system

Abstract

The system according to this embodiment aims to streamline video editing and create reaction predictions based on viewing data. [Solution] The system according to the embodiment comprises a reception unit, a generation unit, a confirmation unit, a collection unit, an analysis unit, and a prediction unit. The reception unit accepts video uploads. The generation unit analyzes the videos received by the reception unit, extracts summary points, and generates a digest version. The confirmation unit confirms the digest video generated by the generation unit. The collection unit collects viewing data. The analysis unit analyzes the viewing data collected by the collection unit. The prediction unit creates a reaction prediction based on the analysis results obtained by the analysis unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that video editing takes time and the analysis of viewing data and reaction prediction are not efficiently performed.

[0005] The system according to the embodiment aims to improve the efficiency of video editing and create reaction prediction based on viewing data.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a generation unit, a confirmation unit, a collection unit, an analysis unit, and a prediction unit. The reception unit accepts video uploads. The generation unit analyzes the videos received by the reception unit, extracts summary points, and generates a digest version. The confirmation unit confirms the digest video generated by the generation unit. The collection unit collects viewing data. The analysis unit analyzes the viewing data collected by the collection unit. The prediction unit creates a response prediction based on the analysis results obtained by the analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can streamline video editing and create reaction predictions based on viewing data. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of 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 and marketing support system according to an embodiment of the present invention is a system that utilizes generative AI to streamline the editing of product presentation videos and analyzes viewing data to achieve effective marketing. This system begins with the user uploading a recorded video of a product presentation. The generative AI analyzes the video, extracts key points, and automatically generates a digest version. The generated digest video is reviewed and fine-tuned as needed. The completed digest video is distributed to relevant parties both inside and outside the company. Viewer data (viewing time, number of views, viewer attributes, etc.) is collected and analyzed by the AI. Based on the analysis results, the system predicts how many inquiries or applications the video will generate. This maximizes marketing effectiveness through efficient video editing and the utilization of viewing data. As a result, the video editing and marketing support system can streamline the editing of product presentation videos and achieve effective marketing by analyzing viewing data.

[0029] The video editing and marketing support system according to this embodiment comprises a reception unit, a generation unit, a verification unit, a collection unit, an analysis unit, and a prediction unit. The reception unit accepts user uploads of recorded videos of product presentations. The reception unit enables users to upload video files via a web interface, for example. The reception unit can also verify the format and size of video files and convert them to an appropriate format. The generation unit uses a generation AI to analyze the videos received by the reception unit, extract key points, and generate a digest version. The generation unit uses a generation AI to analyze the video content and extract important scenes, for example. The generation unit can also automatically edit the digest version based on the scenes extracted by the generation AI. The generation unit can also use a generation AI to analyze the audio of the video and extract important statements. The verification unit checks the digest video generated by the generation unit and makes adjustments as needed. The verification unit enables users to preview the digest video and check the edits, for example. The verification unit also allows users to add or delete specific scenes from the digest video. The verification unit also allows users to edit the audio and subtitles of the digest video. The collection unit collects viewing data. For example, the collection unit collects data such as viewers' viewing time, number of views, and viewers' attributes. The collection unit can also collect viewers' device information and geographical location information. The collection unit can also collect viewers' feedback and comments. The analysis unit analyzes the viewing data collected by the collection unit using AI. For example, the analysis unit analyzes viewing trends based on the viewing data. The analysis unit can also analyze viewers' attributes and behavioral patterns based on the viewing data. The analysis unit can also analyze viewers' interests and concerns based on the viewing data. The prediction unit predicts how many inquiries or applications the video will generate based on the analysis results obtained by the analysis unit. For example, the prediction unit builds a prediction model for inquiries and applications based on the viewing data. The prediction unit can also predict marketing effectiveness based on the viewing data. The prediction unit can also predict viewers' behavior based on the viewing data.As a result, the video editing and marketing support system according to this embodiment can consistently perform tasks from uploading videos to generating digest versions, collecting and analyzing viewing data, and predicting responses.

[0030] The reception desk accepts user uploads of recorded video presentations. For example, the reception desk allows users to upload video files via a web interface. Specifically, users can access a dedicated web portal and easily upload video files using drag-and-drop functionality. The reception desk can also verify the format and size of video files and convert them to the appropriate format. For instance, if an uploaded video is not in a specific format (e.g., MP4, AVI, MOV), it has a function to automatically convert it to the correct format. Furthermore, it verifies the video's resolution and bitrate and optimizes it as needed. This allows users to upload videos smoothly without cumbersome procedures. The reception desk also provides an interface for entering metadata for uploaded videos (e.g., title, description, tags), allowing users to easily manage the content of their videos. This improves video searchability and organization, and streamlines subsequent processing.

[0031] The generation unit uses a generation AI to analyze videos received by the reception unit, extract key points, and generate a digest version. For example, the generation AI analyzes the video content and extracts important scenes. Specifically, the generation AI uses natural language processing technology to convert the video's audio into text and extract keywords and phrases. Furthermore, it uses image recognition technology to identify visually important scenes (e.g., product demonstrations or important slide displays). Based on this information, the generation AI extracts key points from the video and automatically edits the digest version. The generation unit can also automatically edit the digest version based on the scenes extracted by the generation AI. For example, the generation AI can arrange the extracted scenes in an appropriate order to generate a digest version with a smooth flow. The generation unit can also have the generation AI analyze the video's audio and extract important statements. This allows viewers to grasp the main points of the video in a short amount of time. The generation unit can also periodically update the generation AI's training data to improve analysis accuracy. This allows the production unit to always use the latest technology to provide high-quality digest versions.

[0032] The verification unit reviews the digest video generated by the generation unit and makes adjustments as needed. For example, the verification unit allows users to preview the digest video and review their edits. Specifically, users can play the digest video through a web interface and review the content of each scene. The verification unit also allows users to add or delete specific scenes from the digest video. For example, users can change the order of scenes or delete unwanted scenes using drag-and-drop functionality. Furthermore, the verification unit allows users to edit the audio and subtitles of the digest video. For example, they can adjust the audio volume or change the content and timing of the subtitles. This allows users to customize the digest video to their needs. The verification unit also saves the user's editing history and provides a function to revert to the original state at any time. This allows users to edit with confidence.

[0033] The data collection unit collects viewing data. For example, the data collection unit collects data such as viewers' viewing time, number of views, and viewer attributes. Specifically, it collects detailed data such as the time viewers played a video, the number of views, and where they paused during playback. The data collection unit can also collect viewers' device information and geographical location information. For example, it collects the type of device the viewer is using (smartphone, tablet, PC, etc.) and geographical location information based on the viewer's IP address. Furthermore, the data collection unit can also collect viewer feedback and comments. For example, it collects comments and ratings left by viewers on videos, and opinions provided through feedback forms. This allows the data collection unit to understand viewer behavior and reactions in detail, which can be used for subsequent analysis and prediction. It is also important for the data collection unit to securely store the collected data and take appropriate measures to protect privacy.

[0034] The analytics department uses AI to analyze viewing data collected by the data collection department. For example, the analytics department analyzes viewing trends based on viewing data. Specifically, it analyzes data such as which scenes viewers watched the longest and at which scenes they stopped watching, in order to identify viewers' interests and preferences. The analytics department can also analyze viewers' attributes and behavioral patterns based on viewing data. For example, it analyzes the viewing trends of specific attribute groups based on attribute information such as viewers' age, gender, and region. Furthermore, the analytics department can analyze viewers' interests and preferences based on viewing data. For example, it can evaluate the degree of interest viewers have in a particular product or service, which can be used to formulate marketing strategies. The analytics department can also use AI machine learning algorithms to extract patterns and trends from viewing data and predict future viewing trends. As a result, the analytics department can perform advanced analysis based on viewing data and provide valuable insights to maximize the effectiveness of marketing activities.

[0035] The prediction unit predicts how many inquiries or applications a video will generate, based on the analysis results obtained by the analysis unit. For example, the prediction unit builds a predictive model for inquiries and applications based on viewing data. Specifically, it trains a machine learning algorithm using past viewing data and actual inquiry and application data to predict the probability of future inquiries and applications. The prediction unit can also predict marketing effectiveness based on viewing data. For example, it can predict how many viewers a particular video will reach and how much engagement it will generate. Furthermore, the prediction unit can predict viewer behavior based on viewing data. For example, it can predict what actions viewers will take after watching a video (e.g., visiting a website, purchasing a product), which can be used to optimize marketing strategies. It is important for the prediction unit to update prediction results in real time and provide highly accurate predictions based on the latest data. This allows the prediction unit to play a crucial role in maximizing the effectiveness of marketing activities and supporting business growth.

[0036] The generation unit can analyze a video using a generation AI, extract important points, and generate a digest version. For example, the generation unit can use the generation AI to analyze the video content and extract important scenes. The generation unit can also automatically edit the digest version based on the scenes extracted by the generation AI. The generation unit can also use the generation AI to analyze the audio of the video and extract important statements. In this way, by using the generation AI, it is possible to efficiently extract important points from a video and generate a digest version. Some or all of the above processing in the generation unit may be performed using the generation AI, or it may be performed without using the generation AI. For example, the generation unit can input video data into the generation AI to analyze the video content, and the generation AI can extract important scenes and generate a digest version.

[0037] The data collection unit can collect viewer data. For example, the data collection unit can collect data such as viewer viewing time, number of views, and viewer attributes. The data collection unit can also collect viewer device information and geographical location information. The data collection unit can also collect viewer feedback and comments. This makes it easier to understand viewing trends by collecting viewer data. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input viewer viewing data into AI, which can analyze the viewing data and understand viewing trends.

[0038] The analysis unit can analyze viewing data collected by the collection unit using AI. For example, the analysis unit can analyze viewing trends based on the viewing data. The analysis unit can also analyze viewer attributes and behavioral patterns based on the viewing data. The analysis unit can also analyze viewer interests and concerns based on the viewing data. As a result, the accuracy of viewing data analysis is improved by using AI. Some or all of the above-mentioned processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input viewing data into AI, which can analyze the viewing data and understand viewing trends.

[0039] The prediction unit can predict how many inquiries or applications a video will generate based on the analysis results obtained by the analysis unit. For example, the prediction unit can build a prediction model for inquiries and applications based on viewing data. The prediction unit can also predict marketing effectiveness based on viewing data. The prediction unit can also predict viewer behavior based on viewing data. This allows for the effective development of marketing strategies by predicting video responses. Some or all of the above processes in the prediction unit may be performed using AI or not. For example, the prediction unit can input viewing data into AI, which can analyze the viewing data and make response predictions.

[0040] The verification unit can review the automatically generated digest video and make adjustments as needed. For example, the verification unit allows the user to preview the digest video and review the edits. It also allows the user to add or delete specific scenes from the digest video. Furthermore, the verification unit allows the user to edit the audio and subtitles of the digest video. This enables the provision of higher-quality videos by checking the quality of the digest video and making adjustments as needed. Some or all of the above processes in the verification unit may be performed using AI or not. For example, the verification unit can input the digest video into an AI, which can evaluate the video quality and make necessary adjustments.

[0041] The reception desk can analyze a user's past upload history and select the optimal upload method. For example, the reception desk can automatically suggest upload methods that the user has frequently used in the past. It can also suggest the optimal upload method for a specific time period based on the user's past upload history. Furthermore, the reception desk can analyze the content of videos previously uploaded by the user and suggest optimal upload settings. This allows the reception desk to provide the user with the most suitable upload method by analyzing their past upload history. Some or all of the above processes in the reception desk may be performed using AI, or not. For example, the reception desk can input the user's past upload history into an AI, which can then select the optimal upload method.

[0042] The reception desk can filter videos based on the user's current projects and areas of interest when they are uploaded. For example, the reception desk can prioritize uploading videos related to the user's current projects. The reception desk can also filter and upload highly relevant videos based on the user's areas of interest. The reception desk can also select and upload the most suitable videos according to the progress of the user's projects. This allows for the priority uploading of highly relevant videos by filtering videos based on the user's projects and areas of interest. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the user's project information and areas of interest into an AI, which can then select and upload the most suitable videos.

[0043] The reception desk can prioritize uploading videos that are highly relevant to the user, taking into account the user's geographical location when uploading videos. For example, if the user is in a specific region, the reception desk will prioritize uploading videos related to that region. The reception desk can also prioritize uploading videos filmed near the user's current location. The reception desk can also filter and upload videos that are highly relevant based on the user's geographical location. This allows for the provision of region-specific content by uploading videos that are highly relevant based on the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the user's geographical location into an AI, which can then select and upload highly relevant videos.

[0044] The reception desk can analyze a user's social media activity when uploading videos and upload relevant videos. For example, the reception desk can upload relevant videos based on what the user has shared on social media. It can also analyze a user's social media activity history and select and upload the most suitable videos. The reception desk can also prioritize uploading videos that the user's followers and friends are likely to be interested in. This allows the reception desk to provide content that matches the user's interests by uploading relevant videos based on the user's social media activity. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the user's social media activity data into an AI, which can then select and upload relevant videos.

[0045] The generation unit can adjust the level of detail in the summary based on the importance of the video when generating a digest version. For example, if a video has many important points, the generation unit will generate a detailed summary. Conversely, if a video has few important points, the generation unit can also generate a concise summary. The generation unit can also dynamically adjust the level of detail in the summary according to the importance of the video. This allows for the provision of optimal information to viewers by adjusting the level of detail in the summary according to the importance of the video. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input video importance data into a generation AI, and the generation AI can adjust the level of detail in the summary.

[0046] The generation unit can apply different summarization algorithms depending on the video category when generating a digest version. For example, in the case of a product introduction video, the generation unit can generate a summary that emphasizes the product's features. It can also generate a summary that emphasizes important skills and techniques in the case of a training video. In the case of an event report video, the generation unit can generate a summary that emphasizes the highlights of the main event. This allows for the generation of more appropriate summaries by applying a summarization algorithm according to the video category. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input video category data into a generation AI, which can then apply the most suitable summarization algorithm.

[0047] The generation unit can determine the priority of summaries based on the video shooting dates when generating a digest version. For example, the generation unit may prioritize summarizing recently filmed videos. It can also prioritize summarizing videos related to specific events or campaigns. The generation unit can also dynamically adjust the priority of summaries based on the video shooting dates. This allows for the prioritization of the most up-to-date information by determining the priority of summaries based on the video shooting dates. Some or all of the above processing in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input video shooting date data into a generation AI, which can then determine the priority of summaries.

[0048] The generation unit can adjust the order of summaries based on the relevance of the video when generating a digest version. For example, the generation unit can prioritize summarizing points that are highly relevant. It can also postpone summarizing points that are less relevant. The generation unit can also dynamically adjust the order of summaries based on the relevance of the video. This allows information to be provided to the viewer in the optimal order by adjusting the order of summaries based on the relevance of the video. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input video relevance data into a generation AI, and the generation AI can adjust the order of summaries.

[0049] The verification unit can select the optimal verification method by referring to the user's past verification history during verification. For example, the verification unit may prioritize suggesting verification methods that the user has used in the past. The verification unit can also suggest the optimal verification method for a specific time period based on the user's past verification history. The verification unit can also analyze the user's past verification history and suggest the optimal verification settings. In this way, by referring to past verification history, the verification unit can provide the user with the most suitable verification method. Some or all of the above processes in the verification unit may be performed using AI or not. For example, the verification unit can input the user's past verification history into AI, and the AI ​​can select the optimal verification method.

[0050] The verification unit can adjust the level of detail of the verification based on the importance of the video during the verification process. For example, if a video has many important points, the verification unit will perform a detailed verification. Conversely, if a video has few important points, the verification unit can perform a concise verification. The verification unit can also dynamically adjust the level of detail of the verification according to the importance of the video. This allows for efficient verification by adjusting the level of detail according to the importance of the video. Some or all of the above processing in the verification unit may be performed using AI or not. For example, the verification unit can input video importance data into the AI, and the AI ​​can adjust the level of detail of the verification.

[0051] The verification unit can select the optimal verification method by considering the user's device information during verification. For example, if the user is using a smartphone, the verification unit can provide a verification method that matches the screen size. Furthermore, if the user is using a tablet, the verification unit can provide a verification method optimized for a larger screen. If the user is using a smartwatch, the verification unit can provide a concise and highly visible verification method. This improves convenience by providing the optimal verification method based on the user's device information. Some or all of the above processing in the verification unit may be performed using AI, or not. For example, the verification unit can input the user's device information into the AI, which can then select the optimal verification method.

[0052] The verification unit can analyze the user's social media activity during verification and review relevant digest versions. For example, the verification unit can review relevant digest versions based on content the user has shared on social media. The verification unit can also analyze the user's social media activity history and select and review the most appropriate digest version. The verification unit can also prioritize reviewing digest versions that the user's followers and friends are likely to be interested in. This allows for the provision of more relevant content by reviewing relevant digest versions based on the user's social media activity. Some or all of the above processing in the verification unit may be performed using AI or not. For example, the verification unit can input the user's social media activity data into AI, which can then select and review relevant digest versions.

[0053] The data collection unit can analyze a user's past viewing history and select the optimal data collection method when collecting viewing data. For example, the data collection unit can suggest the optimal data collection method based on data of videos the user has watched in the past. The data collection unit can also suggest the optimal data collection method for a specific time period based on the user's past viewing history. The data collection unit can also analyze a user's past viewing history and suggest the most efficient data collection method. In this way, by analyzing past viewing history, the data collection unit can provide the user with the most suitable method for collecting viewing data. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's past viewing history into AI, which can then select the optimal data collection method.

[0054] The data collection unit can filter viewing data based on the user's current viewing status and areas of interest. For example, the data collection unit can prioritize collecting data related to the video the user is currently watching. The data collection unit can also filter and collect highly relevant viewing data based on the user's areas of interest. The data collection unit can also select and collect the most relevant viewing data according to the user's viewing status. This allows for the collection of more relevant data by filtering viewing data based on the user's viewing status and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's viewing status and areas of interest data into an AI, which can then select and collect the most relevant viewing data.

[0055] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information when collecting viewing data. For example, if the user is in a specific region, the data collection unit will prioritize the collection of viewing data related to that region. The data collection unit can also prioritize the collection of viewing data filmed in locations close to the user's current location. The data collection unit can also filter and collect highly relevant viewing data based on the user's geographical location information. This allows for the provision of region-specific data by collecting highly relevant viewing data based on the user's geographical location information. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's geographical location information into AI, which can then select and collect highly relevant viewing data.

[0056] The data collection unit can analyze the user's social media activity and collect relevant data when collecting viewing data. For example, the data collection unit can collect relevant viewing data based on what the user has shared on social media. The data collection unit can also analyze the user's social media activity history and select and collect the most relevant viewing data. The data collection unit can also prioritize collecting viewing data that the user's followers and friends are likely to be interested in. This allows for the provision of more relevant data by collecting relevant viewing data based on the user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's social media activity data into AI, which can then select and collect relevant viewing data.

[0057] The analysis unit can predict current viewing trends by referring to past viewing data during analysis. For example, the analysis unit predicts current viewing trends based on past viewing data. The analysis unit can also predict viewing trends for specific time periods from past viewing data. The analysis unit can also analyze past viewing data and predict the most efficient viewing trends. This allows for a more accurate prediction of current viewing trends by referring to past viewing data. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input past viewing data into AI, which can then predict current viewing trends.

[0058] The analysis department can apply different analytical methods to each category of viewing data during analysis. For example, in the case of product introduction videos, the analysis department can perform an analysis that emphasizes the product's features. Similarly, in the case of training videos, the analysis department can perform an analysis that emphasizes important skills and techniques. In the case of event report videos, the analysis department can perform an analysis that emphasizes the highlights of the main event. This allows for more accurate analytical results by applying the most appropriate analytical method according to the category of viewing data. Some or all of the above processing in the analysis department may be performed using AI, or not. For example, the analysis department can input the category data of the viewing data into an AI, which can then apply the most appropriate analytical method.

[0059] The analysis unit can analyze changes in viewing trends based on the timing of viewing data collection during the analysis process. For example, the analysis unit can analyze changes in viewing trends based on the timing of viewing data collection. The analysis unit can also analyze changes in viewing data related to specific events or campaigns. The analysis unit can also dynamically analyze changes in viewing trends based on the timing of viewing data collection. This allows for more accurate trend analysis by analyzing changes in viewing trends based on the timing of viewing data collection. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input viewing data collection timing data into AI, and the AI ​​can analyze changes in viewing trends.

[0060] The analysis unit can analyze viewing trends by referring to relevant market data for viewing data during the analysis process. For example, the analysis unit can analyze viewing trends based on relevant market data for viewing data. The analysis unit can also analyze viewing trends for specific time periods from relevant market data for viewing data. The analysis unit can also analyze relevant market data for viewing data to determine the most efficient viewing trends. This allows for a more accurate analysis of viewing trends by referring to relevant market data for viewing data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input relevant market data for viewing data into an AI, which can then analyze viewing trends.

[0061] The prediction unit can analyze past viewing data to select the optimal response prediction method during prediction. For example, the prediction unit can propose the optimal response prediction method based on past viewing data. The prediction unit can also propose a response prediction method for a specific time period based on past viewing data. The prediction unit can also analyze past viewing data and propose the most efficient response prediction method. In this way, the optimal response prediction method can be provided by analyzing past viewing data. Some or all of the above processing in the prediction unit may be performed using AI or not. For example, the prediction unit can input past viewing data into AI, and the AI ​​can select the optimal response prediction method.

[0062] The prediction unit can customize the response prediction method based on the category of the viewing data during prediction. For example, in the case of a product introduction video, the prediction unit can perform response predictions that emphasize the product's features. The prediction unit can also perform response predictions that emphasize important skills and techniques in the case of a training video. In the case of an event report video, the prediction unit can perform response predictions that emphasize the highlights of the main event. This allows for more accurate prediction results by customizing the response prediction method according to the category of the viewing data. Some or all of the above processing in the prediction unit may be performed using AI or not. For example, the prediction unit can input the category data of the viewing data into the AI, which can then apply the most suitable response prediction method.

[0063] The prediction unit can select the optimal response prediction method by considering the geographical location information of the viewing data during prediction. For example, if the user is in a specific region, the prediction unit will perform a response prediction relevant to that region. The prediction unit can also perform a response prediction based on viewing data taken in a location close to the user's current location. The prediction unit can also perform a highly relevant response prediction based on the user's geographical location information. This allows for the provision of region-specific prediction results by providing the optimal response prediction method based on the geographical location information of the viewing data. Some or all of the above processing in the prediction unit may be performed using AI or not. For example, the prediction unit can input the geographical location information of the viewing data into the AI, which can then select the optimal response prediction method.

[0064] The prediction unit can improve the accuracy of response predictions by referring to relevant literature for viewing data during the prediction process. For example, the prediction unit improves the accuracy of response predictions based on relevant literature for viewing data. The prediction unit can also improve the accuracy of response predictions for specific time periods from relevant literature for viewing data. The prediction unit can also analyze relevant literature for viewing data to improve the accuracy of the most efficient response prediction. In this way, the accuracy of response predictions can be improved by referring to relevant literature for viewing data. Some or all of the above processing in the prediction unit may be performed using AI or not. For example, the prediction unit can input relevant literature for viewing data into AI, and the AI ​​can improve the accuracy of response predictions.

[0065] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0066] The reception desk can analyze a user's past upload history and select the optimal upload method. For example, it can automatically suggest upload methods that the user has frequently used in the past. It can also suggest the optimal upload method for a specific time of day based on the user's past upload history. Furthermore, it can analyze the content of videos the user has uploaded in the past and suggest the optimal upload settings. In this way, by analyzing past upload history, the system can provide the user with the most suitable upload method. Some or all of the above processes in the reception desk may be performed using AI or not. For example, the reception desk can input the user's past upload history into the AI, which can then select the optimal upload method.

[0067] The reception system can filter videos based on the user's current projects and areas of interest when they are uploaded. For example, it can prioritize uploading videos related to the user's current projects. It can also filter and upload highly relevant videos based on the user's areas of interest. Furthermore, it can select and upload the most suitable videos according to the progress of the user's projects. This allows for the priority uploading of highly relevant videos by filtering videos based on the user's projects and areas of interest. Some or all of the above processing in the reception system may be performed using AI or not. For example, the reception system can input the user's project information and areas of interest into an AI, which can then select and upload the most suitable videos.

[0068] The generation unit can adjust the level of detail in the summary based on the importance of the video when generating a digest version. For example, if a video has many important points, it can generate a detailed summary. Conversely, if a video has few important points, it can generate a concise summary. Furthermore, the level of detail in the summary can be dynamically adjusted according to the importance of the video. This allows for the provision of optimal information to viewers by adjusting the level of detail in the summary according to the importance of the video. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input video importance data into the generation AI, and the generation AI can adjust the level of detail in the summary.

[0069] The generation unit can apply different summarization algorithms depending on the video category when generating a digest version. For example, in the case of a product introduction video, it can generate a summary that emphasizes the product's features. In the case of a training video, it can also generate a summary that emphasizes important skills and techniques. Furthermore, in the case of an event report video, it can generate a summary that emphasizes the highlights of the main event. By applying a summarization algorithm according to the video category, a more appropriate summary can be generated. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input video category data into the generation AI, and the generation AI can apply the optimal summarization algorithm.

[0070] The analysis department can apply different analytical methods to each category of viewing data during analysis. For example, in the case of product introduction videos, the analysis can highlight the product's features. In the case of training videos, the analysis can highlight important skills and techniques. Furthermore, in the case of event report videos, the analysis can highlight the key event's highlights. This allows for more accurate analysis results by applying the most appropriate analytical method according to the category of viewing data. Some or all of the above processing in the analysis department may be performed using AI or not. For example, the analysis department can input the category data of the viewing data into the AI, which can then apply the most appropriate analytical method.

[0071] The following briefly describes the processing flow for example form 1.

[0072] Step 1: The reception desk accepts user uploads of recorded video presentations. The reception desk allows users to upload video files, for example, through a web interface. The reception desk can also verify the format and size of the video files and convert them to an appropriate format. Step 2: The generation unit uses a generation AI to analyze the video received by the reception unit, extract key points, and generate a digest version. For example, the generation unit's generation AI analyzes the video content and extracts important scenes. The generation unit can also automatically edit the digest version based on the scenes extracted by the generation AI. The generation unit's generation AI can also analyze the audio of the video and extract important statements. Step 3: The verification unit reviews the digest video generated by the generation unit and makes adjustments as needed. The verification unit allows the user to preview the digest video and check the edits. It also allows the user to add or delete specific scenes from the digest video. The verification unit also allows the user to edit the audio and subtitles of the digest video. Step 4: The data collection unit collects viewing data. The data collection unit collects data such as viewers' viewing time, number of views, and viewers' attributes. The data collection unit can also collect viewers' device information and geographical location information. The data collection unit can also collect viewers' feedback and comments. Step 5: The analysis department uses AI to analyze the viewing data collected by the data collection department. For example, the analysis department analyzes viewing trends based on the viewing data. The analysis department can also analyze viewer attributes and behavioral patterns based on the viewing data. The analysis department can also analyze viewer interests and preferences based on the viewing data. Step 6: The prediction unit predicts how many inquiries or applications the video will generate based on the analysis results obtained by the analysis unit. For example, the prediction unit builds a predictive model for inquiries and applications based on viewing data. The prediction unit can also predict marketing effectiveness based on viewing data. The prediction unit can also predict viewer behavior based on viewing data.

[0073] (Example of form 2) The video editing and marketing support system according to an embodiment of the present invention is a system that utilizes generative AI to streamline the editing of product presentation videos and analyzes viewing data to achieve effective marketing. This system begins with the user uploading a recorded video of a product presentation. The generative AI analyzes the video, extracts key points, and automatically generates a digest version. The generated digest video is reviewed and fine-tuned as needed. The completed digest video is distributed to relevant parties both inside and outside the company. Viewer data (viewing time, number of views, viewer attributes, etc.) is collected and analyzed by the AI. Based on the analysis results, the system predicts how many inquiries or applications the video will generate. This maximizes marketing effectiveness through efficient video editing and the utilization of viewing data. As a result, the video editing and marketing support system can streamline the editing of product presentation videos and achieve effective marketing by analyzing viewing data.

[0074] The video editing and marketing support system according to this embodiment comprises a reception unit, a generation unit, a verification unit, a collection unit, an analysis unit, and a prediction unit. The reception unit accepts user uploads of recorded videos of product presentations. The reception unit enables users to upload video files via a web interface, for example. The reception unit can also verify the format and size of video files and convert them to an appropriate format. The generation unit uses a generation AI to analyze the videos received by the reception unit, extract key points, and generate a digest version. The generation unit uses a generation AI to analyze the video content and extract important scenes, for example. The generation unit can also automatically edit the digest version based on the scenes extracted by the generation AI. The generation unit can also use a generation AI to analyze the audio of the video and extract important statements. The verification unit checks the digest video generated by the generation unit and makes adjustments as needed. The verification unit enables users to preview the digest video and check the edits, for example. The verification unit also allows users to add or delete specific scenes from the digest video. The verification unit also allows users to edit the audio and subtitles of the digest video. The collection unit collects viewing data. For example, the collection unit collects data such as viewers' viewing time, number of views, and viewers' attributes. The collection unit can also collect viewers' device information and geographical location information. The collection unit can also collect viewers' feedback and comments. The analysis unit analyzes the viewing data collected by the collection unit using AI. For example, the analysis unit analyzes viewing trends based on the viewing data. The analysis unit can also analyze viewers' attributes and behavioral patterns based on the viewing data. The analysis unit can also analyze viewers' interests and concerns based on the viewing data. The prediction unit predicts how many inquiries or applications the video will generate based on the analysis results obtained by the analysis unit. For example, the prediction unit builds a prediction model for inquiries and applications based on the viewing data. The prediction unit can also predict marketing effectiveness based on the viewing data. The prediction unit can also predict viewers' behavior based on the viewing data.As a result, the video editing and marketing support system according to this embodiment can consistently perform tasks from uploading videos to generating digest versions, collecting and analyzing viewing data, and predicting responses.

[0075] The reception desk accepts user uploads of recorded video presentations. For example, the reception desk allows users to upload video files via a web interface. Specifically, users can access a dedicated web portal and easily upload video files using drag-and-drop functionality. The reception desk can also verify the format and size of video files and convert them to the appropriate format. For instance, if an uploaded video is not in a specific format (e.g., MP4, AVI, MOV), it has a function to automatically convert it to the correct format. Furthermore, it verifies the video's resolution and bitrate and optimizes it as needed. This allows users to upload videos smoothly without cumbersome procedures. The reception desk also provides an interface for entering metadata for uploaded videos (e.g., title, description, tags), allowing users to easily manage the content of their videos. This improves video searchability and organization, and streamlines subsequent processing.

[0076] The generation unit uses a generation AI to analyze videos received by the reception unit, extract key points, and generate a digest version. For example, the generation AI analyzes the video content and extracts important scenes. Specifically, the generation AI uses natural language processing technology to convert the video's audio into text and extract keywords and phrases. Furthermore, it uses image recognition technology to identify visually important scenes (e.g., product demonstrations or important slide displays). Based on this information, the generation AI extracts key points from the video and automatically edits the digest version. The generation unit can also automatically edit the digest version based on the scenes extracted by the generation AI. For example, the generation AI can arrange the extracted scenes in an appropriate order to generate a digest version with a smooth flow. The generation unit can also have the generation AI analyze the video's audio and extract important statements. This allows viewers to grasp the main points of the video in a short amount of time. The generation unit can also periodically update the generation AI's training data to improve analysis accuracy. This allows the production unit to always use the latest technology to provide high-quality digest versions.

[0077] The verification unit reviews the digest video generated by the generation unit and makes adjustments as needed. For example, the verification unit allows users to preview the digest video and review their edits. Specifically, users can play the digest video through a web interface and review the content of each scene. The verification unit also allows users to add or delete specific scenes from the digest video. For example, users can change the order of scenes or delete unwanted scenes using drag-and-drop functionality. Furthermore, the verification unit allows users to edit the audio and subtitles of the digest video. For example, they can adjust the audio volume or change the content and timing of the subtitles. This allows users to customize the digest video to their needs. The verification unit also saves the user's editing history and provides a function to revert to the original state at any time. This allows users to edit with confidence.

[0078] The data collection unit collects viewing data. For example, the data collection unit collects data such as viewers' viewing time, number of views, and viewer attributes. Specifically, it collects detailed data such as the time viewers played a video, the number of views, and where they paused during playback. The data collection unit can also collect viewers' device information and geographical location information. For example, it collects the type of device the viewer is using (smartphone, tablet, PC, etc.) and geographical location information based on the viewer's IP address. Furthermore, the data collection unit can also collect viewer feedback and comments. For example, it collects comments and ratings left by viewers on videos, and opinions provided through feedback forms. This allows the data collection unit to understand viewer behavior and reactions in detail, which can be used for subsequent analysis and prediction. It is also important for the data collection unit to securely store the collected data and take appropriate measures to protect privacy.

[0079] The analytics department uses AI to analyze viewing data collected by the data collection department. For example, the analytics department analyzes viewing trends based on viewing data. Specifically, it analyzes data such as which scenes viewers watched the longest and at which scenes they stopped watching, in order to identify viewers' interests and preferences. The analytics department can also analyze viewers' attributes and behavioral patterns based on viewing data. For example, it analyzes the viewing trends of specific attribute groups based on attribute information such as viewers' age, gender, and region. Furthermore, the analytics department can analyze viewers' interests and preferences based on viewing data. For example, it can evaluate the degree of interest viewers have in a particular product or service, which can be used to formulate marketing strategies. The analytics department can also use AI machine learning algorithms to extract patterns and trends from viewing data and predict future viewing trends. As a result, the analytics department can perform advanced analysis based on viewing data and provide valuable insights to maximize the effectiveness of marketing activities.

[0080] The prediction unit predicts how many inquiries or applications a video will generate, based on the analysis results obtained by the analysis unit. For example, the prediction unit builds a predictive model for inquiries and applications based on viewing data. Specifically, it trains a machine learning algorithm using past viewing data and actual inquiry and application data to predict the probability of future inquiries and applications. The prediction unit can also predict marketing effectiveness based on viewing data. For example, it can predict how many viewers a particular video will reach and how much engagement it will generate. Furthermore, the prediction unit can predict viewer behavior based on viewing data. For example, it can predict what actions viewers will take after watching a video (e.g., visiting a website, purchasing a product), which can be used to optimize marketing strategies. It is important for the prediction unit to update prediction results in real time and provide highly accurate predictions based on the latest data. This allows the prediction unit to play a crucial role in maximizing the effectiveness of marketing activities and supporting business growth.

[0081] The generation unit can analyze a video using a generation AI, extract important points, and generate a digest version. For example, the generation unit can use the generation AI to analyze the video content and extract important scenes. The generation unit can also automatically edit the digest version based on the scenes extracted by the generation AI. The generation unit can also use the generation AI to analyze the audio of the video and extract important statements. In this way, by using the generation AI, it is possible to efficiently extract important points from a video and generate a digest version. Some or all of the above processing in the generation unit may be performed using the generation AI, or it may be performed without using the generation AI. For example, the generation unit can input video data into the generation AI to analyze the video content, and the generation AI can extract important scenes and generate a digest version.

[0082] The data collection unit can collect viewer data. For example, the data collection unit can collect data such as viewer viewing time, number of views, and viewer attributes. The data collection unit can also collect viewer device information and geographical location information. The data collection unit can also collect viewer feedback and comments. This makes it easier to understand viewing trends by collecting viewer data. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input viewer viewing data into AI, which can analyze the viewing data and understand viewing trends.

[0083] The analysis unit can analyze viewing data collected by the collection unit using AI. For example, the analysis unit can analyze viewing trends based on the viewing data. The analysis unit can also analyze viewer attributes and behavioral patterns based on the viewing data. The analysis unit can also analyze viewer interests and concerns based on the viewing data. As a result, the accuracy of viewing data analysis is improved by using AI. Some or all of the above-mentioned processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input viewing data into AI, which can analyze the viewing data and understand viewing trends.

[0084] The prediction unit can predict how many inquiries or applications a video will generate based on the analysis results obtained by the analysis unit. For example, the prediction unit can build a prediction model for inquiries and applications based on viewing data. The prediction unit can also predict marketing effectiveness based on viewing data. The prediction unit can also predict viewer behavior based on viewing data. This allows for the effective development of marketing strategies by predicting video responses. Some or all of the above processes in the prediction unit may be performed using AI or not. For example, the prediction unit can input viewing data into AI, which can analyze the viewing data and make response predictions.

[0085] The verification unit can review the automatically generated digest video and make adjustments as needed. For example, the verification unit allows the user to preview the digest video and review the edits. It also allows the user to add or delete specific scenes from the digest video. Furthermore, the verification unit allows the user to edit the audio and subtitles of the digest video. This enables the provision of higher-quality videos by checking the quality of the digest video and making adjustments as needed. Some or all of the above processes in the verification unit may be performed using AI or not. For example, the verification unit can input the digest video into an AI, which can evaluate the video quality and make necessary adjustments.

[0086] The reception desk can estimate the user's emotions and adjust the video upload timing based on the estimated emotions. For example, if the user is stressed, the reception desk can simplify the upload process and allow for a quicker upload. If the user is relaxed, the reception desk can also provide detailed upload options and suggest a customizable upload method. If the user is in a hurry, the reception desk can prioritize voice input and allow for a quicker video upload. This improves user convenience by adjusting the upload timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input user emotion data into an AI, which can estimate the emotions and adjust the upload timing.

[0087] The reception desk can analyze a user's past upload history and select the optimal upload method. For example, the reception desk can automatically suggest upload methods that the user has frequently used in the past. It can also suggest the optimal upload method for a specific time period based on the user's past upload history. Furthermore, the reception desk can analyze the content of videos previously uploaded by the user and suggest optimal upload settings. This allows the reception desk to provide the user with the most suitable upload method by analyzing their past upload history. Some or all of the above processes in the reception desk may be performed using AI, or not. For example, the reception desk can input the user's past upload history into an AI, which can then select the optimal upload method.

[0088] The reception desk can filter videos based on the user's current projects and areas of interest when they are uploaded. For example, the reception desk can prioritize uploading videos related to the user's current projects. The reception desk can also filter and upload highly relevant videos based on the user's areas of interest. The reception desk can also select and upload the most suitable videos according to the progress of the user's projects. This allows for the priority uploading of highly relevant videos by filtering videos based on the user's projects and areas of interest. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the user's project information and areas of interest into an AI, which can then select and upload the most suitable videos.

[0089] The reception desk can estimate the user's emotions and determine the priority of videos to upload based on the estimated emotions. For example, if the user is excited, the reception desk may prioritize uploading visually stimulating videos. It may also prioritize uploading calming videos if the user is relaxed, or relaxing videos if the user is stressed. This allows for the uploading of more appropriate videos by prioritizing them according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input user emotion data into an AI, which can estimate the emotions and determine the priority of videos.

[0090] The reception desk can prioritize uploading videos that are highly relevant to the user, taking into account the user's geographical location when uploading videos. For example, if the user is in a specific region, the reception desk will prioritize uploading videos related to that region. The reception desk can also prioritize uploading videos filmed near the user's current location. The reception desk can also filter and upload videos that are highly relevant based on the user's geographical location. This allows for the provision of region-specific content by uploading videos that are highly relevant based on the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the user's geographical location into an AI, which can then select and upload highly relevant videos.

[0091] The reception desk can analyze a user's social media activity when uploading videos and upload relevant videos. For example, the reception desk can upload relevant videos based on what the user has shared on social media. It can also analyze a user's social media activity history and select and upload the most suitable videos. The reception desk can also prioritize uploading videos that the user's followers and friends are likely to be interested in. This allows the reception desk to provide content that matches the user's interests by uploading relevant videos based on the user's social media activity. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the user's social media activity data into an AI, which can then select and upload relevant videos.

[0092] The generation unit can estimate the user's emotions and adjust the presentation of the digest version based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate a digest version that proceeds at a leisurely pace. If the user is in a hurry, the generation unit can also generate a digest version that emphasizes the shortest route. If the user is excited, the generation unit can also generate a digest version with visually stimulating effects. By adjusting the presentation of the digest version according to the user's emotions, a more engaging video can be provided to the viewer. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using the generation AI or not. For example, the generation unit can input user emotion data into the generation AI, which can estimate the emotions and adjust the presentation of the digest version.

[0093] The generation unit can adjust the level of detail in the summary based on the importance of the video when generating a digest version. For example, if a video has many important points, the generation unit will generate a detailed summary. Conversely, if a video has few important points, the generation unit can also generate a concise summary. The generation unit can also dynamically adjust the level of detail in the summary according to the importance of the video. This allows for the provision of optimal information to viewers by adjusting the level of detail in the summary according to the importance of the video. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input video importance data into a generation AI, and the generation AI can adjust the level of detail in the summary.

[0094] The generation unit can apply different summarization algorithms depending on the video category when generating a digest version. For example, in the case of a product introduction video, the generation unit can generate a summary that emphasizes the product's features. It can also generate a summary that emphasizes important skills and techniques in the case of a training video. In the case of an event report video, the generation unit can generate a summary that emphasizes the highlights of the main event. This allows for the generation of more appropriate summaries by applying a summarization algorithm according to the video category. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input video category data into a generation AI, which can then apply the most suitable summarization algorithm.

[0095] The generation unit can estimate the user's emotions and adjust the length of the digest based on the estimated emotions. For example, if the user is in a hurry, the generation unit can generate a short, concise digest. If the user is relaxed, the generation unit can also generate a longer digest with more detailed explanations. If the user is excited, the generation unit can generate a digest with visually stimulating effects. By adjusting the length of the digest according to the user's emotions, the system can provide the viewer with the most suitable video. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using or without a generation AI. For example, the generation unit can input user emotion data into a generation AI, which can estimate the emotions and adjust the length of the digest.

[0096] The generation unit can determine the priority of summaries based on the video shooting dates when generating a digest version. For example, the generation unit may prioritize summarizing recently filmed videos. It can also prioritize summarizing videos related to specific events or campaigns. The generation unit can also dynamically adjust the priority of summaries based on the video shooting dates. This allows for the prioritization of the most up-to-date information by determining the priority of summaries based on the video shooting dates. Some or all of the above processing in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input video shooting date data into a generation AI, which can then determine the priority of summaries.

[0097] The generation unit can adjust the order of summaries based on the relevance of the video when generating a digest version. For example, the generation unit can prioritize summarizing points that are highly relevant. It can also postpone summarizing points that are less relevant. The generation unit can also dynamically adjust the order of summaries based on the relevance of the video. This allows information to be provided to the viewer in the optimal order by adjusting the order of summaries based on the relevance of the video. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input video relevance data into a generation AI, and the generation AI can adjust the order of summaries.

[0098] The verification unit can estimate the user's emotions and adjust the condensed version's verification method based on the estimated emotions. For example, if the user is relaxed, the verification unit can provide detailed verification options. If the user is in a hurry, it can also provide concise verification options. If the user is excited, it can also provide visually stimulating verification options. This allows for a more appropriate verification method by adjusting the condensed version's verification method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the verification unit may be performed using AI or not. For example, the verification unit can input user emotion data into an AI, which can estimate the emotions and adjust the verification method.

[0099] The verification unit can select the optimal verification method by referring to the user's past verification history during verification. For example, the verification unit may prioritize suggesting verification methods that the user has used in the past. The verification unit can also suggest the optimal verification method for a specific time period based on the user's past verification history. The verification unit can also analyze the user's past verification history and suggest the optimal verification settings. In this way, by referring to past verification history, the verification unit can provide the user with the most suitable verification method. Some or all of the above processes in the verification unit may be performed using AI or not. For example, the verification unit can input the user's past verification history into AI, and the AI ​​can select the optimal verification method.

[0100] The verification unit can adjust the level of detail of the verification based on the importance of the video during the verification process. For example, if a video has many important points, the verification unit will perform a detailed verification. Conversely, if a video has few important points, the verification unit can perform a concise verification. The verification unit can also dynamically adjust the level of detail of the verification according to the importance of the video. This allows for efficient verification by adjusting the level of detail according to the importance of the video. Some or all of the above processing in the verification unit may be performed using AI or not. For example, the verification unit can input video importance data into the AI, and the AI ​​can adjust the level of detail of the verification.

[0101] The verification unit can estimate the user's emotions and determine the priority of the digest versions to review based on the estimated emotions. For example, if the user is excited, the verification unit will prioritize reviewing visually stimulating digest versions. It can also prioritize reviewing calming digest versions if the user is relaxed, or relaxing digest versions if the user is stressed. This allows for a more appropriate review order by prioritizing the digest versions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the verification unit may be performed using AI or not. For example, the verification unit can input user emotion data into an AI, which can estimate the emotions and determine the priority of the digest versions.

[0102] The verification unit can select the optimal verification method by considering the user's device information during verification. For example, if the user is using a smartphone, the verification unit can provide a verification method that matches the screen size. Furthermore, if the user is using a tablet, the verification unit can provide a verification method optimized for a larger screen. If the user is using a smartwatch, the verification unit can provide a concise and highly visible verification method. This improves convenience by providing the optimal verification method based on the user's device information. Some or all of the above processing in the verification unit may be performed using AI, or not. For example, the verification unit can input the user's device information into the AI, which can then select the optimal verification method.

[0103] The verification unit can analyze the user's social media activity during verification and review relevant digest versions. For example, the verification unit can review relevant digest versions based on content the user has shared on social media. The verification unit can also analyze the user's social media activity history and select and review the most appropriate digest version. The verification unit can also prioritize reviewing digest versions that the user's followers and friends are likely to be interested in. This allows for the provision of more relevant content by reviewing relevant digest versions based on the user's social media activity. Some or all of the above processing in the verification unit may be performed using AI or not. For example, the verification unit can input the user's social media activity data into AI, which can then select and review relevant digest versions.

[0104] The data collection unit can estimate the user's emotions and adjust the timing of viewing data collection based on the estimated emotions. For example, if the user is relaxed, the data collection unit can collect detailed viewing data. If the user is in a hurry, the data collection unit can also collect concise viewing data. If the user is excited, the data collection unit can also collect visually stimulating viewing data. This allows for more appropriate data collection by adjusting the timing of viewing data collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into an AI, which can estimate the emotions and adjust the timing of viewing data collection.

[0105] The data collection unit can analyze a user's past viewing history and select the optimal data collection method when collecting viewing data. For example, the data collection unit can suggest the optimal data collection method based on data of videos the user has watched in the past. The data collection unit can also suggest the optimal data collection method for a specific time period based on the user's past viewing history. The data collection unit can also analyze a user's past viewing history and suggest the most efficient data collection method. In this way, by analyzing past viewing history, the data collection unit can provide the user with the most suitable method for collecting viewing data. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's past viewing history into AI, which can then select the optimal data collection method.

[0106] The data collection unit can filter viewing data based on the user's current viewing status and areas of interest. For example, the data collection unit can prioritize collecting data related to the video the user is currently watching. The data collection unit can also filter and collect highly relevant viewing data based on the user's areas of interest. The data collection unit can also select and collect the most relevant viewing data according to the user's viewing status. This allows for the collection of more relevant data by filtering viewing data based on the user's viewing status and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's viewing status and areas of interest data into an AI, which can then select and collect the most relevant viewing data.

[0107] The data collection unit can estimate the user's emotions and determine the priority of viewing data to collect based on the estimated emotions. For example, if the user is excited, the data collection unit may prioritize collecting visually stimulating viewing data. Similarly, if the user is relaxed, the data collection unit may prioritize collecting calming viewing data. If the user is stressed, the data collection unit may prioritize collecting relaxing viewing data. This allows for the collection of more appropriate data by prioritizing viewing data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into an AI, which can estimate the emotions and determine the priority of viewing data.

[0108] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information when collecting viewing data. For example, if the user is in a specific region, the data collection unit will prioritize the collection of viewing data related to that region. The data collection unit can also prioritize the collection of viewing data filmed in locations close to the user's current location. The data collection unit can also filter and collect highly relevant viewing data based on the user's geographical location information. This allows for the provision of region-specific data by collecting highly relevant viewing data based on the user's geographical location information. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's geographical location information into AI, which can then select and collect highly relevant viewing data.

[0109] The data collection unit can analyze the user's social media activity and collect relevant data when collecting viewing data. For example, the data collection unit can collect relevant viewing data based on what the user has shared on social media. The data collection unit can also analyze the user's social media activity history and select and collect the most relevant viewing data. The data collection unit can also prioritize collecting viewing data that the user's followers and friends are likely to be interested in. This allows for the provision of more relevant data by collecting relevant viewing data based on the user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's social media activity data into AI, which can then select and collect relevant viewing data.

[0110] The analysis unit can estimate the user's emotions and adjust the method of analyzing viewing data based on the estimated emotions. For example, if the user is relaxed, the analysis unit can perform a detailed analysis. If the user is in a hurry, the analysis unit can perform a concise analysis. If the user is excited, the analysis unit can provide visually stimulating analysis results. This allows for more appropriate analysis results by adjusting the method of analyzing viewing data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into an AI, which can estimate the emotions and adjust the analysis method.

[0111] The analysis unit can predict current viewing trends by referring to past viewing data during analysis. For example, the analysis unit predicts current viewing trends based on past viewing data. The analysis unit can also predict viewing trends for specific time periods from past viewing data. The analysis unit can also analyze past viewing data and predict the most efficient viewing trends. This allows for a more accurate prediction of current viewing trends by referring to past viewing data. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input past viewing data into AI, which can then predict current viewing trends.

[0112] The analysis department can apply different analytical methods to each category of viewing data during analysis. For example, in the case of product introduction videos, the analysis department can perform an analysis that emphasizes the product's features. Similarly, in the case of training videos, the analysis department can perform an analysis that emphasizes important skills and techniques. In the case of event report videos, the analysis department can perform an analysis that emphasizes the highlights of the main event. This allows for more accurate analytical results by applying the most appropriate analytical method according to the category of viewing data. Some or all of the above processing in the analysis department may be performed using AI, or not. For example, the analysis department can input the category data of the viewing data into an AI, which can then apply the most appropriate analytical method.

[0113] The analysis unit can estimate the user's emotions and adjust the importance of viewing data based on the estimated emotions. For example, if the user is excited, the analysis unit will prioritize visually stimulating viewing data. If the user is relaxed, the analysis unit can also prioritize calming viewing data. If the user is stressed, the analysis unit can also prioritize viewing data with a relaxing effect. This allows for the analysis of more appropriate data by adjusting the importance of viewing data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into an AI, which can estimate the emotions and adjust the importance of the viewing data.

[0114] The analysis unit can analyze changes in viewing trends based on the timing of viewing data collection during the analysis process. For example, the analysis unit can analyze changes in viewing trends based on the timing of viewing data collection. The analysis unit can also analyze changes in viewing data related to specific events or campaigns. The analysis unit can also dynamically analyze changes in viewing trends based on the timing of viewing data collection. This allows for more accurate trend analysis by analyzing changes in viewing trends based on the timing of viewing data collection. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input viewing data collection timing data into AI, and the AI ​​can analyze changes in viewing trends.

[0115] The analysis unit can analyze viewing trends by referring to relevant market data for viewing data during the analysis process. For example, the analysis unit can analyze viewing trends based on relevant market data for viewing data. The analysis unit can also analyze viewing trends for specific time periods from relevant market data for viewing data. The analysis unit can also analyze relevant market data for viewing data to determine the most efficient viewing trends. This allows for a more accurate analysis of viewing trends by referring to relevant market data for viewing data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input relevant market data for viewing data into an AI, which can then analyze viewing trends.

[0116] The prediction unit can estimate the user's emotions and adjust the response prediction method based on the estimated user emotions. For example, if the user is relaxed, the prediction unit can provide a detailed response prediction. If the user is in a hurry, the prediction unit can also provide a concise response prediction. If the user is excited, the prediction unit can also provide a visually stimulating response prediction. By adjusting the response prediction method according to the user's emotions, more accurate prediction results can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prediction unit may be performed using AI or not. For example, the prediction unit can input user emotion data into an AI, which can estimate the emotions and adjust the response prediction method.

[0117] The prediction unit can analyze past viewing data to select the optimal response prediction method during prediction. For example, the prediction unit can propose the optimal response prediction method based on past viewing data. The prediction unit can also propose a response prediction method for a specific time period based on past viewing data. The prediction unit can also analyze past viewing data and propose the most efficient response prediction method. In this way, the optimal response prediction method can be provided by analyzing past viewing data. Some or all of the above processing in the prediction unit may be performed using AI or not. For example, the prediction unit can input past viewing data into AI, and the AI ​​can select the optimal response prediction method.

[0118] The prediction unit can customize the response prediction method based on the category of the viewing data during prediction. For example, in the case of a product introduction video, the prediction unit can perform response predictions that emphasize the product's features. The prediction unit can also perform response predictions that emphasize important skills and techniques in the case of a training video. In the case of an event report video, the prediction unit can perform response predictions that emphasize the highlights of the main event. This allows for more accurate prediction results by customizing the response prediction method according to the category of the viewing data. Some or all of the above processing in the prediction unit may be performed using AI or not. For example, the prediction unit can input the category data of the viewing data into the AI, which can then apply the most suitable response prediction method.

[0119] The prediction unit can estimate the user's emotions and determine the priority of response predictions based on the estimated emotions. For example, if the user is excited, the prediction unit may prioritize visually stimulating response predictions. Similarly, if the user is relaxed, the prediction unit may prioritize calming response predictions. If the user is stressed, the prediction unit may prioritize relaxing response predictions. This allows for more appropriate prediction results by prioritizing response predictions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the prediction unit may be performed using AI or not. For example, the prediction unit can input user emotion data into an AI, which can estimate the emotions and determine the priority of response predictions.

[0120] The prediction unit can select the optimal response prediction method by considering the geographical location information of the viewing data during prediction. For example, if the user is in a specific region, the prediction unit will perform a response prediction relevant to that region. The prediction unit can also perform a response prediction based on viewing data taken in a location close to the user's current location. The prediction unit can also perform a highly relevant response prediction based on the user's geographical location information. This allows for the provision of region-specific prediction results by providing the optimal response prediction method based on the geographical location information of the viewing data. Some or all of the above processing in the prediction unit may be performed using AI or not. For example, the prediction unit can input the geographical location information of the viewing data into the AI, which can then select the optimal response prediction method.

[0121] The prediction unit can improve the accuracy of response predictions by referring to relevant literature for viewing data during the prediction process. For example, the prediction unit improves the accuracy of response predictions based on relevant literature for viewing data. The prediction unit can also improve the accuracy of response predictions for specific time periods from relevant literature for viewing data. The prediction unit can also analyze relevant literature for viewing data to improve the accuracy of the most efficient response prediction. In this way, the accuracy of response predictions can be improved by referring to relevant literature for viewing data. Some or all of the above processing in the prediction unit may be performed using AI or not. For example, the prediction unit can input relevant literature for viewing data into AI, and the AI ​​can improve the accuracy of response predictions.

[0122] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0123] The reception desk can estimate the user's emotions and adjust the video upload timing based on the estimated emotions. For example, if the user is stressed, the upload procedure can be simplified to allow for faster uploads. If the user is relaxed, detailed upload options can be provided, and a customizable upload method can be suggested. Furthermore, if the user is in a hurry, voice input can be prioritized to allow for faster video uploads. This improves user convenience by adjusting the upload timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input user emotion data into an AI, which can estimate the emotions and adjust the upload timing.

[0124] The generation unit can estimate the user's emotions and adjust the presentation of the digest version based on the estimated emotions. For example, if the user is relaxed, it can generate a digest version that proceeds at a leisurely pace. If the user is in a hurry, it can also generate a digest version that emphasizes the shortest route. Furthermore, if the user is excited, it can generate a digest version with visually stimulating effects. By adjusting the presentation of the digest version according to the user's emotions, it is possible to provide a more engaging video for viewers. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using the generative AI or not. For example, the generation unit can input user emotion data into the generative AI, which can estimate the emotions and adjust the presentation of the digest version.

[0125] The data collection unit can estimate the user's emotions and adjust the timing of viewing data collection based on the estimated emotions. For example, if the user is relaxed, detailed viewing data can be collected. If the user is in a hurry, concise viewing data can be collected. Furthermore, if the user is excited, visually stimulating viewing data can be collected. By adjusting the timing of viewing data collection according to the user's emotions, more appropriate data collection becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into an AI, which can estimate the emotions and adjust the timing of viewing data collection.

[0126] The analysis unit can estimate the user's emotions and adjust the analysis method of viewing data based on the estimated user emotions. For example, if the user is relaxed, a detailed analysis can be performed. If the user is in a hurry, a concise analysis can be performed. Furthermore, if the user is excited, visually stimulating analysis results can be provided. In this way, by adjusting the analysis method of viewing data according to the user's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into AI, which can estimate emotions and adjust the analysis method.

[0127] The prediction unit can estimate the user's emotions and adjust the response prediction method based on the estimated user emotions. For example, if the user is relaxed, it can provide a detailed response prediction. If the user is in a hurry, it can provide a concise response prediction. Furthermore, if the user is excited, it can provide a visually stimulating response prediction. By adjusting the response prediction method according to the user's emotions, more accurate prediction results can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prediction unit may be performed using AI or not. For example, the prediction unit can input user emotion data into an AI, which can estimate the emotions and adjust the response prediction method.

[0128] The reception desk can analyze a user's past upload history and select the optimal upload method. For example, it can automatically suggest upload methods that the user has frequently used in the past. It can also suggest the optimal upload method for a specific time of day based on the user's past upload history. Furthermore, it can analyze the content of videos the user has uploaded in the past and suggest the optimal upload settings. In this way, by analyzing past upload history, the system can provide the user with the most suitable upload method. Some or all of the above processes in the reception desk may be performed using AI or not. For example, the reception desk can input the user's past upload history into the AI, which can then select the optimal upload method.

[0129] The reception system can filter videos based on the user's current projects and areas of interest when they are uploaded. For example, it can prioritize uploading videos related to the user's current projects. It can also filter and upload highly relevant videos based on the user's areas of interest. Furthermore, it can select and upload the most suitable videos according to the progress of the user's projects. This allows for the priority uploading of highly relevant videos by filtering videos based on the user's projects and areas of interest. Some or all of the above processing in the reception system may be performed using AI or not. For example, the reception system can input the user's project information and areas of interest into an AI, which can then select and upload the most suitable videos.

[0130] The generation unit can adjust the level of detail in the summary based on the importance of the video when generating a digest version. For example, if a video has many important points, it can generate a detailed summary. Conversely, if a video has few important points, it can generate a concise summary. Furthermore, the level of detail in the summary can be dynamically adjusted according to the importance of the video. This allows for the provision of optimal information to viewers by adjusting the level of detail in the summary according to the importance of the video. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input video importance data into the generation AI, and the generation AI can adjust the level of detail in the summary.

[0131] The generation unit can apply different summarization algorithms depending on the video category when generating a digest version. For example, in the case of a product introduction video, it can generate a summary that emphasizes the product's features. In the case of a training video, it can also generate a summary that emphasizes important skills and techniques. Furthermore, in the case of an event report video, it can generate a summary that emphasizes the highlights of the main event. By applying a summarization algorithm according to the video category, a more appropriate summary can be generated. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input video category data into the generation AI, and the generation AI can apply the optimal summarization algorithm.

[0132] The analysis department can apply different analytical methods to each category of viewing data during analysis. For example, in the case of product introduction videos, the analysis can highlight the product's features. In the case of training videos, the analysis can highlight important skills and techniques. Furthermore, in the case of event report videos, the analysis can highlight the key event's highlights. This allows for more accurate analysis results by applying the most appropriate analytical method according to the category of viewing data. Some or all of the above processing in the analysis department may be performed using AI or not. For example, the analysis department can input the category data of the viewing data into the AI, which can then apply the most appropriate analytical method.

[0133] The following briefly describes the processing flow for example form 2.

[0134] Step 1: The reception desk accepts user uploads of recorded video presentations. The reception desk allows users to upload video files, for example, through a web interface. The reception desk can also verify the format and size of the video files and convert them to an appropriate format. Step 2: The generation unit uses a generation AI to analyze the video received by the reception unit, extract key points, and generate a digest version. For example, the generation unit's generation AI analyzes the video content and extracts important scenes. The generation unit can also automatically edit the digest version based on the scenes extracted by the generation AI. The generation unit's generation AI can also analyze the audio of the video and extract important statements. Step 3: The verification unit reviews the digest video generated by the generation unit and makes adjustments as needed. The verification unit allows the user to preview the digest video and check the edits. It also allows the user to add or delete specific scenes from the digest video. The verification unit also allows the user to edit the audio and subtitles of the digest video. Step 4: The data collection unit collects viewing data. The data collection unit collects data such as viewers' viewing time, number of views, and viewers' attributes. The data collection unit can also collect viewers' device information and geographical location information. The data collection unit can also collect viewers' feedback and comments. Step 5: The analysis department uses AI to analyze the viewing data collected by the data collection department. For example, the analysis department analyzes viewing trends based on the viewing data. The analysis department can also analyze viewer attributes and behavioral patterns based on the viewing data. The analysis department can also analyze viewer interests and preferences based on the viewing data. Step 6: The prediction unit predicts how many inquiries or applications the video will generate based on the analysis results obtained by the analysis unit. For example, the prediction unit builds a predictive model for inquiries and applications based on viewing data. The prediction unit can also predict marketing effectiveness based on viewing data. The prediction unit can also predict viewer behavior based on viewing data.

[0135] 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.

[0136] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0137] 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.

[0138] Each of the multiple elements described above, including the reception unit, generation unit, confirmation unit, collection unit, analysis unit, and prediction unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14, enabling the user to upload video files via a web interface. The generation unit is implemented by the specific processing unit 290 of the data processing device 12, analyzing the video using generation AI, extracting summary points, and generating a digest version. The confirmation unit is implemented by the control unit 46A of the smart device 14, enabling the user to preview the digest version video and confirm the edited content. The collection unit is implemented by the specific processing unit 290 of the data processing device 12, collecting viewing data. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12, analyzing the collected viewing data using AI. The prediction unit is implemented by the specific processing unit 290 of the data processing device 12, predicting how many inquiries or applications the video will generate based on the analysis results. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0139] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.).

[0151] 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.

[0152] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0153] 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.

[0154] Each of the multiple elements described above, including the reception unit, generation unit, confirmation unit, collection unit, analysis unit, and prediction unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214, enabling the user to upload video files via a web interface. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, analyzing the video using generation AI, extracting summary points, and generating a digest version. The confirmation unit is implemented by the control unit 46A of the smart glasses 214, enabling the user to preview the digest version video and confirm the edited content. The collection unit is implemented by the specific processing unit 290 of the data processing unit 12, collecting viewing data. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, analyzing the collected viewing data using AI. The prediction unit is implemented by the specific processing unit 290 of the data processing unit 12, predicting how many inquiries or applications the video will generate based on the analysis results. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0155] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.).

[0167] 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.

[0168] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0169] 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.

[0170] Each of the multiple elements described above, including the reception unit, generation unit, confirmation unit, collection unit, analysis unit, and prediction unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314, enabling the user to upload video files via a web interface. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, analyzing the video using generation AI, extracting summary points, and generating a digest version. The confirmation unit is implemented by the control unit 46A of the headset terminal 314, enabling the user to preview the digest video and confirm the edited content. The collection unit is implemented by the specific processing unit 290 of the data processing unit 12, collecting viewing data. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, analyzing the collected viewing data using AI. The prediction unit is implemented by the specific processing unit 290 of the data processing unit 12, predicting how many inquiries or applications the video will generate based on the analysis results. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0171] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.).

[0184] 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.

[0185] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0186] 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.

[0187] Each of the multiple elements described above, including the reception unit, generation unit, confirmation unit, collection unit, analysis unit, and prediction unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414, enabling users to upload video files through a web interface. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which analyzes the video using generation AI, extracts summary points, and generates a digest version. The confirmation unit is implemented by, for example, the control unit 46A of the robot 414, enabling users to preview the digest version video and confirm the edited content. The collection unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and collects viewing data. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and analyzes the collected viewing data using AI. The prediction unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and predicts how many inquiries or applications the video will generate based on the analysis results. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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."

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] (Note 1) The reception desk that accepts video uploads, A generation unit analyzes the video received by the reception unit, extracts key points, and generates a digest version. A confirmation unit for checking the digest video generated by the generation unit, A data collection unit that collects viewing data, An analysis unit analyzes the viewing data collected by the aforementioned collection unit, The system includes a prediction unit that creates a reaction prediction based on the analysis results obtained by the analysis unit. A system characterized by the following features. (Note 2) The generating unit is The AI ​​analyzes the video, extracts key points, and generates a digest version. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is Collect viewer data The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned analysis unit is The viewing data collected by the aforementioned collection unit is analyzed using AI. The system described in Appendix 1, characterized by the features described herein. (Note 5) The prediction unit, Based on the analysis results obtained by the aforementioned analysis unit, we predict how many inquiries or applications the video will generate. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned verification unit is Review the automatically generated digest video and make any necessary adjustments. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is It estimates the user's emotions and adjusts the video upload timing based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is Analyze the user's past upload history and select the optimal upload method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When uploading videos, filtering is performed based on the user's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is It estimates user sentiment and prioritizes uploading videos based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When uploading videos, the system prioritizes uploading videos that are highly relevant to the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When uploading a video, the system analyzes the user's social media activity and uploads relevant videos. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is The system estimates the user's emotions and adjusts the presentation of the digest version based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is When generating a digest version, adjust the level of detail in the summary based on the importance of the video. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is When generating a digest version, different summarization algorithms are applied depending on the video category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is It estimates the user's emotions and adjusts the length of the digest version based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is When generating a digest version, the priority of the summaries is determined based on when the videos were filmed. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is When generating the digest version, the order of the summaries is adjusted based on the relevance of the videos. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned verification unit is The system estimates the user's emotions and adjusts how the digest version is viewed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned verification unit is During verification, the system will refer to the user's past verification history to select the most suitable verification method. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned verification unit is During the review process, adjust the level of detail based on the importance of the video. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned verification unit is It estimates the user's emotions and determines the priority of the digest version to review based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned verification unit is During verification, the optimal verification method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned verification unit is During the verification process, we analyze the user's social media activity and review relevant digest versions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of viewing data collection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned collection unit is When collecting viewing data, the system analyzes the user's past viewing history to select the most suitable collection method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned collection unit is When collecting viewing data, filtering is performed based on the user's current viewing habits and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned collection unit is It estimates the user's emotions and determines the priority of viewing data to collect based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned collection unit is When collecting viewing data, the system prioritizes collecting highly relevant data by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned collection unit is When collecting viewing data, we analyze users' social media activity and collect relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned analysis unit is We estimate user emotions and adjust the analysis method of viewing data based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned analysis unit is During analysis, past viewing data is referenced to predict current viewing trends. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned analysis unit is During analysis, different analytical methods are applied to each category of viewing data. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned analysis unit is It estimates the user's emotions and adjusts the importance of viewing data based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned analysis unit is During the analysis, we analyze changes in viewing trends based on when the viewing data was collected. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned analysis unit is During the analysis, we refer to relevant market data related to viewing data to analyze viewing trends. The system described in Appendix 1, characterized by the features described herein. (Note 37) The prediction unit, We estimate the user's emotions and adjust the response prediction method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The prediction unit, During the prediction process, past viewing data is analyzed to select the optimal response prediction method. The system described in Appendix 1, characterized by the features described herein. (Note 39) The prediction unit, During prediction, customize the response prediction method based on the categories of viewing data. The system described in Appendix 1, characterized by the features described herein. (Note 40) The prediction unit, It estimates the user's emotions and determines the priority of response predictions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 41) The prediction unit, During prediction, the optimal response prediction method is selected by considering the geographical location information of the viewing data. The system described in Appendix 1, characterized by the features described herein. (Note 42) The prediction unit, During prediction, we improve the accuracy of response predictions by referring to relevant literature on viewing data. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0207] 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 reception desk that accepts video uploads, A generation unit analyzes the video received by the reception unit, extracts key points, and generates a digest version. A confirmation unit for checking the digest video generated by the generation unit, A data collection unit that collects viewing data, An analysis unit analyzes the viewing data collected by the aforementioned collection unit, The system includes a prediction unit that creates a reaction prediction based on the analysis results obtained by the analysis unit. A system characterized by the following features.

2. The generating unit is The AI ​​analyzes the video, extracts key points, and generates a digest version. The system according to feature 1.

3. The aforementioned collection unit is Collect viewer data The system according to feature 1.

4. The aforementioned analysis unit is The viewing data collected by the aforementioned collection unit is analyzed using AI. The system according to feature 1.

5. The prediction unit, Based on the analysis results obtained by the aforementioned analysis unit, we predict how many inquiries or applications the video will generate. The system according to feature 1.

6. The aforementioned verification unit is Review the automatically generated digest video and make any necessary adjustments. The system according to feature 1.

7. The aforementioned reception unit is It estimates the user's emotions and adjusts the video upload timing based on the estimated user emotions. The system according to feature 1.

8. The aforementioned reception unit is Analyze the user's past upload history and select the optimal upload method. The system according to feature 1.

9. The aforementioned reception unit is When uploading videos, filtering is performed based on the user's current projects and areas of interest. The system according to feature 1.

10. The aforementioned reception unit is It estimates user sentiment and prioritizes uploading videos based on the estimated user sentiment. The system according to feature 1.

Images