System

Abstract

To embed advertisements naturally in the original content of videos by the system in accordance with the embodiment.SOLUTION: A system according to the embodiment has an analysis unit, a generation unit, and an embedding unit. The analysis unit analyzes video content. The generation unit generates advertisements in the locations identified by the analysis unit. The embedding unit embeds the advertisement generated by the generation unit into the video.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] In conventional technology, advertisements in video streaming are forced and may be unpleasant for users.

[0005] The system according to the embodiment aims to naturally embed advertisements within the original content of a video. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a generation unit, and an embedding unit. The analysis unit analyzes video content. The generation unit generates an advertisement at a location identified by the analysis unit. The embedding unit embeds the advertisement generated by the generation unit into the video. Effect of the Invention

[0007] The system according to the embodiment can naturally embed advertisements within the original content of a video. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The advertisement embedding system according to the embodiment of the present invention is a system that uses a generation AI to embed advertisements in the original content of a video, thereby eliminating the compulsion of advertisements and improving the user experience of video distribution. This advertisement embedding system analyzes video content and identifies appropriate locations for embedding advertisements. This analysis is performed by a generation AI. Next, the generation AI generates content for embedding advertisements naturally in the identified locations. For example, an advertisement may be displayed in the background of a video, or a scene may be added in which a character uses an advertised product. This allows users to see advertisements in a natural way without being forced to watch the advertisements. This mechanism improves the user experience of video distribution and reduces the aversion to advertisements. In addition, more effective advertisement delivery is possible for advertisers. For example, the effectiveness of advertisements is increased by embedding advertisements in content that is likely to interest users. For example, the video content is analyzed and an appropriate location for embedding advertisements is identified. This analysis is performed by a generation AI. Next, the generation AI generates content for embedding advertisements naturally in the identified locations. For example, an advertisement may be displayed in the background of a video, or a scene may be added in which a character uses an advertised product. This allows users to see advertisements in a natural way without being forced to watch the advertisements. This mechanism improves the user experience of video streaming and reduces the aversion to advertisements. It also enables advertisers to deliver advertisements more effectively. For example, the effectiveness of advertisements can be increased by embedding advertisements in content that is likely to interest users. In this way, the advertisement embedding system can make the user experience of video streaming more comfortable and eliminate the compulsion of advertisements.

[0029] The advertisement embedding system according to the embodiment includes an analysis unit, a generation unit, and an embedding unit. The analysis unit uses a generation AI to analyze video content and identify an appropriate location for embedding an advertisement. The analysis unit analyzes the content of the video using techniques such as image analysis, audio analysis, and text analysis. For example, the analysis unit can identify a location for embedding an advertisement based on the importance of a scene in the video and the interest of a viewer. The generation unit uses the generation AI to generate content for naturally embedding an advertisement in the identified location. The generation unit can generate advertisements in the form of, for example, a banner advertisement, a video advertisement, and the like. For example, the generation unit generates content that displays an advertisement in the background of the video. The generation unit can also generate content that adds a scene in which a character uses an advertised product. The embedding unit embeds the generated advertisement into the video. The embedding unit determines, for example, which part of the video and how to embed the advertisement. For example, the embedding unit can embed an advertisement when a scene of the video is switched or when a specific event occurs. This allows the advertisement embedding system according to the embodiment to naturally embed an advertisement in the video content. This makes it possible to eliminate the compulsion of advertisements and improve the user experience. Some or all of the above-mentioned processing in the embedding unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, when embedding a generated advertisement in a video, the embedding unit can adjust the position and timing of the advertisement using the generation AI. This enables the advertisement to be displayed naturally.

[0030] The analysis unit uses generative AI to analyze video content and identify appropriate locations for embedding advertisements. Specifically, the analysis unit uses image analysis, audio analysis, text analysis, and other technologies to analyze the content of the video in detail. In image analysis, each frame in the video is analyzed to evaluate the importance of the scene and the viewer's interest. For example, facial recognition technology can be used to analyze the facial expressions and movements of the characters to detect changes in emotions. In audio analysis, speech recognition technology is used to analyze the conversations and sound effects in the video to identify the atmosphere of the scene and important remarks. In text analysis, the content of subtitles and captions is analyzed to understand the context and theme of the scene. By integrating these analysis results, the analysis unit can comprehensively evaluate the importance of the scene in the video and the viewer's interest, and identify the optimal location for embedding advertisements. In addition, the analysis unit can customize the optimal ad embedding location for each individual viewer by utilizing the viewer's viewing history and preference data. This allows the analysis unit to precisely grasp the content of the video content and the viewer's interest, providing a foundation for maximizing the effectiveness of advertisements.

[0031] The generation unit uses the generation AI to generate content for naturally embedding advertisements in the identified locations. Specifically, the generation unit can generate advertisements in the form of banner advertisements, video advertisements, and the like. For example, when generating content for displaying advertisements in the background of a video, the generation unit adjusts the design of the advertisement to match the color tone and lighting conditions of the video. This allows the advertisement to blend naturally as part of the video. The generation unit can also generate content that adds a scene in which a character uses the advertised product. In this case, the generation AI analyzes the movements and facial expressions of the character to generate a scene in which the advertised product is used in a natural manner. Furthermore, the generation unit can use voice synthesis technology to generate lines in which the character mentions the advertised product. This allows the generation unit to effectively convey the advertising message to the viewer. The generation unit can also generate advertising content that is optimal for each individual viewer based on the viewer's preferences and viewing history. For example, the effectiveness of the advertisement can be increased by generating advertisements related to products and services in which the viewer has shown interest in the past. This allows the generation unit to generate advertisements that blend naturally into the video content and attract the viewer's interest.

[0032] The embedding unit embeds the generated advertisement into the video. Specifically, the embedding unit determines which part of the video to embed the advertisement and how. For example, the embedding unit can embed the advertisement when the scene of the video changes or when a specific event occurs. When the scene changes, the viewer's attention is temporarily interrupted, making it an ideal timing to naturally insert the advertisement. In addition, when a specific event occurs, the viewer's interest increases, so the effectiveness of the advertisement can be maximized. The embedding unit can adjust the position and timing of the advertisement using the generation AI. For example, the generation AI analyzes the movement and visual elements in the video to ensure that the advertisement is placed in the optimal position to attract the viewer's attention. In addition, the generation AI can analyze the movement of the viewer's gaze and place the advertisement in the place where the gaze is concentrated. This allows the advertisement to be displayed naturally and minimizes the discomfort to the viewer. Furthermore, the embedding unit can reduce the viewer's stress and increase the effectiveness of the advertisement by adjusting the display time and frequency of the advertisement. For example, in a long video, by inserting short advertisements multiple times, the message of the advertisement can be conveyed while maintaining the viewer's concentration. This allows the embedder to embed advertisements naturally within the video content, enhancing the viewer experience.

[0033] The analysis unit can analyze the contents of the video and identify the location where the advertisement is embedded. The analysis unit can analyze the contents of the video using techniques such as image analysis, audio analysis, and text analysis. For example, the analysis unit can identify the location where the advertisement is embedded based on the importance of a scene in the video and the viewer's interest. This allows the advertisement to be inserted naturally by identifying the location where the advertisement is embedded based on the content of the video. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, when analyzing the contents of the video, the analysis unit can evaluate the importance of a scene and the viewer's interest using a generation AI.

[0034] The generation unit can generate content for embedding an advertisement in the specified location. The generation unit generates content for naturally embedding an advertisement in the specified location using a generation AI. The generation unit can generate advertisements in the form of, for example, banner advertisements, video advertisements, etc. For example, the generation unit generates content for displaying advertisements in the background of a video. The generation unit can also generate content for adding a scene in which a character uses an advertised product. This allows the advertisement to be generated in a natural manner, thereby reducing the user's aversion to the advertisement. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, when generating content for embedding an advertisement in the specified location, the generation unit can determine the content and format of the advertisement using a generation AI.

[0035] The embedding unit can embed the generated advertisement into the video. The embedding unit embeds the generated advertisement into the video. The embedding unit determines, for example, in which part of the video and how to embed the advertisement. For example, the embedding unit can embed the advertisement when the scene of the video changes or when a specific event occurs. As a result, by embedding the generated advertisement into the video, the advertisement can be displayed naturally. A part or all of the above-mentioned processing in the embedding unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, when embedding the generated advertisement into the video, the embedding unit can adjust the position and timing of the advertisement using the generation AI.

[0036] The generation unit can generate an advertisement based on the user's viewing history. The generation unit generates an advertisement based on the user's viewing history using a generation AI. The generation unit can customize the advertisement based on data such as the titles and viewing times of videos the user has viewed in the past. This enables more effective advertisement delivery by customizing the advertisement based on the user's viewing history. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can analyze the user's viewing history and determine the content and format of the advertisement using a generation AI.

[0037] The advertisement may further include an evaluation unit that evaluates the effectiveness of the advertisement. The evaluation unit evaluates the effectiveness of the advertisement using the generation AI. The evaluation unit can evaluate the effectiveness of the advertisement based on data such as the click rate and viewing completion rate of the advertisement. This makes it possible to measure and improve the effectiveness of advertisement delivery by evaluating the effectiveness of the advertisement. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can analyze the viewing data of the advertisement and evaluate the effectiveness of the advertisement using the generation AI.

[0038] The analysis unit can analyze the viewer's interest level for each scene of the video and specify the timing to embed the advertisement. The analysis unit can use the generation AI to analyze the viewer's interest level for each scene of the video and specify the optimal timing to embed the advertisement. The analysis unit can evaluate the viewer's interest level based on data such as viewing time and the number of clicks. For example, the analysis unit can specify the timing to insert an advertisement before or after a climax scene in which the viewer's interest is heightened. The analysis unit can also specify the timing to insert an advertisement before a scene in which the viewer's interest is reduced. Furthermore, the analysis unit can also specify the timing to insert an advertisement in the middle of a scene in which the viewer's interest is sustained. This allows the effectiveness of the advertisement to be maximized by specifying the timing to embed the advertisement based on the viewer's interest level. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can analyze the viewer's interest level and specify the optimal timing to embed the advertisement using the generation AI.

[0039] The analysis unit can adjust the location where the advertisement is embedded based on the genre and theme of the video. The analysis unit dynamically adjusts the location where the advertisement is embedded based on the genre and theme of the video using the generation AI. The analysis unit can specify the location where the advertisement is embedded based on the genre and theme, such as comedy, drama, and action. For example, the analysis unit can specify the location where the advertisement is inserted into a humorous scene in a comedy video. The analysis unit can also specify the location where the advertisement is inserted into a moving scene in a drama video. Furthermore, the analysis unit can also specify the location where the advertisement is inserted into a tense scene in an action video. This allows the advertisement to be inserted naturally by adjusting the location where the advertisement is embedded based on the genre and theme of the video. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can analyze the genre and theme of the video and dynamically adjust the location where the advertisement is embedded using the generation AI.

[0040] The analysis unit can perform audio analysis of the video and identify a location where an advertisement is embedded based on the content of the audio. The analysis unit can perform audio analysis of the video using a generation AI and identify a location where an advertisement is embedded based on the content of the audio. The analysis unit can analyze the audio content of the video using technologies such as voice recognition and emotion analysis. For example, the analysis unit can identify a location where an advertisement is inserted at a break in a conversation in the video. The analysis unit can also identify a location where an advertisement is inserted at a change in music in the video. Furthermore, the analysis unit can also identify a location where an advertisement is inserted in accordance with the timing of a sound effect in the video. This makes it possible to insert an advertisement naturally by identifying a location where an advertisement is embedded based on the audio content of the video. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can analyze the audio content of the video and identify a location where an advertisement is embedded using a generation AI.

[0041] The analysis unit can customize the location where the advertisement is embedded based on the age group and gender of the viewer of the video. The analysis unit uses the generation AI to customize the location where the advertisement is embedded based on the age group and gender of the viewer of the video. The analysis unit can customize the advertisement based on data such as age category and gender identification method. For example, the analysis unit can identify the location where the advertisement is inserted in a visually flashy scene in a video for young people. Also, the analysis unit can identify the location where the advertisement is inserted in a calm scene in a video for older people. Furthermore, the analysis unit can identify the location where the advertisement is inserted in a scene that is likely to attract interest, by gender. This enables more effective advertisement delivery by customizing the location where the advertisement is embedded based on the age group and gender of the viewer. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can analyze the age group and gender of the viewer and customize the location where the advertisement is embedded using the generation AI.

[0042] The generation unit can customize the design of the advertisement according to the color tone and style of the video when generating the advertisement. The generation unit customizes the design of the advertisement according to the color tone and style of the video when generating the advertisement using the generation AI. The generation unit can adjust the design of the advertisement using techniques such as color adjustment and design style. For example, if the video has a light color tone, the generation unit can design the advertisement in a light color tone. In addition, if the video has a dark color tone, the generation unit can also design the advertisement in a dark color tone. Furthermore, if the video has a cartoon style, the generation unit can also design the advertisement in a cartoon style. This enables natural insertion of the advertisement by customizing the design of the advertisement according to the color tone and style of the video. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the color tone and style of the video and customize the design of the advertisement using the generation AI.

[0043] The generation unit can naturally insert the advertisement in accordance with the storyline of the video when generating the advertisement. The generation unit can naturally insert the advertisement in accordance with the storyline of the video when generating the advertisement using the generation AI. The generation unit can analyze the storyline of the video using techniques such as scenario analysis and plot analysis. For example, the generation unit can add a scene in which a character in the video uses an advertised product. The generation unit can also display an advertisement in the background of the video. Furthermore, the generation unit can also insert an advertisement related to the story of the video. This enables the advertisement to be inserted naturally by inserting the advertisement in accordance with the storyline of the video. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the storyline of the video and insert the advertisement naturally using the generation AI.

[0044] The generation unit can customize the audio of the advertisement to match the music and sound effects of the video when generating the advertisement. The generation unit customizes the audio of the advertisement to match the music and sound effects of the video when generating the advertisement using the generation AI. The generation unit can adjust the audio of the advertisement using techniques such as volume adjustment and timing adjustment. For example, the generation unit can adjust the background music of the advertisement to match the music of the video. The generation unit can also add sound effects of the advertisement to match the sound effects of the video. Furthermore, the generation unit can adjust the narration of the advertisement to match the tone of the audio of the video. This enables natural insertion of the advertisement by customizing the audio of the advertisement to match the music and sound effects of the video. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the music and sound effects of the video and customize the audio of the advertisement using the generation AI.

[0045] The generation unit can adjust the content of the advertisement to match the lines of the characters in the video when generating the advertisement. The generation unit adjusts the content of the advertisement to match the lines of the characters in the video when generating the advertisement using the generation AI. The generation unit can analyze the lines of the characters using technologies such as voice recognition and context analysis. For example, the generation unit can add a scene in which the characters in the video mention the advertised product. The generation unit can also insert an advertisement related to the lines of the characters in the video. Furthermore, the generation unit can adjust the catchphrase of the advertisement to match the lines of the characters in the video. This allows the advertisement to be inserted naturally by adjusting the content of the advertisement to match the lines of the characters in the video. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the lines of the characters and adjust the content of the advertisement using the generation AI.

[0046] The embedding unit can adjust the quality of the advertisement according to the frame rate and resolution of the video when embedding the advertisement. The embedding unit adjusts the quality of the advertisement according to the frame rate and resolution of the video when embedding the advertisement using the generation AI. The embedding unit can adjust the quality of the advertisement using techniques such as setting the frame rate and adjusting the resolution. For example, the embedding unit can embed a high frame rate advertisement in a high frame rate video. In addition, the embedding unit can also embed a high resolution advertisement in a high resolution video. Furthermore, the embedding unit can also embed a low frame rate advertisement in a low frame rate video. This allows the advertisement to be inserted naturally by adjusting the quality of the advertisement according to the frame rate and resolution of the video. Part or all of the above-mentioned processing in the embedding unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the embedding unit can analyze the frame rate and resolution of the video and adjust the quality of the advertisement using the generation AI.

[0047] The embedding unit can naturally insert an advertisement in accordance with a scene transition of a video when embedding an advertisement. The embedding unit uses a generation AI to naturally insert an advertisement in accordance with a scene transition of a video when embedding an advertisement. The embedding unit can insert an advertisement based on the timing, for example, when a scene is switched or when a specific event occurs. For example, the embedding unit can insert an advertisement at the timing of a scene transition. The embedding unit can also insert an advertisement before and after a scene transition. Furthermore, the embedding unit can also insert an advertisement in the middle of a scene transition. This allows for natural insertion of an advertisement by inserting an advertisement in accordance with a scene transition. A part or all of the above-mentioned processing in the embedding unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the embedding unit can analyze the timing of a scene transition and naturally insert an advertisement using a generation AI.

[0048] The embedding unit can adjust the position of the advertisement according to the subtitles and text information of the video when embedding the advertisement. The embedding unit adjusts the position of the advertisement according to the subtitles and text information of the video using the generation AI when embedding the advertisement. The embedding unit can analyze the subtitles and text information of the video using techniques such as character recognition and context analysis. For example, the embedding unit can display the advertisement above the subtitles of the video. In addition, the embedding unit can also display the advertisement next to the text information of the video. Furthermore, the embedding unit can also display the advertisement below the subtitles of the video. This allows the advertisement to be inserted naturally by adjusting the position of the advertisement according to the subtitles and text information of the video. A part or all of the above-mentioned processing in the embedding unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the embedding unit can analyze the subtitles and text information of the video and adjust the position of the advertisement using the generation AI.

[0049] The embedding unit can customize the format of the advertisement according to the viewing device of the video when embedding the advertisement. The embedding unit customizes the format of the advertisement according to the viewing device of the video when embedding the advertisement using the generation AI. The embedding unit can adjust the format of the advertisement using techniques such as screen size and resolution. For example, the embedding unit can display a vertically long advertisement when viewed on a smartphone. In addition, the embedding unit can also display a horizontally long advertisement when viewed on a tablet. Furthermore, the embedding unit can display a full-screen advertisement when viewed on a personal computer. This enables natural insertion of the advertisement by customizing the format of the advertisement according to the viewing device. Part or all of the above-mentioned processing in the embedding unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the embedding unit can analyze the viewing device and customize the format of the advertisement using the generation AI.

[0050] The evaluation unit can analyze the viewing data of the advertisement and evaluate the effectiveness of the advertisement in real time. The evaluation unit can analyze the viewing data of the advertisement using the generation AI and evaluate the effectiveness of the advertisement in real time. The evaluation unit can evaluate the effectiveness of the advertisement based on data such as the viewing time and the number of clicks. For example, the evaluation unit can analyze the viewing start time and end time of the advertisement and evaluate the viewing completion rate. The evaluation unit can also analyze the number of clicks on the advertisement and evaluate the click rate. Furthermore, the evaluation unit can analyze the behavior data of the user while viewing the advertisement and evaluate the effectiveness of the advertisement. This makes it possible to instantly evaluate the effectiveness of the advertisement by analyzing the viewing data of the advertisement in real time. Part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can analyze the viewing data of the advertisement and evaluate the effectiveness of the advertisement in real time using the generation AI.

[0051] The evaluation unit can evaluate the effectiveness of the advertisement based on the click rate and the viewing completion rate of the advertisement. The evaluation unit uses the generation AI to evaluate the effectiveness of the advertisement based on the click rate and the viewing completion rate of the advertisement. The evaluation unit can evaluate the effectiveness of the advertisement based on data such as the number of clicks and the number of viewing completions. For example, the evaluation unit can evaluate the effectiveness of the advertisement based on the click rate of the advertisement. The evaluation unit can also evaluate the effectiveness of the advertisement based on the viewing completion rate of the advertisement. Furthermore, the evaluation unit can comprehensively evaluate the click rate and the viewing completion rate of the advertisement to determine the effectiveness of the advertisement. This makes it possible to accurately measure the effectiveness of the advertisement by evaluating the effectiveness of the advertisement based on the click rate and the viewing completion rate of the advertisement. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can analyze the click rate and the viewing completion rate of the advertisement and evaluate the effectiveness of the advertisement using the generation AI.

[0052] The evaluation unit can collect feedback from viewers of the advertisement and evaluate the effectiveness of the advertisement. The evaluation unit can collect feedback from viewers of the advertisement using the generation AI and evaluate the effectiveness of the advertisement. The evaluation unit can evaluate the effectiveness of the advertisement based on data such as questionnaires, comments, and social media responses. For example, the evaluation unit can collect feedback through questionnaires after viewing the advertisement and evaluate the effectiveness of the advertisement. The evaluation unit can also analyze comments after viewing the advertisement and evaluate the effectiveness of the advertisement. Furthermore, the evaluation unit can collect social media responses after viewing the advertisement and evaluate the effectiveness of the advertisement. This makes it possible to accurately evaluate the effectiveness of the advertisement by collecting feedback from viewers of the advertisement. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can collect feedback from viewers of the advertisement and evaluate the effectiveness of the advertisement using the generation AI.

[0053] The evaluation unit can evaluate the effectiveness of the advertisement based on the viewing environment of the advertisement. The evaluation unit uses the generation AI to evaluate the effectiveness of the advertisement based on the viewing environment of the advertisement (device, location, time period). The evaluation unit can evaluate the effectiveness of the advertisement based on data such as the viewing device, viewing location, and viewing time period. For example, the evaluation unit can evaluate the effectiveness of the advertisement viewed on a smartphone. The evaluation unit can also evaluate the effectiveness of the advertisement viewed at home. Furthermore, the evaluation unit can evaluate the effectiveness of the advertisement viewed at night. This makes it possible to accurately measure the effectiveness of the advertisement by evaluating the effectiveness of the advertisement based on the viewing environment of the advertisement. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can analyze the viewing environment of the advertisement and evaluate the effectiveness of the advertisement using the generation AI.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The advertisement embedding system may further include a history analysis unit that analyzes the user's viewing history. The history analysis unit may identify the user's interests and concerns based on data such as the genres and themes of videos the user has viewed in the past, the viewing time, and the viewing frequency. For example, the history analysis unit may preferentially embed advertisements related to videos of a genre that the user frequently views. The history analysis unit may also embed more detailed advertisements in videos that the user views for a long time. Furthermore, the history analysis unit may also embed advertisements appropriate for a time period in accordance with videos that the user views during a specific time period. This may maximize the effectiveness of advertisements by customizing advertisements based on the user's viewing history.

[0056] The advertisement embedding system may further include a behavior monitoring unit that monitors the real-time viewing behavior of the user. The behavior monitoring unit may collect and analyze behavior data when the user is viewing a video. For example, the behavior monitoring unit may analyze the timing when the user pauses or rewinds the video, and insert an advertisement at that timing. In addition, if the user performs another action (e.g., posting a comment, clicking a link, etc.) while viewing the video, the behavior monitoring unit may also display an advertisement related to that action. Furthermore, if the user reacts to a particular scene while viewing the video, the behavior monitoring unit may also insert an advertisement related to that scene. This may improve the effectiveness of the advertisement by customizing the advertisement based on the user's real-time viewing behavior.

[0057] The advertisement embedding system may further include a social analysis unit that analyzes the user's social media activity. The social analysis unit may analyze information shared by the user on social media and the contents of posts to identify the user's interests. For example, the social analysis unit may analyze posts in which the user mentions a particular brand or product, and embed advertisements related to the brand or product. The social analysis unit may also display relevant advertisements based on information about accounts the user follows and groups the user participates in. The social analysis unit may also insert advertisements related to posts in which the user has performed actions such as "like" or "share". This may increase the effectiveness of advertisements by customizing advertisements based on the user's social media activity.

[0058] The advertisement embedding system may further include a device analysis unit that analyzes the device information of the user. The device analysis unit may analyze the type of device used by the user and setting information, and optimize the advertisement display method. For example, the device analysis unit may display a portrait advertisement when the user is using a smartphone. Furthermore, the device analysis unit may display a landscape advertisement when the user is using a tablet. Furthermore, the device analysis unit may display a full-screen advertisement when the user is using a personal computer. This allows the effectiveness of the advertisement to be maximized by customizing the advertisement display method based on the user's device information.

[0059] The advertisement embedding system may further include a location analysis unit that analyzes the user's location information. The location analysis unit may analyze the user's current location and past movement history, and customize advertisements based on the location information. For example, when the user is in a specific area, the location analysis unit may display advertisements related to that area. The location analysis unit may also display related advertisements based on information about places the user has visited in the past. Furthermore, when the user is at a specific event or store, the location analysis unit may display advertisements related to that event or store. This may increase the effectiveness of advertisements by customizing advertisements based on the user's location information.

[0060] The process flow of the first embodiment will be briefly described below.

[0061] Step 1: The analysis unit uses generative AI to analyze the video content and identify appropriate locations to embed advertisements. The analysis unit analyzes the content of the video using image analysis, audio analysis, text analysis, and other technologies, and identifies locations to embed advertisements based on the importance of scenes in the video and the viewer's level of interest. Step 2: The generator uses generative AI to generate content for embedding advertisements naturally in the identified locations. The generator generates advertisements in the form of banner ads, video ads, etc., and generates content to display advertisements in the background of videos and content to add scenes in which characters use the advertised products. Step 3: The embedding unit embeds the generated advertisement into the video. The embedding unit decides where in the video to embed the advertisement and how, and embeds the advertisement when the video scene changes or when a specific event occurs. The embedding unit can also adjust the position and timing of the advertisement using the generation AI.

[0062] (Example 2) The advertisement embedding system according to the embodiment of the present invention is a system that uses a generation AI to embed advertisements in the original content of a video, thereby eliminating the compulsion of advertisements and improving the user experience of video distribution. This advertisement embedding system analyzes video content and identifies appropriate locations for embedding advertisements. This analysis is performed by a generation AI. Next, the generation AI generates content for embedding advertisements naturally in the identified locations. For example, an advertisement may be displayed in the background of a video, or a scene may be added in which a character uses an advertised product. This allows users to see advertisements in a natural way without being forced to watch the advertisements. This mechanism improves the user experience of video distribution and reduces the aversion to advertisements. In addition, more effective advertisement delivery is possible for advertisers. For example, the effectiveness of advertisements is increased by embedding advertisements in content that is likely to interest users. For example, the video content is analyzed and an appropriate location for embedding advertisements is identified. This analysis is performed by a generation AI. Next, the generation AI generates content for embedding advertisements naturally in the identified locations. For example, an advertisement may be displayed in the background of a video, or a scene may be added in which a character uses an advertised product. This allows users to see advertisements in a natural way without being forced to watch the advertisements. This mechanism improves the user experience of video streaming and reduces the aversion to advertisements. It also enables advertisers to deliver advertisements more effectively. For example, the effectiveness of advertisements can be increased by embedding advertisements in content that is likely to interest users. In this way, the advertisement embedding system can make the user experience of video streaming more comfortable and eliminate the compulsion of advertisements.

[0063] The advertisement embedding system according to the embodiment includes an analysis unit, a generation unit, and an embedding unit. The analysis unit uses a generation AI to analyze video content and identify an appropriate location for embedding an advertisement. The analysis unit analyzes the content of the video using techniques such as image analysis, audio analysis, and text analysis. For example, the analysis unit can identify a location for embedding an advertisement based on the importance of a scene in the video and the interest of a viewer. The generation unit uses the generation AI to generate content for naturally embedding an advertisement in the identified location. The generation unit can generate advertisements in the form of, for example, a banner advertisement, a video advertisement, and the like. For example, the generation unit generates content that displays an advertisement in the background of the video. The generation unit can also generate content that adds a scene in which a character uses an advertised product. The embedding unit embeds the generated advertisement into the video. The embedding unit determines, for example, which part of the video and how to embed the advertisement. For example, the embedding unit can embed an advertisement when a scene of the video is switched or when a specific event occurs. This allows the advertisement embedding system according to the embodiment to naturally embed an advertisement in the video content. This makes it possible to eliminate the compulsion of advertisements and improve the user experience. Some or all of the above-mentioned processing in the embedding unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, when embedding a generated advertisement in a video, the embedding unit can adjust the position and timing of the advertisement using the generation AI. This enables the advertisement to be displayed naturally.

[0064] The analysis unit uses generative AI to analyze video content and identify appropriate locations for embedding advertisements. Specifically, the analysis unit uses image analysis, audio analysis, text analysis, and other technologies to analyze the content of the video in detail. In image analysis, each frame in the video is analyzed to evaluate the importance of the scene and the viewer's interest. For example, facial recognition technology can be used to analyze the facial expressions and movements of the characters to detect changes in emotions. In audio analysis, speech recognition technology is used to analyze the conversations and sound effects in the video to identify the atmosphere of the scene and important remarks. In text analysis, the content of subtitles and captions is analyzed to understand the context and theme of the scene. By integrating these analysis results, the analysis unit can comprehensively evaluate the importance of the scene in the video and the viewer's interest, and identify the optimal location for embedding advertisements. In addition, the analysis unit can customize the optimal ad embedding location for each individual viewer by utilizing the viewer's viewing history and preference data. This allows the analysis unit to precisely grasp the content of the video content and the viewer's interest, providing a foundation for maximizing the effectiveness of advertisements.

[0065] The generation unit uses the generation AI to generate content for naturally embedding advertisements in the identified locations. Specifically, the generation unit can generate advertisements in the form of banner advertisements, video advertisements, and the like. For example, when generating content for displaying advertisements in the background of a video, the generation unit adjusts the design of the advertisement to match the color tone and lighting conditions of the video. This allows the advertisement to blend naturally as part of the video. The generation unit can also generate content that adds a scene in which a character uses the advertised product. In this case, the generation AI analyzes the movements and facial expressions of the character to generate a scene in which the advertised product is used in a natural manner. Furthermore, the generation unit can use voice synthesis technology to generate lines in which the character mentions the advertised product. This allows the generation unit to effectively convey the advertising message to the viewer. The generation unit can also generate advertising content that is optimal for each individual viewer based on the viewer's preferences and viewing history. For example, the effectiveness of the advertisement can be increased by generating advertisements related to products and services in which the viewer has shown interest in the past. This allows the generation unit to generate advertisements that blend naturally into the video content and attract the viewer's interest.

[0066] The embedding unit embeds the generated advertisement into the video. Specifically, the embedding unit determines which part of the video to embed the advertisement and how. For example, the embedding unit can embed the advertisement when the scene of the video changes or when a specific event occurs. When the scene changes, the viewer's attention is temporarily interrupted, making it an ideal timing to naturally insert the advertisement. In addition, when a specific event occurs, the viewer's interest increases, so the effectiveness of the advertisement can be maximized. The embedding unit can adjust the position and timing of the advertisement using the generation AI. For example, the generation AI analyzes the movement and visual elements in the video to ensure that the advertisement is placed in the optimal position to attract the viewer's attention. In addition, the generation AI can analyze the movement of the viewer's gaze and place the advertisement in the place where the gaze is concentrated. This allows the advertisement to be displayed naturally and minimizes the discomfort to the viewer. Furthermore, the embedding unit can reduce the viewer's stress and increase the effectiveness of the advertisement by adjusting the display time and frequency of the advertisement. For example, in a long video, by inserting short advertisements multiple times, the message of the advertisement can be conveyed while maintaining the viewer's concentration. This allows the embedder to embed advertisements naturally within the video content, enhancing the viewer experience.

[0067] The analysis unit can analyze the contents of the video and identify the location where the advertisement is embedded. The analysis unit can analyze the contents of the video using techniques such as image analysis, audio analysis, and text analysis. For example, the analysis unit can identify the location where the advertisement is embedded based on the importance of a scene in the video and the viewer's interest. This allows the advertisement to be inserted naturally by identifying the location where the advertisement is embedded based on the content of the video. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, when analyzing the contents of the video, the analysis unit can evaluate the importance of a scene and the viewer's interest using a generation AI.

[0068] The generation unit can generate content for embedding an advertisement in the specified location. The generation unit generates content for naturally embedding an advertisement in the specified location using a generation AI. The generation unit can generate advertisements in the form of, for example, banner advertisements, video advertisements, etc. For example, the generation unit generates content for displaying advertisements in the background of a video. The generation unit can also generate content for adding a scene in which a character uses an advertised product. This allows the advertisement to be generated in a natural manner, thereby reducing the user's aversion to the advertisement. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, when generating content for embedding an advertisement in the specified location, the generation unit can determine the content and format of the advertisement using a generation AI.

[0069] The embedding unit can embed the generated advertisement into the video. The embedding unit embeds the generated advertisement into the video. The embedding unit determines, for example, in which part of the video and how to embed the advertisement. For example, the embedding unit can embed the advertisement when the scene of the video changes or when a specific event occurs. As a result, by embedding the generated advertisement into the video, the advertisement can be displayed naturally. A part or all of the above-mentioned processing in the embedding unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, when embedding the generated advertisement into the video, the embedding unit can adjust the position and timing of the advertisement using the generation AI.

[0070] The generation unit can generate an advertisement based on the user's viewing history. The generation unit generates an advertisement based on the user's viewing history using a generation AI. The generation unit can customize the advertisement based on data such as the titles and viewing times of videos the user has viewed in the past. This enables more effective advertisement delivery by customizing the advertisement based on the user's viewing history. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can analyze the user's viewing history and determine the content and format of the advertisement using a generation AI.

[0071] The advertisement may further include an evaluation unit that evaluates the effectiveness of the advertisement. The evaluation unit evaluates the effectiveness of the advertisement using the generation AI. The evaluation unit can evaluate the effectiveness of the advertisement based on data such as the click rate and viewing completion rate of the advertisement. This makes it possible to measure and improve the effectiveness of advertisement delivery by evaluating the effectiveness of the advertisement. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can analyze the viewing data of the advertisement and evaluate the effectiveness of the advertisement using the generation AI.

[0072] The analysis unit can estimate the user's emotion and identify an appropriate location to embed an advertisement based on the estimated user's emotion. The analysis unit can estimate the user's emotion using the generation AI and identify an appropriate location to embed an advertisement based on the estimated user's emotion. The analysis unit estimates the user's emotion using, for example, facial expression analysis, voice analysis, or other technology. For example, when the user is excited, the analysis unit can identify a location to insert an advertisement in accordance with the heightened emotion. In addition, when the user is relaxed, the analysis unit can also identify a location to insert an advertisement in a relaxing scene. Furthermore, when the user is concentrating, the analysis unit can also identify a location to insert an advertisement at a timing that does not disturb the user's concentration. This enables more effective advertisement delivery by identifying a location to embed an advertisement based on the user's emotion. The emotion estimation is realized using, for example, an emotion engine or a generation AI, using an emotion estimation function. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can infer user sentiment and use generative AI to identify appropriate locations to embed advertisements.

[0073] The analysis unit can analyze the viewer's interest level for each scene of the video and specify the timing to embed the advertisement. The analysis unit can use the generation AI to analyze the viewer's interest level for each scene of the video and specify the optimal timing to embed the advertisement. The analysis unit can evaluate the viewer's interest level based on data such as viewing time and the number of clicks. For example, the analysis unit can specify the timing to insert an advertisement before or after a climax scene in which the viewer's interest is heightened. The analysis unit can also specify the timing to insert an advertisement before a scene in which the viewer's interest is reduced. Furthermore, the analysis unit can also specify the timing to insert an advertisement in the middle of a scene in which the viewer's interest is sustained. This allows the effectiveness of the advertisement to be maximized by specifying the timing to embed the advertisement based on the viewer's interest level. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can analyze the viewer's interest level and specify the optimal timing to embed the advertisement using the generation AI.

[0074] The analysis unit can adjust the location where the advertisement is embedded based on the genre and theme of the video. The analysis unit dynamically adjusts the location where the advertisement is embedded based on the genre and theme of the video using the generation AI. The analysis unit can specify the location where the advertisement is embedded based on the genre and theme, such as comedy, drama, and action. For example, the analysis unit can specify the location where the advertisement is inserted into a humorous scene in a comedy video. The analysis unit can also specify the location where the advertisement is inserted into a moving scene in a drama video. Furthermore, the analysis unit can also specify the location where the advertisement is inserted into a tense scene in an action video. This allows the advertisement to be inserted naturally by adjusting the location where the advertisement is embedded based on the genre and theme of the video. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can analyze the genre and theme of the video and dynamically adjust the location where the advertisement is embedded using the generation AI.

[0075] The analysis unit can estimate the user's emotion and determine the priority of the location where the advertisement is embedded based on the estimated user's emotion. The analysis unit estimates the user's emotion using the generation AI and determines the priority of the location where the advertisement is embedded based on the estimated user's emotion. The analysis unit estimates the user's emotion using, for example, facial expression analysis, voice analysis, or other technology. For example, when the user is excited, the analysis unit can determine the priority of the location where the advertisement is inserted according to the heightened emotion. In addition, when the user is relaxed, the analysis unit can also determine the priority of the location where the advertisement is inserted in the relaxing scene. Furthermore, when the user is concentrating, the analysis unit can also determine the priority of the location where the advertisement is inserted at a timing that does not disturb the concentration. As a result, by determining the priority of the location where the advertisement is embedded based on the user's emotion, more effective advertisement delivery is possible. The emotion estimation is realized using, for example, an emotion engine or a generation AI, using an emotion estimation function. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the analysis unit can estimate the user's emotions and determine the priority of the locations where advertisements are embedded using the generation AI.

[0076] The analysis unit can perform audio analysis of the video and identify a location where an advertisement is embedded based on the content of the audio. The analysis unit can perform audio analysis of the video using a generation AI and identify a location where an advertisement is embedded based on the content of the audio. The analysis unit can analyze the audio content of the video using technologies such as voice recognition and emotion analysis. For example, the analysis unit can identify a location where an advertisement is inserted at a break in a conversation in the video. The analysis unit can also identify a location where an advertisement is inserted at a change in music in the video. Furthermore, the analysis unit can also identify a location where an advertisement is inserted in accordance with the timing of a sound effect in the video. This makes it possible to insert an advertisement naturally by identifying a location where an advertisement is embedded based on the audio content of the video. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can analyze the audio content of the video and identify a location where an advertisement is embedded using a generation AI.

[0077] The analysis unit can customize the location where the advertisement is embedded based on the age group and gender of the viewer of the video. The analysis unit uses the generation AI to customize the location where the advertisement is embedded based on the age group and gender of the viewer of the video. The analysis unit can customize the advertisement based on data such as age category and gender identification method. For example, the analysis unit can identify the location where the advertisement is inserted in a visually flashy scene in a video for young people. Also, the analysis unit can identify the location where the advertisement is inserted in a calm scene in a video for older people. Furthermore, the analysis unit can identify the location where the advertisement is inserted in a scene that is likely to attract interest, by gender. This enables more effective advertisement delivery by customizing the location where the advertisement is embedded based on the age group and gender of the viewer. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can analyze the age group and gender of the viewer and customize the location where the advertisement is embedded using the generation AI.

[0078] The generation unit can estimate the user's emotion and adjust the advertisement expression method based on the estimated user's emotion. The generation unit estimates the user's emotion using the generation AI and adjusts the advertisement expression method based on the estimated user's emotion. The generation unit estimates the user's emotion using techniques such as facial expression analysis and voice analysis. For example, the generation unit can generate an advertisement with a calm tone when the user is relaxed. In addition, the generation unit can also generate an advertisement with an energetic tone when the user is excited. Furthermore, the generation unit can also generate an advertisement that is simple and to the point when the user is focused. This enables more effective advertisement delivery by adjusting the advertisement expression method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generator can estimate a user's emotions and use generation AI to adjust how the advertisement is presented.

[0079] The generation unit can customize the design of the advertisement according to the color tone and style of the video when generating the advertisement. The generation unit customizes the design of the advertisement according to the color tone and style of the video when generating the advertisement using the generation AI. The generation unit can adjust the design of the advertisement using techniques such as color adjustment and design style. For example, if the video has a light color tone, the generation unit can design the advertisement in a light color tone. In addition, if the video has a dark color tone, the generation unit can also design the advertisement in a dark color tone. Furthermore, if the video has a cartoon style, the generation unit can also design the advertisement in a cartoon style. This enables natural insertion of the advertisement by customizing the design of the advertisement according to the color tone and style of the video. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the color tone and style of the video and customize the design of the advertisement using the generation AI.

[0080] The generation unit can naturally insert the advertisement in accordance with the storyline of the video when generating the advertisement. The generation unit can naturally insert the advertisement in accordance with the storyline of the video when generating the advertisement using the generation AI. The generation unit can analyze the storyline of the video using techniques such as scenario analysis and plot analysis. For example, the generation unit can add a scene in which a character in the video uses an advertised product. The generation unit can also display an advertisement in the background of the video. Furthermore, the generation unit can also insert an advertisement related to the story of the video. This enables the advertisement to be inserted naturally by inserting the advertisement in accordance with the storyline of the video. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the storyline of the video and insert the advertisement naturally using the generation AI.

[0081] The generation unit can estimate the user's emotion and adjust the length of the advertisement based on the estimated user's emotion. The generation unit can estimate the user's emotion using a generation AI and adjust the length of the advertisement based on the estimated user's emotion. The generation unit estimates the user's emotion using techniques such as facial expression analysis and voice analysis. For example, the generation unit can generate a short advertisement when the user is in a hurry. In addition, the generation unit can also generate a longer advertisement when the user is relaxed. Furthermore, the generation unit can also generate a visually stimulating advertisement when the user is excited. This enables more effective advertisement delivery by adjusting the length of the advertisement based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can estimate the user's emotion and adjust the length of the advertisement using a generation AI.

[0082] The generation unit can customize the audio of the advertisement to match the music and sound effects of the video when generating the advertisement. The generation unit customizes the audio of the advertisement to match the music and sound effects of the video when generating the advertisement using the generation AI. The generation unit can adjust the audio of the advertisement using techniques such as volume adjustment and timing adjustment. For example, the generation unit can adjust the background music of the advertisement to match the music of the video. The generation unit can also add sound effects of the advertisement to match the sound effects of the video. Furthermore, the generation unit can adjust the narration of the advertisement to match the tone of the audio of the video. This enables natural insertion of the advertisement by customizing the audio of the advertisement to match the music and sound effects of the video. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the music and sound effects of the video and customize the audio of the advertisement using the generation AI.

[0083] The generation unit can adjust the content of the advertisement to match the lines of the characters in the video when generating the advertisement. The generation unit adjusts the content of the advertisement to match the lines of the characters in the video when generating the advertisement using the generation AI. The generation unit can analyze the lines of the characters using technologies such as voice recognition and context analysis. For example, the generation unit can add a scene in which the characters in the video mention the advertised product. The generation unit can also insert an advertisement related to the lines of the characters in the video. Furthermore, the generation unit can adjust the catchphrase of the advertisement to match the lines of the characters in the video. This allows the advertisement to be inserted naturally by adjusting the content of the advertisement to match the lines of the characters in the video. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the lines of the characters and adjust the content of the advertisement using the generation AI.

[0084] The embedding unit can estimate the user's emotion and adjust the advertisement embedding method based on the estimated user's emotion. The embedding unit estimates the user's emotion using the generation AI and adjusts the advertisement embedding method based on the estimated user's emotion. The embedding unit estimates the user's emotion using techniques such as facial expression analysis and voice analysis. For example, the embedding unit can embed an advertisement in a calm tone when the user is relaxed. Also, the embedding unit can embed an advertisement in an energetic tone when the user is excited. Furthermore, the embedding unit can embed an advertisement that is simple and to the point when the user is focused. This enables more effective advertisement delivery by adjusting the advertisement embedding method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the embedding unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the embedder can infer a user's emotions and use generative AI to adjust how ads are embedded.

[0085] The embedding unit can adjust the quality of the advertisement according to the frame rate and resolution of the video when embedding the advertisement. The embedding unit adjusts the quality of the advertisement according to the frame rate and resolution of the video when embedding the advertisement using the generation AI. The embedding unit can adjust the quality of the advertisement using techniques such as setting the frame rate and adjusting the resolution. For example, the embedding unit can embed a high frame rate advertisement in a high frame rate video. In addition, the embedding unit can also embed a high resolution advertisement in a high resolution video. Furthermore, the embedding unit can also embed a low frame rate advertisement in a low frame rate video. This allows the advertisement to be inserted naturally by adjusting the quality of the advertisement according to the frame rate and resolution of the video. Part or all of the above-mentioned processing in the embedding unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the embedding unit can analyze the frame rate and resolution of the video and adjust the quality of the advertisement using the generation AI.

[0086] The embedding unit can naturally insert an advertisement in accordance with a scene transition of a video when embedding an advertisement. The embedding unit uses a generation AI to naturally insert an advertisement in accordance with a scene transition of a video when embedding an advertisement. The embedding unit can insert an advertisement based on the timing, for example, when a scene is switched or when a specific event occurs. For example, the embedding unit can insert an advertisement at the timing of a scene transition. The embedding unit can also insert an advertisement before and after a scene transition. Furthermore, the embedding unit can also insert an advertisement in the middle of a scene transition. This allows for natural insertion of an advertisement by inserting an advertisement in accordance with a scene transition. A part or all of the above-mentioned processing in the embedding unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the embedding unit can analyze the timing of a scene transition and naturally insert an advertisement using a generation AI.

[0087] The embedding unit can estimate the user's emotion and adjust the display timing of the advertisement based on the estimated user's emotion. The embedding unit estimates the user's emotion using the generation AI and adjusts the display timing of the advertisement based on the estimated user's emotion. The embedding unit estimates the user's emotion using, for example, facial expression analysis, voice analysis, or other technology. For example, the embedding unit can display the advertisement at a calm timing when the user is relaxed. In addition, the embedding unit can also display the advertisement at an energetic timing when the user is excited. Furthermore, the embedding unit can also display the advertisement at a simple and to the point timing when the user is concentrating. This enables more effective advertisement delivery by adjusting the display timing of the advertisement based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the embedding unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the embedding unit can estimate a user's emotions and use generative AI to adjust the timing of advertisement display.

[0088] The embedding unit can adjust the position of the advertisement according to the subtitles and text information of the video when embedding the advertisement. The embedding unit adjusts the position of the advertisement according to the subtitles and text information of the video using the generation AI when embedding the advertisement. The embedding unit can analyze the subtitles and text information of the video using techniques such as character recognition and context analysis. For example, the embedding unit can display the advertisement above the subtitles of the video. In addition, the embedding unit can also display the advertisement next to the text information of the video. Furthermore, the embedding unit can also display the advertisement below the subtitles of the video. This allows the advertisement to be inserted naturally by adjusting the position of the advertisement according to the subtitles and text information of the video. A part or all of the above-mentioned processing in the embedding unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the embedding unit can analyze the subtitles and text information of the video and adjust the position of the advertisement using the generation AI.

[0089] The embedding unit can customize the format of the advertisement according to the viewing device of the video when embedding the advertisement. The embedding unit customizes the format of the advertisement according to the viewing device of the video when embedding the advertisement using the generation AI. The embedding unit can adjust the format of the advertisement using techniques such as screen size and resolution. For example, the embedding unit can display a vertically long advertisement when viewed on a smartphone. In addition, the embedding unit can also display a horizontally long advertisement when viewed on a tablet. Furthermore, the embedding unit can display a full-screen advertisement when viewed on a personal computer. This enables natural insertion of the advertisement by customizing the format of the advertisement according to the viewing device. Part or all of the above-mentioned processing in the embedding unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the embedding unit can analyze the viewing device and customize the format of the advertisement using the generation AI.

[0090] The evaluation unit can estimate the user's emotion and evaluate the effectiveness of the advertisement based on the estimated user's emotion. The evaluation unit can estimate the user's emotion using the generation AI and evaluate the effectiveness of the advertisement based on the estimated user's emotion. The evaluation unit estimates the user's emotion using techniques such as facial expression analysis and voice analysis. For example, the evaluation unit can evaluate the viewing time of the advertisement when the user is relaxed. In addition, the evaluation unit can also evaluate the click rate of the advertisement when the user is excited. Furthermore, the evaluation unit can also evaluate the viewing completion rate of the advertisement when the user is focused. This enables more effective advertisement delivery by evaluating the effectiveness of the advertisement based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can estimate the user's emotion and evaluate the effectiveness of the advertisement using the generation AI.

[0091] The evaluation unit can analyze the viewing data of the advertisement and evaluate the effectiveness of the advertisement in real time. The evaluation unit can analyze the viewing data of the advertisement using the generation AI and evaluate the effectiveness of the advertisement in real time. The evaluation unit can evaluate the effectiveness of the advertisement based on data such as the viewing time and the number of clicks. For example, the evaluation unit can analyze the viewing start time and end time of the advertisement and evaluate the viewing completion rate. The evaluation unit can also analyze the number of clicks on the advertisement and evaluate the click rate. Furthermore, the evaluation unit can analyze the behavior data of the user while viewing the advertisement and evaluate the effectiveness of the advertisement. This makes it possible to instantly evaluate the effectiveness of the advertisement by analyzing the viewing data of the advertisement in real time. Part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can analyze the viewing data of the advertisement and evaluate the effectiveness of the advertisement in real time using the generation AI.

[0092] The evaluation unit can evaluate the effectiveness of the advertisement based on the click rate and the viewing completion rate of the advertisement. The evaluation unit uses the generation AI to evaluate the effectiveness of the advertisement based on the click rate and the viewing completion rate of the advertisement. The evaluation unit can evaluate the effectiveness of the advertisement based on data such as the number of clicks and the number of viewing completions. For example, the evaluation unit can evaluate the effectiveness of the advertisement based on the click rate of the advertisement. The evaluation unit can also evaluate the effectiveness of the advertisement based on the viewing completion rate of the advertisement. Furthermore, the evaluation unit can comprehensively evaluate the click rate and the viewing completion rate of the advertisement to determine the effectiveness of the advertisement. This makes it possible to accurately measure the effectiveness of the advertisement by evaluating the effectiveness of the advertisement based on the click rate and the viewing completion rate of the advertisement. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can analyze the click rate and the viewing completion rate of the advertisement and evaluate the effectiveness of the advertisement using the generation AI.

[0093] The evaluation unit can estimate the user's emotions and adjust the criteria for evaluating the effectiveness of the advertisement based on the estimated user's emotions. The evaluation unit estimates the user's emotions using the generation AI and adjusts the criteria for evaluating the effectiveness of the advertisement based on the estimated user's emotions. The evaluation unit estimates the user's emotions using techniques such as facial expression analysis and voice analysis. For example, when the user is relaxed, the evaluation unit can evaluate the effectiveness of the advertisement by placing emphasis on the viewing time. In addition, when the user is excited, the evaluation unit can also evaluate the effectiveness of the advertisement by placing emphasis on the click rate. Furthermore, when the user is focused, the evaluation unit can also evaluate the effectiveness of the advertisement by placing emphasis on the viewing completion rate. This enables more effective advertisement delivery by adjusting the criteria for evaluating the effectiveness of the advertisement based on the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can estimate user emotions and use generative AI to adjust the criteria for evaluating the effectiveness of advertisements.

[0094] The evaluation unit can collect feedback from viewers of the advertisement and evaluate the effectiveness of the advertisement. The evaluation unit can collect feedback from viewers of the advertisement using the generation AI and evaluate the effectiveness of the advertisement. The evaluation unit can evaluate the effectiveness of the advertisement based on data such as questionnaires, comments, and social media responses. For example, the evaluation unit can collect feedback through questionnaires after viewing the advertisement and evaluate the effectiveness of the advertisement. The evaluation unit can also analyze comments after viewing the advertisement and evaluate the effectiveness of the advertisement. Furthermore, the evaluation unit can collect social media responses after viewing the advertisement and evaluate the effectiveness of the advertisement. This makes it possible to accurately evaluate the effectiveness of the advertisement by collecting feedback from viewers of the advertisement. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can collect feedback from viewers of the advertisement and evaluate the effectiveness of the advertisement using the generation AI.

[0095] The evaluation unit can evaluate the effectiveness of the advertisement based on the viewing environment of the advertisement. The evaluation unit uses the generation AI to evaluate the effectiveness of the advertisement based on the viewing environment of the advertisement (device, location, time period). The evaluation unit can evaluate the effectiveness of the advertisement based on data such as the viewing device, viewing location, and viewing time period. For example, the evaluation unit can evaluate the effectiveness of the advertisement viewed on a smartphone. The evaluation unit can also evaluate the effectiveness of the advertisement viewed at home. Furthermore, the evaluation unit can evaluate the effectiveness of the advertisement viewed at night. This makes it possible to accurately measure the effectiveness of the advertisement by evaluating the effectiveness of the advertisement based on the viewing environment of the advertisement. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can analyze the viewing environment of the advertisement and evaluate the effectiveness of the advertisement using the generation AI.

[0096] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0097] The advertisement embedding system may further include a history analysis unit that analyzes the user's viewing history. The history analysis unit may identify the user's interests and concerns based on data such as the genres and themes of videos the user has viewed in the past, the viewing time, and the viewing frequency. For example, the history analysis unit may preferentially embed advertisements related to videos of a genre that the user frequently views. The history analysis unit may also embed more detailed advertisements in videos that the user views for a long time. Furthermore, the history analysis unit may also embed advertisements appropriate for a time period in accordance with videos that the user views during a specific time period. This may maximize the effectiveness of advertisements by customizing advertisements based on the user's viewing history.

[0098] The advertisement embedding system may further include a behavior monitoring unit that monitors the real-time viewing behavior of the user. The behavior monitoring unit may collect and analyze behavior data when the user is viewing a video. For example, the behavior monitoring unit may analyze the timing when the user pauses or rewinds the video, and insert an advertisement at that timing. In addition, if the user performs another action (e.g., posting a comment, clicking a link, etc.) while viewing the video, the behavior monitoring unit may also display an advertisement related to that action. Furthermore, if the user reacts to a particular scene while viewing the video, the behavior monitoring unit may also insert an advertisement related to that scene. This may improve the effectiveness of the advertisement by customizing the advertisement based on the user's real-time viewing behavior.

[0099] The advertisement embedding system may further include a social analysis unit that analyzes the user's social media activity. The social analysis unit may analyze information shared by the user on social media and the contents of posts to identify the user's interests. For example, the social analysis unit may analyze posts in which the user mentions a particular brand or product, and embed advertisements related to the brand or product. The social analysis unit may also display relevant advertisements based on information about accounts the user follows and groups the user participates in. The social analysis unit may also insert advertisements related to posts in which the user has performed actions such as "like" or "share". This may increase the effectiveness of advertisements by customizing advertisements based on the user's social media activity.

[0100] The advertisement embedding system may further include a device analysis unit that analyzes the device information of the user. The device analysis unit may analyze the type of device used by the user and setting information, and optimize the advertisement display method. For example, the device analysis unit may display a portrait advertisement when the user is using a smartphone. Furthermore, the device analysis unit may display a landscape advertisement when the user is using a tablet. Furthermore, the device analysis unit may display a full-screen advertisement when the user is using a personal computer. This allows the effectiveness of the advertisement to be maximized by customizing the advertisement display method based on the user's device information.

[0101] The advertisement embedding system may further include a location analysis unit that analyzes the user's location information. The location analysis unit may analyze the user's current location and past movement history, and customize advertisements based on the location information. For example, when the user is in a specific area, the location analysis unit may display advertisements related to that area. The location analysis unit may also display related advertisements based on information about places the user has visited in the past. Furthermore, when the user is at a specific event or store, the location analysis unit may display advertisements related to that event or store. This may increase the effectiveness of advertisements by customizing advertisements based on the user's location information.

[0102] The ad embedding system can further estimate the user's emotions and adjust the display format of the ad based on the estimated emotions. For example, if the user is relaxed, an ad with a calm tone can be displayed. If the user is excited, an ad with an energetic tone can be displayed. Furthermore, if the user is focused, an ad with a simple and to-the-point tone can be displayed. This allows for more effective ad delivery by adjusting the display format of the ad based on the user's emotions.

[0103] The ad embedding system can further estimate the user's emotions and adjust the timing of ad display based on the estimated emotions. For example, if the user is relaxed, the ad can be displayed at a calm timing. If the user is excited, the ad can be displayed at an energetic timing. If the user is focused, the ad can be displayed at a simple and to-the-point timing. This allows for more effective ad delivery by adjusting the ad display timing based on the user's emotions.

[0104] The ad embedding system can further estimate the user's emotions and customize the content of the advertisement based on the estimated emotions. For example, if the user is relaxed, an advertisement with calm content can be displayed. If the user is excited, an advertisement with energetic content can be displayed. Furthermore, if the user is focused, an advertisement with simple and to the point content can be displayed. This allows for more effective ad delivery by customizing the content of the advertisement based on the user's emotions.

[0105] The ad embedding system can further estimate the user's emotions and adjust the frequency of advertisement display based on the estimated emotions. For example, when the user is relaxed, the frequency of advertisement display can be reduced. Also, when the user is excited, the frequency of advertisement display can be increased. Furthermore, when the user is focused, the frequency of advertisement display can be appropriately adjusted. In this way, by adjusting the frequency of advertisement display based on the user's emotions, more effective advertisement delivery is possible.

[0106] The ad embedding system can further estimate the user's emotions and adjust the display location of the ad based on the estimated emotions. For example, if the user is relaxed, the ad can be displayed at the bottom of the screen. If the user is excited, the ad can be displayed in the center of the screen. If the user is focused, the ad can be displayed at the edge of the screen. This allows for more effective ad delivery by adjusting the display location of the ad based on the user's emotions.

[0107] The process flow of the second embodiment will be briefly described below.

[0108] Step 1: The analysis unit uses generative AI to analyze the video content and identify appropriate locations to embed advertisements. The analysis unit analyzes the content of the video using image analysis, audio analysis, text analysis, and other technologies, and identifies locations to embed advertisements based on the importance of scenes in the video and the viewer's level of interest. Step 2: The generator uses generative AI to generate content for embedding advertisements naturally in the identified locations. The generator generates advertisements in the form of banner ads, video ads, etc., and generates content to display advertisements in the background of videos and content to add scenes in which characters use the advertised products. Step 3: The embedding unit embeds the generated advertisement into the video. The embedding unit decides where in the video to embed the advertisement and how, and embeds the advertisement when the video scene changes or when a specific event occurs. The embedding unit can also adjust the position and timing of the advertisement using the generation AI.

[0109] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0110] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0111] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0112] Each of the multiple elements including the above-mentioned analysis unit, generation unit, embedding unit, and evaluation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing device 12, and analyzes video content and identifies an appropriate location for embedding an advertisement. The generation unit is realized, for example, by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing device 12, and generates content for naturally embedding an advertisement in the identified location. The embedding unit is realized, for example, by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing device 12, and embeds the generated advertisement into the video. The evaluation unit is realized, for example, by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing device 12, and evaluates the effectiveness of the advertisement. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0113] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0114] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0115] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0116] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0117] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0119] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0120] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0121] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0122] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0123] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0124] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0126] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0127] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements including the above-mentioned analysis unit, generation unit, embedding unit, and evaluation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and analyzes video content and identifies an appropriate location for embedding an advertisement. The generation unit is realized, for example, by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and generates content for naturally embedding an advertisement at the identified location. The embedding unit is realized, for example, by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and embeds the generated advertisement into the video. The evaluation unit is realized, for example, by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and evaluates the effectiveness of the advertisement. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0129] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0130] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0131] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0132] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0133] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0135] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0136] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0137] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0138] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0139] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0140] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0141] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0143] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements including the above-mentioned analysis unit, generation unit, embedding unit, and evaluation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and analyzes video content and identifies an appropriate location for embedding an advertisement. The generation unit is realized, for example, by the processor 46 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and generates content for naturally embedding an advertisement in the identified location. The embedding unit is realized, for example, by the processor 46 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and embeds the generated advertisement into the video. The evaluation unit is realized, for example, by the processor 46 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and evaluates the effectiveness of the advertisement. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0145] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0146] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0147] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0148] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0149] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0151] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0152] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0153] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0154] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0155] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0156] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0157] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0158] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0159] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0160] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0161] Each of the multiple elements including the above-mentioned analysis unit, generation unit, embedding unit, and evaluation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing device 12, and analyzes video content and identifies an appropriate location for embedding an advertisement. The generation unit is realized, for example, by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing device 12, and generates content for naturally embedding an advertisement in the identified location. The embedding unit is realized, for example, by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing device 12, and embeds the generated advertisement into the video. The evaluation unit is realized, for example, by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing device 12, and evaluates the effectiveness of the advertisement. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0162] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0163] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0164] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0165] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0166] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0167] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0169] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0170] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0171] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0172] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0173] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0174] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0175] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0176] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0177] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0178] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0179] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0180] (Appendix 1) An analysis unit that analyzes video content; a generation unit that generates an advertisement in the location identified by the analysis unit; An embedding unit that embeds the advertisement generated by the generation unit into the video. A system characterized by: (Appendix 2) The analysis unit is Analyze the content of the video and identify where to embed ads 2. The system of claim 1, (Appendix 3) The generation unit is Generate content to embed ads in identified locations 2. The system of claim 1, (Appendix 4) The embedding portion is Embed the generated ad into your video 2. The system of claim 1, (Appendix 5) The generation unit is Generate ads based on user viewing history 2. The system of claim 1, (Appendix 6) The apparatus further includes an evaluation unit for evaluating the effectiveness of the advertisement. 2. The system of claim 1, (Appendix 7) The analysis unit is Infer user sentiment and identify appropriate locations for embedding advertisements based on the inferred user sentiment 2. The system of claim 1, (Appendix 8) The analysis unit is Analyze the viewer's interest in each scene of the video and identify the best time to embed advertisements 2. The system of claim 1, (Appendix 9) The analysis unit is Adjust ad placement based on video genre or theme 2. The system of claim 1, (Appendix 10) The analysis unit is Estimate user emotions and prioritize ad placements based on the estimated user emotions. 2. The system of claim 1, (Appendix 11) The analysis unit is Perform audio analysis of videos and identify where to embed ads based on the audio content 2. The system of claim 1, (Appendix 12) The analysis unit is Customize ad placements based on the age and gender of your video viewers 2. The system of claim 1, (Appendix 13) The generation unit is Infer user emotions and adjust advertisement presentation based on the inferred user emotions 2. The system of claim 1, (Appendix 14) The generation unit is When generating the ad, customize the ad design to match the tone and style of your video 2. The system of claim 1, (Appendix 15) The generation unit is When generating ads, insert them naturally in line with the video storyline 2. The system of claim 1, (Appendix 16) The generation unit is Inferring user emotion and adjusting the length of advertisements based on the estimated user emotion 2. The system of claim 1, (Appendix 17) The generation unit is Customize the audio for your ad to match the music and sound effects in your video when you generate the ad 2. The system of claim 1, (Appendix 18) The generation unit is When generating ads, adjust the ad content to match the dialogue of the characters in the video 2. The system of claim 1, (Appendix 19) The embedding portion is Infer user emotions and adjust ad embedding methods based on the estimated user emotions 2. The system of claim 1, (Appendix 20) The embedding portion is When embedding ads, adjust the quality of the ads to match the frame rate and resolution of the video. 2. The system of claim 1, (Appendix 21) The embedding portion is When embedding ads, insert them naturally in line with video scene changes. 2. The system of claim 1, (Appendix 22) The embedding portion is Estimating user emotions and adjusting the timing of advertisement display based on the estimated user emotions 2. The system of claim 1, (Appendix 23) The embedding portion is When embedding ads, adjust the position of the ads to match the subtitles and text information in the video. 2. The system of claim 1, (Appendix 24) The embedding portion is When embedding ads, customize the ad format to match the device the video is viewed on 2. The system of claim 1, (Appendix 25) The evaluation unit is To estimate a user's emotions and evaluate the effectiveness of advertisements based on the estimated user's emotions 3. The system of claim 2, (Appendix 26) The evaluation unit is Analyze ad viewing data and evaluate the effectiveness of ads in real time 3. The system of claim 2, (Appendix 27) The evaluation unit is Evaluate the effectiveness of your ads based on click-through rates and completion rates 3. The system of claim 2, (Appendix 28) The evaluation unit is To estimate a user's emotions and adjust a criterion for evaluating the effectiveness of an advertisement based on the estimated user's emotions. 3. The system of claim 2, (Appendix 29) The evaluation unit is Collecting feedback from viewers of our ads and evaluating their effectiveness 3. The system of claim 2, (Appendix 30) The evaluation unit is Evaluate the effectiveness of ads based on the viewing environment of the ads 3. The system of claim 2, [Explanation of symbols]

[0181] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes video content and identifies locations where advertisements are to be embedded; a generation unit that generates an advertisement in the location identified by the analysis unit; An embedding unit that embeds the advertisement generated by the generation unit into the video. A system characterized by:

2. The generation unit is Generate ads based on user viewing history 2. The system of claim 1 .

3. The apparatus further includes an evaluation unit for evaluating the effectiveness of the advertisement.

2. The system of claim 1 .

4. The analysis unit is Infer user sentiment and identify appropriate locations for embedding advertisements based on the inferred user sentiment 2. The system of claim 1 .

5. The analysis unit is Analyze the viewer's interest in each scene of the video and identify the best time to embed advertisements 2. The system of claim 1 .

6. The analysis unit is Adjust ad placement based on video genre or theme 2. The system of claim 1 .

Images