

[0097] The embedded system can estimate the user's emotions and determine the priority of embedded content based on those emotions. For example, if the user is relaxed, the embedded system may prioritize embedding talent with calm expressions. For example, if the user is relaxed, the embedded system may prioritize embedding talent with calm expressions. For example, if the user is excited, the embedded system may prioritize embedding talent with energetic expressions. For example, if the user is excited, the embedded system may prioritize embedding talent with energetic expressions. If the user is stressed, the embedded system may prioritize embedding talent with calm expressions. For example, if the user is stressed, the embedded system may prioritize embedding talent with calm expressions. This allows the embedded system to generate more effective advertisements by determining the priority of embedded content according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the embedded unit may be performed using AI or not. For example, the embedded unit can input user emotion data into the AI, which can then estimate the emotion and determine the priority of the embedded system.

[0098] The embedding unit can select the optimal embedding method by considering the user's geographical location information during embedding. For example, the embedding unit selects the optimal embedding method by considering the user's geographical location information during embedding. The embedding unit can also embed talent into advertisements based on trend information in the user's current location. For example, the embedding unit embeds talent into advertisements based on trend information in the user's current location. The embedding unit can also embed relevant talent into advertisements by referring to the user's past location information. For example, the embedding unit embeds relevant talent into advertisements by referring to the user's past location information. The embedding unit can also embed talent related to places the user frequently visits into advertisements. For example, the embedding unit embeds talent related to places the user frequently visits into advertisements. In this way, the embedding unit can select the optimal embedding method by considering geographical location information. Some or all of the above processing in the embedding unit may be performed using AI or not. For example, the embedding unit can input the user's geographical location information into AI, and the AI ​​can select the optimal embedding method.

[0099] The embedded unit can analyze the user's social media activity during the embedding process and propose embedding methods. For example, the embedded unit can analyze the user's social media activity during the embedding process and propose embedding methods. The embedded unit can also embed talent related to topics that the user frequently posts about into the advertisement. For example, the embedded unit can embed talent related to topics that the user's followers and friends are interested in into the advertisement. For example, the embedded unit can embed talent related to topics that the user's followers and friends are interested in into the advertisement. The embedded unit can also embed talent related to topics in online communities that the user participates in into the advertisement. For example, the embedded unit can embed talent related to topics in online communities that the user participates in into the advertisement. In this way, the embedded unit can propose the optimal embedding method by analyzing social media activity. Some or all of the above processing in the embedded unit may be performed using AI or not. For example, the embedded unit can input the user's social media activity into AI, and the AI ​​can propose the optimal embedding method.

[0100] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0101] The ad generation system can customize the voices of talents generated based on user preference data. For example, the generation unit can identify the tone and accent of voices preferred by the user and generate voices of talents with those characteristics. Furthermore, the generation unit can adjust the speed and intonation of the talent's voice according to the user's preferences. For instance, if the user prefers a calm voice, the generation unit can generate a talent's voice that speaks slowly in a gentle tone. Conversely, if the user prefers an energetic voice, the generation unit can generate a talent's voice that speaks in a bright and cheerful tone. This allows the ad generation system to generate talent voices that match the user's preferences, further enhancing the effectiveness of the advertisements.

[0102] The ad generation system can customize the actions of the talent generated based on user preference data. For example, the generation unit can identify the actions and gestures that the user prefers and generate actions of talent that possess those characteristics. Furthermore, the generation unit can adjust the speed and rhythm of the talent's actions according to the user's preferences. For example, if the user prefers calm actions, the generation unit can generate talent that perform slow actions. Conversely, if the user prefers lively actions, the generation unit can generate talent that perform energetic actions. In this way, the ad generation system can generate talent actions that match the user's preferences, further enhancing the effectiveness of the advertisements.

[0103] The ad generation system can customize the backgrounds of the talent generated based on user preference data. For example, the generation unit can identify the background style and color scheme preferred by the user and generate backgrounds with those characteristics. Furthermore, the generation unit can adjust the level of detail and atmosphere of the background according to the user's preferences. For instance, if the user prefers a simple background, the generation unit can generate a simple and calm background. Conversely, if the user prefers a vibrant background, the generation unit can generate a colorful and lively background. This allows the ad generation system to generate backgrounds that match the user's preferences, further enhancing the effectiveness of the advertisements.

[0104] The ad generation system can customize the clothing of the talents generated based on user preference data. For example, the generation unit can identify the style and color scheme of clothing preferred by the user and generate clothing for talents that possess those characteristics. Furthermore, the generation unit can adjust the level of detail and accessories of the clothing according to the user's preferences. For instance, if the user prefers casual clothing, the generation unit can generate talents wearing casual and relaxed attire. Similarly, if the user prefers formal clothing, the generation unit can generate talents wearing formal and elegant attire. This allows the ad generation system to generate talent clothing that matches the user's preferences, further enhancing the effectiveness of the advertisements.

[0105] The ad generation system can customize the facial expressions of the talent generated based on user preference data. For example, the generation unit can identify the style and emotion of facial expressions preferred by the user and generate facial expressions of talent with those characteristics. Furthermore, the generation unit can adjust the level of detail and intensity of the facial expressions according to the user's preferences. For example, if the user prefers calm facial expressions, the generation unit can generate talent with calm and gentle facial expressions. Also, if the user prefers cheerful facial expressions, the generation unit can generate talent with bright and energetic facial expressions. In this way, the ad generation system can generate talent facial expressions that match the user's preferences, further enhancing the effectiveness of the advertisements.

[0106] The ad generation system can estimate the user's emotions and adjust the timing of ad display based on those emotions. For example, the ad provider can display ads when the user is relaxed, increasing the likelihood of a more positive response. If the user is stressed, the ad provider can temporarily withhold the ad display, reducing user stress and preventing any loss of ad effectiveness. Furthermore, if the user is excited, the ad provider can display ads in real time, leveraging the user's excitement to maximize ad effectiveness. In this way, the ad generation system can adjust ad display timing according to the user's emotions, further enhancing ad effectiveness.

[0107] The ad generation system can estimate the user's emotions and customize the ad content based on those emotions. For example, if the user is relaxed, the ad provider can display calming ads. This increases the likelihood that the user will respond more favorably to the ad. If the user is excited, the ad provider can display energetic ads. This leverages the user's excitement to maximize the ad's effectiveness. Furthermore, if the user is stressed, the ad provider can display relaxing ads. This reduces the user's stress and does not diminish the ad's effectiveness. In this way, the ad generation system can customize ad content according to the user's emotions, further enhancing the ad's effectiveness.

[0108] The ad generation system can estimate the user's emotions and adjust the ad format based on those emotions. For example, if the user is relaxed, the ad provider can display ads with calming music and gentle visuals. This increases the likelihood that the user will respond more favorably to the ad. If the user is excited, the ad provider can display ads with upbeat music and dynamic visuals. This leverages the user's excitement to maximize the ad's effectiveness. Furthermore, if the user is stressed, the ad provider can display ads with relaxing music and visuals. This reduces the user's stress and does not diminish the ad's effectiveness. In this way, the ad generation system can adjust the ad format according to the user's emotions, further enhancing the ad's effectiveness.

[0109] The ad generation system can estimate a user's emotions and adjust ad targeting based on those emotions. For example, if a user is relaxed, the system can display ads for relaxing products and services. This increases the likelihood that the user will respond more favorably to the ad. If a user is excited, the system can display ads for energetic products and services. This leverages the user's excitement to maximize ad effectiveness. Furthermore, if a user is stressed, the system can display ads for products and services that help reduce stress. This reduces the user's stress without compromising the effectiveness of the ad. In this way, the ad generation system can adjust ad targeting according to the user's emotions, further enhancing ad effectiveness.

[0110] The ad generation system can estimate the user's emotions and adjust the frequency of ads based on those emotions. For example, if the user is relaxed, the ad provider can increase the frequency of ad displays. This increases the likelihood that the user will respond more favorably to the ad. Conversely, if the user is stressed, the provider can decrease the frequency of ad displays. This reduces user stress and does not impair the effectiveness of the ad. Furthermore, if the user is excited, the provider can display ads in real time, leveraging the user's excitement to maximize the ad's effectiveness. In this way, the ad generation system can adjust the frequency of ads according to the user's emotions and further enhance the effectiveness of the ad.

[0111] The following briefly describes the processing flow for example form 2.

[0112] Step 1: The data collection unit collects user preference data. For example, it collects data such as purchase history on e-commerce sites, social media posts, users' hobbies and interests, past behavioral history, browsing history, and survey results. Step 2: The analysis unit analyzes the data collected by the collection unit to identify the characteristics of talent that match the user's preferences. For example, it uses data mining or machine learning algorithms to extract specific features such as facial shape, hairstyle, and clothing. Step 3: The generation unit generates talents based on the features identified by the analysis unit. For example, it uses a generation AI to generate talents with specific facial features such as face shape, hairstyle, and clothing. Step 4: The integration unit integrates the talent generated by the generation unit into the advertising content. For example, it replaces the generated talent with pre-recorded talent assets.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, and integration unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects user preference data. The analysis unit is implemented by the identification processing unit 290 of the data processing device 12 and analyzes the collected data to identify the characteristics of talents that match the user's preferences. The generation unit is implemented by the identification processing unit 290 of the data processing device 12 and generates talents based on the analysis results. The integration unit is implemented by the control unit 46A of the smart device 14 and integrates the generated talents into advertising content. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0117] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, and integration unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects user preference data. The analysis unit is implemented by the identification processing unit 290 of the data processing device 12 and analyzes the collected data to identify the characteristics of talents that match the user's preferences. The generation unit is implemented by the identification processing unit 290 of the data processing device 12 and generates talents based on the analysis results. The integration unit is implemented by the control unit 46A of the smart glasses 214 and integrates the generated talents into advertising content. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0133] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, and integration unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and collects user preference data. The analysis unit is implemented by the identification processing unit 290 of the data processing device 12 and analyzes the collected data to identify the characteristics of talent that match the user's preferences. The generation unit is implemented by the identification processing unit 290 of the data processing device 12 and generates talent based on the analysis results. The integration unit is implemented by the control unit 46A of the headset terminal 314 and integrates the generated talent into advertising content. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0149] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, and integration unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects user preference data. The analysis unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and analyzes the collected data to identify the characteristics of talent that match the user's preferences. The generation unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and generates talent based on the analysis results. The integration unit is implemented by, for example, the control unit 46A of the robot 414 and integrates the generated talent into advertising content. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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."

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] (Note 1) A data collection unit that collects user preference data, An analysis unit analyzes the data collected by the aforementioned collection unit and identifies the characteristics of talents that match the user's preferences, A generation unit that generates talents based on the characteristics identified by the analysis unit, The system includes an integration unit that incorporates the talent generated by the generation unit into advertising content. A system characterized by the following features. (Note 2) The aforementioned collection unit is They collect data such as purchase history from e-commerce sites and content from social media posts. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Based on user preference data, we identify the characteristics of talents that users like. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Generate talents with specific facial features, hairstyles, clothing styles, and other characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned integrated part is The generated talent is replaced using pre-recorded talent assets. The system described in Appendix 1, characterized by the features described herein. (Note 6) The generating unit is Using deep learning technology to reproduce realistic facial expressions and movements. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned integrated part is Using image processing techniques to create natural-looking composites The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is It estimates the user's emotions and adjusts the timing of collecting preference data based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is Analyze the user's past behavior history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is When collecting data, filtering is performed based on the user's current interests and trends. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is During data collection, the system prioritizes the collection of highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is During data collection, the system analyzes users' social media activity and collects relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, the level of detail is adjusted based on the importance of the user's preference data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the user's preference category. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, The system estimates the user's emotions and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the accuracy of the analysis is improved by referencing the user's past preference data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During the analysis, the analysis is performed by referencing the user's relevant market data. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is It estimates the user's emotions and adjusts the talent features generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is During generation, the accuracy of the generation is adjusted based on the level of detail in the user's preference data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is During generation, different generation algorithms are applied depending on the user's preference category. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is It estimates the user's emotions and determines the priority of talents to generate based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is During generation, the system references the user's past preference data to improve generation accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 25) The generating unit is During generation, the system references the user's relevant market data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned integrated part is We estimate the user's emotions and adjust the implementation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned integrated part is During integration, the system selects the optimal integration method by referring to the user's past ad viewing history. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned integrated part is During implementation, customize the implementation method based on the user's current concerns. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned integrated part is It estimates the user's emotions and determines built-in priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned integrated part is During implementation, the optimal implementation method is selected considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned integrated part is During the integration process, we analyze users' social media activity and propose integration methods. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A data collection unit that collects user preference data, An analysis unit analyzes the data collected by the aforementioned collection unit and identifies the characteristics of talents that match the user's preferences, A generation unit that generates talents based on the characteristics identified by the analysis unit, The system includes an integration unit that incorporates the talent generated by the generation unit into advertising content. A system characterized by the following features.

2. The aforementioned collection unit is They collect data such as purchase history from e-commerce sites and content from social media posts. The system according to feature 1.

3. The aforementioned analysis unit, Based on user preference data, we identify the characteristics of talents that users like. The system according to feature 1.

4. The generating unit is Generate talents with specific facial features, hairstyles, clothing styles, and other characteristics. The system according to feature 1.

5. The aforementioned integrated part is The generated talent is replaced using pre-recorded talent assets. The system according to feature 1.

6. The generating unit is Using deep learning technology to reproduce realistic facial expressions and movements. The system according to feature 1.

7. The aforementioned integrated part is Using image processing techniques to create natural-looking composites The system according to feature 1.

8. The aforementioned collection unit is It estimates the user's emotions and adjusts the timing of collecting preference data based on the estimated user emotions. The system according to feature 1.

Images