system

Abstract

The system according to this embodiment aims to streamline the editing process for explanatory videos and to predict viewer reactions. [Solution] The system according to the embodiment comprises an analysis unit, a generation unit, and a prediction unit. The analysis unit analyzes real-time explanatory video and extracts key points. The generation unit automatically generates a digest version video based on the points extracted by the analysis unit. The prediction unit analyzes the viewer's viewing time and viewing trends based on the video generated by the generation unit and creates a video reaction prediction.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the editing work of an explanatory video takes time and it is difficult to predict the reaction of viewers.

[0005] The system according to the embodiment aims to improve the efficiency of the editing work of an explanatory video and predict the reaction of viewers.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a generation unit, and a prediction unit. The analysis unit analyzes real-time explanatory video and extracts key points. The generation unit automatically generates a digest version video based on the points extracted by the analysis unit. The prediction unit analyzes viewer viewing time and viewing trends based on the video generated by the generation unit and creates a video response prediction. [Effects of the Invention]

[0007] The system according to this embodiment can streamline the editing process for explanatory videos and predict viewer reactions. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The video editing system according to an embodiment of the present invention is a system that uses a generating AI to automatically generate a digest version video with key summary points, in order to streamline the video editing work for product presentations held both inside and outside the company. In this video editing system, first, the generating AI analyzes the presentation video in real time and extracts important points. Next, based on the extracted points, the generating AI automatically generates a digest version video. Furthermore, it analyzes the viewing time and viewing trends of viewers and creates a video response prediction (inquiries and applications). For example, the generating AI analyzes the presentation video in real time. In this process, the generating AI understands the content of the video and extracts important points. For example, it can extract important information such as product features, advantages, and usage instructions. This allows the generating AI to narrow down the key summary points. Next, based on the extracted points, the generating AI automatically generates a digest version video. The generating AI combines the extracted important points to create a digest version video that is easy for viewers to understand. For example, it can generate a short video that emphasizes the features and advantages of the product. This allows viewers to grasp important information in a short amount of time. Furthermore, the system analyzes viewer viewing time and trends to create video response predictions. The generating AI collects and analyzes data such as which parts viewers watched and for how long. This allows it to predict viewer interest and reactions. For example, if a viewer watches a particular part for a long time, it can be determined that they have a high level of interest in that part, and it can be predicted that they are likely to make inquiries or applications. This system streamlines video editing and automatically generates easy-to-understand digest videos for viewers. In addition, effective marketing strategies can be developed based on viewer response predictions. For example, by conducting promotions that emphasize parts of the video that viewers are most interested in, an increase in inquiries and applications can be expected. As a result, the video editing system can streamline video editing for product presentations held both internally and externally, and automatically generate easy-to-understand digest videos for viewers. In addition, effective marketing strategies can be developed based on viewer response predictions.

[0029] The video editing system according to this embodiment comprises an analysis unit, a generation unit, and a prediction unit. The analysis unit analyzes a real-time presentation video and extracts key points. The analysis unit, for example, uses a generation AI to understand the content of the video and extract important points. The generation AI can extract important information such as product features, benefits, and usage instructions using a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the generation AI converts audio data in the video into text and extracts important keywords and phrases. The generation AI can also analyze the content of slides and materials in the video and extract important information. The generation unit automatically generates a digest video based on the points extracted by the analysis unit. The generation unit, for example, uses a generation AI to combine the extracted important points and create a digest video that is easy for viewers to understand. The generation AI can generate a visually appealing video based on the extracted points. For example, the generation AI generates a short video that emphasizes the features and benefits of the product. The generation AI can also add effects and animations that will attract the viewer's attention. The prediction unit analyzes viewer viewing time and viewing trends based on the video generated by the generation unit and creates a video response prediction. The prediction unit collects and analyzes data such as which parts viewers watched and for how long, for example, using generation AI. Based on the viewer's viewing data, the generation AI can predict the viewer's level of interest and response. For example, if a viewer watches a particular part for a long time, the generation AI will determine that the viewer has a high level of interest in that part and predict that there is a high probability of inquiries or applications. The generation AI can also improve the accuracy of response predictions by considering the viewer's viewing history and attribute information. As a result, the video editing system according to the embodiment can efficiently summarize real-time explanatory video and predict viewer responses.

[0030] The analysis unit can extract important information about the product's features, benefits, and usage. For example, the analysis unit uses generative AI to extract important information such as product features, benefits, and usage. The generative AI can convert audio data within a video into text using text generation AI (e.g., LLM) or multimodal generation AI, and extract important keywords and phrases. For example, the generative AI can extract the parts that describe the product's features and summarize their content. It can also extract the parts that emphasize the product's benefits and summarize their content. Furthermore, the generative AI can extract the parts that explain how to use the product and summarize their content. This allows the analysis unit to efficiently extract important information about the product.

[0031] The generation unit can generate a digest video by combining the extracted points. For example, the generation unit uses a generation AI to combine the extracted key points to generate a digest video. Based on the extracted points, the generation AI can generate a visually appealing video. For example, the generation AI can generate a short video that highlights the features and benefits of a product. The generation AI can also add effects and animations to attract the viewer's attention. Furthermore, the generation AI can devise the structure and order of the video to attract the viewer's attention. For example, the generation AI can arrange points in an order that is likely to interest the viewer, keeping the viewer engaged. As a result, the generation unit can automatically generate a digest video that is easy for viewers to understand.

[0032] The prediction unit can collect and analyze data on which parts viewers watched and for how long. For example, the prediction unit uses generative AI to collect and analyze data such as which parts viewers watched and for how long. Based on the viewers' viewing data, the generative AI can predict viewers' level of interest and reactions. For example, if a viewer watches a particular part for a long time, the generative AI will determine that the viewer has a high level of interest in that part and predict that there is a high probability of inquiries or applications. The generative AI can also improve the accuracy of reaction predictions by considering the viewers' viewing history and attribute information. This allows the prediction unit to analyze viewers' viewing trends in detail.

[0033] The prediction unit can predict viewer reactions. For example, using generative AI, the prediction unit can predict viewer interest and reactions based on viewer viewing data. If a viewer watches a particular section for a long time, the generative AI will determine that they have a high level of interest in that section and predict that there is a high probability of inquiries or applications. The generative AI can also improve the accuracy of reaction predictions by considering the viewer's viewing history and attribute information. As a result, the prediction unit can develop effective marketing strategies by predicting viewer reactions. For example, by conducting promotions that emphasize the parts that are of high interest to viewers, an increase in inquiries and applications can be expected.

[0034] The analysis unit can improve the accuracy of extracting important points based on past video data of the briefing sessions. For example, the analysis unit can use a generative AI to refer to past video data of the briefing sessions and improve the accuracy of extracting important points. The generative AI can learn common important points from past briefing session videos and improve extraction accuracy. For example, the generative AI can refer to past viewer reaction data and extract points that viewers were interested in. The generative AI can also evaluate the accuracy of the points extracted from past video data and apply the optimal extraction algorithm. As a result, the analysis unit can improve the accuracy of extracting important points by referring to past data.

[0035] The analysis unit can apply multiple extraction algorithms depending on the content of the briefing. For example, the analysis unit can use a generative AI to apply different extraction algorithms depending on the content of the briefing. The generative AI can select the optimal extraction algorithm according to the content of the briefing and extract important points. For example, in a technical briefing about a product, the generative AI can apply an extraction algorithm that emphasizes technical details. In a marketing briefing, it can also apply an extraction algorithm that emphasizes points that attract the audience's attention. Furthermore, in a training briefing, it can apply an extraction algorithm that emphasizes points that enhance learning effectiveness. As a result, the analysis unit can improve the accuracy of extracting important points by applying the optimal extraction algorithm according to the content of the briefing.

[0036] The analysis unit can analyze the speaker's speaking style and tone during a presentation and extract key points. For example, the analysis unit uses generative AI to analyze the speaker's speaking style and tone and extract important points. The generative AI can analyze the speaker's emphasized parts and changes in tone and extract points that will attract the audience's attention. For example, the generative AI extracts the parts the speaker emphasizes as important points. The generative AI can also analyze changes in the speaker's tone and extract points that will attract the audience's attention. Furthermore, the generative AI can analyze the rhythm of the speaker's speech and extract parts containing important information. As a result, the analysis unit can accurately extract important points by analyzing the speaker's speaking style and tone.

[0037] The analysis unit can analyze the slides and materials of a presentation and extract key points in conjunction with the video content. For example, the analysis unit uses a generation AI to analyze the slides and materials of a presentation and extract important points in conjunction with the video content. The generation AI can analyze the text of the slides and the charts and graphs of the materials and extract parts that contain visually important information. For example, the generation AI can analyze the text of the slides and extract parts that contain important keywords. The generation AI can also analyze the charts and graphs of the materials and extract parts that contain visually important information. Furthermore, the generation AI can analyze the structure of the slides and extract important points in conjunction with the video content. As a result, the analysis unit can extract important points in conjunction with the video content by analyzing the slides and materials.

[0038] The generation unit can adjust the level of detail in the digest video based on the importance of the extracted points. For example, the generation unit can use a generation AI to adjust the level of detail in the digest video based on the importance of the extracted points. The generation AI can evaluate the importance of the extracted points and adjust the level of detail in the video according to their importance. For example, the generation AI can add detailed explanations to points of high importance and generate a video. The generation AI can also add concise explanations to points of low importance and generate a video. Furthermore, the generation AI can also adjust the length of the video according to its importance. In this way, the generation unit can provide the optimal amount of information to the viewer by adjusting the level of detail in the video according to the importance of the points.

[0039] The generation unit can apply multiple generation algorithms to the digest video depending on the viewer's area of ​​interest. For example, the generation unit can use a generation AI to apply different generation algorithms depending on the viewer's area of ​​interest when generating the digest video. The generation AI can identify the viewer's area of ​​interest and select the optimal generation algorithm. For example, the generation AI can generate a video that emphasizes technical details for viewers with technical interests. It can also generate a video that emphasizes points that will capture the viewer's interest for viewers with marketing interests. Furthermore, it can generate a video that emphasizes points that enhance learning effectiveness for viewers with training interests. In this way, the generation unit can generate more interesting videos for viewers by applying a generation algorithm that matches the viewer's area of ​​interest.

[0040] The generation unit can adjust the order of videos based on the viewer's viewing history when generating a digest version of a video. For example, the generation unit uses a generation AI to adjust the order of videos based on the viewer's viewing history when generating a digest version of a video. The generation AI can analyze the viewer's past viewing data and generate videos in the optimal order. For example, the generation AI can generate videos in the optimal order by referring to the order in which the viewer has watched videos in the past. The generation AI can also prioritize points of high interest based on the viewer's viewing history. Furthermore, the generation AI can analyze the viewer's viewing history and generate videos in an order that is easy for the viewer to understand. As a result, the generation unit can provide videos in the optimal order for the viewer by adjusting the order of videos based on the viewer's viewing history.

[0041] The generation unit can generate digest videos in the optimal format based on the viewer's device information. For example, the generation unit uses a generation AI to generate digest videos in the optimal format, taking the viewer's device information into consideration. The generation AI can identify the viewer's device information and select the optimal format. For example, if the viewer is using a smartphone, the generation AI will generate the video in a format optimized for smartphones. If the viewer is using a tablet, the generation AI can also generate the video in a format optimized for tablets. Furthermore, if the viewer is using a desktop computer, the generation AI can also generate the video in a format optimized for desktop computers. In this way, the generation unit can provide viewers with the best possible viewing experience by generating videos in the optimal format based on the viewer's device information.

[0042] The prediction unit can optimize the response prediction algorithm based on the viewer's past viewing data. For example, the prediction unit uses generative AI to refer to the viewer's past viewing data and optimize the response prediction algorithm. The generative AI can analyze the viewer's past viewing data and optimize the response prediction algorithm. For example, the generative AI identifies points that will attract the viewer's interest from the viewer's past viewing data and makes a response prediction. The generative AI can also predict the likelihood of inquiries or applications based on the viewer's past viewing data. As a result, the accuracy of the response prediction algorithm is improved by the prediction unit referring to the viewer's past viewing data.

[0043] The prediction unit can improve the accuracy of response predictions based on viewer attribute information. For example, the prediction unit uses generative AI to improve the accuracy of response predictions by considering viewer attribute information. Generative AI can perform response predictions by considering viewer attribute information such as age and gender. For example, generative AI can predict the likelihood of inquiries or applications based on viewer age and gender. Generative AI can also perform response predictions by considering viewer occupation and interests. Furthermore, generative AI can perform response predictions by considering viewer region and cultural background. As a result, the prediction unit improves the accuracy of response predictions by considering viewer attribute information.

[0044] The prediction unit can improve the accuracy of response predictions based on the geographical location information of viewers. For example, the prediction unit uses generative AI to improve the accuracy of response predictions by considering the geographical location information of viewers. The generative AI can predict response trends for each region based on the geographical location information of viewers. For example, the generative AI can predict the likelihood of inquiries and applications for each region by considering the geographical location information of viewers. In addition, the generative AI can identify points of interest for each region based on the geographical location information of viewers and perform response predictions. As a result, the prediction unit improves the accuracy of response predictions by considering the geographical location information of viewers.

[0045] The prediction unit can analyze viewers' social media activity and improve the accuracy of response predictions. For example, the prediction unit uses generative AI to analyze viewers' social media activity and improve the accuracy of response predictions. Generative AI can analyze viewers' social media activity and identify points of high interest. For example, based on viewers' social media responses, generative AI can predict the likelihood of inquiries or applications. Generative AI can also optimize the response prediction algorithm by considering viewers' social media activity. As a result, the prediction unit improves the accuracy of response predictions by analyzing viewers' social media activity.

[0046] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0047] The analysis unit can improve the accuracy of extracting important points based on past video data of information sessions. For example, the generation AI can learn common important points from past information session videos and improve extraction accuracy. The generation AI refers to past viewer reaction data and extracts points that viewers were interested in. The generation AI can also evaluate the accuracy of points extracted from past video data and apply the optimal extraction algorithm. As a result, the analysis unit can improve the accuracy of extracting important points by referring to past data.

[0048] The generation unit can apply multiple generation algorithms to create digest videos according to the viewer's areas of interest. For example, the generation AI can identify the viewer's areas of interest and select the optimal generation algorithm. For viewers with technical interests, the generation AI can generate videos that emphasize technical details. For viewers with marketing interests, it can generate videos that emphasize points that will capture the viewer's attention. Furthermore, for viewers with training interests, it can generate videos that emphasize points that enhance learning effectiveness. In this way, the generation unit can create more interesting videos for viewers by applying generation algorithms tailored to their areas of interest.

[0049] The prediction unit can optimize the response prediction algorithm based on the viewer's past viewing data. For example, the generative AI can analyze the viewer's past viewing data and optimize the response prediction algorithm. The generative AI identifies points that will attract the viewer's interest from the viewer's past viewing data and makes a response prediction. The generative AI can also predict the likelihood of inquiries or applications based on the viewer's past viewing data. As a result, the accuracy of the response prediction algorithm is improved by the prediction unit referring to the viewer's past viewing data.

[0050] The analysis unit can analyze the speaker's speaking style and tone during a presentation and extract key points. For example, the generation AI can analyze the speaker's emphasized parts and changes in tone to extract points that will capture the audience's attention. The generation AI extracts the parts the speaker emphasizes as important points. Furthermore, the generation AI can analyze changes in the speaker's tone and extract points that will capture the audience's attention. In addition, the generation AI can analyze the rhythm of the speaker's speech and extract parts containing important information. As a result, the analysis unit can accurately extract important points by analyzing the speaker's speaking style and tone.

[0051] The generation unit can generate digest videos in the optimal format based on the viewer's device information. For example, the generation AI can identify the viewer's device information and select the optimal format. If the viewer is using a smartphone, the generation AI will generate the video in a format optimized for smartphones. If the viewer is using a tablet, the generation AI can also generate the video in a format optimized for tablets. Furthermore, if the viewer is using a desktop computer, the generation AI can also generate the video in a format optimized for desktop computers. As a result, the generation unit can provide viewers with the best possible viewing experience by generating videos in the optimal format based on their device information.

[0052] The following briefly describes the processing flow for example form 1.

[0053] Step 1: The analysis unit analyzes the real-time presentation video and extracts key points. The analysis unit uses generative AI to understand the content of the video and extract important points. The generative AI uses text generation AI (e.g., LLM) or multimodal generation AI to extract important information such as product features, benefits, and usage instructions. For example, the generative AI converts audio data in the video into text and extracts important keywords and phrases. The generative AI can also analyze the content of slides and materials in the video and extract important information. Step 2: The generation unit automatically generates a digest video based on the points extracted by the analysis unit. The generation unit uses a generation AI to combine the extracted key points and create an easy-to-understand digest video for viewers. The generation AI can generate a visually appealing video based on the extracted points. For example, the generation AI can generate a short video that highlights the features and benefits of a product. The generation AI can also add effects and animations to attract the viewer's attention. Step 3: The prediction unit analyzes viewer viewing time and viewing trends based on the video generated by the generation unit and creates a video response prediction. The prediction unit uses generation AI to collect and analyze data such as which parts viewers watched and for how long. Based on viewer viewing data, generation AI can predict viewer interest and response. For example, if a viewer watches a particular part for a long time, generation AI will determine that they have a high level of interest in that part and predict that there is a high probability of inquiries or applications. Furthermore, generation AI can also improve the accuracy of response predictions by considering the viewer's viewing history and attribute information.

[0054] (Example of form 2) The video editing system according to an embodiment of the present invention is a system that uses a generating AI to automatically generate a digest version video with key summary points, in order to streamline the video editing work for product presentations held both inside and outside the company. In this video editing system, first, the generating AI analyzes the presentation video in real time and extracts important points. Next, based on the extracted points, the generating AI automatically generates a digest version video. Furthermore, it analyzes the viewing time and viewing trends of viewers and creates a video response prediction (inquiries and applications). For example, the generating AI analyzes the presentation video in real time. In this process, the generating AI understands the content of the video and extracts important points. For example, it can extract important information such as product features, advantages, and usage instructions. This allows the generating AI to narrow down the key summary points. Next, based on the extracted points, the generating AI automatically generates a digest version video. The generating AI combines the extracted important points to create a digest version video that is easy for viewers to understand. For example, it can generate a short video that emphasizes the features and advantages of the product. This allows viewers to grasp important information in a short amount of time. Furthermore, the system analyzes viewer viewing time and trends to create video response predictions. The generating AI collects and analyzes data such as which parts viewers watched and for how long. This allows it to predict viewer interest and reactions. For example, if a viewer watches a particular part for a long time, it can be determined that they have a high level of interest in that part, and it can be predicted that they are likely to make inquiries or applications. This system streamlines video editing and automatically generates easy-to-understand digest videos for viewers. In addition, effective marketing strategies can be developed based on viewer response predictions. For example, by conducting promotions that emphasize parts of the video that viewers are most interested in, an increase in inquiries and applications can be expected. As a result, the video editing system can streamline video editing for product presentations held both internally and externally, and automatically generate easy-to-understand digest videos for viewers. In addition, effective marketing strategies can be developed based on viewer response predictions.

[0055] The video editing system according to this embodiment comprises an analysis unit, a generation unit, and a prediction unit. The analysis unit analyzes a real-time presentation video and extracts key points. The analysis unit, for example, uses a generation AI to understand the content of the video and extract important points. The generation AI can extract important information such as product features, benefits, and usage instructions using a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the generation AI converts audio data in the video into text and extracts important keywords and phrases. The generation AI can also analyze the content of slides and materials in the video and extract important information. The generation unit automatically generates a digest video based on the points extracted by the analysis unit. The generation unit, for example, uses a generation AI to combine the extracted important points and create a digest video that is easy for viewers to understand. The generation AI can generate a visually appealing video based on the extracted points. For example, the generation AI generates a short video that emphasizes the features and benefits of the product. The generation AI can also add effects and animations that will attract the viewer's attention. The prediction unit analyzes viewer viewing time and viewing trends based on the video generated by the generation unit and creates a video response prediction. The prediction unit collects and analyzes data such as which parts viewers watched and for how long, for example, using generation AI. Based on the viewer's viewing data, the generation AI can predict the viewer's level of interest and response. For example, if a viewer watches a particular part for a long time, the generation AI will determine that the viewer has a high level of interest in that part and predict that there is a high probability of inquiries or applications. The generation AI can also improve the accuracy of response predictions by considering the viewer's viewing history and attribute information. As a result, the video editing system according to the embodiment can efficiently summarize real-time explanatory video and predict viewer responses.

[0056] The analysis unit can extract important information about the product's features, benefits, and usage. For example, the analysis unit uses generative AI to extract important information such as product features, benefits, and usage. The generative AI can convert audio data within a video into text using text generation AI (e.g., LLM) or multimodal generation AI, and extract important keywords and phrases. For example, the generative AI can extract the parts that describe the product's features and summarize their content. It can also extract the parts that emphasize the product's benefits and summarize their content. Furthermore, the generative AI can extract the parts that explain how to use the product and summarize their content. This allows the analysis unit to efficiently extract important information about the product.

[0057] The generation unit can generate a digest video by combining the extracted points. For example, the generation unit uses a generation AI to combine the extracted key points to generate a digest video. Based on the extracted points, the generation AI can generate a visually appealing video. For example, the generation AI can generate a short video that highlights the features and benefits of a product. The generation AI can also add effects and animations to attract the viewer's attention. Furthermore, the generation AI can devise the structure and order of the video to attract the viewer's attention. For example, the generation AI can arrange points in an order that is likely to interest the viewer, keeping the viewer engaged. As a result, the generation unit can automatically generate a digest video that is easy for viewers to understand.

[0058] The prediction unit can collect and analyze data on which parts viewers watched and for how long. For example, the prediction unit uses generative AI to collect and analyze data such as which parts viewers watched and for how long. Based on the viewers' viewing data, the generative AI can predict viewers' level of interest and reactions. For example, if a viewer watches a particular part for a long time, the generative AI will determine that the viewer has a high level of interest in that part and predict that there is a high probability of inquiries or applications. The generative AI can also improve the accuracy of reaction predictions by considering the viewers' viewing history and attribute information. This allows the prediction unit to analyze viewers' viewing trends in detail.

[0059] The prediction unit can predict viewer reactions. For example, using generative AI, the prediction unit can predict viewer interest and reactions based on viewer viewing data. If a viewer watches a particular section for a long time, the generative AI will determine that they have a high level of interest in that section and predict that there is a high probability of inquiries or applications. The generative AI can also improve the accuracy of reaction predictions by considering the viewer's viewing history and attribute information. As a result, the prediction unit can develop effective marketing strategies by predicting viewer reactions. For example, by conducting promotions that emphasize the parts that are of high interest to viewers, an increase in inquiries and applications can be expected.

[0060] The analysis unit can estimate the viewer's emotions and adjust the criteria for extracting key points based on those estimated emotions. For example, the analysis unit can use generative AI to estimate the viewer's emotions and adjust the criteria for extracting important points based on those estimated emotions. The generative AI can estimate the viewer's emotions using facial expression analysis and voice analysis. For example, if the viewer is excited, the generative AI will prioritize extracting points that will capture the viewer's interest. If the viewer is bored, the generative AI can also extract points that will regain the viewer's attention. Furthermore, if the viewer is attentive, the generative AI can extract points that contain detailed information. As a result, the analysis unit can create a more appropriate summary by adjusting the criteria for extracting important points according to the viewer's emotions.

[0061] The analysis unit can improve the accuracy of extracting important points based on past video data of the briefing sessions. For example, the analysis unit can use a generative AI to refer to past video data of the briefing sessions and improve the accuracy of extracting important points. The generative AI can learn common important points from past briefing session videos and improve extraction accuracy. For example, the generative AI can refer to past viewer reaction data and extract points that viewers were interested in. The generative AI can also evaluate the accuracy of the points extracted from past video data and apply the optimal extraction algorithm. As a result, the analysis unit can improve the accuracy of extracting important points by referring to past data.

[0062] The analysis unit can apply multiple extraction algorithms depending on the content of the briefing. For example, the analysis unit can use a generative AI to apply different extraction algorithms depending on the content of the briefing. The generative AI can select the optimal extraction algorithm according to the content of the briefing and extract important points. For example, in a technical briefing about a product, the generative AI can apply an extraction algorithm that emphasizes technical details. In a marketing briefing, it can also apply an extraction algorithm that emphasizes points that attract the audience's attention. Furthermore, in a training briefing, it can apply an extraction algorithm that emphasizes points that enhance learning effectiveness. As a result, the analysis unit can improve the accuracy of extracting important points by applying the optimal extraction algorithm according to the content of the briefing.

[0063] The analysis unit can estimate the viewer's emotions and determine the order of points to extract based on those estimated emotions. For example, the analysis unit can use generative AI to estimate the viewer's emotions and determine the priority of points to extract based on those estimated emotions. The generative AI can estimate the viewer's emotions using facial expression analysis and voice analysis. For example, if the viewer is excited, the generative AI will prioritize extracting points that will capture the viewer's interest. If the viewer is bored, the generative AI can also prioritize extracting points that will regain the viewer's attention. Furthermore, if the viewer is focused, the generative AI can also prioritize extracting points that contain detailed information. This allows the analysis unit to perform more effective summarization by determining the priority of points to extract according to the viewer's emotions.

[0064] The analysis unit can analyze the speaker's speaking style and tone during a presentation and extract key points. For example, the analysis unit uses generative AI to analyze the speaker's speaking style and tone and extract important points. The generative AI can analyze the speaker's emphasized parts and changes in tone and extract points that will attract the audience's attention. For example, the generative AI extracts the parts the speaker emphasizes as important points. The generative AI can also analyze changes in the speaker's tone and extract points that will attract the audience's attention. Furthermore, the generative AI can analyze the rhythm of the speaker's speech and extract parts containing important information. As a result, the analysis unit can accurately extract important points by analyzing the speaker's speaking style and tone.

[0065] The analysis unit can analyze the slides and materials of a presentation and extract key points in conjunction with the video content. For example, the analysis unit uses a generation AI to analyze the slides and materials of a presentation and extract important points in conjunction with the video content. The generation AI can analyze the text of the slides and the charts and graphs of the materials and extract parts that contain visually important information. For example, the generation AI can analyze the text of the slides and extract parts that contain important keywords. The generation AI can also analyze the charts and graphs of the materials and extract parts that contain visually important information. Furthermore, the generation AI can analyze the structure of the slides and extract important points in conjunction with the video content. As a result, the analysis unit can extract important points in conjunction with the video content by analyzing the slides and materials.

[0066] The generation unit can estimate the viewer's emotions and adjust the presentation of the digest video based on those estimated emotions. For example, the generation unit uses a generation AI to estimate the viewer's emotions and adjust the presentation of the digest video based on those estimated emotions. The generation AI can estimate the viewer's emotions using facial expression analysis and voice analysis. For example, if the viewer is excited, the generation AI can generate a video with visually stimulating effects. If the viewer is relaxed, the generation AI can also generate a video with a calm tone. Furthermore, if the viewer is focused, the generation AI can generate a video with detailed information. In this way, the generation unit can create a more engaging video for the viewer by adjusting the presentation of the digest video according to the viewer's emotions.

[0067] The generation unit can adjust the level of detail in the digest video based on the importance of the extracted points. For example, the generation unit can use a generation AI to adjust the level of detail in the digest video based on the importance of the extracted points. The generation AI can evaluate the importance of the extracted points and adjust the level of detail in the video according to their importance. For example, the generation AI can add detailed explanations to points of high importance and generate a video. The generation AI can also add concise explanations to points of low importance and generate a video. Furthermore, the generation AI can also adjust the length of the video according to its importance. In this way, the generation unit can provide the optimal amount of information to the viewer by adjusting the level of detail in the video according to the importance of the points.

[0068] The generation unit can apply multiple generation algorithms to the digest video depending on the viewer's area of ​​interest. For example, the generation unit can use a generation AI to apply different generation algorithms depending on the viewer's area of ​​interest when generating the digest video. The generation AI can identify the viewer's area of ​​interest and select the optimal generation algorithm. For example, the generation AI can generate a video that emphasizes technical details for viewers with technical interests. It can also generate a video that emphasizes points that will capture the viewer's interest for viewers with marketing interests. Furthermore, it can generate a video that emphasizes points that enhance learning effectiveness for viewers with training interests. In this way, the generation unit can generate more interesting videos for viewers by applying a generation algorithm that matches the viewer's area of ​​interest.

[0069] The generation unit can estimate the viewer's emotions and adjust the length of the digest video based on those emotions. For example, the generation unit uses a generation AI to estimate the viewer's emotions and adjust the length of the digest video based on those emotions. The generation AI can estimate the viewer's emotions using facial expression analysis and voice analysis. For example, if the viewer is in a hurry, the generation AI will generate a short, concise video. If the viewer is relaxed, the generation AI can also generate a longer video with detailed explanations. Furthermore, if the viewer is excited, the generation AI can generate a video with visually stimulating effects. In this way, the generation unit can provide the viewer with the optimal viewing experience by adjusting the video length according to the viewer's emotions.

[0070] The generation unit can adjust the order of videos based on the viewer's viewing history when generating a digest version of a video. For example, the generation unit uses a generation AI to adjust the order of videos based on the viewer's viewing history when generating a digest version of a video. The generation AI can analyze the viewer's past viewing data and generate videos in the optimal order. For example, the generation AI can generate videos in the optimal order by referring to the order in which the viewer has watched videos in the past. The generation AI can also prioritize points of high interest based on the viewer's viewing history. Furthermore, the generation AI can analyze the viewer's viewing history and generate videos in an order that is easy for the viewer to understand. As a result, the generation unit can provide videos in the optimal order for the viewer by adjusting the order of videos based on the viewer's viewing history.

[0071] The generation unit can generate digest videos in the optimal format based on the viewer's device information. For example, the generation unit uses a generation AI to generate digest videos in the optimal format, taking the viewer's device information into consideration. The generation AI can identify the viewer's device information and select the optimal format. For example, if the viewer is using a smartphone, the generation AI will generate the video in a format optimized for smartphones. If the viewer is using a tablet, the generation AI can also generate the video in a format optimized for tablets. Furthermore, if the viewer is using a desktop computer, the generation AI can also generate the video in a format optimized for desktop computers. In this way, the generation unit can provide viewers with the best possible viewing experience by generating videos in the optimal format based on the viewer's device information.

[0072] The prediction unit can estimate the viewer's emotions and improve the accuracy of response predictions based on those estimated emotions. For example, the prediction unit uses generative AI to estimate the viewer's emotions and improve the accuracy of response predictions based on those estimated emotions. The generative AI can estimate the viewer's emotions using facial expression analysis and voice analysis. For example, if the viewer is excited, the generative AI predicts that there is a high probability of inquiries or applications. Also, if the viewer is bored, the generative AI can predict that there will be little response. Furthermore, if the viewer is attentive, the generative AI can predict that there is a high probability of detailed inquiries. In this way, the prediction unit can improve the accuracy of response predictions based on the viewer's emotions, enabling more accurate response predictions.

[0073] The prediction unit can optimize the response prediction algorithm based on the viewer's past viewing data. For example, the prediction unit uses generative AI to refer to the viewer's past viewing data and optimize the response prediction algorithm. The generative AI can analyze the viewer's past viewing data and optimize the response prediction algorithm. For example, the generative AI identifies points that will attract the viewer's interest from the viewer's past viewing data and makes a response prediction. The generative AI can also predict the likelihood of inquiries or applications based on the viewer's past viewing data. As a result, the accuracy of the response prediction algorithm is improved by the prediction unit referring to the viewer's past viewing data.

[0074] The prediction unit can improve the accuracy of response predictions based on viewer attribute information. For example, the prediction unit uses generative AI to improve the accuracy of response predictions by considering viewer attribute information. Generative AI can perform response predictions by considering viewer attribute information such as age and gender. For example, generative AI can predict the likelihood of inquiries or applications based on viewer age and gender. Generative AI can also perform response predictions by considering viewer occupation and interests. Furthermore, generative AI can perform response predictions by considering viewer region and cultural background. As a result, the prediction unit improves the accuracy of response predictions by considering viewer attribute information.

[0075] The prediction unit can estimate the viewer's emotions and determine the order of response predictions based on those estimated emotions. For example, the prediction unit can use generative AI to estimate the viewer's emotions and determine the priority of response predictions based on those estimated emotions. The generative AI can estimate the viewer's emotions using facial expression analysis or voice analysis. For example, if the viewer is excited, the generative AI predicts a high probability of inquiries or applications and sets a high priority. Conversely, if the viewer is bored, the generative AI can predict a low response and set a low priority. Furthermore, if the viewer is attentive, the generative AI can predict a high probability of detailed inquiries and set a high priority. In this way, the prediction unit can develop more effective marketing strategies by determining the priority of response predictions based on the viewer's emotions.

[0076] The prediction unit can improve the accuracy of response predictions based on the geographical location information of viewers. For example, the prediction unit uses generative AI to improve the accuracy of response predictions by considering the geographical location information of viewers. The generative AI can predict response trends for each region based on the geographical location information of viewers. For example, the generative AI can predict the likelihood of inquiries and applications for each region by considering the geographical location information of viewers. In addition, the generative AI can identify points of interest for each region based on the geographical location information of viewers and perform response predictions. As a result, the prediction unit improves the accuracy of response predictions by considering the geographical location information of viewers.

[0077] The prediction unit can analyze viewers' social media activity and improve the accuracy of response predictions. For example, the prediction unit uses generative AI to analyze viewers' social media activity and improve the accuracy of response predictions. Generative AI can analyze viewers' social media activity and identify points of high interest. For example, based on viewers' social media responses, generative AI can predict the likelihood of inquiries or applications. Generative AI can also optimize the response prediction algorithm by considering viewers' social media activity. As a result, the prediction unit improves the accuracy of response predictions by analyzing viewers' social media activity. === Hard Collateral 1-1 === Each of the multiple elements described above, including the analysis unit, generation unit, and prediction unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit acquires real-time video of the briefing using the camera 42 and microphone 38B of the smart device 14, analyzes the content of the video using the specific processing unit 290 of the data processing unit 12, and extracts important points. The generation unit automatically generates a digest version of the video based on the points extracted by the specific processing unit 290 of the data processing unit 12. The prediction unit analyzes the viewing time and viewing trends of viewers using the specific processing unit 290 of the data processing unit 12, for example, and creates a video reaction prediction. === Hard Collateral 1-2 === Each of the multiple elements described above, including the analysis unit, generation unit, and prediction unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit acquires real-time video of the briefing using the camera 42 and microphone 238 of the smart glasses 214, analyzes the content of the video using the specific processing unit 290 of the data processing unit 12, and extracts important points. The generation unit automatically generates a digest version of the video based on the points extracted by the specific processing unit 290 of the data processing unit 12. The prediction unit analyzes the viewing time and viewing trends of viewers using the specific processing unit 290 of the data processing unit 12, for example, and creates a video reaction prediction. === Hard Collateral 1-3 === Each of the multiple elements described above, including the analysis unit, generation unit, and prediction unit, is implemented, for example, in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit acquires real-time video of the briefing using the camera 42 and microphone 238 of the headset terminal 314, analyzes the content of the video using the specific processing unit 290 of the data processing unit 12, and extracts important points. The generation unit automatically generates a digest version of the video based on the points extracted by the specific processing unit 290 of the data processing unit 12. The prediction unit analyzes the viewing time and viewing trends of viewers using the specific processing unit 290 of the data processing unit 12, for example, and creates a video reaction prediction. === Hard Collateral 1-4 === Each of the multiple elements described above, including the analysis unit, generation unit, and prediction unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the analysis unit acquires real-time video of the briefing using the camera 42 and microphone 238 of the robot 414, analyzes the content of the video using the specific processing unit 290 of the data processing unit 12, and extracts important points. The generation unit automatically generates a digest version of the video based on the points extracted by the specific processing unit 290 of the data processing unit 12. The prediction unit analyzes the viewing time and viewing trends of viewers using the specific processing unit 290 of the data processing unit 12, for example, and creates a video reaction prediction.

[0078] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0079] The analysis unit can estimate the viewer's emotions and adjust the point extraction criteria based on those emotions. For example, if the viewer is excited, the generating AI will prioritize extracting points that will capture the viewer's interest. If the viewer is bored, the generating AI can also extract points that will re-engage the viewer. Furthermore, if the viewer is attentive, the generating AI can extract points that contain detailed information. This allows the analysis unit to adjust the criteria for extracting important points according to the viewer's emotions, enabling a more appropriate summary.

[0080] The generation unit can estimate the viewer's emotions and adjust the presentation of the digest video based on those emotions. For example, if the viewer is excited, the generation AI will create a video with visually stimulating effects. If the viewer is relaxed, the generation AI can also create a video with a calm tone. Furthermore, if the viewer is focused, the generation AI can create a video that includes detailed information. In this way, the generation unit can create a more engaging video for the viewer by adjusting the presentation of the digest video according to the viewer's emotions.

[0081] The prediction unit can estimate the viewer's emotions and improve the accuracy of response predictions based on those estimated emotions. For example, if the viewer is excited, the generating AI predicts a high probability of inquiries or applications. Conversely, if the viewer is bored, the generating AI can predict a low response rate. Furthermore, if the viewer is attentive, the generating AI can predict a high probability of detailed inquiries. In this way, the prediction unit can improve the accuracy of response predictions based on the viewer's emotions, enabling more accurate response predictions.

[0082] The analysis unit can improve the accuracy of extracting important points based on past video data of information sessions. For example, the generation AI can learn common important points from past information session videos and improve extraction accuracy. The generation AI refers to past viewer reaction data and extracts points that viewers were interested in. The generation AI can also evaluate the accuracy of points extracted from past video data and apply the optimal extraction algorithm. As a result, the analysis unit can improve the accuracy of extracting important points by referring to past data.

[0083] The generation unit can apply multiple generation algorithms to create digest videos according to the viewer's areas of interest. For example, the generation AI can identify the viewer's areas of interest and select the optimal generation algorithm. For viewers with technical interests, the generation AI can generate videos that emphasize technical details. For viewers with marketing interests, it can generate videos that emphasize points that will capture the viewer's attention. Furthermore, for viewers with training interests, it can generate videos that emphasize points that enhance learning effectiveness. In this way, the generation unit can create more interesting videos for viewers by applying generation algorithms tailored to their areas of interest.

[0084] The prediction unit can optimize the response prediction algorithm based on the viewer's past viewing data. For example, the generative AI can analyze the viewer's past viewing data and optimize the response prediction algorithm. The generative AI identifies points that will attract the viewer's interest from the viewer's past viewing data and makes a response prediction. The generative AI can also predict the likelihood of inquiries or applications based on the viewer's past viewing data. As a result, the accuracy of the response prediction algorithm is improved by the prediction unit referring to the viewer's past viewing data.

[0085] The generation unit can estimate the viewer's emotions and adjust the length of the digest video based on those emotions. For example, if the viewer is in a hurry, the generation AI will produce a short, concise video. If the viewer is relaxed, the generation AI can produce a longer video with detailed explanations. Furthermore, if the viewer is excited, the generation AI can produce a video with visually stimulating effects. In this way, the generation unit can provide the viewer with the optimal viewing experience by adjusting the video length according to their emotions.

[0086] The analysis unit can analyze the speaker's speaking style and tone during a presentation and extract key points. For example, the generation AI can analyze the speaker's emphasized parts and changes in tone to extract points that will capture the audience's attention. The generation AI extracts the parts the speaker emphasizes as important points. Furthermore, the generation AI can analyze changes in the speaker's tone and extract points that will capture the audience's attention. In addition, the generation AI can analyze the rhythm of the speaker's speech and extract parts containing important information. As a result, the analysis unit can accurately extract important points by analyzing the speaker's speaking style and tone.

[0087] The prediction unit can estimate the audience's emotions and determine the order of response predictions based on those emotions. For example, if the audience is excited, the generating AI predicts a high probability of inquiries or applications and sets a high priority. Conversely, if the audience is bored, the generating AI can predict a low response and set a low priority. Furthermore, if the audience is attentive, the generating AI can predict a high probability of detailed inquiries and set a high priority. In this way, the prediction unit can develop more effective marketing strategies by determining the priority of response predictions based on the audience's emotions.

[0088] The generation unit can generate digest videos in the optimal format based on the viewer's device information. For example, the generation AI can identify the viewer's device information and select the optimal format. If the viewer is using a smartphone, the generation AI will generate the video in a format optimized for smartphones. If the viewer is using a tablet, the generation AI can also generate the video in a format optimized for tablets. Furthermore, if the viewer is using a desktop computer, the generation AI can also generate the video in a format optimized for desktop computers. As a result, the generation unit can provide viewers with the best possible viewing experience by generating videos in the optimal format based on their device information.

[0089] The following briefly describes the processing flow for example form 2.

[0090] Step 1: The analysis unit analyzes the real-time presentation video and extracts key points. The analysis unit uses generative AI to understand the content of the video and extract important points. The generative AI uses text generation AI (e.g., LLM) or multimodal generation AI to extract important information such as product features, benefits, and usage instructions. For example, the generative AI converts audio data in the video into text and extracts important keywords and phrases. The generative AI can also analyze the content of slides and materials in the video and extract important information. Step 2: The generation unit automatically generates a digest video based on the points extracted by the analysis unit. The generation unit uses a generation AI to combine the extracted key points and create an easy-to-understand digest video for viewers. The generation AI can generate a visually appealing video based on the extracted points. For example, the generation AI can generate a short video that highlights the features and benefits of a product. The generation AI can also add effects and animations to attract the viewer's attention. Step 3: The prediction unit analyzes viewer viewing time and viewing trends based on the video generated by the generation unit and creates a video response prediction. The prediction unit uses generation AI to collect and analyze data such as which parts viewers watched and for how long. Based on viewer viewing data, generation AI can predict viewer interest and response. For example, if a viewer watches a particular part for a long time, generation AI will determine that they have a high level of interest in that part and predict that there is a high probability of inquiries or applications. Furthermore, generation AI can also improve the accuracy of response predictions by considering the viewer's viewing history and attribute information.

[0091] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0092] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0093] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0094] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0095] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0096] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0097] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0098] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0099] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0100] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0101] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0102] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0103] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0104] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0105] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0106] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0107] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0108] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0109] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0110] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0111] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0112] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0113] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0114] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0115] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0117] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0118] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0119] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0120] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0121] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0122] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0123] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0125] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0127] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0128] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0135] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0136] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0137] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0138] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0139] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0140] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0141] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0142] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0143] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0144] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0145] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0146] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0147] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0148] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0149] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0150] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0151] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0152] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0153] 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.

[0154] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0155] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0156] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0157] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0158] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0159] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0160] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0161] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0162] [Explanation of Symbols]

[0163] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis unit analyzes real-time explanatory video and extracts key points, A generation unit that automatically generates a digest version video based on the points extracted by the analysis unit, The system includes a prediction unit that analyzes viewers' viewing time and viewing trends based on the video generated by the generation unit and creates a prediction of the video's reaction. A system characterized by the following features.

2. The aforementioned analysis unit, Extract key information about the product's features, benefits, and usage. The system according to feature 1.

3. The generating unit is Combine the extracted points to generate a digest video. The system according to feature 1.

4. The prediction unit, We collect and analyze data on which parts viewers watched and for how long. The system according to feature 1.

5. The prediction unit, Predicting viewer reactions The system according to feature 1.

6. The aforementioned analysis unit, We estimate the audience's emotions and adjust the point extraction criteria based on those estimated emotions. The system according to feature 1.

7. The aforementioned analysis unit, Based on past video data from information sessions, we will improve the accuracy of extracting key points. The system according to feature 1.

8. The aforementioned analysis unit, Depending on the content of the briefing session, multiple extraction algorithms will be applied. The system according to feature 1.

9. The aforementioned analysis unit, The system estimates the viewer's emotions and determines the order of points to extract based on those estimated emotions. The system according to feature 1.

10. The aforementioned analysis unit, Analyze the speaking style and tone of the speakers at the information session and extract key points. The system according to feature 1.

Images