system

Abstract

The system according to the embodiment aims to automatically create a cut-out video at low cost. [Solution] A system according to an embodiment includes an analysis unit, an emotion analysis unit, a content analysis unit, and a generation unit. The analysis unit analyzes the content of a comment section. The emotion analysis unit analyzes the emotion of a broadcaster based on the content of the comment section analyzed by the analysis unit. The content analysis unit analyzes the content based on the emotion analyzed by the emotion analysis unit. The generation unit generates a clipped video based on the content analyzed by the content analysis unit.

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 an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques require manual editing to create cut-out videos, which is costly.

[0005] The system according to the embodiment aims to automatically create a cut-out video at low cost. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, an emotion analysis unit, a content analysis unit, and a generation unit. The analysis unit analyzes the content of the comment section. The emotion analysis unit analyzes the emotion of the distributor based on the content of the comment section analyzed by the analysis unit. The content analysis unit analyzes the content based on the emotion analyzed by the emotion analysis unit. The generation unit generates a clipped video based on the content analyzed by the content analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically create a cut-out video at low cost. [Brief explanation 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. [Figure 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. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 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. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 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 INVENTION

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

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

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single 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 coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, 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 symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and 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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "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, RAM 30, and 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 (for example, 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., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with 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 CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

[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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 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 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. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) An automatic crop video generation system according to an embodiment of the present invention automatically creates crop videos using a large-scale language model (LLM). This system analyzes the comment section of a video, the streamer's emotions, and the content of the content, automatically extracting highlights and generating crop videos. For example, the system analyzes the comment section of a video to identify parts of the video that viewers particularly care about. Viewer comments may include comments such as "This scene was funny!" or "This part was moving," and analyzing these comments can identify highlights. The system also analyzes the streamer's emotions by analyzing the streamer's facial expressions and tone of voice to identify emotional intensities. For example, highlights can be extracted by identifying scenes in which the streamer is laughing or feeling moved. Furthermore, the system analyzes the content of the content. The system analyzes the content of the video to identify important scenes and story developments. For example, highlights can be extracted by identifying scenes containing the climax of the story or important statements. Based on these analysis results, the system automatically extracts highlights and generates crop videos. The system comprehensively considers viewer comments, the streamer's emotions, and the content itself to cut out the most noteworthy scenes. In this way, it is possible to create cut-out videos at low cost. This allows the automatic cut-out video generation system to analyze viewer comments, the streamer's emotions, and the content itself, and automatically generate cut-out videos at low cost.

[0029] The automatic cut-out video generation system according to the embodiment includes an analysis unit, an emotion analysis unit, a content analysis unit, and a generation unit. The analysis unit analyzes viewer comments. Viewer comments include, but are not limited to, text comments, emojis, and links. The analysis unit, for example, analyzes the viewer comments using natural language processing technology to identify parts of the viewer's interest. For example, if a viewer comments, "This scene is interesting!", the analysis unit can identify that scene as a highlight. The analysis unit can also identify parts of the viewer's interest based on the frequency of the viewer's comments and the results of emotion analysis. The emotion analysis unit analyzes the streamer's emotions. The streamer's emotions include, but are not limited to, joy, sadness, anger, and the like. The emotion analysis unit, for example, analyzes the streamer's facial expressions using facial recognition technology to identify emotional intensity. The emotion analysis unit can also analyze the streamer's tone of voice using voice analysis technology to identify emotional intensity. For example, scenes in which the streamer is laughing or feeling moved can be identified. The content analysis unit analyzes the content of the video. The content of the video includes, for example, scene types, audio, text, etc., but is not limited to these examples. The content analysis unit, for example, analyzes scenes in the video and identifies important scenes and story developments. For example, it can identify scenes that include the climax of the story or important statements. The content analysis unit can also identify important scenes based on viewer reactions and scene content. The generation unit comprehensively considers viewer comments, the streamer's emotions, and the content of the content, automatically extracts highlights, and generates a cutout video. The generation unit can generate a cutout video using a generation AI that inputs, for example, viewer comments, the streamer's emotions, and the content of the content, and outputs highlights. As a result, the automatic cutout video generation system according to the embodiment can analyze viewer comments, the streamer's emotions, and the content of the content, and automatically generate cutout videos at low cost.

[0030] The analysis unit can analyze viewer comments and identify parts of the program that viewers are particularly interested in. For example, the analysis unit can analyze viewer comments using natural language processing technology to identify parts of the program that viewers are particularly interested in. For example, if a viewer comments, "This scene is interesting!", the analysis unit can identify that scene as a highlight. The analysis unit can also identify parts of the program that viewers are particularly interested in based on the frequency of viewer comments and the results of sentiment analysis. For example, it can identify scenes on which viewers frequently comment or scenes that show a high emotional score in the sentiment analysis results. This allows the analysis unit to efficiently extract highlights by identifying viewer interests. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input viewer comments to a generation AI and have the generation AI identify parts of the program that viewers are particularly interested in.

[0031] The emotion analysis unit can analyze the streamer's facial expressions and tone of voice to identify emotional intensity. For example, the emotion analysis unit can analyze the streamer's facial expressions using facial recognition technology to identify emotional intensity. For example, it can identify scenes in which the streamer is laughing or feeling moved. The emotion analysis unit can also analyze the streamer's tone of voice using audio analysis technology to identify emotional intensity. For example, it can identify scenes in which the streamer is excited or sad. This allows the streamer's emotional intensity to be identified, thereby efficiently extracting highlights. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the streamer's facial expressions and tone of voice into the generation AI and have the generation AI identify emotional intensity.

[0032] The content analysis unit can analyze the content of a video and identify important scenes and story developments. The content analysis unit can, for example, analyze scenes in a video and identify important scenes and story developments. For example, it can identify scenes that include the climax of the story or important statements. The content analysis unit can also identify important scenes based on viewer reactions and the content of the scenes. For example, it can identify scenes where viewers have left many comments or scenes whose content includes particularly important information. By identifying important scenes and story developments in a video, it is possible to efficiently extract highlights. Some or all of the above-described processing in the content analysis unit can be performed using, for example, AI, or without AI. For example, the content analysis unit can input video scenes into a generation AI and cause the generation AI to identify important scenes and story developments.

[0033] The generation unit can automatically extract highlights based on a comprehensive consideration of viewer comments, the streamer's emotions, and the content of the content, and generate a cut-out video. The generation unit can generate a cut-out video using a generation AI that inputs viewer comments, the streamer's emotions, and the content of the content and outputs highlights. For example, the generation unit can extract the most noteworthy scenes by comprehensively considering scenes that receive many viewer comments, scenes that elicit the streamer's emotions, the climax of the story, etc. This makes it possible to efficiently extract highlights and generate a cut-out video by comprehensively considering viewer comments, the streamer's emotions, and the content of the content. Some or all of the above-described processing by the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input viewer comments, the streamer's emotions, and the content of the content into the generation AI and have the generation AI extract highlights and generate a cut-out video.

[0034] When analyzing comments, the analysis unit can improve the accuracy of the analysis by referring to the viewer's past comment history. The analysis unit, for example, refers to the viewer's past comment history to improve the accuracy of the analysis. The viewer's past comment history includes, for example, comments that the viewer has previously liked and comments that show interest in a particular theme, but is not limited to these examples. The analysis unit, for example, can prioritize analyzing comments that the viewer has previously liked and identify highlights. Furthermore, if the viewer's past comment history shows interest in a particular theme, the analysis unit can focus on analyzing comments related to that theme. Furthermore, it is possible to take into account time periods in which the viewer frequently commented in the past and prioritize analysis of comments from those time periods. This improves the accuracy of the analysis by referring to the viewer's past comment history. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the viewer's past comment history into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0035] When analyzing comments, the analysis unit can customize the analysis method based on the viewer's device information. The analysis unit, for example, customizes the analysis method by taking into account the viewer's device information. The viewer's device information includes, but is not limited to, a smartphone, a tablet, a desktop, etc. For example, if the viewer is using a smartphone, the analysis unit can prioritize analyzing short comments. Furthermore, if the viewer is using a tablet, the analysis unit can prioritize analyzing detailed comments. Furthermore, if the viewer is using a desktop, the analysis unit can prioritize analyzing long comments. This allows the analysis method to be customized by taking into account the viewer's device information. Some or all of the above-described 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 input the viewer's device information into the generation AI and cause the generation AI to customize the analysis method.

[0036] When analyzing comments, the analysis unit can prioritize analyzing highly relevant comments by taking into account the viewer's geographical location information. The analysis unit, for example, analyzes comments by taking into account the viewer's geographical location information. The viewer's geographical location information includes, but is not limited to, a specific region, a travel destination, or a home. For example, if the viewer is in a specific region, the analysis unit can prioritize analyzing comments related to that region. Furthermore, if the viewer is traveling, the analysis unit can prioritize analyzing comments related to the travel destination. Furthermore, if the viewer is at home, the analysis unit can prioritize analyzing comments related to the home. In this way, by taking into account the viewer's geographical location information, highly relevant comments can be prioritized for analysis. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the viewer's geographical location information to the generation AI and cause the generation AI to perform preferential analysis of highly relevant comments.

[0037] When analyzing comments, the analysis unit can analyze the viewer's social media activity and analyze related comments. The analysis unit, for example, analyzes the viewer's social media activity and analyzes related comments. The viewer's social media activity includes, but is not limited to, sharing, liking, and following. The analysis unit, for example, can prioritize analyzing comments shared by the viewer on social media. It can also prioritize analyzing comments that the viewer has "liked" on social media. It can also prioritize analyzing comments from accounts that the viewer follows on social media. In this way, related comments can be analyzed by analyzing the viewer's social media activity. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the viewer's social media activity into the generation AI and cause the generation AI to analyze related comments.

[0038] The emotion analysis unit can improve the accuracy of the emotion analysis by referring to the streamer's past emotion data. The emotion analysis unit, for example, refers to the streamer's past emotion data to improve the accuracy of the analysis. The streamer's past emotion data includes, for example, scenes in which the streamer expressed strong emotions in the past and patterns expressing specific emotions, but is not limited to these examples. The emotion analysis unit can, for example, analyze scenes in which the streamer expressed strong emotions in the past. It can also extract patterns expressing specific emotions from the streamer's past emotion data and use them in the analysis. Furthermore, it can also take into account time periods in which the streamer expressed emotions in the past and prioritize analysis of data from those time periods. By referring to the streamer's past emotion data, the accuracy of the analysis is improved. The streamer's emotion is estimated using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, an AI, or without an AI. For example, the emotion analysis unit can input the broadcaster's past emotion data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0039] The emotion analysis unit can customize the analysis method by taking into account the device information of the broadcaster when analyzing emotions. The emotion analysis unit customizes the analysis method by taking into account, for example, the device information of the broadcaster. The device information of the broadcaster includes, but is not limited to, a smartphone, tablet, desktop, etc. For example, if the broadcaster is using a smartphone, the emotion analysis unit can prioritize analyzing short emotional expressions. Furthermore, if the broadcaster is using a tablet, the emotion analysis unit can prioritize analyzing detailed emotional expressions. Furthermore, if the broadcaster is using a desktop, the emotion analysis unit can prioritize analyzing long emotional expressions. This allows the analysis method to be customized by taking into account the device information of the broadcaster. The broadcaster's emotions are estimated using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the emotion analysis unit can input the broadcaster's device information into the generation AI and have the generation AI customize the analysis method.

[0040] During emotion analysis, the emotion analysis unit can prioritize analyzing highly relevant emotion data by taking into account the geographical location information of the broadcaster. The emotion analysis unit, for example, analyzes emotion data by taking into account the geographical location information of the broadcaster. The geographical location information of the broadcaster includes, for example, a specific region, a travel destination, or a home, but is not limited to these examples. For example, if the broadcaster is in a specific region, the emotion analysis unit can prioritize analyzing emotion data related to that region. Furthermore, if the broadcaster is traveling, the emotion analysis unit can prioritize analyzing emotion data related to the travel destination. Furthermore, if the broadcaster is at home, the emotion analysis unit can prioritize analyzing emotion data related to the home. In this way, by taking the broadcaster's geographical location information into account, highly relevant emotion data can be prioritized for analysis. Estimation of the broadcaster's emotion is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or without AI. For example, the emotion analysis unit can input the geographical location information of the broadcaster into the generation AI and have the generation AI perform prioritized analysis of highly relevant emotion data.

[0041] During emotion analysis, the emotion analysis unit can analyze the streamer's social media activity and analyze related emotion data. The emotion analysis unit, for example, analyzes the streamer's social media activity and analyzes related emotion data. The streamer's social media activity includes, but is not limited to, shares, likes, and follows. The emotion analysis unit, for example, can prioritize analyzing emotion data shared by the streamer on social media. It can also prioritize analyzing emotion data of accounts the streamer "likes" on social media. It can also prioritize analyzing emotion data of accounts the streamer follows on social media. This allows related emotion data to be analyzed by analyzing the streamer's social media activity. The streamer's emotion is estimated using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or without AI. For example, the emotion analysis unit can input the streamer's social media activity into the generation AI and have the generation AI analyze the related emotion data.

[0042] The content analysis unit can improve the accuracy of the analysis by referring to past content data during content analysis. The content analysis unit, for example, refers to past content data to improve the accuracy of the analysis. Past content data includes, for example, content that has received high ratings in the past and scenes related to a specific theme, but is not limited to these examples. The content analysis unit can, for example, perform analysis by referring to data of content that has received high ratings in the past. Scenes related to a specific theme can be extracted from the past content data and used for analysis. Furthermore, past content data can be analyzed to identify and analyze scenes that attract viewers' attention. By referring to past content data, the accuracy of the analysis can be improved. Some or all of the above-described processing in the content analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the content analysis unit can input past content data into a generation AI and cause the generation AI to improve the accuracy of the analysis.

[0043] The content analysis unit can customize the analysis method by taking into account device information of the content when analyzing the content. The content analysis unit customizes the analysis method by taking into account, for example, the device information of the content. The device information of the content includes, but is not limited to, for example, a smartphone, a tablet, and a desktop. For example, if the content was shot on a smartphone, the content analysis unit can prioritize analyzing short scenes. Furthermore, if the content was shot on a tablet, the content analysis unit can prioritize analyzing detailed scenes. Furthermore, if the content was shot on a desktop, the content analysis unit can prioritize analyzing long scenes. This allows the analysis method to be customized by taking into account the device information of the content. Some or all of the above-described processing in the content analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the content analysis unit can input the device information of the content to the generation AI and cause the generation AI to customize the analysis method.

[0044] During content analysis, the content analysis unit can prioritize analysis of highly relevant data by taking into account the geographical location information of the content. The content analysis unit, for example, analyzes data by taking into account the geographical location information of the content. The geographical location information of the content includes, but is not limited to, a specific region, a travel destination, or a home. For example, if the content is related to a specific region, the content analysis unit can prioritize analysis of data related to that region. Furthermore, if the content is related to travel, the content analysis unit can prioritize analysis of data related to the travel destination. Furthermore, if the content is related to home, the content analysis unit can prioritize analysis of data related to home. In this way, by taking into account the geographical location information of the content, highly relevant data can be prioritized for analysis. Some or all of the above-described processing in the content analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the content analysis unit can input the geographical location information of the content to a generation AI and cause the generation AI to perform a prioritized analysis of highly relevant data.

[0045] During content analysis, the content analysis unit can analyze the social media activity of the content and analyze related data. The content analysis unit, for example, analyzes the social media activity of the content and analyzes related data. The social media activity of the content includes, but is not limited to, shares, likes, follows, etc. The content analysis unit, for example, can prioritize analyzing data on content being shared on social media. It can also prioritize analyzing data on content being "liked" on social media. It can also prioritize analyzing data on accounts that follow the content on social media. In this way, related data can be analyzed by analyzing the social media activity of the content. Some or all of the above-described processing in the content analysis unit may be performed using, or without using, AI. For example, the content analysis unit can input the social media activity of the content into a generation AI and cause the generation AI to analyze the related data.

[0046] When generating a cutout video, the generation unit can optimize the generation algorithm by referring to past generation data. The generation unit, for example, optimizes the generation algorithm by referring to past generation data. Past generation data includes, for example, cutout videos that have received high ratings in the past and scenes related to a specific theme, but is not limited to these examples. The generation unit can optimize the generation algorithm by referring to data of cutout videos that have received high ratings in the past. Scenes related to a specific theme can be extracted from the past generation data and reflected in the generation algorithm. Furthermore, the generation unit can analyze the past generation data, identify scenes that attract viewers' attention, and optimize the generation algorithm. In this way, the generation algorithm can be optimized by referring to the past generation data. Some 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 input past generation data into the generation AI and cause the generation AI to optimize the generation algorithm.

[0047] When generating a cut-out video, the generation unit can customize the generation method by taking into account the viewer's device information. The generation unit customizes the generation method by taking into account, for example, the viewer's device information. The viewer's device information includes, but is not limited to, for example, a smartphone, a tablet, or a desktop. For example, if the viewer is using a smartphone, the generation unit can generate a short cut-out video. Furthermore, if the viewer is using a tablet, the generation unit can generate a detailed cut-out video. Furthermore, if the viewer is using a desktop, the generation unit can generate a long cut-out video. In this way, the generation method can be customized by taking into account the viewer's device information. Some or all of the above-described 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 input the viewer's device information into the generation AI and cause the generation AI to customize the generation method.

[0048] When generating a cut-out video, the generation unit can prioritize generating highly relevant videos by taking into account the viewer's geographical location information. The generation unit, for example, generates videos by taking into account the viewer's geographical location information. The viewer's geographical location information includes, but is not limited to, a specific region, a travel destination, or a home. For example, if the viewer is in a specific region, the generation unit can prioritize generating videos related to that region. Furthermore, if the viewer is traveling, the generation unit can prioritize generating videos related to the travel destination. Furthermore, if the viewer is at home, the generation unit can prioritize generating videos related to the home. In this way, highly relevant videos can be generated by taking into account the viewer's geographical location information. Some or all of the above-described processing by the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the viewer's geographical location information to the generation AI and cause the generation AI to prioritize generating highly relevant videos.

[0049] The generation unit can analyze the viewer's social media activity and generate related videos when generating the cut-out video. The generation unit, for example, analyzes the viewer's social media activity and generates related videos. The viewer's social media activity includes, but is not limited to, shares, likes, and follows. The generation unit can, for example, prioritize generating videos that the viewer has shared on social media. It can also prioritize generating videos that the viewer has "liked" on social media. It can also prioritize generating videos of accounts that the viewer follows on social media. In this way, related videos can be generated by analyzing the viewer's social media activity. Some or all of the above-described processing in the generation unit may be performed, for example, using AI or without AI. For example, the generation unit can input the viewer's social media activity into the generation AI and cause the generation AI to generate related videos.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] When analyzing viewer comments, the analysis unit can adjust the analysis method taking into account the viewer's age group. For example, if there are many young viewers, it can prioritize analyzing comments containing slang and buzzwords to identify highlights. On the other hand, if there are many middle-aged and older viewers, it can focus on analyzing comments using more formal language. Furthermore, it can also take into account the viewer's tendency to be interested in certain topics depending on their age group and prioritize analyzing comments related to those topics. In this way, by adjusting the comment analysis method based on the viewer's age group, it is possible to identify more appropriate highlights.

[0052] When analyzing the content of a video, the content analysis unit can customize the analysis method according to the genre of the video. For example, in the case of a comedy video, it can focus on analyzing funny scenes to identify highlights. In the case of a documentary video, it can focus on analyzing important information and interview scenes. Furthermore, in the case of an action video, it can focus on analyzing action scenes and the climax. In this way, by customizing the analysis method according to the genre of the video, it is possible to identify more appropriate highlights.

[0053] The generation unit can automatically extract highlights based on a comprehensive consideration of viewer comments, the streamer's emotions, and the content of the content, and generate a cut-out video. The generation unit can generate a cut-out video using a generation AI that inputs viewer comments, the streamer's emotions, and the content of the content and outputs highlights. For example, the generation unit can extract the most noteworthy scenes by comprehensively considering scenes that receive many viewer comments, scenes that elicit the streamer's emotions, the climax of the story, etc. This makes it possible to efficiently extract highlights and generate a cut-out video by comprehensively considering viewer comments, the streamer's emotions, and the content of the content. Some or all of the above-described processing by the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input viewer comments, the streamer's emotions, and the content of the content into the generation AI and have the generation AI extract highlights and generate a cut-out video.

[0054] When analyzing viewer comments, the analysis unit can estimate the viewer's interests and adjust the comment analysis method based on the estimated interests. For example, if a viewer is interested in a particular genre, comments related to that genre can be analyzed preferentially to identify highlights. Also, if a viewer is interested in a particular character or scene, comments related to that character or scene can be analyzed with a focus. Furthermore, based on the viewer's interests, comments containing related keywords can also be analyzed preferentially. In this way, by adjusting the comment analysis method based on the viewer's interests, more appropriate highlights can be identified.

[0055] When analyzing the content of a video, the content analysis unit can adjust the analysis method taking into account the time of day the video is viewed. For example, if a viewer often watches at night, it can focus on analyzing relaxing or moving scenes to identify highlights. Alternatively, if a viewer often watches during the day, it can focus on analyzing active or interesting scenes. Furthermore, it can prioritize analysis of scenes related to a specific theme depending on the viewer's viewing time. This allows for more appropriate highlights to be identified by adjusting the analysis method based on the viewing time.

[0056] The generation unit can automatically extract highlights based on a comprehensive consideration of viewer comments, the streamer's emotions, and the content of the content, and generate a cut-out video. The generation unit can generate a cut-out video using a generation AI that inputs viewer comments, the streamer's emotions, and the content of the content and outputs highlights. For example, the generation unit can extract the most noteworthy scenes by comprehensively considering scenes that receive many viewer comments, scenes that elicit the streamer's emotions, the climax of the story, etc. This makes it possible to efficiently extract highlights and generate a cut-out video by comprehensively considering viewer comments, the streamer's emotions, and the content of the content. Some or all of the above-described processing by the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input viewer comments, the streamer's emotions, and the content of the content into the generation AI and have the generation AI extract highlights and generate a cut-out video.

[0057] When analyzing viewer comments, the analysis unit can adjust the analysis method taking into account the language of the viewer comments. For example, if a viewer comments in English, the analysis unit can prioritize analyzing the English comments to identify highlights. Also, if a viewer comments in multiple languages, the analysis unit can analyze comments in each language equally. Furthermore, based on the language of the viewer comments, the analysis unit can prioritize analyzing comments related to a particular culture or background. This allows for more appropriate highlights to be identified by adjusting the analysis method based on the language of the viewer comments.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The analysis unit analyzes the viewer's comments. The viewer's comments include text comments, emojis, links, etc. The analysis unit uses natural language processing technology to analyze the comments and identify parts of the video that the viewer is particularly interested in. For example, if a viewer comments, "This scene is interesting!", that scene is identified as a highlight. It is also possible to identify parts of the video that the viewer is particularly interested in based on the frequency of comments and the results of sentiment analysis. Step 2: The emotion analysis unit analyzes the streamer's emotions. Streamer emotions include joy, sadness, anger, etc. The emotion analysis unit uses facial recognition technology to analyze the streamer's facial expressions and identify emotional intensity. It can also use voice analysis technology to analyze the streamer's tone of voice and identify emotional intensity. For example, it can identify scenes where the streamer is laughing or feeling moved. Step 3: The content analysis unit analyzes the content of the video. The content of the video includes scene types, audio, text, etc. The content analysis unit analyzes the scenes in the video and identifies important scenes and story developments. For example, it identifies scenes that include the climax of the story or important statements. It can also identify important scenes based on viewer reactions and the content of the scenes. Step 4: The generation unit takes into consideration the viewer's comments, the streamer's emotions, and the content of the content, automatically extracts the highlights, and generates a cut-out video.The generation unit takes the viewer's comments, the streamer's emotions, and the content of the content as input, and uses generation AI to output the highlights, generating a cut-out video.

[0060] (Example 2) An automatic crop video generation system according to an embodiment of the present invention automatically creates crop videos using a large-scale language model (LLM). This system analyzes the comment section of a video, the streamer's emotions, and the content of the content, automatically extracting highlights and generating crop videos. For example, the system analyzes the comment section of a video to identify parts of the video that viewers particularly care about. Viewer comments may include comments such as "This scene was funny!" or "This part was moving," and analyzing these comments can identify highlights. The system also analyzes the streamer's emotions by analyzing the streamer's facial expressions and tone of voice to identify emotional intensities. For example, highlights can be extracted by identifying scenes in which the streamer is laughing or feeling moved. Furthermore, the system analyzes the content of the content. The system analyzes the content of the video to identify important scenes and story developments. For example, highlights can be extracted by identifying scenes containing the climax of the story or important statements. Based on these analysis results, the system automatically extracts highlights and generates crop videos. The system comprehensively considers viewer comments, the streamer's emotions, and the content itself to cut out the most noteworthy scenes. In this way, it is possible to create cut-out videos at low cost. This allows the automatic cut-out video generation system to analyze viewer comments, the streamer's emotions, and the content itself, and automatically generate cut-out videos at low cost.

[0061] The automatic cut-out video generation system according to the embodiment includes an analysis unit, an emotion analysis unit, a content analysis unit, and a generation unit. The analysis unit analyzes viewer comments. Viewer comments include, but are not limited to, text comments, emojis, and links. The analysis unit, for example, analyzes the viewer comments using natural language processing technology to identify parts of the viewer's interest. For example, if a viewer comments, "This scene is interesting!", the analysis unit can identify that scene as a highlight. The analysis unit can also identify parts of the viewer's interest based on the frequency of the viewer's comments and the results of emotion analysis. The emotion analysis unit analyzes the streamer's emotions. The streamer's emotions include, but are not limited to, joy, sadness, anger, and the like. The emotion analysis unit, for example, analyzes the streamer's facial expressions using facial recognition technology to identify emotional intensity. The emotion analysis unit can also analyze the streamer's tone of voice using voice analysis technology to identify emotional intensity. For example, scenes in which the streamer is laughing or feeling moved can be identified. The content analysis unit analyzes the content of the video. The content of the video includes, for example, scene types, audio, text, etc., but is not limited to these examples. The content analysis unit, for example, analyzes scenes in the video and identifies important scenes and story developments. For example, it can identify scenes that include the climax of the story or important statements. The content analysis unit can also identify important scenes based on viewer reactions and scene content. The generation unit comprehensively considers viewer comments, the streamer's emotions, and the content of the content, automatically extracts highlights, and generates a cutout video. The generation unit can generate a cutout video using a generation AI that inputs, for example, viewer comments, the streamer's emotions, and the content of the content, and outputs highlights. As a result, the automatic cutout video generation system according to the embodiment can analyze viewer comments, the streamer's emotions, and the content of the content, and automatically generate cutout videos at low cost.

[0062] The analysis unit can analyze viewer comments and identify parts of the program that viewers are particularly interested in. For example, the analysis unit can analyze viewer comments using natural language processing technology to identify parts of the program that viewers are particularly interested in. For example, if a viewer comments, "This scene is interesting!", the analysis unit can identify that scene as a highlight. The analysis unit can also identify parts of the program that viewers are particularly interested in based on the frequency of viewer comments and the results of sentiment analysis. For example, it can identify scenes on which viewers frequently comment or scenes that show a high emotional score in the sentiment analysis results. This allows the analysis unit to efficiently extract highlights by identifying viewer interests. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input viewer comments to a generation AI and have the generation AI identify parts of the program that viewers are particularly interested in.

[0063] The emotion analysis unit can analyze the streamer's facial expressions and tone of voice to identify emotional intensity. For example, the emotion analysis unit can analyze the streamer's facial expressions using facial recognition technology to identify emotional intensity. For example, it can identify scenes in which the streamer is laughing or feeling moved. The emotion analysis unit can also analyze the streamer's tone of voice using audio analysis technology to identify emotional intensity. For example, it can identify scenes in which the streamer is excited or sad. This allows the streamer's emotional intensity to be identified, thereby efficiently extracting highlights. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the streamer's facial expressions and tone of voice into the generation AI and have the generation AI identify emotional intensity.

[0064] The content analysis unit can analyze the content of a video and identify important scenes and story developments. The content analysis unit can, for example, analyze scenes in a video and identify important scenes and story developments. For example, it can identify scenes that include the climax of the story or important statements. The content analysis unit can also identify important scenes based on viewer reactions and the content of the scenes. For example, it can identify scenes where viewers have left many comments or scenes whose content includes particularly important information. By identifying important scenes and story developments in a video, it is possible to efficiently extract highlights. Some or all of the above-described processing in the content analysis unit can be performed using, for example, AI, or without AI. For example, the content analysis unit can input video scenes into a generation AI and cause the generation AI to identify important scenes and story developments.

[0065] The generation unit can automatically extract highlights based on a comprehensive consideration of viewer comments, the streamer's emotions, and the content of the content, and generate a cut-out video. The generation unit can generate a cut-out video using a generation AI that inputs viewer comments, the streamer's emotions, and the content of the content and outputs highlights. For example, the generation unit can extract the most noteworthy scenes by comprehensively considering scenes that receive many viewer comments, scenes that elicit the streamer's emotions, the climax of the story, etc. This makes it possible to efficiently extract highlights and generate a cut-out video by comprehensively considering viewer comments, the streamer's emotions, and the content of the content. Some or all of the above-described processing by the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input viewer comments, the streamer's emotions, and the content of the content into the generation AI and have the generation AI extract highlights and generate a cut-out video.

[0066] The analysis unit can estimate the viewer's emotions and adjust the comment analysis method based on the estimated viewer's emotions. The analysis unit, for example, analyzes the viewer's comments to estimate the viewer's emotions. Viewer emotions include, but are not limited to, excitement, emotion, and dissatisfaction. For example, if the viewer is excited, the analysis unit can prioritize analyzing comments indicating excitement and identify highlights. Also, if the viewer is emotional, the analysis unit can focus on analyzing comments indicating emotion and identify moving scenes. Furthermore, if the viewer is dissatisfied, the analysis unit can analyze comments indicating dissatisfaction and identify areas for improvement. In this way, by adjusting the comment analysis method based on the viewer's emotions, more appropriate highlights can be identified. The estimation of the viewer's emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or without an AI. For example, the analysis unit can input viewer comments into the generation AI and have the generation AI estimate the viewer's emotions and adjust the method of analyzing the comments.

[0067] When analyzing comments, the analysis unit can improve the accuracy of the analysis by referring to the viewer's past comment history. The analysis unit, for example, refers to the viewer's past comment history to improve the accuracy of the analysis. The viewer's past comment history includes, for example, comments that the viewer has previously liked and comments that show interest in a particular theme, but is not limited to these examples. The analysis unit, for example, can prioritize analyzing comments that the viewer has previously liked and identify highlights. Furthermore, if the viewer's past comment history shows interest in a particular theme, the analysis unit can focus on analyzing comments related to that theme. Furthermore, it is possible to take into account time periods in which the viewer frequently commented in the past and prioritize analysis of comments from those time periods. This improves the accuracy of the analysis by referring to the viewer's past comment history. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the viewer's past comment history into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0068] When analyzing comments, the analysis unit can customize the analysis method based on the viewer's device information. The analysis unit, for example, customizes the analysis method by taking into account the viewer's device information. The viewer's device information includes, but is not limited to, a smartphone, a tablet, a desktop, etc. For example, if the viewer is using a smartphone, the analysis unit can prioritize analyzing short comments. Furthermore, if the viewer is using a tablet, the analysis unit can prioritize analyzing detailed comments. Furthermore, if the viewer is using a desktop, the analysis unit can prioritize analyzing long comments. This allows the analysis method to be customized by taking into account the viewer's device information. Some or all of the above-described 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 input the viewer's device information into the generation AI and cause the generation AI to customize the analysis method.

[0069] The analysis unit can estimate the viewer's emotions and adjust the display method of the analysis results based on the estimated viewer's emotions. The analysis unit, for example, analyzes the viewer's comments to estimate the viewer's emotions. Viewer emotions include, but are not limited to, excitement, emotion, and dissatisfaction. For example, if the viewer is excited, the analysis unit can highlight comments indicating excitement. Furthermore, if the viewer is emotional, the analysis unit can prominently display comments indicating emotion. Furthermore, if the viewer is dissatisfied, the analysis unit can inconspicuously display comments indicating dissatisfaction. This allows for more appropriate display by adjusting the display method of the analysis results based on the viewer's emotions. The estimation of the viewer's emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or without using an AI. For example, the analysis unit can input viewer comments into the generation AI and have the generation AI estimate the viewer's emotions and adjust the way the analysis results are displayed.

[0070] When analyzing comments, the analysis unit can prioritize analyzing highly relevant comments by taking into account the viewer's geographical location information. The analysis unit, for example, analyzes comments by taking into account the viewer's geographical location information. The viewer's geographical location information includes, but is not limited to, a specific region, a travel destination, or a home. For example, if the viewer is in a specific region, the analysis unit can prioritize analyzing comments related to that region. Furthermore, if the viewer is traveling, the analysis unit can prioritize analyzing comments related to the travel destination. Furthermore, if the viewer is at home, the analysis unit can prioritize analyzing comments related to the home. In this way, by taking into account the viewer's geographical location information, highly relevant comments can be prioritized for analysis. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the viewer's geographical location information to the generation AI and cause the generation AI to perform preferential analysis of highly relevant comments.

[0071] When analyzing comments, the analysis unit can analyze the viewer's social media activity and analyze related comments. The analysis unit, for example, analyzes the viewer's social media activity and analyzes related comments. The viewer's social media activity includes, but is not limited to, sharing, liking, and following. The analysis unit, for example, can prioritize analyzing comments shared by the viewer on social media. It can also prioritize analyzing comments that the viewer has "liked" on social media. It can also prioritize analyzing comments from accounts that the viewer follows on social media. In this way, related comments can be analyzed by analyzing the viewer's social media activity. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the viewer's social media activity into the generation AI and cause the generation AI to analyze related comments.

[0072] The emotion analysis unit can estimate the streamer's emotions and adjust the emotion analysis method based on the estimated emotions. The emotion analysis unit, for example, analyzes the streamer's facial expressions and tone of voice to estimate the streamer's emotions. The streamer's emotions include, but are not limited to, joy, sadness, anger, etc. For example, if the streamer is laughing, the emotion analysis unit can focus on analyzing funny scenes. Also, if the streamer is crying, the emotion analysis unit can focus on analyzing emotional scenes. Furthermore, if the streamer is angry, the emotion analysis unit can focus on analyzing angry scenes. This allows for more appropriate analysis by adjusting the emotion analysis method based on the streamer's emotions. The streamer's emotions are estimated using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, for example, AI, or without AI. For example, the emotion analysis unit can input the streamer's facial expressions and tone of voice into the generation AI, allowing the generation AI to estimate the streamer's emotions and adjust the emotion analysis method.

[0073] The emotion analysis unit can improve the accuracy of the emotion analysis by referring to the streamer's past emotion data. The emotion analysis unit, for example, refers to the streamer's past emotion data to improve the accuracy of the analysis. The streamer's past emotion data includes, for example, scenes in which the streamer expressed strong emotions in the past and patterns expressing specific emotions, but is not limited to these examples. The emotion analysis unit can, for example, analyze scenes in which the streamer expressed strong emotions in the past. It can also extract patterns expressing specific emotions from the streamer's past emotion data and use them in the analysis. Furthermore, it can also take into account time periods in which the streamer expressed emotions in the past and prioritize analysis of data from those time periods. By referring to the streamer's past emotion data, the accuracy of the analysis is improved. The streamer's emotion is estimated using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, an AI, or without an AI. For example, the emotion analysis unit can input the broadcaster's past emotion data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0074] The emotion analysis unit can customize the analysis method by taking into account the device information of the broadcaster when analyzing emotions. The emotion analysis unit customizes the analysis method by taking into account, for example, the device information of the broadcaster. The device information of the broadcaster includes, but is not limited to, a smartphone, tablet, desktop, etc. For example, if the broadcaster is using a smartphone, the emotion analysis unit can prioritize analyzing short emotional expressions. Furthermore, if the broadcaster is using a tablet, the emotion analysis unit can prioritize analyzing detailed emotional expressions. Furthermore, if the broadcaster is using a desktop, the emotion analysis unit can prioritize analyzing long emotional expressions. This allows the analysis method to be customized by taking into account the device information of the broadcaster. The broadcaster's emotions are estimated using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the emotion analysis unit can input the broadcaster's device information into the generation AI and have the generation AI customize the analysis method.

[0075] The emotion analysis unit can estimate the streamer's emotions and adjust the display method of the analysis results based on the estimated emotions. The emotion analysis unit, for example, analyzes the streamer's facial expressions and tone of voice to estimate the streamer's emotions. The streamer's emotions include, but are not limited to, joy, sadness, anger, etc. For example, if the streamer is laughing, the emotion analysis unit can highlight funny scenes. Furthermore, if the streamer is crying, the emotion analysis unit can highlight moving scenes. Furthermore, if the streamer is angry, the emotion analysis unit can lessen the prominence of angry scenes. This allows for more appropriate display by adjusting the display method of the analysis results based on the streamer's emotions. The streamer's emotions are estimated using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or without AI. For example, the emotion analysis unit can input the streamer's facial expressions and tone of voice into the generation AI, allowing the generation AI to estimate the streamer's emotions and adjust the way the analysis results are displayed.

[0076] During emotion analysis, the emotion analysis unit can prioritize analyzing highly relevant emotion data by taking into account the geographical location information of the broadcaster. The emotion analysis unit, for example, analyzes emotion data by taking into account the geographical location information of the broadcaster. The geographical location information of the broadcaster includes, for example, a specific region, a travel destination, or a home, but is not limited to these examples. For example, if the broadcaster is in a specific region, the emotion analysis unit can prioritize analyzing emotion data related to that region. Furthermore, if the broadcaster is traveling, the emotion analysis unit can prioritize analyzing emotion data related to the travel destination. Furthermore, if the broadcaster is at home, the emotion analysis unit can prioritize analyzing emotion data related to the home. In this way, by taking the broadcaster's geographical location information into account, highly relevant emotion data can be prioritized for analysis. Estimation of the broadcaster's emotion is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or without AI. For example, the emotion analysis unit can input the geographical location information of the broadcaster into the generation AI and have the generation AI perform prioritized analysis of highly relevant emotion data.

[0077] During emotion analysis, the emotion analysis unit can analyze the streamer's social media activity and analyze related emotion data. The emotion analysis unit, for example, analyzes the streamer's social media activity and analyzes related emotion data. The streamer's social media activity includes, but is not limited to, shares, likes, and follows. The emotion analysis unit, for example, can prioritize analyzing emotion data shared by the streamer on social media. It can also prioritize analyzing emotion data of accounts the streamer "likes" on social media. It can also prioritize analyzing emotion data of accounts the streamer follows on social media. This allows related emotion data to be analyzed by analyzing the streamer's social media activity. The streamer's emotion is estimated using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or without AI. For example, the emotion analysis unit can input the streamer's social media activity into the generation AI and have the generation AI analyze the related emotion data.

[0078] The content analysis unit can estimate the emotion of the content and adjust the content analysis method based on the estimated emotion of the content. The content analysis unit, for example, analyzes the scenes and sounds of the content to estimate the emotion of the content. The emotion of the content includes, but is not limited to, emotions, excitement, and tension. For example, if the content is emotional, the content analysis unit can focus on analyzing emotional scenes. If the content is interesting, the content analysis unit can focus on analyzing interesting scenes. Furthermore, if the content is tense, the content analysis unit can focus on analyzing tense scenes. This allows for more appropriate analysis by adjusting the content analysis method based on the emotion of the content. The emotion of the content is estimated using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the content analysis unit may be performed using, for example, AI, or without AI. For example, the content analysis unit can input the scenes and sounds of the content into the generation AI and have the generation AI estimate the emotions of the content and adjust the content analysis method.

[0079] The content analysis unit can improve the accuracy of the analysis by referring to past content data during content analysis. The content analysis unit, for example, refers to past content data to improve the accuracy of the analysis. Past content data includes, for example, content that has received high ratings in the past and scenes related to a specific theme, but is not limited to these examples. The content analysis unit can, for example, perform analysis by referring to data of content that has received high ratings in the past. Scenes related to a specific theme can be extracted from the past content data and used for analysis. Furthermore, past content data can be analyzed to identify and analyze scenes that attract viewers' attention. By referring to past content data, the accuracy of the analysis can be improved. Some or all of the above-described processing in the content analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the content analysis unit can input past content data into a generation AI and cause the generation AI to improve the accuracy of the analysis.

[0080] The content analysis unit can customize the analysis method by taking into account device information of the content when analyzing the content. The content analysis unit customizes the analysis method by taking into account, for example, the device information of the content. The device information of the content includes, but is not limited to, for example, a smartphone, a tablet, and a desktop. For example, if the content was shot on a smartphone, the content analysis unit can prioritize analyzing short scenes. Furthermore, if the content was shot on a tablet, the content analysis unit can prioritize analyzing detailed scenes. Furthermore, if the content was shot on a desktop, the content analysis unit can prioritize analyzing long scenes. This allows the analysis method to be customized by taking into account the device information of the content. Some or all of the above-described processing in the content analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the content analysis unit can input the device information of the content to the generation AI and cause the generation AI to customize the analysis method.

[0081] The content analysis unit can estimate the emotion of the content and adjust the display method of the analysis results based on the estimated emotion of the content. The content analysis unit, for example, analyzes the scenes and sounds of the content to estimate the emotion of the content. The emotion of the content includes, but is not limited to, moving, interesting, and tense. For example, if the content is moving, the content analysis unit can highlight moving scenes. Furthermore, if the content is interesting, the content analysis unit can prominently display interesting scenes. Furthermore, if the content is tense, the content analysis unit can also display tense scenes less prominently. This allows for more appropriate display by adjusting the display method of the analysis results based on the emotion of the content. The emotion of the content is estimated using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the content analysis unit may be performed using, for example, an AI, or without an AI. For example, the content analysis unit can input the scenes and sounds of the content into the generation AI, and have the generation AI estimate the emotions of the content and adjust the way the analysis results are displayed.

[0082] During content analysis, the content analysis unit can prioritize analysis of highly relevant data by taking into account the geographical location information of the content. The content analysis unit, for example, analyzes data by taking into account the geographical location information of the content. The geographical location information of the content includes, but is not limited to, a specific region, a travel destination, or a home. For example, if the content is related to a specific region, the content analysis unit can prioritize analysis of data related to that region. Furthermore, if the content is related to travel, the content analysis unit can prioritize analysis of data related to the travel destination. Furthermore, if the content is related to home, the content analysis unit can prioritize analysis of data related to home. In this way, by taking into account the geographical location information of the content, highly relevant data can be prioritized for analysis. Some or all of the above-described processing in the content analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the content analysis unit can input the geographical location information of the content to a generation AI and cause the generation AI to perform a prioritized analysis of highly relevant data.

[0083] During content analysis, the content analysis unit can analyze the social media activity of the content and analyze related data. The content analysis unit, for example, analyzes the social media activity of the content and analyzes related data. The social media activity of the content includes, but is not limited to, shares, likes, follows, etc. The content analysis unit, for example, can prioritize analyzing data on content being shared on social media. It can also prioritize analyzing data on content being "liked" on social media. It can also prioritize analyzing data on accounts that follow the content on social media. In this way, related data can be analyzed by analyzing the social media activity of the content. Some or all of the above-described processing in the content analysis unit may be performed using, or without using, AI. For example, the content analysis unit can input the social media activity of the content into a generation AI and cause the generation AI to analyze the related data.

[0084] The generation unit can estimate the viewer's emotions and adjust the cutout video generation method based on the estimated viewer's emotions. The generation unit, for example, analyzes the viewer's comments to estimate the viewer's emotions. Viewer emotions include, but are not limited to, excitement, emotion, and dissatisfaction. For example, if the viewer is excited, the generation unit can focus on cutting out scenes that show excitement. Also, if the viewer is emotional, the generation unit can focus on cutting out emotional scenes. Furthermore, if the viewer is dissatisfied, the generation unit can exclude and cut out scenes that show dissatisfaction. In this way, by adjusting the cutout video generation method based on the viewer's emotions, a more appropriate video can be generated. The viewer's emotions are estimated using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or without AI. For example, the generation unit can input the viewer's comments into the generation AI and have the generation AI estimate the viewer's emotions and adjust the method for generating the cut-out video.

[0085] When generating a cutout video, the generation unit can optimize the generation algorithm by referring to past generation data. The generation unit, for example, optimizes the generation algorithm by referring to past generation data. Past generation data includes, for example, cutout videos that have received high ratings in the past and scenes related to a specific theme, but is not limited to these examples. The generation unit can optimize the generation algorithm by referring to data of cutout videos that have received high ratings in the past. Scenes related to a specific theme can be extracted from the past generation data and reflected in the generation algorithm. Furthermore, the generation unit can analyze the past generation data, identify scenes that attract viewers' attention, and optimize the generation algorithm. In this way, the generation algorithm can be optimized by referring to the past generation data. Some 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 input past generation data into the generation AI and cause the generation AI to optimize the generation algorithm.

[0086] When generating a cut-out video, the generation unit can customize the generation method by taking into account the viewer's device information. The generation unit customizes the generation method by taking into account, for example, the viewer's device information. The viewer's device information includes, but is not limited to, for example, a smartphone, a tablet, or a desktop. For example, if the viewer is using a smartphone, the generation unit can generate a short cut-out video. Furthermore, if the viewer is using a tablet, the generation unit can generate a detailed cut-out video. Furthermore, if the viewer is using a desktop, the generation unit can generate a long cut-out video. In this way, the generation method can be customized by taking into account the viewer's device information. Some or all of the above-described 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 input the viewer's device information into the generation AI and cause the generation AI to customize the generation method.

[0087] The generation unit can estimate the viewer's emotions and determine the priority of videos to be generated based on the estimated viewer's emotions. The generation unit, for example, analyzes the viewer's comments to estimate the viewer's emotions. Viewer emotions include, but are not limited to, excitement, emotion, and dissatisfaction. For example, if the viewer is excited, the generation unit can prioritize generating scenes that show excitement. Also, if the viewer is emotional, the generation unit can prioritize generating emotional scenes. Furthermore, if the viewer is dissatisfied, the generation unit can exclude scenes that show dissatisfaction when generating videos. This allows for the generation of more appropriate videos by determining the priority of videos to be generated based on the viewer's emotions. The estimation of the viewer's emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or without AI. For example, the generation unit can input viewer comments into the generation AI and have the generation AI estimate the viewer's emotions and determine the priority of the videos to be generated.

[0088] When generating a cut-out video, the generation unit can prioritize generating highly relevant videos by taking into account the viewer's geographical location information. The generation unit, for example, generates videos by taking into account the viewer's geographical location information. The viewer's geographical location information includes, but is not limited to, a specific region, a travel destination, or a home. For example, if the viewer is in a specific region, the generation unit can prioritize generating videos related to that region. Furthermore, if the viewer is traveling, the generation unit can prioritize generating videos related to the travel destination. Furthermore, if the viewer is at home, the generation unit can prioritize generating videos related to the home. In this way, highly relevant videos can be generated by taking into account the viewer's geographical location information. Some or all of the above-described processing by the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the viewer's geographical location information to the generation AI and cause the generation AI to prioritize generating highly relevant videos.

[0089] The generation unit can analyze the viewer's social media activity and generate related videos when generating the cut-out video. The generation unit, for example, analyzes the viewer's social media activity and generates related videos. The viewer's social media activity includes, but is not limited to, shares, likes, and follows. The generation unit can, for example, prioritize generating videos that the viewer has shared on social media. It can also prioritize generating videos that the viewer has "liked" on social media. It can also prioritize generating videos of accounts that the viewer follows on social media. In this way, related videos can be generated by analyzing the viewer's social media activity. Some or all of the above-described processing in the generation unit may be performed, for example, using AI or without AI. For example, the generation unit can input the viewer's social media activity into the generation AI and cause the generation AI to generate related videos. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, emotion analysis unit, content analysis unit, and generation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit analyzes viewers' comments using the control unit 46A of the smart device 14 and identifies parts of particular interest. The emotion analysis unit analyzes the emotions of the broadcaster using the identification processing unit 290 of the data processing device 12 and identifies emotional highlights. The content analysis unit analyzes the content of the video using the control unit 46A of the smart device 14 and identifies important scenes. The generation unit extracts highlights using the identification processing unit 290 of the data processing device 12 and generates a clipped video. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, emotion analysis unit, content analysis unit, and generation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit analyzes viewers' comments using the control unit 46A of the smart glasses 214 and identifies parts of particular interest. The emotion analysis unit analyzes the broadcaster's emotions using the identification processing unit 290 of the data processing device 12 and identifies emotional highlights. The content analysis unit analyzes the content of the video using the control unit 46A of the smart glasses 214 and identifies important scenes. The generation unit extracts highlights using the identification processing unit 290 of the data processing device 12 and generates a clipped video. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, emotion analysis unit, content analysis unit, and generation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit analyzes viewers' comments using the control unit 46A of the headset type terminal 314 and identifies parts of particular interest. The emotion analysis unit analyzes the emotions of the broadcaster using the identification processing unit 290 of the data processing device 12 and identifies emotional highs. The content analysis unit analyzes the content of the video using the control unit 46A of the headset type terminal 314 and identifies important scenes. The generation unit extracts highlights using the identification processing unit 290 of the data processing device 12 and generates a clipped video. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, emotion analysis unit, content analysis unit, and generation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit analyzes viewers' comments using the control unit 46A of the robot 414 and identifies parts of particular interest. The emotion analysis unit analyzes the emotions of the distributor using the identification processing unit 290 of the data processing device 12 and identifies emotional intensities. The content analysis unit analyzes the content of the video using the control unit 46A of the robot 414 and identifies important scenes. The generation unit extracts highlights using the identification processing unit 290 of the data processing device 12 and generates a clipped video.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] When analyzing viewer comments, the analysis unit can adjust the analysis method taking into account the viewer's age group. For example, if there are many young viewers, it can prioritize analyzing comments containing slang and buzzwords to identify highlights. On the other hand, if there are many middle-aged and older viewers, it can focus on analyzing comments using more formal language. Furthermore, it can also take into account the viewer's tendency to be interested in certain topics depending on their age group and prioritize analyzing comments related to those topics. In this way, by adjusting the comment analysis method based on the viewer's age group, it is possible to identify more appropriate highlights.

[0092] When analyzing a streamer's emotions, the emotion analysis unit learns the streamer's past emotional patterns and can predict emotional changes. For example, if a streamer has expressed strong emotions in a particular situation in the past, it can predict similar emotions when that situation occurs again. It can also track the streamer's emotional changes in real time and identify emotional peaks. Furthermore, based on the streamer's emotional changes, it can focus its analysis on scenes where emotional intensity is predicted to increase. This makes it possible to efficiently extract highlights by predicting the streamer's emotional changes.

[0093] When analyzing the content of a video, the content analysis unit can customize the analysis method according to the genre of the video. For example, in the case of a comedy video, it can focus on analyzing funny scenes to identify highlights. In the case of a documentary video, it can focus on analyzing important information and interview scenes. Furthermore, in the case of an action video, it can focus on analyzing action scenes and the climax. In this way, by customizing the analysis method according to the genre of the video, it is possible to identify more appropriate highlights.

[0094] The generation unit can automatically extract highlights based on a comprehensive consideration of viewer comments, the streamer's emotions, and the content of the content, and generate a cut-out video. The generation unit can generate a cut-out video using a generation AI that inputs viewer comments, the streamer's emotions, and the content of the content and outputs highlights. For example, the generation unit can extract the most noteworthy scenes by comprehensively considering scenes that receive many viewer comments, scenes that elicit the streamer's emotions, the climax of the story, etc. This makes it possible to efficiently extract highlights and generate a cut-out video by comprehensively considering viewer comments, the streamer's emotions, and the content of the content. Some or all of the above-described processing by the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input viewer comments, the streamer's emotions, and the content of the content into the generation AI and have the generation AI extract highlights and generate a cut-out video.

[0095] When analyzing viewer comments, the analysis unit can estimate the viewer's interests and adjust the comment analysis method based on the estimated interests. For example, if a viewer is interested in a particular genre, comments related to that genre can be analyzed preferentially to identify highlights. Also, if a viewer is interested in a particular character or scene, comments related to that character or scene can be analyzed with a focus. Furthermore, based on the viewer's interests, comments containing related keywords can also be analyzed preferentially. In this way, by adjusting the comment analysis method based on the viewer's interests, more appropriate highlights can be identified.

[0096] When analyzing a streamer's emotions, the emotion analysis unit can analyze not only the streamer's tone of voice, but also their gestures and body movements. For example, by identifying scenes in which the streamer is waving their hands or making large body movements, it is possible to more accurately identify emotional heights. It is also possible to identify the type of emotion based on the streamer's gestures and body movements. Furthermore, by comprehensively analyzing the streamer's tone of voice, gestures, and body movements, it is possible to identify emotional peaks. This allows for a more accurate analysis of the streamer's emotions, allowing for efficient extraction of highlights.

[0097] When analyzing the content of a video, the content analysis unit can adjust the analysis method taking into account the time of day the video is viewed. For example, if a viewer often watches at night, it can focus on analyzing relaxing or moving scenes to identify highlights. Alternatively, if a viewer often watches during the day, it can focus on analyzing active or interesting scenes. Furthermore, it can prioritize analysis of scenes related to a specific theme depending on the viewer's viewing time. This allows for more appropriate highlights to be identified by adjusting the analysis method based on the viewing time.

[0098] The generation unit can automatically extract highlights based on a comprehensive consideration of viewer comments, the streamer's emotions, and the content of the content, and generate a cut-out video. The generation unit can generate a cut-out video using a generation AI that inputs viewer comments, the streamer's emotions, and the content of the content and outputs highlights. For example, the generation unit can extract the most noteworthy scenes by comprehensively considering scenes that receive many viewer comments, scenes that elicit the streamer's emotions, the climax of the story, etc. This makes it possible to efficiently extract highlights and generate a cut-out video by comprehensively considering viewer comments, the streamer's emotions, and the content of the content. Some or all of the above-described processing by the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input viewer comments, the streamer's emotions, and the content of the content into the generation AI and have the generation AI extract highlights and generate a cut-out video.

[0099] When analyzing viewer comments, the analysis unit can adjust the analysis method taking into account the language of the viewer comments. For example, if a viewer comments in English, the analysis unit can prioritize analyzing the English comments to identify highlights. Also, if a viewer comments in multiple languages, the analysis unit can analyze comments in each language equally. Furthermore, based on the language of the viewer comments, the analysis unit can prioritize analyzing comments related to a particular culture or background. This allows for more appropriate highlights to be identified by adjusting the analysis method based on the language of the viewer comments.

[0100] When analyzing a streamer's emotions, the emotion analysis unit can also analyze the streamer's background and environmental sounds. For example, by identifying scenes where cheering is occurring around the streamer or scenes where the streamer is talking in a quiet environment, it is possible to more accurately identify emotional heights. It is also possible to identify the type of emotion based on the streamer's background and environmental sounds. Furthermore, by comprehensively analyzing the streamer's tone of voice and the background and environmental sounds, it is possible to identify emotional peaks. This allows for a more accurate analysis of the streamer's emotions, allowing for efficient extraction of highlights.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The analysis unit analyzes the viewer's comments. The viewer's comments include text comments, emojis, links, etc. The analysis unit uses natural language processing technology to analyze the comments and identify parts of the video that the viewer is particularly interested in. For example, if a viewer comments, "This scene is interesting!", that scene is identified as a highlight. It is also possible to identify parts of the video that the viewer is particularly interested in based on the frequency of comments and the results of sentiment analysis. Step 2: The emotion analysis unit analyzes the streamer's emotions. Streamer emotions include joy, sadness, anger, etc. The emotion analysis unit uses facial recognition technology to analyze the streamer's facial expressions and identify emotional intensity. It can also use voice analysis technology to analyze the streamer's tone of voice and identify emotional intensity. For example, it can identify scenes where the streamer is laughing or feeling moved. Step 3: The content analysis unit analyzes the content of the video. The content of the video includes scene types, audio, text, etc. The content analysis unit analyzes the scenes in the video and identifies important scenes and story developments. For example, it identifies scenes that include the climax of the story or important statements. It can also identify important scenes based on viewer reactions and the content of the scenes. Step 4: The generation unit takes into consideration the viewer's comments, the streamer's emotions, and the content of the content, automatically extracts the highlights, and generates a cut-out video.The generation unit takes the viewer's comments, the streamer's emotions, and the content of the content as input, and uses generation AI to output the highlights, generating a cut-out video.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0104] 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 engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0105] Furthermore, the processing by the data processing system 10 described above 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 necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0106] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0109] 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, RAM 30, and 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.

[0110] 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.

[0111] 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 audio according to instructions from the processor 46.

[0112] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0113] 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 carried out in a secure state.

[0114] Fig. 4 shows an example of the 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.

[0115] 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.

[0116] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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. The smart glasses 214 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0118] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0120] 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. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0121] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, 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, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 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.

[0125] 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, RAM 30, and 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.

[0126] 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.

[0127] 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 audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] 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 carried out in a secure state.

[0130] 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.

[0131] 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.

[0132] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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.

[0134] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0136] 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. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0137] 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 also 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. Furthermore, 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, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 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.

[0141] 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, RAM 30, and 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.

[0142] 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.

[0143] 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 audio according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0145] 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 carried out in a secure state.

[0146] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0147] 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.

[0148] 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.

[0149] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0150] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0151] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0152] 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 voice indicating a user input regarding 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.

[0153] 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. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0154] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0157] FIG. 9 illustrates 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. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0158] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically 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.

[0159] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0160] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0161] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0162] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of 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, "relieved," "calm," and "reassuring," have similar emotion values.

[0163] 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.

[0164] 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 USB (Universal Serial Bus) 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.

[0165] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0166] 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.

[0167] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0168] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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.

[0169] As an example of a system configured with a single 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 system that uses a processor that realizes the functions of an 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.

[0170] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0171] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0172] The above-described description and illustrations are a detailed explanation 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, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects 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 replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0173] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0174] [Explanation of symbols]

[0175] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes the contents of the comment field; an emotion analysis unit that analyzes the emotion of the distributor based on the content of the comment field analyzed by the analysis unit; a content analysis unit that analyzes the content based on the emotion analyzed by the emotion analysis unit; a generation unit that generates a cut-out video based on the content analyzed by the content analysis unit. A system characterized by:

2. The analysis unit Analyze viewer comments to identify areas of particular interest 2. The system of claim 1.

3. The emotion analysis unit Analyzing the streamer's facial expressions and tone of voice to identify emotional intensities 2. The system of claim 1.

4. The content analysis unit Analyze video content to identify key scenes and story developments 2. The system of claim 1.

5. The generation unit Based on the viewer's comments, the streamer's emotions, and the content itself, the system automatically extracts the highlights and generates a cut-out video.

2. The system of claim 1.

6. The analysis unit Estimate viewer sentiment and adjust comment analysis based on the estimated viewer sentiment 2. The system of claim 1.

7. The analysis unit When analyzing comments, refer to the viewer's past comment history to improve the accuracy of the analysis.

2. The system of claim 1.

8. The analysis unit Customize comment analysis based on viewer device information 2. The system of claim 1.

Images