system

Abstract

The system according to the embodiment aims to analyze talk data and generate and distribute effective short videos. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, a generation unit, and a distribution unit. The collection unit collects talk data. The analysis unit analyzes the talk data collected by the collection unit and learns patterns of jokes. The generation unit generates short videos based on the patterns of jokes learned by the analysis unit. The distribution unit distributes the short videos generated by the generation unit with advertisements attached.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, there was a problem in that there was no well-established method for utilizing talk data to generate effective short videos and generate advertising revenue.

[0005] The system according to the embodiment aims to analyze talk data and generate and distribute effective short videos. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a distribution unit. The collection unit collects talk data. The analysis unit analyzes the talk data collected by the collection unit and learns patterns of jokes. The generation unit generates short videos based on the patterns of jokes learned by the analysis unit. The distribution unit distributes the short videos generated by the generation unit with advertisements attached. [Effects of the Invention]

[0007] The system according to the embodiment can analyze talk data and generate and distribute effective short videos. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention learns from chat data on messaging apps such as LINE (registered trademark) and SMS, learning comments with "lol" or "w" to memorize jokes. This system consists of the following steps: First, chat data on messaging apps is collected and trained by an AI. Next, the AI ​​analyzes comments with "lol" or "w" to learn joke patterns. Based on the learned content, the AI ​​creates short videos. These short videos are distributed with advertisements. As the videos are viewed, the distributor earns advertising revenue and viewers can laugh. First, chat data on messaging apps is collected. This is done with the user's permission. For example, a user provides chat data including comments with "lol" or "w." This data is input into the AI. Next, the AI ​​analyzes the collected chat data. The AI ​​identifies comments with "lol" or "w" and analyzes the context surrounding the comments. For example, if someone makes a comment like "What happened yesterday was funny lol," the AI ​​analyzes the context before and after the comment and learns what kind of joke was used. Based on what it has learned, the AI ​​creates a short video. Based on the learned patterns of jokes, the AI ​​generates a video scenario. For example, based on the comment "What happened yesterday was funny lol," a short video containing a similar joke is created. The created short video is then distributed with advertisements attached. As the video is viewed, the broadcaster can earn advertising revenue. For example, the system allows viewers to earn advertising revenue based on the number of times the video is played. This system makes viewers laugh. Short videos created based on the patterns of jokes learned by the AI ​​are entertaining for viewers. For example, videos that depict everyday events in a humorous way can make viewers laugh. The system collects and analyzes talk data, generates short videos, and distributes them with advertisements, allowing the broadcaster to earn advertising revenue and viewers to laugh.

[0029] The system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a distribution unit. The collection unit collects talk data. The talk data includes, but is not limited to, audio data, text data, and video data. The collection unit collects the talk data with, for example, a user's permission. Specific methods and criteria for obtaining the user's permission include pop-up notifications, email notifications, and in-app notifications. The analysis unit analyzes the talk data collected by the collection unit and learns joke patterns. Examples of joke patterns include, but are not limited to, wordplay, physical jokes, and situational comedies. The analysis unit, for example, identifies comments with specific characters or character strings (e.g., "laugh" or "w") and analyzes the context surrounding the comment. For example, the analysis unit identifies a comment such as "What happened yesterday was funny lol" and analyzes the context surrounding the comment. The generation unit generates short videos based on the joke patterns learned by the analysis unit. Short videos include, but are not limited to, videos of less than 30 seconds or less than 1 minute. The generation unit generates a video scenario based on, for example, the learned joke patterns. For example, the generation unit creates a short video containing a similar joke based on a comment such as, "What happened yesterday was funny lol." The distribution unit distributes the short videos generated by the generation unit with advertisements attached. Examples of advertisements include, but are not limited to, banner ads, in-stream ads, and pop-up ads. The distribution unit has a mechanism for earning advertising revenue based on the number of times the video is played, for example. As a result, the system collects and analyzes talk data, generates short videos, and distributes them with advertisements, allowing the distributor to earn advertising revenue and viewers to laugh.

[0030] The system includes a permission unit that obtains user permission. The permission unit obtains user permission. Specific methods and standards for obtaining user permission include pop-up notifications, email notifications, in-app notifications, and the like. For example, the permission unit can obtain user permission using a pop-up notification. The permission unit can also obtain user permission using an email notification. Furthermore, the permission unit can also obtain user permission using an in-app notification. In this way, the system obtains user permission and thereby legally collects talk data.

[0031] The system includes a management unit that manages advertising revenue. The management unit manages advertising revenue. Specific methods for calculating and managing advertising revenue include revenue based on the number of clicks and revenue based on the number of impressions. For example, the management unit can calculate advertising revenue based on the number of clicks. The management unit can also calculate advertising revenue based on the number of impressions. Furthermore, the management unit can adjust the management method for advertising revenue. For example, the management unit can predict increases or decreases in revenue and adjust the management method. This allows the system to efficiently manage the revenue earned by distributors by managing advertising revenue.

[0032] The system includes a feedback unit that collects user feedback. The feedback unit collects user feedback. Specific methods and standards for collecting user feedback include questionnaires, comments, ratings, and the like. For example, the feedback unit can collect user feedback using questionnaires. The feedback unit can also collect user feedback using comments. Furthermore, the feedback unit can collect user feedback using ratings. In this way, the system can collect user feedback to help improve the system.

[0033] The collection unit can collect talk data with the user's permission. The collection unit collects talk data with the user's permission. Specific methods and standards for obtaining the user's permission include pop-up notifications, email notifications, in-app notifications, etc. For example, the collection unit can obtain the user's permission using a pop-up notification. The collection unit can also obtain the user's permission using an email notification. Furthermore, the collection unit can obtain the user's permission using an in-app notification. In this way, the collection unit can legally collect data by collecting talk data with the user's permission.

[0034] The analysis unit can identify comments containing "lol" or "w" and analyze the context surrounding them. The analysis unit can identify comments containing specific characters or character strings (e.g., "lol" or "w") and analyze the context surrounding them. Specific definitions and extraction methods for comments containing "lol" or "w" include keywords such as "lol," "w," and "LOL." For example, the analysis unit can identify comments containing the keyword "lol." The analysis unit can also identify comments containing the keyword "w." Furthermore, the analysis unit can identify comments containing the keyword "LOL." In this way, the analysis unit can learn patterns of jokes by identifying comments containing specific characters or character strings (e.g., "lol" or "w") and analyzing the context surrounding them.

[0035] The generation unit can generate a video scenario based on the learned bokeh patterns. The generation unit generates a video scenario based on the learned bokeh patterns. Specific methods and standards for creating a video scenario include a storyboard, a script, and scene composition. For example, the generation unit can create a video scenario using a storyboard. The generation unit can also create a video scenario using a script. Furthermore, the generation unit can also create a video scenario using scene composition. In this way, the generation unit can create an interesting short video by generating a video scenario based on the learned bokeh patterns.

[0036] The distribution unit can be equipped with a mechanism for earning advertising revenue according to the number of times a video is played. The distribution unit is equipped with a mechanism for earning advertising revenue according to the number of times a video is played. Specific methods and standards for measuring the number of times a video is played include unique views, total playback time, and the like. For example, the distribution unit can measure the number of times a video is played using unique views. The distribution unit can also measure the number of times a video is played using total playback time. Furthermore, the distribution unit can adjust the mechanism for earning advertising revenue based on the number of times a video is played. For example, the distribution unit can set it so that the more times a video is played, the higher the advertising revenue. In this way, the distribution unit can earn advertising revenue according to the number of times a video is played, allowing the distributor to earn income.

[0037] The collection unit can analyze the user's past talk data collection history and select the optimal collection method. The collection unit analyzes the user's past talk data collection history and selects the optimal collection method. Specific criteria and selection methods for the most effective collection method include collection speed, data quality, and user burden. For example, the collection unit can analyze time periods during which the user frequently provided talk data in the past and collect data during those time periods. The collection unit can also analyze the content of talk data provided by the user in the past and prioritize collection of data related to specific topics. Furthermore, the collection unit can select and execute the most efficient collection method from the user's past talk data collection history. In this way, the collection unit can select the optimal collection method by analyzing the past collection history.

[0038] The collection unit may filter the talk data based on the user's current areas of interest when collecting the talk data. Specific methods and criteria for identifying the user's current areas of interest include search history, browsing history, social media activity, etc. For example, the collection unit may preferentially collect talk data related to topics in which the user is currently interested. The collection unit may also analyze the user's social media activity and collect talk data related to the user's areas of interest. Furthermore, the collection unit may filter and collect related talk data based on keywords recently searched by the user. This allows the collection unit to collect highly relevant data by filtering data based on the user's areas of interest.

[0039] When collecting talk data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. When collecting talk data, the collection unit prioritizes collecting highly relevant data by taking into account the user's geographical location information. Specific methods and criteria for identifying the user's geographical location information include GPS data, IP address, Wi-Fi information, etc. For example, if the user is in a specific area, the collection unit can prioritize collecting talk data related to that area. Also, if the user is traveling, the collection unit can prioritize collecting talk data related to the user's travel destination. Furthermore, if the user is participating in a specific event, the collection unit can prioritize collecting talk data related to the event. In this way, the collection unit can collect highly relevant data by taking into account the geographical location information.

[0040] The collection unit can analyze the user's social media activities and collect related data when collecting the talk data. The collection unit analyzes the user's social media activities and collects related data when collecting the talk data. Specific methods and criteria for analyzing the user's social media activities include the content of posts, the number of likes, the number of followers, etc. For example, the collection unit can analyze the content of social media posts recently made by the user and collect related talk data. The collection unit can also analyze the content of posts made by accounts the user follows and collect related talk data. Furthermore, the collection unit can analyze the activities of groups and communities in which the user participates and collect related talk data. This allows the collection unit to collect highly relevant data by analyzing social media activities.

[0041] The analysis unit can adjust the level of detail of the analysis based on the importance of the comment during analysis. The analysis unit adjusts the level of detail of the analysis based on the importance of the comment during analysis. Specific criteria and methods for evaluating the importance of a comment include the number of likes, the number of replies, the influence of the poster, etc. For example, the analysis unit can perform a detailed analysis on important comments. The analysis unit can also perform a concise analysis on comments with low importance. Furthermore, the analysis unit can determine the priority of the analysis based on the importance of the comment. This allows the analysis unit to adjust the level of detail of the analysis based on the importance of the comment, enabling efficient analysis.

[0042] The analysis unit can apply different analysis algorithms depending on the category of the comment during analysis. The analysis unit applies different analysis algorithms depending on the category of the comment during analysis. Specific criteria and methods for classifying comment categories include positive, negative, neutral, etc. For example, the analysis unit can apply a humor analysis algorithm to humorous comments. The analysis unit can also apply a sentiment analysis algorithm to emotional comments. Furthermore, the analysis unit can select and apply the optimal analysis algorithm depending on the topic. This allows the analysis unit to apply the optimal analysis algorithm depending on the comment category, enabling highly accurate analysis.

[0043] During analysis, the analysis unit can determine the priority of analysis based on the time when the comment was posted. During analysis, the analysis unit determines the priority of analysis based on the time when the comment was posted. Specific methods and criteria for identifying the time when the comment was posted include timestamps, posting history, etc. For example, the analysis unit can prioritize the analysis of the most recent comment. The analysis unit can also place emphasis on the most recent comment while referring to past comments. Furthermore, the analysis unit can adjust the priority of analysis based on the time when the comment was posted. This allows the analysis unit to determine the priority of analysis based on the time when the comment was posted, enabling efficient analysis.

[0044] The analysis unit can adjust the order of analysis based on the relevance of the comments during analysis. The analysis unit can adjust the order of analysis based on the relevance of the comments during analysis. Specific criteria and methods for evaluating the relevance of comments include common keywords, matching topics, etc. For example, the analysis unit can prioritize the analysis of highly relevant comments. The analysis unit can also postpone the analysis of less relevant comments. Furthermore, the analysis unit can adjust the order of analysis based on the relevance of the comments. This allows the analysis unit to adjust the order of analysis based on the relevance of the comments, thereby enabling efficient analysis.

[0045] The generation unit can adjust the level of detail of the scenario based on the importance of the blur pattern during generation. The generation unit adjusts the level of detail of the scenario based on the importance of the blur pattern during generation. Specific criteria and methods for evaluating the importance of the blur pattern include viewer reaction, number of plays, etc. For example, the generation unit can generate a detailed scenario for an important blur. The generation unit can also generate a concise scenario for a blur with low importance. Furthermore, the generation unit can determine the priority of the scenario according to the importance of the blur. In this way, the generation unit can adjust the level of detail of the scenario according to the importance of the blur pattern, thereby enabling efficient video generation.

[0046] The generation unit can apply different generation algorithms depending on the category of the joke pattern during generation. The generation unit applies different generation algorithms depending on the category of the joke pattern during generation. Specific criteria and methods for classifying the categories of joke patterns include word play, physical jokes, situation comedy, etc. For example, the generation unit can apply a humor generation algorithm to jokes related to humor. The generation unit can also apply an emotion generation algorithm to jokes related to emotions. Furthermore, the generation unit can select and apply an optimal generation algorithm depending on the topic. In this way, the generation unit can apply an optimal generation algorithm depending on the category of the joke pattern, thereby enabling highly accurate video generation.

[0047] The generation unit can determine the priority of scenarios based on the posting time of the bokeh patterns at the time of generation. The generation unit determines the priority of scenarios based on the posting time of the bokeh patterns at the time of generation. Specific methods and criteria for identifying the posting time of the bokeh patterns include timestamps, posting history, etc. For example, the generation unit can preferentially reflect the latest bokeh in the scenario. The generation unit can also prioritize the latest bokeh while referring to past bokehs. Furthermore, the generation unit can adjust the priority of scenarios depending on the posting time of the bokeh. This allows the generation unit to determine the priority of scenarios depending on the posting time of the bokeh patterns, thereby enabling efficient video generation.

[0048] The generation unit can adjust the order of scenarios based on the relevance of blur patterns during generation. The generation unit adjusts the order of scenarios based on the relevance of blur patterns during generation. Specific criteria and methods for evaluating the relevance of blur patterns include common keywords, matching topics, etc. For example, the generation unit can preferentially reflect highly relevant blurs in the scenario. The generation unit can also postpone less relevant blurs. Furthermore, the generation unit can adjust the order of scenarios according to the relevance of blurs. This allows the generation unit to adjust the order of scenarios according to the relevance of blur patterns, thereby enabling efficient video generation.

[0049] The distribution unit can adjust the advertisement display method based on the number of times a video is played during distribution. The distribution unit adjusts the advertisement display method based on the number of times a video is played during distribution. Specific methods and criteria for measuring the number of times a video is played include unique views, total playback time, etc. For example, the distribution unit can measure the number of times a video is played using unique views. The distribution unit can also measure the number of times a video is played using total playback time. Furthermore, the distribution unit can adjust the advertisement display method based on the number of times a video is played. For example, the distribution unit can display a detailed advertisement for a video with a high number of views. The distribution unit can also display a concise advertisement for a video with a low number of views. In this way, the distribution unit can adjust the advertisement display method according to the number of times a video is played, thereby enabling effective advertisement display.

[0050] The distribution unit can apply different distribution algorithms depending on the category of the video during distribution. The distribution unit applies different distribution algorithms depending on the category of the video during distribution. Specific criteria and methods for classifying video categories include entertainment, education, news, etc. For example, the distribution unit can apply a humor distribution algorithm to videos related to humor. The distribution unit can also apply an emotion distribution algorithm to videos related to emotions. Furthermore, the distribution unit can select and apply an optimal distribution algorithm depending on the topic. This allows the distribution unit to apply an optimal distribution algorithm depending on the category of the video, enabling effective video distribution.

[0051] The distribution unit can adjust the order of distribution based on the posting time of the videos during distribution. The distribution unit can adjust the order of distribution based on the posting time of the videos during distribution. Specific methods and criteria for identifying the posting time of the videos include timestamps, posting history, etc. For example, the distribution unit can prioritize the most recent videos. The distribution unit can also prioritize the most recent videos while referring to past videos. Furthermore, the distribution unit can adjust the order of distribution based on the posting time of the videos. This allows the distribution unit to adjust the order of distribution based on the posting time of the videos, enabling efficient video distribution.

[0052] The distribution unit can adjust the order of distribution based on the relevance of the videos during distribution. The distribution unit adjusts the order of distribution based on the relevance of the videos during distribution. Specific criteria and methods for evaluating the relevance of videos include common keywords, matching topics, etc. For example, the distribution unit can prioritize the distribution of highly relevant videos. The distribution unit can also postpone videos with low relevance. Furthermore, the distribution unit can adjust the order of distribution based on the relevance of the videos. This allows the distribution unit to adjust the order of distribution based on the relevance of the videos, thereby enabling efficient video distribution.

[0053] The permission unit can select the optimal permission acquisition method by referring to the user's past permission history when obtaining permission. The permission unit can select the optimal permission acquisition method by referring to the user's past permission history when obtaining permission. Specific methods and criteria for referring to the user's past permission history include the types of past permission, the frequency of permission, etc. For example, the permission unit can preferentially suggest methods for which the user has previously granted permission. The permission unit can also select the most efficient permission acquisition method from the user's past permission history. Furthermore, the permission unit can analyze the user's past permission history and obtain permission at the optimal timing. In this way, the permission unit can select the optimal permission acquisition method by referring to the past permission history.

[0054] The permission unit can select the optimal permission acquisition method by taking into consideration the user's device information when obtaining permission. The permission unit selects the optimal permission acquisition method by taking into consideration the user's device information when obtaining permission. Specific methods and criteria for identifying the user's device information include the device type, OS, browser, etc. For example, if the user is using a smartphone, the permission unit can provide a permission acquisition method optimized for the smartphone. Furthermore, if the user is using a tablet, the permission unit can also provide a permission acquisition method optimized for the tablet. Furthermore, if the user is using a smartwatch, the permission unit can provide a permission acquisition method optimized for the smartwatch. This allows the permission unit to select the optimal permission acquisition method by taking into consideration the device information.

[0055] The management unit can refer to past advertising revenue data during management to select the optimal management method. The management unit can refer to past advertising revenue data during management to select the optimal management method. Specific methods and criteria for referring to past advertising revenue data include the timing of revenue and the type of revenue. For example, the management unit can analyze past advertising revenue data to select the optimal management method. The management unit can also predict increases or decreases in revenue from past advertising revenue data and adjust the management method. Furthermore, the management unit can select a management method that maximizes revenue based on past advertising revenue data. In this way, the management unit can select the optimal management method by referring to past advertising revenue data.

[0056] The management unit can adjust the revenue management method based on the advertisement display time during management. The management unit can adjust the revenue management method based on the advertisement display time during management. Specific methods and criteria for specifying the advertisement display time include time of day, day of the week, specific events, etc. For example, the management unit can adjust the revenue management method according to the advertisement display time. The management unit can also analyze the advertisement display time and select an optimal revenue management method. Furthermore, the management unit can provide a management method that maximizes revenue based on the advertisement display time. As a result, the management unit can maximize revenue by adjusting the revenue management method based on the advertisement display time.

[0057] When collecting feedback, the feedback unit can select the optimal collection method by referring to the user's past feedback history. When collecting feedback, the feedback unit selects the optimal collection method by referring to the user's past feedback history. Specific methods and criteria for referring to the user's past feedback history include the type of past feedback, the frequency of feedback, etc. For example, the feedback unit can select the optimal collection method based on feedback provided by the user in the past. The feedback unit can also select the most efficient collection method from the user's past feedback history. Furthermore, the feedback unit can analyze the user's past feedback history and collect feedback at the optimal timing. In this way, the feedback unit can select the optimal collection method by referring to the past feedback history.

[0058] The feedback unit may select an optimal feedback collection method in consideration of device information of the user when collecting feedback. The feedback unit may select an optimal feedback collection method in consideration of device information of the user when collecting feedback. Specific methods and criteria for identifying the user's device information include the type of device, OS, browser, etc. For example, if the user is using a smartphone, the feedback unit may provide a feedback collection method optimized for the smartphone. Also, if the user is using a tablet, the feedback unit may provide a feedback collection method optimized for the tablet. Furthermore, if the user is using a smartwatch, the feedback unit may provide a feedback collection method optimized for the smartwatch. In this way, the feedback unit can select an optimal feedback collection method in consideration of device information.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The system can analyze the user's past talk data and filter the talk data based on the user's interests and concerns. For example, if the user has provided a lot of talk data about sports in the past, the system can prioritize collection of talk data related to sports. Also, if the user has provided talk data about cooking in the past, the system can collect talk data related to cooking. Furthermore, if the user has provided talk data about travel in the past, the system can collect talk data related to travel. This allows the system to collect more relevant data by filtering the talk data based on the user's interests and concerns.

[0061] The system can collect user feedback in real time and instantly reflect the analysis results. For example, if a user provides feedback while watching a video, the system can instantly analyze that feedback and reflect it in the next video. Also, if a user posts a comment, the system can analyze that comment and recommend related videos. Furthermore, if a user provides a rating, the system can improve the quality of the video based on that rating. This allows the system to improve the user experience by collecting feedback in real time and instantly reflecting the analysis results.

[0062] The system can analyze a user's past viewing history and recommend the most suitable video. For example, if a user has watched many comedy videos in the past, comedy videos can be recommended preferentially. If a user has watched documentary videos in the past, documentary videos can be recommended. Furthermore, if a user has watched music videos in the past, music videos can be recommended. In this way, the system can recommend the most suitable videos based on the user's past viewing history, thereby providing content that matches the user's interests.

[0063] The system can provide content specific to a region by taking into account the user's geographic location information. For example, if the user is in a particular region, news and event information related to that region can be provided. If the user is traveling, tourist information and restaurant recommendations related to the travel destination can be provided. Furthermore, if the user is attending a particular event, content related to that event can be provided. In this way, the system can provide content specific to a region by taking into account the user's geographic location information.

[0064] The system can analyze the user's past feedback history and select the optimal feedback collection method. For example, if the user has provided a lot of feedback in the form of a questionnaire in the past, feedback can be collected in the form of a questionnaire. Also, if the user has provided feedback in the form of a comment in the past, feedback can be collected in the form of a comment. Furthermore, if the user has provided feedback in the form of an evaluation in the past, feedback can be collected in the form of an evaluation. In this way, the system can select the optimal collection method based on the user's past feedback history, thereby enabling effective feedback collection.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The collection unit collects chat data. The chat data includes audio data, text data, video data, etc. The collection unit collects the chat data with the user's permission. Specific methods and standards for obtaining the user's permission include pop-up notifications, email notifications, in-app notifications, etc. Step 2: The analysis unit analyzes the talk data collected by the collection unit and learns the patterns of jokes. These patterns include wordplay, physical jokes, and situational comedy. The analysis unit identifies comments that start with "lol" or "w" and analyzes the context surrounding them. For example, it identifies the comment "What happened yesterday was funny lol" and analyzes the context surrounding it. Step 3: The generator generates short videos based on the joke patterns learned by the analyzer. Short videos include videos of 30 seconds or less, videos of 1 minute or less, etc. The generator generates a video scenario based on the learned joke patterns. For example, based on the comment "What happened yesterday was funny lol," it creates a short video containing a similar joke. Step 4: The distribution unit distributes the short videos generated by the generation unit with advertisements attached. Advertisements include banner ads, in-stream ads, and pop-up ads. The distribution unit has a mechanism for earning advertising revenue according to the number of times the video is played.

[0067] (Example 2) A system according to an embodiment of the present invention learns from chat data on messaging apps such as LINE and SMS, learning comments containing "lol" or "w" to memorize jokes. This system consists of the following steps: First, chat data on messaging apps is collected and trained by an AI. Next, the AI ​​analyzes comments containing "lol" or "w" to learn joke patterns. Based on the learned content, the AI ​​creates short videos. These short videos are distributed with advertisements. As the videos are viewed, the distributor earns advertising revenue and viewers can laugh. First, chat data on messaging apps is collected. This is done with the user's permission. For example, a user provides chat data containing comments containing "lol" or "w." This data is input into the AI. Next, the AI ​​analyzes the collected chat data. The AI ​​identifies comments containing specific characters or strings of characters (e.g., "lol" or "w") and analyzes the context surrounding the comments. For example, if someone makes a comment like "What happened yesterday was funny lol," the AI ​​analyzes the context before and after the comment and learns what kind of joke was used. Based on what it has learned, the AI ​​creates a short video. Based on the learned patterns of jokes, the AI ​​generates a video scenario. For example, based on the comment "What happened yesterday was funny lol," a short video containing a similar joke is created. The created short video is then distributed with advertisements attached. As the video is viewed, the broadcaster can earn advertising revenue. For example, the system allows viewers to earn advertising revenue based on the number of times the video is played. This system makes viewers laugh. Short videos created based on the patterns of jokes learned by the AI ​​are entertaining for viewers. For example, videos that depict everyday events in a humorous way can make viewers laugh. The system collects and analyzes talk data, generates short videos, and distributes them with advertisements, allowing the broadcaster to earn advertising revenue and viewers to laugh.

[0068] The system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a distribution unit. The collection unit collects talk data. The talk data includes, but is not limited to, audio data, text data, and video data. The collection unit collects the talk data with, for example, a user's permission. Specific methods and criteria for obtaining the user's permission include pop-up notifications, email notifications, and in-app notifications. The analysis unit analyzes the talk data collected by the collection unit and learns joke patterns. Examples of joke patterns include, but are not limited to, wordplay, physical jokes, and situational comedies. The analysis unit, for example, identifies comments with specific characters or character strings (e.g., "laugh" or "w") and analyzes the context surrounding the comment. For example, the analysis unit identifies a comment such as "What happened yesterday was funny lol" and analyzes the context surrounding the comment. The generation unit generates short videos based on the joke patterns learned by the analysis unit. Short videos include, but are not limited to, videos of less than 30 seconds or less than 1 minute. The generation unit generates a video scenario based on, for example, the learned joke patterns. For example, the generation unit creates a short video containing a similar joke based on a comment such as, "What happened yesterday was funny lol." The distribution unit distributes the short videos generated by the generation unit with advertisements attached. Examples of advertisements include, but are not limited to, banner ads, in-stream ads, and pop-up ads. The distribution unit has a mechanism for earning advertising revenue based on the number of times the video is played, for example. As a result, the system collects and analyzes talk data, generates short videos, and distributes them with advertisements, allowing the distributor to earn advertising revenue and viewers to laugh.

[0069] The system includes a permission unit that obtains user permission. The permission unit obtains user permission. Specific methods and standards for obtaining user permission include pop-up notifications, email notifications, in-app notifications, and the like. For example, the permission unit can obtain user permission using a pop-up notification. The permission unit can also obtain user permission using an email notification. Furthermore, the permission unit can also obtain user permission using an in-app notification. In this way, the system obtains user permission and thereby legally collects talk data.

[0070] The system includes a management unit that manages advertising revenue. The management unit manages advertising revenue. Specific methods for calculating and managing advertising revenue include revenue based on the number of clicks and revenue based on the number of impressions. For example, the management unit can calculate advertising revenue based on the number of clicks. The management unit can also calculate advertising revenue based on the number of impressions. Furthermore, the management unit can adjust the management method for advertising revenue. For example, the management unit can predict increases or decreases in revenue and adjust the management method. This allows the system to efficiently manage the revenue earned by distributors by managing advertising revenue.

[0071] The system includes a feedback unit that collects user feedback. The feedback unit collects user feedback. Specific methods and standards for collecting user feedback include questionnaires, comments, ratings, and the like. For example, the feedback unit can collect user feedback using questionnaires. The feedback unit can also collect user feedback using comments. Furthermore, the feedback unit can collect user feedback using ratings. In this way, the system can collect user feedback to help improve the system.

[0072] The collection unit can collect talk data with the user's permission. The collection unit collects talk data with the user's permission. Specific methods and standards for obtaining the user's permission include pop-up notifications, email notifications, in-app notifications, etc. For example, the collection unit can obtain the user's permission using a pop-up notification. The collection unit can also obtain the user's permission using an email notification. Furthermore, the collection unit can obtain the user's permission using an in-app notification. In this way, the collection unit can legally collect data by collecting talk data with the user's permission.

[0073] The analysis unit can identify comments containing "lol" or "w" and analyze the context surrounding them. The analysis unit can identify comments containing specific characters or character strings (e.g., "lol" or "w") and analyze the context surrounding them. Specific definitions and extraction methods for comments containing "lol" or "w" include keywords such as "lol," "w," and "LOL." For example, the analysis unit can identify comments containing the keyword "lol." The analysis unit can also identify comments containing the keyword "w." Furthermore, the analysis unit can identify comments containing the keyword "LOL." In this way, the analysis unit can learn patterns of jokes by identifying comments containing specific characters or character strings (e.g., "lol" or "w") and analyzing the context surrounding them.

[0074] The generation unit can generate a video scenario based on the learned bokeh patterns. The generation unit generates a video scenario based on the learned bokeh patterns. Specific methods and standards for creating a video scenario include a storyboard, a script, and scene composition. For example, the generation unit can create a video scenario using a storyboard. The generation unit can also create a video scenario using a script. Furthermore, the generation unit can also create a video scenario using scene composition. In this way, the generation unit can create an interesting short video by generating a video scenario based on the learned bokeh patterns.

[0075] The distribution unit can be equipped with a mechanism for earning advertising revenue according to the number of times a video is played. The distribution unit is equipped with a mechanism for earning advertising revenue according to the number of times a video is played. Specific methods and standards for measuring the number of times a video is played include unique views, total playback time, and the like. For example, the distribution unit can measure the number of times a video is played using unique views. The distribution unit can also measure the number of times a video is played using total playback time. Furthermore, the distribution unit can adjust the mechanism for earning advertising revenue based on the number of times a video is played. For example, the distribution unit can set it so that the more times a video is played, the higher the advertising revenue. In this way, the distribution unit can earn advertising revenue according to the number of times a video is played, allowing the distributor to earn income.

[0076] The collection unit can estimate the user's emotions and adjust the timing of collecting talk data based on the estimated user's emotions. The collection unit can estimate the user's emotions and adjust the timing of collecting talk data based on the estimated user's emotions. Specific algorithms and methods for estimating the user's emotions include facial expression recognition, voice analysis, and text analysis. For example, the collection unit can estimate the user's emotions using facial expression recognition. The collection unit can also estimate the user's emotions using voice analysis. Furthermore, the collection unit can estimate the user's emotions using text analysis. This allows the collection unit to adjust the collection timing according to the user's emotions, enabling more appropriate data collection.

[0077] The collection unit can analyze the user's past talk data collection history and select the optimal collection method. The collection unit analyzes the user's past talk data collection history and selects the optimal collection method. Specific criteria and selection methods for the most effective collection method include collection speed, data quality, and user burden. For example, the collection unit can analyze time periods during which the user frequently provided talk data in the past and collect data during those time periods. The collection unit can also analyze the content of talk data provided by the user in the past and prioritize collection of data related to specific topics. Furthermore, the collection unit can select and execute the most efficient collection method from the user's past talk data collection history. In this way, the collection unit can select the optimal collection method by analyzing the past collection history.

[0078] The collection unit may filter the talk data based on the user's current areas of interest when collecting the talk data. Specific methods and criteria for identifying the user's current areas of interest include search history, browsing history, social media activity, etc. For example, the collection unit may preferentially collect talk data related to topics in which the user is currently interested. The collection unit may also analyze the user's social media activity and collect talk data related to the user's areas of interest. Furthermore, the collection unit may filter and collect related talk data based on keywords recently searched by the user. This allows the collection unit to collect highly relevant data by filtering data based on the user's areas of interest.

[0079] The collection unit can estimate the user's emotions and determine the priority of the talk data to be collected based on the estimated user's emotions. The collection unit can estimate the user's emotions and determine the priority of the talk data to be collected based on the estimated user's emotions. Specific algorithms and methods for estimating the user's emotions include facial expression recognition, voice analysis, and text analysis. For example, the collection unit can estimate the user's emotions using facial expression recognition. The collection unit can also estimate the user's emotions using voice analysis. Furthermore, the collection unit can estimate the user's emotions using text analysis. This allows the collection unit to prioritize data collection based on the user's emotions, thereby allowing important data to be collected preferentially.

[0080] When collecting talk data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. When collecting talk data, the collection unit prioritizes collecting highly relevant data by taking into account the user's geographical location information. Specific methods and criteria for identifying the user's geographical location information include GPS data, IP address, Wi-Fi information, etc. For example, if the user is in a specific area, the collection unit can prioritize collecting talk data related to that area. Also, if the user is traveling, the collection unit can prioritize collecting talk data related to the user's travel destination. Furthermore, if the user is participating in a specific event, the collection unit can prioritize collecting talk data related to the event. In this way, the collection unit can collect highly relevant data by taking into account the geographical location information.

[0081] The collection unit can analyze the user's social media activities and collect related data when collecting the talk data. The collection unit analyzes the user's social media activities and collects related data when collecting the talk data. Specific methods and criteria for analyzing the user's social media activities include the content of posts, the number of likes, the number of followers, etc. For example, the collection unit can analyze the content of social media posts recently made by the user and collect related talk data. The collection unit can also analyze the content of posts made by accounts the user follows and collect related talk data. Furthermore, the collection unit can analyze the activities of groups and communities in which the user participates and collect related talk data. This allows the collection unit to collect highly relevant data by analyzing social media activities.

[0082] The analysis unit can estimate the user's emotion and adjust the way the analysis is presented based on the estimated user's emotion. The analysis unit can estimate the user's emotion and adjust the way the analysis is presented based on the estimated user's emotion. Specific algorithms and methods for estimating the user's emotion include facial expression recognition, voice analysis, and text analysis. For example, the analysis unit can estimate the user's emotion using facial expression recognition. The analysis unit can also estimate the user's emotion using voice analysis. Furthermore, the analysis unit can estimate the user's emotion using text analysis. This allows the analysis unit to adjust the way the analysis is presented based on the user's emotion, thereby providing more appropriate analysis results.

[0083] The analysis unit can adjust the level of detail of the analysis based on the importance of the comment during analysis. The analysis unit adjusts the level of detail of the analysis based on the importance of the comment during analysis. Specific criteria and methods for evaluating the importance of a comment include the number of likes, the number of replies, the influence of the poster, etc. For example, the analysis unit can perform a detailed analysis on important comments. The analysis unit can also perform a concise analysis on comments with low importance. Furthermore, the analysis unit can determine the priority of the analysis based on the importance of the comment. This allows the analysis unit to adjust the level of detail of the analysis based on the importance of the comment, enabling efficient analysis.

[0084] The analysis unit can apply different analysis algorithms depending on the category of the comment during analysis. The analysis unit applies different analysis algorithms depending on the category of the comment during analysis. Specific criteria and methods for classifying comment categories include positive, negative, neutral, etc. For example, the analysis unit can apply a humor analysis algorithm to humorous comments. The analysis unit can also apply a sentiment analysis algorithm to emotional comments. Furthermore, the analysis unit can select and apply the optimal analysis algorithm depending on the topic. This allows the analysis unit to apply the optimal analysis algorithm depending on the comment category, enabling highly accurate analysis.

[0085] The analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user's emotion. The analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user's emotion. Specific algorithms and methods for estimating the user's emotion include facial expression recognition, voice analysis, and text analysis. For example, the analysis unit can estimate the user's emotion using facial expression recognition. The analysis unit can also estimate the user's emotion using voice analysis. Furthermore, the analysis unit can estimate the user's emotion using text analysis. This allows the analysis unit to adjust the length of the analysis according to the user's emotion, thereby providing more appropriate analysis results.

[0086] During analysis, the analysis unit can determine the priority of analysis based on the time when the comment was posted. During analysis, the analysis unit determines the priority of analysis based on the time when the comment was posted. Specific methods and criteria for identifying the time when the comment was posted include timestamps, posting history, etc. For example, the analysis unit can prioritize the analysis of the most recent comment. The analysis unit can also place emphasis on the most recent comment while referring to past comments. Furthermore, the analysis unit can adjust the priority of analysis based on the time when the comment was posted. This allows the analysis unit to determine the priority of analysis based on the time when the comment was posted, enabling efficient analysis.

[0087] The analysis unit can adjust the order of analysis based on the relevance of the comments during analysis. The analysis unit can adjust the order of analysis based on the relevance of the comments during analysis. Specific criteria and methods for evaluating the relevance of comments include common keywords, matching topics, etc. For example, the analysis unit can prioritize the analysis of highly relevant comments. The analysis unit can also postpone the analysis of less relevant comments. Furthermore, the analysis unit can adjust the order of analysis based on the relevance of the comments. This allows the analysis unit to adjust the order of analysis based on the relevance of the comments, thereby enabling efficient analysis.

[0088] The generation unit can estimate the user's emotion and adjust the video scenario based on the estimated user's emotion. The generation unit can estimate the user's emotion and adjust the video scenario based on the estimated user's emotion. Specific algorithms and methods for estimating the user's emotion include facial expression recognition, voice analysis, text analysis, and the like. For example, the generation unit can estimate the user's emotion using facial expression recognition. The generation unit can also estimate the user's emotion using voice analysis. Furthermore, the generation unit can estimate the user's emotion using text analysis. This allows the generation unit to generate a more appropriate video by adjusting the video scenario according to the user's emotion.

[0089] The generation unit can adjust the level of detail of the scenario based on the importance of the blur pattern during generation. The generation unit adjusts the level of detail of the scenario based on the importance of the blur pattern during generation. Specific criteria and methods for evaluating the importance of the blur pattern include viewer reaction, number of plays, etc. For example, the generation unit can generate a detailed scenario for an important blur. The generation unit can also generate a concise scenario for a blur with low importance. Furthermore, the generation unit can determine the priority of the scenario according to the importance of the blur. In this way, the generation unit can adjust the level of detail of the scenario according to the importance of the blur pattern, thereby enabling efficient video generation.

[0090] The generation unit can apply different generation algorithms depending on the category of the joke pattern during generation. The generation unit applies different generation algorithms depending on the category of the joke pattern during generation. Specific criteria and methods for classifying the categories of joke patterns include word play, physical jokes, situation comedy, etc. For example, the generation unit can apply a humor generation algorithm to jokes related to humor. The generation unit can also apply an emotion generation algorithm to jokes related to emotions. Furthermore, the generation unit can select and apply an optimal generation algorithm depending on the topic. In this way, the generation unit can apply an optimal generation algorithm depending on the category of the joke pattern, thereby enabling highly accurate video generation.

[0091] The generation unit can estimate the user's emotion and adjust the length of the video based on the estimated user's emotion. The generation unit can estimate the user's emotion and adjust the length of the video based on the estimated user's emotion. Specific algorithms and methods for estimating the user's emotion include facial expression recognition, voice analysis, text analysis, and the like. For example, the generation unit can estimate the user's emotion using facial expression recognition. The generation unit can also estimate the user's emotion using voice analysis. Furthermore, the generation unit can estimate the user's emotion using text analysis. This allows the generation unit to generate a more appropriate video by adjusting the length of the video according to the user's emotion.

[0092] The generation unit can determine the priority of scenarios based on the posting time of the bokeh patterns at the time of generation. The generation unit determines the priority of scenarios based on the posting time of the bokeh patterns at the time of generation. Specific methods and criteria for identifying the posting time of the bokeh patterns include timestamps, posting history, etc. For example, the generation unit can preferentially reflect the latest bokeh in the scenario. The generation unit can also prioritize the latest bokeh while referring to past bokehs. Furthermore, the generation unit can adjust the priority of scenarios depending on the posting time of the bokeh. This allows the generation unit to determine the priority of scenarios depending on the posting time of the bokeh patterns, thereby enabling efficient video generation.

[0093] The generation unit can adjust the order of scenarios based on the relevance of blur patterns during generation. The generation unit adjusts the order of scenarios based on the relevance of blur patterns during generation. Specific criteria and methods for evaluating the relevance of blur patterns include common keywords, matching topics, etc. For example, the generation unit can preferentially reflect highly relevant blurs in the scenario. The generation unit can also postpone less relevant blurs. Furthermore, the generation unit can adjust the order of scenarios according to the relevance of blurs. This allows the generation unit to adjust the order of scenarios according to the relevance of blur patterns, thereby enabling efficient video generation.

[0094] The distribution unit can estimate the user's emotion and adjust the timing of distribution based on the estimated user's emotion. The distribution unit can estimate the user's emotion and adjust the timing of distribution based on the estimated user's emotion. Specific algorithms and methods for estimating the user's emotion include facial expression recognition, voice analysis, text analysis, and the like. For example, the distribution unit can estimate the user's emotion using facial expression recognition. The distribution unit can also estimate the user's emotion using voice analysis. Furthermore, the distribution unit can estimate the user's emotion using text analysis. This allows the distribution unit to adjust the timing of distribution according to the user's emotion, thereby distributing videos at more appropriate timing.

[0095] The distribution unit can adjust the advertisement display method based on the number of times a video is played during distribution. The distribution unit adjusts the advertisement display method based on the number of times a video is played during distribution. Specific methods and criteria for measuring the number of times a video is played include unique views, total playback time, etc. For example, the distribution unit can measure the number of times a video is played using unique views. The distribution unit can also measure the number of times a video is played using total playback time. Furthermore, the distribution unit can adjust the advertisement display method based on the number of times a video is played. For example, the distribution unit can display a detailed advertisement for a video with a high number of views. The distribution unit can also display a concise advertisement for a video with a low number of views. In this way, the distribution unit can adjust the advertisement display method according to the number of times a video is played, thereby enabling effective advertisement display.

[0096] The distribution unit can apply different distribution algorithms depending on the category of the video during distribution. The distribution unit applies different distribution algorithms depending on the category of the video during distribution. Specific criteria and methods for classifying video categories include entertainment, education, news, etc. For example, the distribution unit can apply a humor distribution algorithm to videos related to humor. The distribution unit can also apply an emotion distribution algorithm to videos related to emotions. Furthermore, the distribution unit can select and apply an optimal distribution algorithm depending on the topic. This allows the distribution unit to apply an optimal distribution algorithm depending on the category of the video, enabling effective video distribution.

[0097] The distribution unit can estimate a user's emotion and determine a distribution priority based on the estimated user's emotion. The distribution unit can estimate a user's emotion and determine a distribution priority based on the estimated user's emotion. Specific algorithms and methods for estimating a user's emotion include facial expression recognition, voice analysis, and text analysis. For example, the distribution unit can estimate a user's emotion using facial expression recognition. The distribution unit can also estimate a user's emotion using voice analysis. Furthermore, the distribution unit can estimate a user's emotion using text analysis. This allows the distribution unit to determine a distribution priority based on the user's emotion, thereby preferentially distributing more appropriate videos.

[0098] The distribution unit can adjust the order of distribution based on the posting time of the videos during distribution. The distribution unit can adjust the order of distribution based on the posting time of the videos during distribution. Specific methods and criteria for identifying the posting time of the videos include timestamps, posting history, etc. For example, the distribution unit can prioritize the most recent videos. The distribution unit can also prioritize the most recent videos while referring to past videos. Furthermore, the distribution unit can adjust the order of distribution based on the posting time of the videos. This allows the distribution unit to adjust the order of distribution based on the posting time of the videos, enabling efficient video distribution.

[0099] The distribution unit can adjust the order of distribution based on the relevance of the videos during distribution. The distribution unit adjusts the order of distribution based on the relevance of the videos during distribution. Specific criteria and methods for evaluating the relevance of videos include common keywords, matching topics, etc. For example, the distribution unit can prioritize the distribution of highly relevant videos. The distribution unit can also postpone videos with low relevance. Furthermore, the distribution unit can adjust the order of distribution based on the relevance of the videos. This allows the distribution unit to adjust the order of distribution based on the relevance of the videos, thereby enabling efficient video distribution.

[0100] The permission unit can estimate the user's emotion and adjust the permission acquisition method based on the estimated user's emotion. The permission unit can estimate the user's emotion and adjust the permission acquisition method based on the estimated user's emotion. Specific algorithms and methods for estimating the user's emotion include facial expression recognition, voice analysis, and text analysis. For example, the permission unit can estimate the user's emotion using facial expression recognition. The permission unit can also estimate the user's emotion using voice analysis. Furthermore, the permission unit can estimate the user's emotion using text analysis. This allows the permission unit to adjust the permission acquisition method according to the user's emotion, thereby enabling more appropriate permission acquisition.

[0101] The permission unit can select the optimal permission acquisition method by referring to the user's past permission history when obtaining permission. The permission unit can select the optimal permission acquisition method by referring to the user's past permission history when obtaining permission. Specific methods and criteria for referring to the user's past permission history include the types of past permission, the frequency of permission, etc. For example, the permission unit can preferentially suggest methods for which the user has previously granted permission. The permission unit can also select the most efficient permission acquisition method from the user's past permission history. Furthermore, the permission unit can analyze the user's past permission history and obtain permission at the optimal timing. In this way, the permission unit can select the optimal permission acquisition method by referring to the past permission history.

[0102] The permission unit can estimate the user's emotion and determine the priority of permission based on the estimated user's emotion. The permission unit can estimate the user's emotion and determine the priority of permission based on the estimated user's emotion. Specific algorithms and methods for estimating the user's emotion include facial expression recognition, voice analysis, text analysis, and the like. For example, the permission unit can estimate the user's emotion using facial expression recognition. The permission unit can also estimate the user's emotion using voice analysis. Furthermore, the permission unit can also estimate the user's emotion using text analysis. This allows the permission unit to determine the priority of permission based on the user's emotion, thereby enabling more appropriate permission acquisition.

[0103] The permission unit can select the optimal permission acquisition method by taking into consideration the user's device information when obtaining permission. The permission unit selects the optimal permission acquisition method by taking into consideration the user's device information when obtaining permission. Specific methods and criteria for identifying the user's device information include the device type, OS, browser, etc. For example, if the user is using a smartphone, the permission unit can provide a permission acquisition method optimized for the smartphone. Furthermore, if the user is using a tablet, the permission unit can also provide a permission acquisition method optimized for the tablet. Furthermore, if the user is using a smartwatch, the permission unit can provide a permission acquisition method optimized for the smartwatch. This allows the permission unit to select the optimal permission acquisition method by taking into consideration the device information.

[0104] The management unit can estimate the user's emotions and adjust the advertising revenue management method based on the estimated user's emotions. The management unit can estimate the user's emotions and adjust the advertising revenue management method based on the estimated user's emotions. Specific algorithms and methods for estimating the user's emotions include facial expression recognition, voice analysis, and text analysis. For example, the management unit can estimate the user's emotions using facial expression recognition. The management unit can also estimate the user's emotions using voice analysis. Furthermore, the management unit can estimate the user's emotions using text analysis. This allows the management unit to adjust the advertising revenue management method according to the user's emotions, enabling more appropriate management.

[0105] The management unit can refer to past advertising revenue data during management to select the optimal management method. The management unit can refer to past advertising revenue data during management to select the optimal management method. Specific methods and criteria for referring to past advertising revenue data include the timing of revenue and the type of revenue. For example, the management unit can analyze past advertising revenue data to select the optimal management method. The management unit can also predict increases or decreases in revenue from past advertising revenue data and adjust the management method. Furthermore, the management unit can select a management method that maximizes revenue based on past advertising revenue data. In this way, the management unit can select the optimal management method by referring to past advertising revenue data.

[0106] The management unit can estimate the user's emotions and determine the priorities of advertising revenue based on the estimated user's emotions. The management unit can estimate the user's emotions and determine the priorities of advertising revenue based on the estimated user's emotions. Specific algorithms and methods for estimating the user's emotions include facial expression recognition, voice analysis, and text analysis. For example, the management unit can estimate the user's emotions using facial expression recognition. The management unit can also estimate the user's emotions using voice analysis. Furthermore, the management unit can estimate the user's emotions using text analysis. This enables the management unit to determine the priorities of advertising revenue according to the user's emotions, thereby enabling more appropriate management.

[0107] The management unit can adjust the revenue management method based on the advertisement display time during management. The management unit can adjust the revenue management method based on the advertisement display time during management. Specific methods and criteria for specifying the advertisement display time include time of day, day of the week, specific events, etc. For example, the management unit can adjust the revenue management method according to the advertisement display time. The management unit can also analyze the advertisement display time and select an optimal revenue management method. Furthermore, the management unit can provide a management method that maximizes revenue based on the advertisement display time. As a result, the management unit can maximize revenue by adjusting the revenue management method based on the advertisement display time.

[0108] The feedback unit can estimate the user's emotion and adjust the feedback collection method based on the estimated user's emotion. The feedback unit can estimate the user's emotion and adjust the feedback collection method based on the estimated user's emotion. Specific algorithms and methods for estimating the user's emotion include facial expression recognition, voice analysis, and text analysis. For example, the feedback unit can estimate the user's emotion using facial expression recognition. The feedback unit can also estimate the user's emotion using voice analysis. Furthermore, the feedback unit can estimate the user's emotion using text analysis. This allows the feedback unit to adjust the feedback collection method according to the user's emotion, thereby enabling more appropriate feedback collection.

[0109] When collecting feedback, the feedback unit can select the optimal collection method by referring to the user's past feedback history. When collecting feedback, the feedback unit selects the optimal collection method by referring to the user's past feedback history. Specific methods and criteria for referring to the user's past feedback history include the type of past feedback, the frequency of feedback, etc. For example, the feedback unit can select the optimal collection method based on feedback provided by the user in the past. The feedback unit can also select the most efficient collection method from the user's past feedback history. Furthermore, the feedback unit can analyze the user's past feedback history and collect feedback at the optimal timing. In this way, the feedback unit can select the optimal collection method by referring to the past feedback history.

[0110] The feedback unit can estimate the user's emotion and determine the priority of feedback based on the estimated user's emotion. The feedback unit can estimate the user's emotion and determine the priority of feedback based on the estimated user's emotion. Specific algorithms and methods for estimating the user's emotion include facial expression recognition, voice analysis, text analysis, and the like. For example, the feedback unit can estimate the user's emotion using facial expression recognition. The feedback unit can also estimate the user's emotion using voice analysis. Furthermore, the feedback unit can estimate the user's emotion using text analysis. This allows the feedback unit to determine the priority of feedback according to the user's emotion, thereby enabling more appropriate feedback collection.

[0111] The feedback unit may select an optimal feedback collection method in consideration of device information of the user when collecting feedback. The feedback unit may select an optimal feedback collection method in consideration of device information of the user when collecting feedback. Specific methods and criteria for identifying the user's device information include the type of device, OS, browser, etc. For example, if the user is using a smartphone, the feedback unit may provide a feedback collection method optimized for the smartphone. Also, if the user is using a tablet, the feedback unit may provide a feedback collection method optimized for the tablet. Furthermore, if the user is using a smartwatch, the feedback unit may provide a feedback collection method optimized for the smartwatch. In this way, the feedback unit can select an optimal feedback collection method in consideration of device information. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, distribution unit, permission unit, management unit, and feedback unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects talk data using the camera 42 and microphone 38B of the smart device 14 and transmits the talk data to the data processing device 12 via the control unit 46A. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected talk data and learns patterns of silly behavior. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates short videos based on the learned patterns of silly behavior. The distribution unit, realized, for example, by the control unit 46A of the smart device 14, distributes the generated short videos with advertisements attached. The permission unit, realized, for example, by the control unit 46A of the smart device 14, obtains user permission. The management unit, realized, for example, by the specific processing unit 290 of the data processing device 12, manages advertising revenue. The feedback unit is realized by, for example, the control unit 46A of the smart device 14, and collects user feedback. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, distribution unit, permission unit, management unit, and feedback unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects talk data using the camera 42 and microphone 238 of the smart glasses 214 and transmits the talk data to the data processing device 12 via the control unit 46A. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected talk data and learns blur patterns. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates short videos based on the learned blur patterns. The distribution unit, realized, for example, by the control unit 46A of the smart glasses 214, distributes the generated short videos with advertisements attached. The permission unit, realized, for example, by the control unit 46A of the smart glasses 214, obtains user permission. The management unit, realized, for example, by the specific processing unit 290 of the data processing device 12, manages advertising revenue. The feedback unit is realized by, for example, the control unit 46A of the smart glasses 214, and collects user feedback. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, distribution unit, permission unit, management unit, and feedback unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects talk data using the camera 42 and microphone 238 of the headset-type terminal 314 and transmits the talk data to the data processing device 12 via the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected talk data and learns patterns of blurring. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates short videos based on the learned patterns of blurring. The distribution unit is realized, for example, by the control unit 46A of the headset-type terminal 314, and distributes the generated short videos with advertisements attached. The permission unit is realized, for example, by the control unit 46A of the headset-type terminal 314, and obtains user permission. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and manages advertising revenue. The feedback unit is realized by, for example, the control unit 46A of the headset type terminal 314, and collects user feedback. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, distribution unit, permission unit, management unit, and feedback unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects talk data using the camera 42 and microphone 238 of the robot 414 and transmits the talk data to the data processing device 12 via the control unit 46A. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected talk data and learns patterns of silly behavior. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates short videos based on the learned patterns of silly behavior. The distribution unit, realized, for example, by the control unit 46A of the robot 414, distributes the generated short videos with advertisements attached. The permission unit, realized, for example, by the control unit 46A of the robot 414, obtains user permission. The management unit, realized, for example, by the specific processing unit 290 of the data processing device 12, manages advertising revenue. The feedback unit is realized by, for example, the control unit 46A of the robot 414, and collects feedback from the user.

[0112] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0113] The system can estimate the user's emotions and customize the content of advertisements based on the estimated emotions. For example, if the user is laughing, a humorous advertisement can be displayed. If the user is sad, an advertisement containing an encouraging message can be displayed. Furthermore, if the user is excited, an energetic advertisement can be displayed. In this way, the system can increase the effectiveness of advertisements by displaying advertisements that correspond to the user's emotions.

[0114] The system can analyze the user's past talk data and filter the talk data based on the user's interests and concerns. For example, if the user has provided a lot of talk data about sports in the past, the system can prioritize collection of talk data related to sports. Also, if the user has provided talk data about cooking in the past, the system can collect talk data related to cooking. Furthermore, if the user has provided talk data about travel in the past, the system can collect talk data related to travel. This allows the system to collect more relevant data by filtering the talk data based on the user's interests and concerns.

[0115] The system can estimate the user's emotions and adjust the frequency of chat data collection based on the estimated emotions. For example, if the user is relaxed, the collection frequency can be increased. Alternatively, if the user is stressed, the collection frequency can be decreased. Furthermore, if the user is excited, the collection frequency can be adjusted to collect data at an appropriate time. In this way, the system can adjust the collection frequency according to the user's emotions, enabling effective data collection while reducing the burden on the user.

[0116] The system can collect user feedback in real time and instantly reflect the analysis results. For example, if a user provides feedback while watching a video, the system can instantly analyze that feedback and reflect it in the next video. Also, if a user posts a comment, the system can analyze that comment and recommend related videos. Furthermore, if a user provides a rating, the system can improve the quality of the video based on that rating. This allows the system to improve the user experience by collecting feedback in real time and instantly reflecting the analysis results.

[0117] The system can estimate the user's emotions and adjust the playback speed of the video based on the estimated emotions. For example, if the user is relaxed, the playback speed can be slower than usual. If the user is excited, the playback speed can be faster. Furthermore, if the user is concentrating, the playback speed can be adjusted to provide an optimal viewing experience. In this way, the system can provide a more comfortable viewing experience by adjusting the playback speed according to the user's emotions.

[0118] The system can analyze a user's past viewing history and recommend the most suitable video. For example, if a user has watched many comedy videos in the past, comedy videos can be recommended preferentially. If a user has watched documentary videos in the past, documentary videos can be recommended. Furthermore, if a user has watched music videos in the past, music videos can be recommended. In this way, the system can recommend the most suitable videos based on the user's past viewing history, thereby providing content that matches the user's interests.

[0119] The system can estimate the user's emotions and adjust the volume of the video based on the estimated emotions. For example, if the user is relaxed, the volume can be lowered. If the user is excited, the volume can be increased. Furthermore, if the user is concentrating, the volume can be adjusted to provide an optimal viewing experience. In this way, the system can provide a more comfortable viewing experience by adjusting the volume according to the user's emotions.

[0120] The system can provide content specific to a region by taking into account the user's geographic location information. For example, if the user is in a particular region, news and event information related to that region can be provided. If the user is traveling, tourist information and restaurant recommendations related to the travel destination can be provided. Furthermore, if the user is attending a particular event, content related to that event can be provided. In this way, the system can provide content specific to a region by taking into account the user's geographic location information.

[0121] The system can estimate the user's emotions and adjust the display of subtitles for videos based on the estimated emotions. For example, if the user is relaxed, subtitles can be hidden. If the user is focused, subtitles can be displayed. Furthermore, if the user is excited, the display speed of the subtitles can be adjusted. This allows the system to provide a more comfortable viewing experience by adjusting the subtitle display according to the user's emotions.

[0122] The system can analyze the user's past feedback history and select the optimal feedback collection method. For example, if the user has provided a lot of feedback in the form of a questionnaire in the past, feedback can be collected in the form of a questionnaire. Also, if the user has provided feedback in the form of a comment in the past, feedback can be collected in the form of a comment. Furthermore, if the user has provided feedback in the form of an evaluation in the past, feedback can be collected in the form of an evaluation. In this way, the system can select the optimal collection method based on the user's past feedback history, thereby enabling effective feedback collection.

[0123] The processing flow of the second embodiment will be briefly explained below.

[0124] Step 1: The collection unit collects chat data. The chat data includes audio data, text data, video data, etc. The collection unit collects the chat data with the user's permission. Specific methods and standards for obtaining the user's permission include pop-up notifications, email notifications, in-app notifications, etc. Step 2: The analysis unit analyzes the talk data collected by the collection unit and learns the patterns of jokes. These patterns include wordplay, physical jokes, and situational comedy. The analysis unit identifies comments that start with "lol" or "w" and analyzes the context surrounding them. For example, it identifies the comment "What happened yesterday was funny lol" and analyzes the context surrounding it. Step 3: The generator generates short videos based on the joke patterns learned by the analyzer. Short videos include videos of 30 seconds or less, videos of 1 minute or less, etc. The generator generates a video scenario based on the learned joke patterns. For example, based on the comment "What happened yesterday was funny lol," it creates a short video containing a similar joke. Step 4: The distribution unit distributes the short videos generated by the generation unit with advertisements attached. Advertisements include banner ads, in-stream ads, and pop-up ads. The distribution unit has a mechanism for earning advertising revenue according to the number of times the video is played.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0127] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0129] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0130] 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.

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

[0132] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

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

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

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

[0136] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

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

[0139] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0143] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0144] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0145] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0146] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0148] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

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

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

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

[0152] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0153] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0154] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0155] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0156] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0157] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0159] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0160] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0161] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0162] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0163] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0164] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0165] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0167] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0168] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0169] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0170] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0171] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0172] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0173] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0174] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0175] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0176] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0177] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0178] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0179] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0180] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0181] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0182] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0183] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0184] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0185] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0186] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0187] 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.

[0188] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0189] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0190] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0191] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0192] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0193] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0194] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0195] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0196] [Explanation of symbols]

[0197] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects talk data; An analysis unit that analyzes the talk data collected by the collection unit and learns patterns of dementia; a generation unit that generates a short video based on the blur patterns learned by the analysis unit; a distribution unit that distributes the short videos generated by the generation unit by attaching advertisements to the short videos; Equipped with A system characterized by:

2. A permission unit is provided to obtain permission from the user.

2. The system of claim 1.

3. Equipped with a management department to manage advertising revenue 2. The system of claim 1.

4. A feedback section is provided to collect user feedback.

2. The system of claim 1.

5. The collecting unit Collect chat data with user permission 2. The system of claim 1.

6. The analysis unit Identify comments with specific characters or strings and analyze their surrounding context 2. The system of claim 1.

7. The generation unit Generate video scenarios based on learned blur patterns 2. The system of claim 1.

8. The distribution unit Equipped with a system that earns advertising revenue based on the number of times a video is played 2. The system of claim 1.

Images