System

Abstract

To provide a system that automatically generates or recommends suitable music for video.SOLUTION: A system according to the embodiment comprises a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit uploads videos. The analysis unit analyzes audio portions and image portions of the videos uploaded by the reception unit, and learns the correspondence between the audio and image. The generation unit generates music based on the correspondence learned by the analysis unit. The provision unit provides the music generated by the generation unit.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] Conventional techniques have the drawback of making it difficult to automatically generate or recommend music suitable for videos.

[0005] The system according to the embodiment aims to automatically generate or recommend music suitable for a video. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit uploads a video. The analysis unit analyzes the audio and video parts of the video uploaded by the reception unit and learns the correspondence between the audio and video. The generation unit generates music based on the correspondence learned by the analysis unit. The provision unit provides the music generated by the generation unit. Effect of the Invention

[0007] The system according to the embodiment can automatically generate or recommend suitable music for 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 audio-video correspondence learning system according to the embodiment of the present invention is a system that generates music that matches the concept of a user by simply uploading multiple videos taken by the user, or recommends the most suitable existing music. This system is a technology that uses countless videos that exist around the world and uses contrastive learning for the audio and video parts to learn the correspondence between audio and video. For example, it is possible to generate music that matches the concept or recommend the most suitable existing music by simply uploading multiple videos taken by the user. Specifically, first, the user uploads multiple videos taken by the user. Next, the system analyzes the audio and video parts of the uploaded videos using contrastive learning to learn the correspondence between audio and video. This learning allows the system to generate music that matches the concept of the video. It is also possible to recommend the most suitable music from an existing music database. For example, if a user uploads a video of a trip, the system analyzes the video and audio of the video and generates music that matches the atmosphere of the trip. In addition, the system also recommends music that is suitable for the trip from an existing music database. This allows users to easily create videos by simply uploading multiple videos and still images. This technology allows users to easily find the best music for their videos, significantly reducing the effort required for video production. In addition, the generated music and recommended songs are perfectly matched to the concept of the user's video, providing content that is attractive to viewers. This allows the audio-visual learning system to automatically generate or recommend the best music for the user's videos.

[0029] The audio-video correspondence learning system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit uploads videos taken by a user. The videos taken by a user include, for example, file formats such as MP4, AVI, and MOV, as well as lengths and resolutions, but are not limited to such examples. The reception unit can upload, for example, videos taken by a user with a smartphone or a camera. The reception unit can also allow a user to upload multiple videos at once. The analysis unit uses a generation AI to analyze the audio and video parts of the video uploaded by the reception unit and learns the correspondence between the audio and video. The analysis unit learns the correspondence between the audio and video, for example, using contrastive learning. Contrastive learning is a technology that generates pairs of audio and video and calculates the similarity of the pairs to learn the correspondence between the audio and video. For example, the analysis unit learns the correspondence based on the match of timestamps and scene matches between the audio and video. The generation unit uses a generation AI to generate music based on the correspondence learned by the analysis unit. The generation unit generates music using an algorithm such as a GAN (generative anti-network), an RNN (recurrent neural network), or a Transformer. The generation unit can automatically generate music that matches the concept of the video, for example. The generation unit can also recommend the optimal music from an existing music database. The provision unit provides the music generated by the generation unit to the user. The provision unit can provide the music by, for example, streaming, download, notification, or other methods. The provision unit can, for example, directly download the generated music to the user's device. The provision unit can also provide the generated music through a streaming service. Thereby, the audio-video compatible learning system according to the embodiment can automatically generate or recommend the optimal music for the user's video. A part or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the provision unit can provide the music using an AI model that notifies the user's device of the generated music.

[0030] The reception unit uploads videos taken by the user. The videos taken by the user include, for example, file formats such as MP4, AVI, and MOV, as well as length and resolution, but are not limited to such examples. The reception unit can upload, for example, videos taken by the user with a smartphone or a camera. The reception unit can also allow the user to upload multiple videos at once. Specifically, the reception unit provides a function for the user to upload videos through a dedicated application or web interface. The user can easily upload a video by simply starting an application, selecting a video file, and pressing an upload button. Furthermore, the reception unit also has a function to automatically obtain metadata (e.g., shooting date and time, location, device information, etc.) of the uploaded video and store it in a database. This enables processing that takes into account the characteristics and context of the video in subsequent analysis and generation processes. The reception unit also has a function to check the quality of the uploaded video and compress or convert it as necessary. For example, videos with low resolution or videos with different file formats are automatically converted to the optimal format so that the analysis unit can efficiently process them. Furthermore, the reception unit also has a security function to protect the privacy of the videos uploaded by the user. For example, video data is encrypted so that only users with the appropriate access rights can view or download it, allowing users to upload videos and use the system with peace of mind.

[0031] The analysis unit uses the generation AI to analyze the audio and video parts of the video uploaded by the reception unit, and learns the correspondence between audio and video. The analysis unit learns the correspondence between audio and video, for example, using contrastive learning. Contrastive learning is a technology that learns the correspondence between audio and video by generating pairs of audio and video and calculating the similarity of those pairs. For example, the analysis unit learns the correspondence based on the match of timestamps and scenes of audio and video. Specifically, the analysis unit extracts audio data corresponding to each frame of the video and treats these data as pairs. Next, the generation AI extracts features of these pairs and calculates the similarity. For example, acoustic features (e.g., Mel Frequency Cepstrum Coefficients (MFCC) and spectrograms) are extracted from the audio data, and image features (e.g., edge detection and color histograms) are extracted from the video data. The correspondence between audio and video is learned using these features. Furthermore, the analysis unit improves the generalization performance of the model by using data augmentation technology in the learning process. For example, noise may be added to audio data, or video data may be rotated or scaled, making it possible to handle a variety of data. The analysis unit can also use the trained model to quickly analyze the correspondence between audio and video of a newly uploaded video. This allows the analysis unit to analyze the correspondence between audio and video of a video uploaded by a user with high accuracy and provide basic data for music generation by the generation unit.

[0032] The generation unit uses a generative AI to generate music based on the correspondence learned by the analysis unit. The generation unit generates music using algorithms such as GAN (generative anti-network), RNN (recurrent neural network), and Transformer. The generation unit can automatically generate music that matches the concept of a video, for example. The generation unit can also recommend optimal music from an existing music database. Specifically, the generation unit receives audio and video correspondence data provided by the analysis unit as input and generates music based on this. For example, when using GAN, the generation unit trains the generation network and the identification network so that the generation network can generate realistic music. The generation network receives random noise vectors as input and converts them into music data. Meanwhile, the identification network plays a role in distinguishing between generated music and actual music data. This allows the generation network to generate realistic music that deceives the identification network. Also, when using RNN or Transformer, the generation unit generates music while taking into account the temporal structure of the music. For example, the RNN can generate new notes while retaining information on past notes and rhythms. Transformer can capture long-term dependencies in music using a self-attention mechanism. This allows the generator to generate music that matches the concept and atmosphere of the video with high accuracy. Furthermore, the generator can customize the music by reflecting the user's preferences and feedback. For example, if a user prefers music of a certain genre or tempo, the generator can generate music taking these factors into account. This allows the generator to provide the best music according to the user's needs.

[0033] The providing unit provides the music generated by the generating unit to the user. The providing unit can provide the music by, for example, streaming, downloading, notification, or other methods. The providing unit can, for example, directly download the generated music to the user's device. The providing unit can also provide the generated music through a streaming service. Specifically, the providing unit uploads the generated music file to a cloud server so that the user can access it. The user can stream or download the generated music through a dedicated application or web interface. Furthermore, the providing unit also has a function of notifying the user of the generated music. For example, when music is generated, a push notification is sent to the user's smartphone and a download link or streaming link for the music is provided. Furthermore, the providing unit can collect user feedback and continuously improve the quality of the generated music and the method of providing it. For example, when the user provides an evaluation or comment on the music, the providing unit analyzes these feedbacks and reflects them in the next music generation and provision. Furthermore, the providing unit also provides a function of sharing the generated music with other users through social media or a sharing platform. This allows the user to easily share the generated music with friends and family. Through these functions, the providing unit can provide music to the user quickly and conveniently, improving the user experience.

[0034] The analysis unit can learn the correspondence between audio and video using contrastive learning. The analysis unit can learn the correspondence between audio and video using, for example, contrastive learning. Contrastive learning is a technology that learns the correspondence between audio and video by generating pairs of audio and video and calculating the similarity of the pairs. For example, the analysis unit learns the correspondence based on the match of timestamps or scenes of audio and video. As a result, the correspondence between audio and video can be learned with high accuracy by using contrastive learning. A part or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can learn the correspondence using an AI model that generates pairs of audio and video and calculates the similarity of the pairs.

[0035] The generation unit can generate music using a generation AI. The generation unit generates music using, for example, a generation AI. The generation AI generates music using, for example, an algorithm such as a GAN (generative artificial network), an RNN (recurrent neural network), or a Transformer. For example, the generation unit can automatically generate music that matches the concept of the video. As a result, by using the generation AI, music that matches the concept of the video can be automatically generated. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can generate music using an AI model that generates music that matches the concept of the video.

[0036] The generation unit can recommend an appropriate song from an existing music database. The generation unit, for example, recommends an appropriate song from an existing music database. The appropriate song is selected based on criteria such as genre, tempo, and mood. For example, the generation unit can recommend a song that matches the concept of the video from an existing music database. This makes it possible to provide optimal music for the user's video by recommending the optimal song from the existing music database. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can recommend a song using an AI model that recommends an appropriate song from an existing music database.

[0037] The providing unit can provide the generated music to the user. The providing unit, for example, provides the generated music to the user. The provision is performed, for example, by a method such as streaming, downloading, or notification. For example, the providing unit can directly download the generated music to the user's device. The providing unit can also provide the generated music through a streaming service. In this way, the user can easily create a video by providing the generated music to the user. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can provide the music using an AI model that notifies the user's device of the generated music.

[0038] The reception unit can analyze the user's past upload history and select an appropriate upload method. The reception unit, for example, analyzes the user's past upload history and selects an appropriate upload method. The upload history includes information such as the past upload date and time, content, and success rate. For example, the reception unit preferentially suggests an upload method (Wi-Fi, mobile data, etc.) that the user has frequently used in the past. The reception unit can also analyze the user's past upload time zone and perform uploading at the optimal time zone. Furthermore, the reception unit can also select the most stable method based on the user's past upload success rate. In this way, the optimal upload method can be selected by analyzing the past upload history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can select an upload method using an AI model that inputs the user's past upload history and outputs the optimal upload method.

[0039] The reception unit can filter based on the user's current project and field of interest when uploading a video. The reception unit, for example, filters based on the user's current project and field of interest when uploading a video. The project includes specific content and types such as, for example, a business project, an academic project, and a personal project. The field of interest includes specific content and identification methods such as, for example, a hobby, a field of expertise, and a history of past activities. For example, the reception unit filters so that the user uploads only videos related to the project currently in progress. The reception unit can also preferentially upload videos with high relevance based on the user's field of interest. Furthermore, the reception unit can automatically select related videos with reference to the user's past project history. As a result, videos with high relevance can be uploaded by filtering based on the user's project and field of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can perform filtering using an AI model that inputs the user's project and field of interest and outputs videos with high relevance.

[0040] The reception unit can preferentially upload videos with high relevance in consideration of the geographical location information of the user when uploading a video. For example, the reception unit preferentially uploads videos with high relevance in consideration of the geographical location information of the user when uploading a video. The geographical location information includes specific acquisition methods and usage methods such as GPS data, IP address, and location information services. Highly relevant videos are selected based on criteria such as geographical proximity, cultural relevance, and user interests. For example, when the user is in a specific area, the reception unit preferentially uploads videos related to the area. In addition, when the user is traveling, the reception unit can also preferentially upload videos related to the travel destination. Furthermore, when the user is at home, the reception unit can also preferentially upload videos related to the area around the user's home. In this way, by considering the geographical location information of the user, videos with high relevance can be preferentially uploaded. Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can upload videos using an AI model that inputs the geographical location information of the user and outputs videos with high relevance.

[0041] The reception unit can analyze the social media activity of the user at the time of uploading a video and upload a related video. For example, the reception unit analyzes the social media activity of the user at the time of uploading a video and uploads a related video. The social media activity includes, for example, specific content such as the post content, the number of likes, and the reaction of followers, and an analysis method. The related video is selected based on criteria such as the same topic, the same hashtag, and the same follower demographic. For example, the reception unit preferentially uploads videos related to the content recently shared by the user on social media. The reception unit can also upload related videos based on the interests of the user's followers on social media. Furthermore, the reception unit can analyze the user's social media activity history and upload the most relevant video. In this way, the user's social media activity can be analyzed to upload a highly relevant video. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can upload a video using an AI model that inputs the user's social media activity and outputs a related video.

[0042] The analysis unit can adjust the level of detail of the analysis based on the importance of the video during analysis. The analysis unit adjusts the level of detail of the analysis based on the importance of the video during analysis, for example. The importance of the video includes specific evaluation criteria and methods such as the number of views, user evaluation, and video content. The level of detail of the analysis includes specific adjustment methods and criteria such as the depth of the analysis, resources used, and analysis time. For example, the analysis unit performs a detailed analysis on a video with high importance, and analyzes the fine correspondence between audio and video. The analysis unit can also perform a simplified analysis on a video with low importance, and analyze only the main correspondence. Furthermore, the analysis unit can perform a balanced analysis on a video with medium importance, and analyze the necessary correspondence. As a result, efficient analysis can be performed by adjusting the level of detail of the analysis based on the importance of the video. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can adjust the level of detail of the analysis using an AI model that inputs the importance of the video and outputs the level of detail of the analysis.

[0043] The analysis unit can apply different analysis algorithms depending on the category of the video during analysis. The analysis unit, for example, applies different analysis algorithms depending on the category of the video during analysis. The category of the video includes specific classification methods and standards such as entertainment, education, and news. The analysis algorithm includes specific types and application methods such as image analysis algorithms, audio analysis algorithms, and text analysis algorithms. For example, the analysis unit applies an analysis algorithm that emphasizes visually stimulating elements to entertainment videos. In addition, the analysis unit can also apply an analysis algorithm that emphasizes the accuracy of information to educational videos. Furthermore, the analysis unit can apply an analysis algorithm that emphasizes reality to documentary videos. This allows more appropriate analysis to be performed by applying an analysis algorithm depending on the category of the video. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that inputs the category of the video and outputs an appropriate analysis algorithm.

[0044] The analysis unit can determine the priority of the analysis based on the submission time of the video during the analysis. The analysis unit, for example, determines the priority of the analysis based on the submission time of the video during the analysis. The submission time includes, for example, a specific acquisition method or usage method such as the submission date and time, the submission deadline, and the submission frequency. The priority includes, for example, a specific decision criterion or method such as the early submission time, the importance, and the user's request. For example, the analysis unit preferentially analyzes the most recently submitted video. In addition, the analysis unit can also analyze videos that have been submitted earlier at a later time. Furthermore, the analysis unit can also preferentially analyze videos that have been submitted at a later time. In this way, efficient analysis can be performed by determining the priority of the analysis based on the submission time of the video. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can determine the priority of the analysis using an AI model that inputs the submission time of the video and outputs the priority of the analysis.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the videos during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of the videos during analysis. The relevance includes specific evaluation criteria and methods such as similarity of content, user interests, and past behavior. The order includes specific decision criteria and methods such as high relevance, high importance, and earliest submission. For example, the analysis unit prioritizes analysis of videos with high relevance. The analysis unit can also analyze videos with low relevance later. Furthermore, the analysis unit can analyze videos with medium relevance in a balanced manner. This allows efficient analysis by adjusting the order of analysis based on the relevance of the videos. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can adjust the order of analysis using an AI model that inputs the relevance of the videos and outputs the order of analysis.

[0046] The generation unit can adjust the level of detail of the generation based on the importance of the video when generating music. The generation unit adjusts the level of detail of the generation based on the importance of the video when generating music, for example. The importance of the video includes specific evaluation criteria and methods such as the number of views, user evaluation, and video content. The level of detail of the generation includes specific adjustment methods and criteria such as the depth of the generation, resources used, and generation time. For example, the generation unit generates detailed music for a video with high importance. In addition, the generation unit can also generate simplified music for a video with low importance. Furthermore, the generation unit can also generate balanced music for a video with medium importance. As a result, efficient music generation can be performed by adjusting the level of detail of the generation based on the importance of the video. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate music using an AI model that inputs the importance of the video and outputs the level of detail of the generation.

[0047] The generation unit can apply different generation algorithms according to the category of the video when generating music. For example, the generation unit applies different generation algorithms according to the category of the video when generating music. The video category includes specific classification methods and standards such as entertainment, education, and news. The generation algorithm includes specific types and application methods such as music generation algorithms, text generation algorithms, and image generation algorithms. For example, the generation unit applies an algorithm that generates visually stimulating music to entertainment videos. In addition, the generation unit can also apply an algorithm that generates music that emphasizes the accuracy of information to educational videos. Furthermore, the generation unit can also apply an algorithm that generates music that emphasizes reality to documentary videos. In this way, more appropriate music can be generated by applying the generation algorithm according to the category of the video. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate music using an AI model that inputs the category of the video and outputs an appropriate generation algorithm.

[0048] The generation unit can determine the priority of generation based on the submission time of the video when generating music. The generation unit, for example, determines the priority of generation based on the submission time of the video when generating music. The submission time includes, for example, a specific acquisition method or usage method such as the submission date and time, the submission deadline, and the submission frequency. The priority includes, for example, a specific decision criterion or method such as the earlyness of the submission time, the importance, and the user's request. For example, the generation unit generates music preferentially for a video that was submitted recently. In addition, the generation unit can also generate music later for a video that was submitted earlier. Furthermore, the generation unit can also generate music preferentially for a video whose submission time is related to a specific event. In this way, efficient music generation can be performed by determining the priority of generation based on the submission time of the video. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate music using an AI model that inputs the submission time of the video and outputs the priority of generation.

[0049] The generation unit can adjust the order of generation based on the relevance of the videos when generating music. The generation unit adjusts the order of generation based on the relevance of the videos when generating music, for example. The relevance includes specific evaluation criteria and methods such as similarity of content, user interests, and past behavior. The order includes specific decision criteria and methods such as order of relevance, order of importance, and order of earliest submission. For example, the generation unit generates music preferentially for videos with high relevance. The generation unit can also generate music later for videos with low relevance. Furthermore, the generation unit can generate music in a balanced manner for videos with medium relevance. As a result, efficient music generation can be performed by adjusting the order of generation based on the relevance of the videos. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate music using an AI model that inputs the relevance of the videos and outputs the order of generation.

[0050] The providing unit can select the optimal providing method by referring to the user's past music selection history when providing music. For example, the providing unit selects the optimal providing method by referring to the user's past music selection history when providing music. The music selection history includes specific contents and analysis methods such as, for example, past selection dates and times, selected songs, and selection reasons. The providing method includes specific contents and selection methods such as, for example, streaming, downloading, and notification. For example, the providing unit selects the optimal providing method based on the genre of music that the user has previously selected. In addition, the providing unit can also provide a specific artist or album preferentially from the user's past music selection history. Furthermore, the providing unit can analyze the user's past music selection history and provide the most relevant music. In this way, the optimal music providing method can be selected by referring to the past music selection history. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can provide music using an AI model that inputs the user's past music selection history and outputs the optimal providing method.

[0051] The providing unit can select the optimal providing method in consideration of the device information of the user when providing music. For example, the providing unit selects the optimal providing method in consideration of the device information of the user when providing music. The device information includes specific contents such as the type of device used by the user, the screen size, and the version of the OS. The providing method includes specific contents and selection methods such as streaming, downloading, and notification. For example, when the user is using a smartphone, the providing unit provides a display method that matches the screen size. In addition, when the user is using a tablet, the providing unit can also provide a display method optimized for a large screen. Furthermore, when the user is using a smartwatch, the providing unit can also provide a display method that is simple and highly visible. This makes it possible to select the optimal music providing method by considering the device information of the user. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can provide music using an AI model that inputs the device information of the user and outputs the optimal providing method.

[0052] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0053] The reception unit can analyze the user's past video upload history and suggest the optimal upload timing. For example, if a video uploaded by the user in the past during a specific time period has received many views, the reception unit can preferentially suggest that time period. The reception unit can also select the most stable upload method based on the success rate of videos the user has uploaded in the past. Furthermore, the reception unit can also suggest the optimal file format and resolution based on the user's past upload history. This allows the user to make more effective video uploads by taking advantage of past successful experiences.

[0054] When generating music, the generation unit can apply different generation algorithms depending on the category of the video. For example, an algorithm that generates visually stimulating music can be applied to entertainment videos. Also, an algorithm that generates music that emphasizes accuracy of information can be applied to educational videos. Furthermore, an algorithm that generates music that emphasizes reality can be applied to documentary videos. In this way, more appropriate music can be generated by applying a generation algorithm depending on the category of the video.

[0055] The reception unit can prioritize uploading highly relevant videos by taking into consideration the geographical location information of the user. For example, when the user is in a specific area, videos related to that area can be prioritized for upload. Also, when the user is traveling, videos related to the travel destination can be prioritized for upload. Furthermore, when the user is at home, videos related to the area around the home can be prioritized for upload. In this way, by taking into consideration the geographical location information of the user, highly relevant videos can be prioritized for upload.

[0056] During the analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the video. For example, a detailed analysis can be performed on a video with high importance, and the minute correspondence between audio and video can be analyzed. Also, a simplified analysis can be performed on a video with low importance, and only the main correspondence can be analyzed. Furthermore, a balanced analysis can be performed on a video with medium importance, and the necessary correspondence can be analyzed. In this way, an efficient analysis can be performed by adjusting the level of detail of the analysis based on the importance of the video.

[0057] When generating music, the generation unit can determine a generation priority based on the submission date of the video. For example, music can be generated preferentially for recently submitted videos. Also, music can be generated later for videos submitted earlier. Furthermore, music can be generated preferentially for videos submitted related to a specific event. In this way, efficient music generation can be achieved by determining the generation priority based on the submission date of the video.

[0058] The providing unit can select the optimal music providing method by referring to the user's past music selection history. For example, the optimal music providing method is selected based on the genre of music that the user has previously selected. Also, it is possible to provide specific artists or albums with priority based on the user's past music selection history. Furthermore, it is possible to analyze the user's past music selection history and provide the most relevant music. In this way, the optimal music providing method can be selected by referring to the past music selection history.

[0059] The process flow of the first embodiment will be briefly described below.

[0060] Step 1: The reception unit uploads a video taken by a user. The video taken by a user may include, but is not limited to, a file format such as MP4, AVI, or MOV, a length, or a resolution. The reception unit can upload, for example, a video taken by a user with a smartphone or a camera. The reception unit can also allow a user to upload multiple videos at once. Step 2: The analysis unit uses the generation AI to analyze the audio and video parts of the video uploaded by the reception unit, and learns the correspondence between audio and video. The analysis unit learns the correspondence between audio and video, for example, using contrastive learning. Contrastive learning is a technology that learns the correspondence between audio and video by generating pairs of audio and video and calculating the similarity between those pairs. For example, the analysis unit learns the correspondence based on matches between timestamps and scenes of audio and video. Step 3: The generator uses a generative AI to generate music based on the correspondence learned by the analyzer. The generator generates music using algorithms such as GAN (generative artificial network), RNN (recurrent neural network), and Transformer. The generator can automatically generate music that matches the concept of the video, for example. The generator can also recommend optimal music from an existing music database. Step 4: The providing unit provides the music generated by the generating unit to the user. The providing unit can provide the music by, for example, streaming, downloading, notification, or other methods. For example, the providing unit can directly download the generated music to the user's device. The providing unit can also provide the generated music through a streaming service.

[0061] (Example 2) The audio-video correspondence learning system according to the embodiment of the present invention is a system that generates music that matches the concept of a user by simply uploading multiple videos taken by the user, or recommends the most suitable existing music. This system is a technology that uses countless videos that exist around the world and uses contrastive learning for the audio and video parts to learn the correspondence between audio and video. For example, it is possible to generate music that matches the concept or recommend the most suitable existing music by simply uploading multiple videos taken by the user. Specifically, first, the user uploads multiple videos taken by the user. Next, the system analyzes the audio and video parts of the uploaded videos using contrastive learning to learn the correspondence between audio and video. This learning allows the system to generate music that matches the concept of the video. It is also possible to recommend the most suitable music from an existing music database. For example, if a user uploads a video of a trip, the system analyzes the video and audio of the video and generates music that matches the atmosphere of the trip. In addition, the system also recommends music that is suitable for the trip from an existing music database. This allows users to easily create videos by simply uploading multiple videos and still images. This technology allows users to easily find the best music for their videos, significantly reducing the effort required for video production. In addition, the generated music and recommended songs are perfectly matched to the concept of the user's video, providing content that is attractive to viewers. This allows the audio-visual learning system to automatically generate or recommend the best music for the user's videos.

[0062] The audio-video correspondence learning system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit uploads videos taken by a user. The videos taken by a user include, for example, file formats such as MP4, AVI, and MOV, as well as lengths and resolutions, but are not limited to such examples. The reception unit can upload, for example, videos taken by a user with a smartphone or a camera. The reception unit can also allow a user to upload multiple videos at once. The analysis unit uses a generation AI to analyze the audio and video parts of the video uploaded by the reception unit and learns the correspondence between the audio and video. The analysis unit learns the correspondence between the audio and video, for example, using contrastive learning. Contrastive learning is a technology that generates pairs of audio and video and calculates the similarity of the pairs to learn the correspondence between the audio and video. For example, the analysis unit learns the correspondence based on the match of timestamps and scene matches between the audio and video. The generation unit uses a generation AI to generate music based on the correspondence learned by the analysis unit. The generation unit generates music using an algorithm such as a GAN (generative anti-network), an RNN (recurrent neural network), or a Transformer. The generation unit can automatically generate music that matches the concept of the video, for example. The generation unit can also recommend the optimal music from an existing music database. The provision unit provides the music generated by the generation unit to the user. The provision unit can provide the music by, for example, streaming, download, notification, or other methods. The provision unit can, for example, directly download the generated music to the user's device. The provision unit can also provide the generated music through a streaming service. Thereby, the audio-video compatible learning system according to the embodiment can automatically generate or recommend the optimal music for the user's video. A part or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the provision unit can provide the music using an AI model that notifies the user's device of the generated music.

[0063] The reception unit uploads videos taken by the user. The videos taken by the user include, for example, file formats such as MP4, AVI, and MOV, as well as length and resolution, but are not limited to such examples. The reception unit can upload, for example, videos taken by the user with a smartphone or a camera. The reception unit can also allow the user to upload multiple videos at once. Specifically, the reception unit provides a function for the user to upload videos through a dedicated application or web interface. The user can easily upload a video by simply starting an application, selecting a video file, and pressing an upload button. Furthermore, the reception unit also has a function to automatically obtain metadata (e.g., shooting date and time, location, device information, etc.) of the uploaded video and store it in a database. This enables processing that takes into account the characteristics and context of the video in subsequent analysis and generation processes. The reception unit also has a function to check the quality of the uploaded video and compress or convert it as necessary. For example, videos with low resolution or videos with different file formats are automatically converted to the optimal format so that the analysis unit can efficiently process them. Furthermore, the reception unit also has a security function to protect the privacy of the videos uploaded by the user. For example, video data is encrypted so that only users with the appropriate access rights can view or download it, allowing users to upload videos and use the system with peace of mind.

[0064] The analysis unit uses the generation AI to analyze the audio and video parts of the video uploaded by the reception unit, and learns the correspondence between audio and video. The analysis unit learns the correspondence between audio and video, for example, using contrastive learning. Contrastive learning is a technology that learns the correspondence between audio and video by generating pairs of audio and video and calculating the similarity of those pairs. For example, the analysis unit learns the correspondence based on the match of timestamps and scenes of audio and video. Specifically, the analysis unit extracts audio data corresponding to each frame of the video and treats these data as pairs. Next, the generation AI extracts features of these pairs and calculates the similarity. For example, acoustic features (e.g., Mel Frequency Cepstrum Coefficients (MFCC) and spectrograms) are extracted from the audio data, and image features (e.g., edge detection and color histograms) are extracted from the video data. The correspondence between audio and video is learned using these features. Furthermore, the analysis unit improves the generalization performance of the model by using data augmentation technology in the learning process. For example, noise may be added to audio data, or video data may be rotated or scaled, making it possible to handle a variety of data. The analysis unit can also use the trained model to quickly analyze the correspondence between audio and video of a newly uploaded video. This allows the analysis unit to analyze the correspondence between audio and video of a video uploaded by a user with high accuracy and provide basic data for music generation by the generation unit.

[0065] The generation unit uses a generative AI to generate music based on the correspondence learned by the analysis unit. The generation unit generates music using algorithms such as GAN (generative anti-network), RNN (recurrent neural network), and Transformer. The generation unit can automatically generate music that matches the concept of a video, for example. The generation unit can also recommend optimal music from an existing music database. Specifically, the generation unit receives audio and video correspondence data provided by the analysis unit as input and generates music based on this. For example, when using GAN, the generation unit trains the generation network and the identification network so that the generation network can generate realistic music. The generation network receives random noise vectors as input and converts them into music data. Meanwhile, the identification network plays a role in distinguishing between generated music and actual music data. This allows the generation network to generate realistic music that deceives the identification network. Also, when using RNN or Transformer, the generation unit generates music while taking into account the temporal structure of the music. For example, the RNN can generate new notes while retaining information on past notes and rhythms. Transformer can capture long-term dependencies in music using a self-attention mechanism. This allows the generator to generate music that matches the concept and atmosphere of the video with high accuracy. Furthermore, the generator can customize the music by reflecting the user's preferences and feedback. For example, if a user prefers music of a certain genre or tempo, the generator can generate music taking these factors into account. This allows the generator to provide the best music according to the user's needs.

[0066] The providing unit provides the music generated by the generating unit to the user. The providing unit can provide the music by, for example, streaming, downloading, notification, or other methods. The providing unit can, for example, directly download the generated music to the user's device. The providing unit can also provide the generated music through a streaming service. Specifically, the providing unit uploads the generated music file to a cloud server so that the user can access it. The user can stream or download the generated music through a dedicated application or web interface. Furthermore, the providing unit also has a function of notifying the user of the generated music. For example, when music is generated, a push notification is sent to the user's smartphone and a download link or streaming link for the music is provided. Furthermore, the providing unit can collect user feedback and continuously improve the quality of the generated music and the method of providing it. For example, when the user provides an evaluation or comment on the music, the providing unit analyzes these feedbacks and reflects them in the next music generation and provision. Furthermore, the providing unit also provides a function of sharing the generated music with other users through social media or a sharing platform. This allows the user to easily share the generated music with friends and family. Through these functions, the providing unit can provide music to the user quickly and conveniently, improving the user experience.

[0067] The analysis unit can learn the correspondence between audio and video using contrastive learning. The analysis unit can learn the correspondence between audio and video using, for example, contrastive learning. Contrastive learning is a technology that learns the correspondence between audio and video by generating pairs of audio and video and calculating the similarity of the pairs. For example, the analysis unit learns the correspondence based on the match of timestamps or scenes of audio and video. As a result, the correspondence between audio and video can be learned with high accuracy by using contrastive learning. A part or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can learn the correspondence using an AI model that generates pairs of audio and video and calculates the similarity of the pairs.

[0068] The generation unit can generate music using a generation AI. The generation unit generates music using, for example, a generation AI. The generation AI generates music using, for example, an algorithm such as a GAN (generative artificial network), an RNN (recurrent neural network), or a Transformer. For example, the generation unit can automatically generate music that matches the concept of the video. As a result, by using the generation AI, music that matches the concept of the video can be automatically generated. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can generate music using an AI model that generates music that matches the concept of the video.

[0069] The generation unit can recommend an appropriate song from an existing music database. The generation unit, for example, recommends an appropriate song from an existing music database. The appropriate song is selected based on criteria such as genre, tempo, and mood. For example, the generation unit can recommend a song that matches the concept of the video from an existing music database. This makes it possible to provide optimal music for the user's video by recommending the optimal song from the existing music database. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can recommend a song using an AI model that recommends an appropriate song from an existing music database.

[0070] The providing unit can provide the generated music to the user. The providing unit, for example, provides the generated music to the user. The provision is performed, for example, by a method such as streaming, downloading, or notification. For example, the providing unit can directly download the generated music to the user's device. The providing unit can also provide the generated music through a streaming service. In this way, the user can easily create a video by providing the generated music to the user. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can provide the music using an AI model that notifies the user's device of the generated music.

[0071] The reception unit can estimate the user's emotion and adjust the timing of uploading the video based on the estimated user's emotion. The reception unit, for example, estimates the user's emotion and adjusts the timing of uploading the video based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI. For example, the reception unit uploads the video immediately when the user is relaxed. In addition, when the user is feeling stressed, the reception unit can postpone the upload and encourage the user to upload when he or she has calmed down. Furthermore, when the user is excited, the reception unit can quickly upload the video and complete the process before the user's excitement cools down. Thereby, by adjusting the timing of uploading the video according to the user's emotion, the video can be uploaded at a more appropriate timing. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can upload videos using an AI model that estimates a user's emotions and adjusts the upload timing based on the estimated emotions.

[0072] The reception unit can analyze the user's past upload history and select an appropriate upload method. The reception unit, for example, analyzes the user's past upload history and selects an appropriate upload method. The upload history includes information such as the past upload date and time, content, and success rate. For example, the reception unit preferentially suggests an upload method (Wi-Fi, mobile data, etc.) that the user has frequently used in the past. The reception unit can also analyze the user's past upload time zone and perform uploading at the optimal time zone. Furthermore, the reception unit can also select the most stable method based on the user's past upload success rate. In this way, the optimal upload method can be selected by analyzing the past upload history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can select an upload method using an AI model that inputs the user's past upload history and outputs the optimal upload method.

[0073] The reception unit can filter based on the user's current project and field of interest when uploading a video. The reception unit, for example, filters based on the user's current project and field of interest when uploading a video. The project includes specific content and types such as, for example, a business project, an academic project, and a personal project. The field of interest includes specific content and identification methods such as, for example, a hobby, a field of expertise, and a history of past activities. For example, the reception unit filters so that the user uploads only videos related to the project currently in progress. The reception unit can also preferentially upload videos with high relevance based on the user's field of interest. Furthermore, the reception unit can automatically select related videos with reference to the user's past project history. As a result, videos with high relevance can be uploaded by filtering based on the user's project and field of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can perform filtering using an AI model that inputs the user's project and field of interest and outputs videos with high relevance.

[0074] The reception unit can estimate the user's emotion and determine the priority of the videos to be uploaded based on the estimated user's emotion. The reception unit, for example, estimates the user's emotion and determines the priority of the videos to be uploaded based on the estimated user's emotion. The emotion estimation is realized by 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. For example, when the user is relaxed, the reception unit preferentially uploads videos with low importance. In addition, when the user is stressed, the reception unit can also preferentially upload videos with high importance. Furthermore, when the user is excited, the reception unit can also preferentially upload videos with high entertainment value. In this way, by determining the priority of the videos according to the user's emotion, it is possible to preferentially upload more appropriate videos. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can upload videos using an AI model that estimates the user's emotion and determines the priority of the videos to be uploaded based on the estimated emotion.

[0075] The reception unit can preferentially upload videos with high relevance in consideration of the geographical location information of the user when uploading a video. For example, the reception unit preferentially uploads videos with high relevance in consideration of the geographical location information of the user when uploading a video. The geographical location information includes specific acquisition methods and usage methods such as GPS data, IP address, and location information services. Highly relevant videos are selected based on criteria such as geographical proximity, cultural relevance, and user interests. For example, when the user is in a specific area, the reception unit preferentially uploads videos related to the area. In addition, when the user is traveling, the reception unit can also preferentially upload videos related to the travel destination. Furthermore, when the user is at home, the reception unit can also preferentially upload videos related to the area around the user's home. In this way, by considering the geographical location information of the user, videos with high relevance can be preferentially uploaded. Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can upload videos using an AI model that inputs the geographical location information of the user and outputs videos with high relevance.

[0076] The reception unit can analyze the social media activity of the user at the time of uploading a video and upload a related video. For example, the reception unit analyzes the social media activity of the user at the time of uploading a video and uploads a related video. The social media activity includes, for example, specific content such as the post content, the number of likes, and the reaction of followers, and an analysis method. The related video is selected based on criteria such as the same topic, the same hashtag, and the same follower demographic. For example, the reception unit preferentially uploads videos related to the content recently shared by the user on social media. The reception unit can also upload related videos based on the interests of the user's followers on social media. Furthermore, the reception unit can analyze the user's social media activity history and upload the most relevant video. In this way, the user's social media activity can be analyzed to upload a highly relevant video. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can upload a video using an AI model that inputs the user's social media activity and outputs a related video.

[0077] The analysis unit can estimate the user's emotion and adjust the analysis method of the correspondence between the voice and the video based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the analysis method of the correspondence between the voice and the video based on the estimated user's emotion. The emotion estimation is realized by 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. For example, when the user is relaxed, the analysis unit performs a detailed analysis to analyze the fine correspondence between the voice and the video. In addition, when the user is in a hurry, the analysis unit can also perform a simplified analysis and analyze only the main correspondence. Furthermore, when the user is excited, the analysis unit can also emphasize visually stimulating elements for analysis. This allows a more appropriate analysis to be performed by adjusting the analysis method according to the user's emotion. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can analyze the correspondence between audio and video using an AI model that infers a user's emotions and adjusts the analysis method based on the inferred emotions.

[0078] The analysis unit can adjust the level of detail of the analysis based on the importance of the video during analysis. The analysis unit adjusts the level of detail of the analysis based on the importance of the video during analysis, for example. The importance of the video includes specific evaluation criteria and methods such as the number of views, user evaluation, and video content. The level of detail of the analysis includes specific adjustment methods and criteria such as the depth of the analysis, resources used, and analysis time. For example, the analysis unit performs a detailed analysis on a video with high importance, and analyzes the fine correspondence between audio and video. The analysis unit can also perform a simplified analysis on a video with low importance, and analyze only the main correspondence. Furthermore, the analysis unit can perform a balanced analysis on a video with medium importance, and analyze the necessary correspondence. As a result, efficient analysis can be performed by adjusting the level of detail of the analysis based on the importance of the video. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can adjust the level of detail of the analysis using an AI model that inputs the importance of the video and outputs the level of detail of the analysis.

[0079] The analysis unit can apply different analysis algorithms depending on the category of the video during analysis. The analysis unit, for example, applies different analysis algorithms depending on the category of the video during analysis. The category of the video includes specific classification methods and standards such as entertainment, education, and news. The analysis algorithm includes specific types and application methods such as image analysis algorithms, audio analysis algorithms, and text analysis algorithms. For example, the analysis unit applies an analysis algorithm that emphasizes visually stimulating elements to entertainment videos. In addition, the analysis unit can also apply an analysis algorithm that emphasizes the accuracy of information to educational videos. Furthermore, the analysis unit can apply an analysis algorithm that emphasizes reality to documentary videos. This allows more appropriate analysis to be performed by applying an analysis algorithm depending on the category of the video. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that inputs the category of the video and outputs an appropriate analysis algorithm.

[0080] The analysis unit can estimate the user's emotion and adjust the display method of the analysis result based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the display method of the analysis result based on the estimated user's emotion. The emotion estimation is realized by 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. For example, the analysis unit provides a simple and highly visible display method when the user is nervous. In addition, the analysis unit can also provide a display method including detailed information when the user is relaxed. Furthermore, the analysis unit can also provide a display method that focuses on the main points when the user is in a hurry. This allows for more appropriate display by adjusting the display method of the analysis result according to the user's emotion. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can display the analysis result using an AI model that estimates the user's emotion and adjusts the display method based on the estimated emotion.

[0081] The analysis unit can determine the priority of the analysis based on the submission time of the video during the analysis. The analysis unit, for example, determines the priority of the analysis based on the submission time of the video during the analysis. The submission time includes, for example, a specific acquisition method or usage method such as the submission date and time, the submission deadline, and the submission frequency. The priority includes, for example, a specific decision criterion or method such as the early submission time, the importance, and the user's request. For example, the analysis unit preferentially analyzes the most recently submitted video. In addition, the analysis unit can also analyze videos that have been submitted earlier at a later time. Furthermore, the analysis unit can also preferentially analyze videos that have been submitted at a later time. In this way, efficient analysis can be performed by determining the priority of the analysis based on the submission time of the video. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can determine the priority of the analysis using an AI model that inputs the submission time of the video and outputs the priority of the analysis.

[0082] The analysis unit can adjust the order of analysis based on the relevance of the videos during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of the videos during analysis. The relevance includes specific evaluation criteria and methods such as similarity of content, user interests, and past behavior. The order includes specific decision criteria and methods such as high relevance, high importance, and earliest submission. For example, the analysis unit prioritizes analysis of videos with high relevance. The analysis unit can also analyze videos with low relevance later. Furthermore, the analysis unit can analyze videos with medium relevance in a balanced manner. This allows efficient analysis by adjusting the order of analysis based on the relevance of the videos. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can adjust the order of analysis using an AI model that inputs the relevance of the videos and outputs the order of analysis.

[0083] The generation unit can estimate the user's emotion and adjust the expression method of the music to be generated based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the expression method of the music to be generated based on the estimated user's emotion. The emotion estimation is realized by 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. For example, the generation unit generates music at a leisurely pace when the user is relaxed. In addition, the generation unit can also generate music with a fast tempo when the user is in a hurry. Furthermore, the generation unit can generate music with a visually stimulating effect added when the user is excited. In this way, by adjusting the expression method of the music according to the user's emotion, more appropriate music can be generated. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can generate music using an AI model that estimates the user's emotion and adjusts the expression method of the music based on the estimated emotion.

[0084] The generation unit can adjust the level of detail of the generation based on the importance of the video when generating music. The generation unit adjusts the level of detail of the generation based on the importance of the video when generating music, for example. The importance of the video includes specific evaluation criteria and methods such as the number of views, user evaluation, and video content. The level of detail of the generation includes specific adjustment methods and criteria such as the depth of the generation, resources used, and generation time. For example, the generation unit generates detailed music for a video with high importance. In addition, the generation unit can also generate simplified music for a video with low importance. Furthermore, the generation unit can also generate balanced music for a video with medium importance. As a result, efficient music generation can be performed by adjusting the level of detail of the generation based on the importance of the video. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate music using an AI model that inputs the importance of the video and outputs the level of detail of the generation.

[0085] The generation unit can apply different generation algorithms according to the category of the video when generating music. For example, the generation unit applies different generation algorithms according to the category of the video when generating music. The video category includes specific classification methods and standards such as entertainment, education, and news. The generation algorithm includes specific types and application methods such as music generation algorithms, text generation algorithms, and image generation algorithms. For example, the generation unit applies an algorithm that generates visually stimulating music to entertainment videos. In addition, the generation unit can also apply an algorithm that generates music that emphasizes the accuracy of information to educational videos. Furthermore, the generation unit can also apply an algorithm that generates music that emphasizes reality to documentary videos. In this way, more appropriate music can be generated by applying the generation algorithm according to the category of the video. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate music using an AI model that inputs the category of the video and outputs an appropriate generation algorithm.

[0086] The generation unit can estimate the user's emotion and adjust the length of the music to be generated based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the length of the music to be generated based on the estimated user's emotion. The emotion estimation is realized by 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. For example, the generation unit generates longer music when the user is relaxed. In addition, the generation unit can also generate shorter music when the user is in a hurry. Furthermore, the generation unit can also generate music with a visually stimulating effect added when the user is excited. In this way, more appropriate music can be generated by adjusting the length of the music according to the user's emotion. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can generate music using an AI model that estimates the user's emotion and adjusts the length of the music based on the estimated emotion.

[0087] The generation unit can determine the priority of generation based on the submission time of the video when generating music. The generation unit, for example, determines the priority of generation based on the submission time of the video when generating music. The submission time includes, for example, a specific acquisition method or usage method such as the submission date and time, the submission deadline, and the submission frequency. The priority includes, for example, a specific decision criterion or method such as the earlyness of the submission time, the importance, and the user's request. For example, the generation unit generates music preferentially for a video that was submitted recently. In addition, the generation unit can also generate music later for a video that was submitted earlier. Furthermore, the generation unit can also generate music preferentially for a video whose submission time is related to a specific event. In this way, efficient music generation can be performed by determining the priority of generation based on the submission time of the video. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate music using an AI model that inputs the submission time of the video and outputs the priority of generation.

[0088] The generation unit can adjust the order of generation based on the relevance of the videos when generating music. The generation unit adjusts the order of generation based on the relevance of the videos when generating music, for example. The relevance includes specific evaluation criteria and methods such as similarity of content, user interests, and past behavior. The order includes specific decision criteria and methods such as order of relevance, order of importance, and order of earliest submission. For example, the generation unit generates music preferentially for videos with high relevance. The generation unit can also generate music later for videos with low relevance. Furthermore, the generation unit can generate music in a balanced manner for videos with medium relevance. As a result, efficient music generation can be performed by adjusting the order of generation based on the relevance of the videos. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate music using an AI model that inputs the relevance of the videos and outputs the order of generation.

[0089] The providing unit can estimate the user's emotion and adjust the display method of the music to be provided based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and adjusts the display method of the music to be provided based on the estimated user's emotion. The estimation of emotion is realized by 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. For example, the providing unit provides a simple and highly visible display method when the user is nervous. In addition, the providing unit can also provide a display method including detailed information when the user is relaxed. Furthermore, the providing unit can also provide a display method that focuses on the main points when the user is in a hurry. This allows a more appropriate display to be performed by adjusting the display method of the music according to the user's emotion. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide music using an AI model that estimates the user's emotion and adjusts the display method based on the estimated emotion.

[0090] The providing unit can select the optimal providing method by referring to the user's past music selection history when providing music. For example, the providing unit selects the optimal providing method by referring to the user's past music selection history when providing music. The music selection history includes specific contents and analysis methods such as, for example, past selection dates and times, selected songs, and selection reasons. The providing method includes specific contents and selection methods such as, for example, streaming, downloading, and notification. For example, the providing unit selects the optimal providing method based on the genre of music that the user has previously selected. In addition, the providing unit can also provide a specific artist or album preferentially from the user's past music selection history. Furthermore, the providing unit can analyze the user's past music selection history and provide the most relevant music. In this way, the optimal music providing method can be selected by referring to the past music selection history. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can provide music using an AI model that inputs the user's past music selection history and outputs the optimal providing method.

[0091] The providing unit can estimate the user's emotion and determine the priority of music to be provided based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and determines the priority of music to be provided based on the estimated user's emotion. The emotion estimation is realized by 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. For example, the providing unit provides relaxing music preferentially when the user is relaxed. In addition, the providing unit can also provide music with a relaxing effect preferentially when the user is stressed. Furthermore, the providing unit can also provide energetic music preferentially when the user is excited. In this way, by determining the priority of music according to the user's emotion, more appropriate music can be provided. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide music using an AI model that estimates the user's emotion and determines the priority of music based on the estimated emotion.

[0092] The providing unit can select the optimal providing method in consideration of the device information of the user when providing music. For example, the providing unit selects the optimal providing method in consideration of the device information of the user when providing music. The device information includes specific contents such as the type of device used by the user, the screen size, and the version of the OS. The providing method includes specific contents and selection methods such as streaming, downloading, and notification. For example, when the user is using a smartphone, the providing unit provides a display method that matches the screen size. In addition, when the user is using a tablet, the providing unit can also provide a display method optimized for a large screen. Furthermore, when the user is using a smartwatch, the providing unit can also provide a display method that is simple and highly visible. This makes it possible to select the optimal music providing method by considering the device information of the user. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can provide music using an AI model that inputs the device information of the user and outputs the optimal providing method.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The reception unit can analyze the user's past video upload history and suggest the optimal upload timing. For example, if a video uploaded by the user in the past during a specific time period has received many views, the reception unit can preferentially suggest that time period. The reception unit can also select the most stable upload method based on the success rate of videos the user has uploaded in the past. Furthermore, the reception unit can also suggest the optimal file format and resolution based on the user's past upload history. This allows the user to make more effective video uploads by taking advantage of past successful experiences.

[0095] The analysis unit can estimate the user's emotions and adjust the level of detail of the analysis based on the estimated emotions. For example, if the user is relaxed, a detailed analysis can be performed to analyze the subtle correspondence between audio and video. If the user is in a hurry, a simplified analysis can be performed to analyze only the main correspondence. Furthermore, if the user is excited, visually stimulating elements can be emphasized in the analysis. This allows for more appropriate analysis by adjusting the analysis method according to the user's emotions.

[0096] The generation unit can estimate the user's emotion when generating music, and adjust the tempo and rhythm of the music based on the estimated emotion. For example, if the user is relaxed, music with a relaxed tempo can be generated. If the user is in a hurry, music with a fast tempo can be generated. Furthermore, if the user is excited, music with an emphasized rhythm can be generated. In this way, more appropriate music can be generated by adjusting the way the music is expressed according to the user's emotion.

[0097] When generating music, the generation unit can apply different generation algorithms depending on the category of the video. For example, an algorithm that generates visually stimulating music can be applied to entertainment videos. Also, an algorithm that generates music that emphasizes accuracy of information can be applied to educational videos. Furthermore, an algorithm that generates music that emphasizes reality can be applied to documentary videos. In this way, more appropriate music can be generated by applying a generation algorithm depending on the category of the video.

[0098] The providing unit can estimate the user's emotion and adjust the display method of the music to be provided based on the estimated emotion. For example, if the user is nervous, a simple and highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the main points can be provided. In this way, a more appropriate display can be provided by adjusting the display method of the music according to the user's emotion.

[0099] The reception unit can prioritize uploading highly relevant videos by taking into consideration the geographical location information of the user. For example, when the user is in a specific area, videos related to that area can be prioritized for upload. Also, when the user is traveling, videos related to the travel destination can be prioritized for upload. Furthermore, when the user is at home, videos related to the area around the home can be prioritized for upload. In this way, by taking into consideration the geographical location information of the user, highly relevant videos can be prioritized for upload.

[0100] During the analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the video. For example, a detailed analysis can be performed on a video with high importance, and the minute correspondence between audio and video can be analyzed. Also, a simplified analysis can be performed on a video with low importance, and only the main correspondence can be analyzed. Furthermore, a balanced analysis can be performed on a video with medium importance, and the necessary correspondence can be analyzed. In this way, an efficient analysis can be performed by adjusting the level of detail of the analysis based on the importance of the video.

[0101] When generating music, the generation unit can determine a generation priority based on the submission date of the video. For example, music can be generated preferentially for recently submitted videos. Also, music can be generated later for videos submitted earlier. Furthermore, music can be generated preferentially for videos submitted related to a specific event. In this way, efficient music generation can be achieved by determining the generation priority based on the submission date of the video.

[0102] The providing unit can select the optimal music providing method by referring to the user's past music selection history. For example, the optimal music providing method is selected based on the genre of music that the user has previously selected. Also, it is possible to provide specific artists or albums with priority based on the user's past music selection history. Furthermore, it is possible to analyze the user's past music selection history and provide the most relevant music. In this way, the optimal music providing method can be selected by referring to the past music selection history.

[0103] The providing unit can estimate the user's emotion and determine the priority order of music to be provided based on the estimated emotion. For example, when the user is relaxed, relaxing music can be provided preferentially. When the user is stressed, music with a relaxing effect can be provided preferentially. Furthermore, when the user is excited, energetic music can be provided preferentially. In this way, by determining the priority order of music according to the user's emotion, more appropriate music can be provided.

[0104] The process flow of the second embodiment will be briefly described below.

[0105] Step 1: The reception unit uploads a video taken by a user. The video taken by a user may include, but is not limited to, a file format such as MP4, AVI, or MOV, a length, or a resolution. The reception unit can upload, for example, a video taken by a user with a smartphone or a camera. The reception unit can also allow a user to upload multiple videos at once. Step 2: The analysis unit uses the generation AI to analyze the audio and video parts of the video uploaded by the reception unit, and learns the correspondence between audio and video. The analysis unit learns the correspondence between audio and video, for example, using contrastive learning. Contrastive learning is a technology that learns the correspondence between audio and video by generating pairs of audio and video and calculating the similarity between those pairs. For example, the analysis unit learns the correspondence based on matches between timestamps and scenes of audio and video. Step 3: The generator uses a generative AI to generate music based on the correspondence learned by the analyzer. The generator generates music using algorithms such as GAN (generative artificial network), RNN (recurrent neural network), and Transformer. The generator can automatically generate music that matches the concept of the video, for example. The generator can also recommend optimal music from an existing music database. Step 4: The providing unit provides the music generated by the generating unit to the user. The providing unit can provide the music by, for example, streaming, downloading, notification, or other methods. For example, the providing unit can directly download the generated music to the user's device. The providing unit can also provide the generated music through a streaming service.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and provision unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14, and uploads a video taken by a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the audio and video parts of the uploaded video, and learns the correspondence between the audio and the video. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates music based on the analyzed correspondence. The provision unit is realized, for example, by the control unit 46A of the smart device 14, and provides the generated music to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214, and uploads a video shot by a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the audio and video parts of the uploaded video and learns the correspondence between the audio and video. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates music based on the analyzed correspondence. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214, and provides the generated music to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and provision unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314, and uploads a video taken by a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the audio part and the video part of the uploaded video, and learns the correspondence between the audio and the video. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates music based on the analyzed correspondence. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314, and provides the generated music to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414, and uploads a video taken by a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the audio and video parts of the uploaded video, and learns the correspondence between the audio and video. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates music based on the analyzed correspondence. The provision unit is realized, for example, by the control unit 46A of the robot 414, and provides the generated music to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0159] 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.

[0160] 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.

[0161] These emotions are distributed in the three 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.

[0162] 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 on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0163] 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.

[0164] 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."

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] (Appendix 1) A reception section for uploading videos; an analysis unit that analyzes the audio and video parts of the video uploaded by the reception unit and learns the correspondence between the audio and the video; a generation unit that generates music based on the correspondence relationship learned by the analysis unit; a providing unit that provides the music generated by the generating unit. A system characterized by: (Appendix 2) The analysis unit is Learning the correspondence between audio and video using contrastive learning 2. The system of claim 1, (Appendix 3) The generation unit is Generating music using generative AI 2. The system of claim 1, (Appendix 4) The generation unit is Recommending suitable songs from an existing music database 2. The system of claim 1, (Appendix 5) The providing unit is Providing generated music to users 2. The system of claim 1, (Appendix 6) The reception unit is Estimate user emotions and adjust the timing of video uploads based on the estimated user emotions 2. The system of claim 1, (Appendix 7) The reception unit is Analyze the user's past upload history and select the appropriate upload method 2. The system of claim 1, (Appendix 8) The reception unit is Filtering video uploads based on a user's current projects and interests 2. The system of claim 1, (Appendix 9) The reception unit is Estimate user sentiment and prioritize videos to upload based on the estimated user sentiment 2. The system of claim 1, (Appendix 10) The reception unit is When uploading videos, it takes into account the user's geographic location to prioritize uploading videos that are more relevant to them 2. The system of claim 1, (Appendix 11) The reception unit is Analyze your social media activity and upload relevant videos when you upload a video 2. The system of claim 1, (Appendix 12) The analysis unit is A method for estimating a user's emotion and adjusting an analysis method for the correspondence between audio and video based on the estimated user's emotion 2. The system of claim 1, (Appendix 13) The analysis unit is During analysis, adjust the analysis detail level based on the importance of the video 2. The system of claim 1, (Appendix 14) The analysis unit is During analysis, different analysis algorithms are applied depending on the video category. 2. The system of claim 1, (Appendix 15) The analysis unit is Infer user emotions and adjust the way analysis results are displayed based on the inferred user emotions 2. The system of claim 1, (Appendix 16) The analysis unit is During analysis, we prioritize analysis based on when the video was submitted 2. The system of claim 1, (Appendix 17) The analysis unit is During analysis, adjust the order of analysis based on video relevance 2. The system of claim 1, (Appendix 18) The generation unit is Estimating a user's emotions and adjusting the expression of generated music based on the estimated user's emotions 2. The system of claim 1, (Appendix 19) The generation unit is When generating music, adjust the level of detail based on the importance of the video 2. The system of claim 1, (Appendix 20) The generation unit is When generating music, different generation algorithms are applied depending on the video category. 2. The system of claim 1, (Appendix 21) The generation unit is Estimate the user's emotion and adjust the length of the generated music based on the estimated user's emotion. 2. The system of claim 1, (Appendix 22) The generation unit is When generating music, prioritize generation based on when the video was submitted 2. The system of claim 1, (Appendix 23) The generation unit is When generating music, adjust the order of generation based on video relevance 2. The system of claim 1, (Appendix 24) The providing unit is To estimate a user's emotion and adjust a method of displaying music based on the estimated user's emotion. 2. The system of claim 1, (Appendix 25) The providing unit is When providing music, the optimal method of providing the music is selected by referring to the user's past music selection history. 2. The system of claim 1, (Appendix 26) The providing unit is Estimate the user's emotions and prioritize music to be provided based on the estimated user's emotions. 2. The system of claim 1, (Appendix 27) The providing unit is When providing music, the optimal delivery method is selected taking into account the user's device information. 2. The system of claim 1, [Explanation of symbols]

[0178] 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. A reception section for uploading videos; an analysis unit that analyzes the audio and video parts of the video uploaded by the reception unit and learns the correspondence between the audio and the video; a generation unit that generates music based on the correspondence relationship learned by the analysis unit; a providing unit that provides the music generated by the generating unit. A system characterized by:

2. The analysis unit is Learning correspondences between audio and video using contrastive learning 2. The system of claim 1 .

3. The generation unit is Generate music using generative AI 2. The system of claim 1 .

4. The generation unit is Recommending suitable songs from an existing music database 2. The system of claim 1 .

5. The reception unit is Estimate user emotions and adjust the timing of video uploads based on the estimated user emotions 2. The system of claim 1 .

6. The reception unit is Analyze the user's past upload history and select the appropriate upload method 2. The system of claim 1 .

7. The reception unit is Filtering video uploads based on a user's current projects and interests 2. The system of claim 1 .

8. The reception unit is Estimate user sentiment and prioritize videos to upload based on the estimated user sentiment 2. The system of claim 1 .

9. The reception unit is When uploading videos, it takes into account the user's geographic location to prioritize uploading videos that are more relevant to them 2. The system of claim 1 .

Images