System

Abstract

An object of the system according to the embodiment is to convert visual information into sound and provide the sound to a visually impaired person or a bedridden person.SOLUTION: A system according to an embodiment includes a visual information analysis unit, a decoder, a voice conversion unit, and an integration unit. The visual information analysis unit analyzes visual information of the video. The decoder decodes the visual information analyzed by the visual information analyzer. The voice conversion unit converts the visual information verbalized by the verbalization unit into voice. The integration unit integrates the visual information and the audio information converted into the voice by the voice conversion unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have not adequately converted visual information into audio and provided it to the visually impaired or bedridden, and there is room for improvement.

[0005] The system according to the embodiment aims to convert visual information into audio and provide it to people who are visually impaired or bedridden. [Means for solving the problem]

[0006] The system according to the embodiment includes a visual information analysis unit, a verbalization unit, a voice conversion unit, and an integration unit. The visual information analysis unit analyzes visual information of a video. The verbalization unit verbalizes the visual information analyzed by the visual information analysis unit. The voice conversion unit converts the visual information verbalized by the verbalization unit into voice. The integration unit integrates the visual information and auditory information converted into voice by the voice conversion unit. [Effects of the Invention]

[0007] The system according to the embodiment can convert visual information into audio and provide it to people who are visually impaired or bedridden. [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 nonvolatile storage devices that store various programs, various parameters, etc. Examples of nonvolatile 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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) The visual information speech system according to an embodiment of the present invention is a system that verbalizes the visual information of a video and converts it into speech. This system enables visually impaired people and bedridden people to enjoy video content more. As a result, the visual information speech system allows visually impaired people and bedridden people to enjoy video content more.

[0029] A visual information speech system according to an embodiment includes a visual information analysis unit, a verbalization unit, a speech conversion unit, and an integration unit. The visual information analysis unit analyzes visual information from a video. For example, it analyzes facial expressions and movements of characters, background scenery, and the like. The visual information analysis unit can also extract and analyze visual information for each frame of a video. For example, it analyzes the positions and movements of characters for each frame of a video. The verbalization unit verbalizes the visual information analyzed by the visual information analysis unit. For example, it verbalizes information such as "Character A is smiling and talking to B" or "A beautiful sunset is spreading in the background." The verbalization unit can also verbalize the visual information using natural language processing technology. For example, it generates the visual information as sentences using natural language processing technology. The speech conversion unit converts the visual information verbalized by the verbalization unit into speech. For example, it converts the verbalized visual information into speech using speech synthesis technology. The speech conversion unit can also convert the verbalized visual information into speech using text-to-speech technology. For example, it outputs the verbalized visual information as speech using text-to-speech technology. The integration unit integrates the visual information and audio information converted into audio by the audio conversion unit. For example, in a movie scene, the dialogue of a character and the visual information of that scene are simultaneously provided as audio. The integration unit can also synchronize and integrate the audio-converted visual information and audio information. For example, the integration unit can synchronize the timing of the audio-converted visual information and the audio information. This allows the visual information to be more enjoyable for visually impaired people and bedridden people. For example, audio explanations of the characters' facial expressions and scenes can deepen understanding of the story and complement the visual information. Furthermore, user convenience is improved as the information can be easily accessed through a dedicated app.

[0030] The visual information analysis unit can use object recognition technology to verbalize in detail the objects held by characters and objects in the background. For example, when the generative AI analyzes the visual information of a video, the visual information analysis unit uses object recognition technology to verbalize in detail the objects held by characters. For example, it may explain the title and contents of the book the character is holding. The visual information analysis unit can also verbalize in detail objects in the background. For example, it may explain the features of buildings and scenery in the background. The visual information analysis unit can also verbalize in detail based on object position information. For example, it may explain the position of the cup held in the character's right hand. This allows for detailed verbalization of the objects held by characters and objects in the background.

[0031] The visual information analysis unit can track changes in a scene over time and provide a detailed explanation of the transitions. For example, when the generative AI analyzes the visual information of a video, the visual information analysis unit tracks changes in a scene over time and provides a detailed explanation of those transitions. For example, it can verbalize the flow of time from morning to night or the change of seasons. The visual information analysis unit can also explain transitions based on the start and end times of a scene. For example, it can clearly indicate the start and end times of a scene. The visual information analysis unit can also explain transitions based on important events in a scene. For example, it can explain important events and actions within a scene. This allows for a detailed explanation of the transitions in a scene over time.

[0032] The visual information analysis unit can simultaneously analyze information from different camera angles and viewpoints, and provide explanations from multiple viewpoints. For example, when the generative AI analyzes the visual information of a video, the visual information analysis unit simultaneously analyzes information from different camera angles and provides explanations from multiple viewpoints. For example, it can verbalize the differences when the same scene is viewed from different angles. The visual information analysis unit can also integrate information from different viewpoints and provide explanations. For example, it can integrate information from a bird's-eye view and a close-up view and provide an explanation. The visual information analysis unit can also compare information from different camera angles and provide explanations. For example, it can compare the positions and movements of characters when viewed from different camera angles. This makes it possible to provide explanations from multiple viewpoints.

[0033] The visual information analysis unit can verbalize changes in color and light in the image in detail to convey the visual atmosphere. For example, when the generative AI analyzes the visual information of an image, the visual information analysis unit verbalizes changes in color in the image in detail to convey the visual atmosphere. For example, it explains the changes in emotions that occur when the color tone of a scene changes. The visual information analysis unit can also verbalize changes in light in detail. For example, it explains changes in brightness or darkness in a scene. The visual information analysis unit can also convey the visual atmosphere based on changes in hue, brightness, and saturation. For example, it explains the changes in emotions that occur when the hue of a scene changes. This makes it possible to verbalize changes in color and light in the image in detail to convey the visual atmosphere.

[0034] The audio conversion unit can automatically add background sounds and sound effects when converting verbalized visual information into audio, thereby enhancing the sense of realism. For example, when the generation AI converts verbalized visual information into audio, the audio conversion unit can automatically add background sounds to enhance the sense of realism. For example, natural sounds and environmental sounds according to the scene are added. The audio conversion unit can also automatically add sound effects. For example, gunshots and explosions are added in action scenes. The audio conversion unit can also automatically add music. For example, moving music is added in moving scenes. In this way, background sounds and sound effects can be automatically added, enhancing the sense of realism.

[0035] When converting verbalized visual information into audio, the audio conversion unit can generate characters with different voices for each character to provide explanations. For example, when the generation AI converts verbalized visual information into audio, the audio conversion unit can generate characters with different voices to provide explanations for each character. For example, different voices are used for male characters and female characters. The audio conversion unit can also generate characters with different voices by changing the pitch or tone of the voice. For example, different voices are used for child characters and adult characters. The audio conversion unit can also generate characters with different voices by changing the accent or dialect. For example, dialects for each region are used. This allows explanations to be provided in different voices for each character.

[0036] The speech conversion unit supports multiple languages ​​when converting verbalized visual information into speech, making it possible to accommodate international users. For example, the speech conversion unit builds a system that supports multiple languages ​​when the generation AI converts verbalized visual information into speech. For example, it supports languages ​​such as English, French, and Chinese. The speech conversion unit can also generate speech using different speech synthesis technologies for each language. For example, it can use English speech synthesis technology and Japanese speech synthesis technology. The speech conversion unit can also automatically switch languages ​​based on the user's language settings. For example, it generates speech according to the language set by the user. This makes it possible to support multiple languages ​​and accommodate international users.

[0037] The speech conversion unit can allow the user to adjust the speed and pitch of the speech when converting verbalized visual information into speech. For example, the speech conversion unit provides a function that allows the user to adjust the speed of the speech when the generation AI converts verbalized visual information into speech. For example, the playback speed can be increased or decreased. The speech conversion unit can also provide a function that allows the user to adjust the pitch of the speech. For example, the pitch of the speech can be changed. The speech conversion unit can also adjust the speed and pitch of the speech through a user interface. For example, the adjustment can be made using a slider or button. This allows the user to adjust the speed and pitch of the speech.

[0038] When integrating auditory information and vocalized visual information, the integration unit can set the priority of information based on the importance of each scene. For example, when the generation AI integrates auditory information and vocalized visual information, the integration unit sets the priority of information based on the importance of each scene. For example, important lines and action scenes are given priority. The integration unit can also analyze the importance of a scene and set the priority of information based on that importance. For example, the importance is evaluated based on the length of the scene and the number of characters. The integration unit can also adjust the priority of information based on user settings. For example, information is provided according to the importance set by the user. This makes it possible to set the priority of information based on the importance of each scene.

[0039] The integration unit can seamlessly integrate background sounds and sound effects when integrating auditory information with audio-enabled visual information, thereby generating natural audio content. For example, when the generation AI integrates auditory information with audio-enabled visual information, the integration unit seamlessly integrates background sounds to generate natural audio content. For example, environmental sounds according to the scene are added. The integration unit can also seamlessly integrate sound effects. For example, in action scenes, gunshots and explosions are naturally integrated. The integration unit can also synchronize audio and background sounds to seamlessly integrate them. For example, the integration unit can align the timing of audio and background sounds to integrate them. This allows background sounds and sound effects to be seamlessly integrated, thereby generating natural audio content.

[0040] The integration unit can also accommodate content of different genres when integrating auditory information and audiovisual visual information. For example, when the generative AI integrates auditory information and audiovisual visual information, the integration unit builds a system that can accommodate content of different genres. For example, it verbalizes and audiovisualizes the visual information of documentaries and anime. The integration unit can also use different visual information analysis methods for each genre. For example, documentaries can emphasize factual information, while anime can emphasize the emotions of the characters. The integration unit can also use different audio effects for each genre. For example, action movies can use powerful sound effects, while romance movies can use moving music. This makes it possible to accommodate content of different genres.

[0041] The integration unit can adjust the level of detail of the information according to the user's preferences when integrating auditory information and vocalized visual information. For example, the integration unit builds a system that can adjust the level of detail of the information according to the user's preferences when the generation AI integrates auditory information and vocalized visual information. For example, it makes it possible to select between a detailed explanation and a concise explanation. The integration unit can also adjust the level of detail of the information based on the user's settings. For example, it provides information according to the level of detail set by the user. The integration unit can also adjust the granularity of the information to be provided. For example, it provides a detailed explanation for each scene or an overall overview. This makes it possible to adjust the level of detail of the information according to the user's preferences.

[0042] When providing audio content, the system can recommend personalized content based on the user's viewing history. For example, when a generative AI provides audio content, the system analyzes the user's viewing history and builds a system that recommends personalized content. For example, recommendations may be made based on genres or themes viewed in the past. The system can also analyze the user's interests based on the user's viewing history and recommend related content. For example, if the user has watched a lot of action movies, action movies may be recommended. The system can also update the user's viewing history in real time and recommend content based on the latest information. For example, new content may be recommended based on recently viewed content. This makes it possible to recommend personalized content based on the user's viewing history.

[0043] The system can add an offline playback function when providing audio content, making it possible to use the content even without an internet connection. For example, when a generative AI provides audio content, the system can add an offline playback function to build a system that can be used even without an internet connection. For example, offline playback can be made possible by downloading the content in advance. The system can also provide storage for offline playback. For example, the system can store the audio content in the device. The system can also display the available playback time for offline playback. For example, the system can display the remaining time available for offline playback. This allows the offline playback function to be added, making it possible to use the content even without an internet connection.

[0044] The system can collect user feedback in real time when providing audio content and continuously improve the quality of the content. For example, when a generative AI provides audio content, the system collects user feedback in real time and builds a system that continuously improves the quality of the content. For example, improvements are made based on user ratings and comments. The system can also analyze user feedback and identify areas for improvement. For example, it can analyze areas with low user ratings and propose improvements. The system can also diversify the methods for collecting feedback. For example, it can collect feedback through surveys, real-time ratings, comments, etc. This makes it possible to collect user feedback in real time and continuously improve the quality of the content.

[0045] The system can support different devices when providing audio content. For example, the system builds a system that supports different devices when a generative AI provides audio content. For example, it enables playback on smart speakers and wearable devices. The system can also provide an interface optimized for each device. For example, it can provide an app for smartphones and a skill for smart speakers. The system can also synchronize between devices. For example, playback can be started on a smartphone and continued on a smart speaker. This allows it to support different devices.

[0046] The system can add a chapter function when providing audio content so that the user can proceed at their own pace. For example, a system can be constructed that adds a chapter function when a generative AI provides audio content so that the user can proceed at their own pace. For example, the system can provide chapters separated by scenes. The system can also provide an interface that makes it easy to move between chapters. For example, the system can display a chapter list and jump to a selected chapter. The system can also allow the user to customize how chapters are divided. For example, the user can set chapters at any point. This makes it possible to add a chapter function that allows the user to proceed at their own pace.

[0047] The system can utilize natural language processing technology in the user interface to make voice guide navigation more intuitive. For example, when a generation AI designs a user interface, the system utilizes natural language processing technology to make voice guide navigation more intuitive. For example, the system analyzes a user's voice commands and performs appropriate operations. The system can also generate the content of the voice guide using natural language processing technology. For example, the system can provide appropriate answers to the user's questions. The system can also customize the voice guide navigation according to the user's usage situation. For example, the system can prioritize the display of functions that the user uses frequently. In this way, natural language processing technology can be utilized to make voice guide navigation more intuitive.

[0048] The system can introduce an operation method using haptic feedback into the user interface, thereby enabling operation without relying on vision. For example, when a generating AI designs a user interface, the system can introduce an operation method using haptic feedback, thereby enabling operation without relying on vision. For example, feedback can be provided by vibration when a button is pressed. The system can also diversify the types of haptic feedback. For example, pressure feedback or temperature feedback can be provided. The system can also adjust the intensity of the haptic feedback. For example, the system can allow the user to set the feedback intensity. This allows an operation method using haptic feedback to be introduced, enabling operation without relying on vision.

[0049] The system can learn the user's usage status in the user interface and provide individually optimized operation methods. For example, when a generative AI designs a user interface, the system learns the user's usage status and builds a system that provides individually optimized operation methods. For example, the system may suggest the optimal operation method based on the user's operation history. The system can also monitor the user's usage status in real time and adjust the operation method. For example, the system may prioritize displaying functions that the user uses frequently. The system can also customize the operation method based on the user's settings. For example, the system adjusts the interface according to the operation method set by the user. This makes it possible to learn the user's usage status and provide individually optimized operation methods.

[0050] The system can provide customizable settings in a user interface to accommodate users with different disabilities. For example, when a generative AI designs a user interface, the system builds a system that provides customizable settings to accommodate users with different disabilities. For example, it provides audio guides for the visually impaired and subtitles for the hearing impaired. The system can also customize the interface according to a user's disability. For example, it adjusts color contrast for users with color blindness. The system can also provide customizable options based on the user's settings. For example, it adjusts the interface according to the disability set by the user. This makes it possible to provide customizable settings to accommodate users with different disabilities.

[0051] The system can learn the characteristics of a user's voice to improve the accuracy of voice commands in a user interface. For example, when a generative AI designs a user interface, the system builds a system that learns the characteristics of a user's voice to improve the accuracy of voice commands. For example, the system analyzes the tone and accent of the user's voice. The system can also improve the accuracy of voice command recognition based on the characteristics of the user's voice. For example, the system analyzes the pitch and speed of the user's voice to improve the accuracy of voice command recognition. The system can also learn the characteristics of the user's voice in real time and adjust the accuracy of voice commands. For example, the system adjusts the accuracy of voice command recognition according to changes in the user's voice. In this way, the system can learn the characteristics of the user's voice to improve the accuracy of voice commands.

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

[0053] When analyzing the visual information of a video, the visual information analysis unit can verbalize details of the clothing and accessories of the characters. For example, it can describe the color, design, and brand name of the clothing worn by the characters. The visual information analysis unit can also verbalize the type and characteristics of accessories worn by the characters. For example, it can describe the design and material of necklaces and watches. The visual information analysis unit can also track changes in the clothing and accessories of the characters and verbalize those changes. For example, it can describe the changes in clothing and accessories that differ from scene to scene. This makes it possible to verbalize details of the clothing and accessories of the characters and complement the visual information.

[0054] When analyzing the visual information of a video, the visual information analysis unit can verbalize the geographical information of the scene. For example, it can explain the place name and characteristics of the location where the scene was shot. The visual information analysis unit can also verbalize the geographical background of the scene in detail. For example, if the scene was shot in a mountainous area, it can explain the name and altitude of the mountain. The visual information analysis unit can also track geographical changes in the scene and verbalize those changes. For example, it can explain the process of the scene moving from a city to a rural area. This allows the geographical information of the scene to be verbalized in detail to complement the visual information.

[0055] When analyzing the visual information of a video, the visual information analysis unit can verbalize the cultural background of a scene. For example, it can explain the cultural meaning of the buildings and costumes that appear in the scene. The visual information analysis unit can also verbalize the cultural background of a scene in detail. For example, if the scene depicts a specific festival or traditional event, it can explain the history and meaning of that festival or event. The visual information analysis unit can also track the cultural changes in the scene and verbalize those changes. For example, it can explain the process by which the scene goes back in time from the present day. This allows the cultural background of the scene to be verbalized in detail to complement the visual information.

[0056] When analyzing the visual information of a video, the visual information analysis unit can verbalize the historical background of a scene. For example, it can explain the historical events and background of the era in which the scene is depicted. The visual information analysis unit can also verbalize the historical background of a scene in detail. For example, if the scene depicts a specific war or incident, it can explain the details of that war or incident. The visual information analysis unit can also track the historical changes of a scene and verbalize those changes. For example, it can explain the process by which the scene progresses from the past to the present. This allows the historical background of the scene to be verbalized in detail to complement the visual information.

[0057] When analyzing the visual information of a video, the visual information analysis unit can verbalize the environmental elements of a scene. For example, it can explain the characteristics of the natural environment or urban environment that appears in the scene. The visual information analysis unit can also verbalize the environmental elements of a scene in detail. For example, if a scene is shot in a forest or on the beach, it can explain the details of the natural environment. The visual information analysis unit can also track environmental changes in a scene and verbalize those changes. For example, if a scene depicts the change of seasons, it can explain the change of seasons. This makes it possible to verbalize the environmental elements of a scene in detail and complement the visual information.

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

[0059] Step 1: The visual information analysis unit analyzes the visual information in the video. For example, it analyzes the facial expressions and movements of the characters, the background scenery, etc. It can also extract and analyze visual information for each frame of the video. For example, it can analyze the position and movement of the characters in each frame of the video. Step 2: The verbalization unit verbalizes the visual information analyzed by the visual information analysis unit. For example, it verbalizes information such as "Character A is smiling and talking to Character B" or "A beautiful sunset is spreading in the background." It can also generate sentences from visual information using natural language processing technology. Step 3: The speech conversion unit converts the visual information verbalized by the verbalization unit into speech, for example, by using speech synthesis technology or text-to-speech technology. Step 4: The integration unit integrates the visual and auditory information converted into audio by the audio conversion unit. For example, in a movie scene, the dialogue of a character and the visual information of that scene can be simultaneously provided as audio. It is also possible to integrate the audio visual information and the dialogue in a timely manner.

[0060] (Example 2) The visual information speech system according to an embodiment of the present invention is a system that verbalizes the visual information of a video and converts it into speech. This system enables visually impaired people and bedridden people to enjoy video content more. As a result, the visual information speech system allows visually impaired people and bedridden people to enjoy video content more.

[0061] A visual information speech system according to an embodiment includes a visual information analysis unit, a verbalization unit, a speech conversion unit, and an integration unit. The visual information analysis unit analyzes visual information from a video. For example, it analyzes facial expressions and movements of characters, background scenery, and the like. The visual information analysis unit can also extract and analyze visual information for each frame of a video. For example, it analyzes the positions and movements of characters for each frame of a video. The verbalization unit verbalizes the visual information analyzed by the visual information analysis unit. For example, it verbalizes information such as "Character A is smiling and talking to B" or "A beautiful sunset is spreading in the background." The verbalization unit can also verbalize the visual information using natural language processing technology. For example, it generates the visual information as sentences using natural language processing technology. The speech conversion unit converts the visual information verbalized by the verbalization unit into speech. For example, it converts the verbalized visual information into speech using speech synthesis technology. The speech conversion unit can also convert the verbalized visual information into speech using text-to-speech technology. For example, it outputs the verbalized visual information as speech using text-to-speech technology. The integration unit integrates the visual information and audio information converted into audio by the audio conversion unit. For example, in a movie scene, the dialogue of a character and the visual information of that scene are simultaneously provided as audio. The integration unit can also synchronize and integrate the audio-converted visual information and audio information. For example, the integration unit can synchronize the timing of the audio-converted visual information and the audio information. This allows the visual information to be more enjoyable for visually impaired people and bedridden people. For example, audio explanations of the characters' facial expressions and scenes can deepen understanding of the story and complement the visual information. Furthermore, user convenience is improved as the information can be easily accessed through a dedicated app.

[0062] The visual information analysis unit can infer the emotions of characters and add detailed explanations based on those emotions. For example, when the generative AI analyzes the visual information of a video, the visual information analysis unit analyzes the facial expressions and movements of characters to infer emotions. For example, if a character is smiling, the visual information analysis unit can provide a detailed explanation of the reason and background behind the smile. The visual information analysis unit can also use voice analysis technology to analyze the tone and speed of a character's voice to infer emotions. For example, a high-pitched voice of a character indicates excitement. The visual information analysis unit can also use biometric technology to analyze a character's biological data to infer emotions. For example, emotions can be inferred based on fluctuations in heart rate. This makes it possible to provide detailed explanations based on the character's emotions.

[0063] The visual information analysis unit can use object recognition technology to verbalize in detail the objects held by characters and objects in the background. For example, when the generative AI analyzes the visual information of a video, the visual information analysis unit uses object recognition technology to verbalize in detail the objects held by characters. For example, it may explain the title and contents of the book the character is holding. The visual information analysis unit can also verbalize in detail objects in the background. For example, it may explain the features of buildings and scenery in the background. The visual information analysis unit can also verbalize in detail based on object position information. For example, it may explain the position of the cup held in the character's right hand. This allows for detailed verbalization of the objects held by characters and objects in the background.

[0064] The visual information analysis unit can track changes in a scene over time and provide a detailed explanation of the transitions. For example, when the generative AI analyzes the visual information of a video, the visual information analysis unit tracks changes in a scene over time and provides a detailed explanation of those transitions. For example, it can verbalize the flow of time from morning to night or the change of seasons. The visual information analysis unit can also explain transitions based on the start and end times of a scene. For example, it can clearly indicate the start and end times of a scene. The visual information analysis unit can also explain transitions based on important events in a scene. For example, it can explain important events and actions within a scene. This allows for a detailed explanation of the transitions in a scene over time.

[0065] The visual information analysis unit can simultaneously analyze information from different camera angles and viewpoints, and provide explanations from multiple viewpoints. For example, when the generative AI analyzes the visual information of a video, the visual information analysis unit simultaneously analyzes information from different camera angles and provides explanations from multiple viewpoints. For example, it can verbalize the differences when the same scene is viewed from different angles. The visual information analysis unit can also integrate information from different viewpoints and provide explanations. For example, it can integrate information from a bird's-eye view and a close-up view and provide an explanation. The visual information analysis unit can also compare information from different camera angles and provide explanations. For example, it can compare the positions and movements of characters when viewed from different camera angles. This makes it possible to provide explanations from multiple viewpoints.

[0066] The visual information analysis unit can verbalize changes in color and light in the image in detail to convey the visual atmosphere. For example, when the generative AI analyzes the visual information of an image, the visual information analysis unit verbalizes changes in color in the image in detail to convey the visual atmosphere. For example, it explains the changes in emotions that occur when the color tone of a scene changes. The visual information analysis unit can also verbalize changes in light in detail. For example, it explains changes in brightness or darkness in a scene. The visual information analysis unit can also convey the visual atmosphere based on changes in hue, brightness, and saturation. For example, it explains the changes in emotions that occur when the hue of a scene changes. This makes it possible to verbalize changes in color and light in the image in detail to convey the visual atmosphere.

[0067] The visual information analysis unit can use the emotion estimation function to analyze the emotions of characters in real time and provide an explanation of the visual information based on those emotions. For example, when the generative AI analyzes the visual information of a video, the visual information analysis unit can use the emotion estimation function to analyze the emotions of characters in real time and provide an explanation of the visual information based on those emotions. For example, if a character is surprised, the visual information analysis unit can explain the reason and background for the surprise. The visual information analysis unit can also analyze the emotions of characters using facial expression recognition technology. For example, it can estimate emotions based on changes in the character's facial expressions. The visual information analysis unit can also analyze the emotions of characters using audio analysis technology. For example, it can analyze the tone and speed of a character's voice to estimate emotions. This makes it possible to provide an explanation of the visual information based on the character's emotions in real time.

[0068] The voice conversion unit can generate a voice tone based on the emotion of a character when converting verbalized visual information into voice. For example, when the generation AI converts verbalized visual information into voice, the voice conversion unit generates a voice tone based on the emotion of a character. For example, if the character is angry, a voice tone that expresses anger is used. The voice conversion unit can also analyze the emotion of a character using an emotion estimation function and generate a voice tone based on that emotion. For example, if the character is sad, a voice tone that expresses sadness is used. The voice conversion unit can also generate a voice tone based on emotion using voice synthesis technology. For example, a voice tone according to emotion is generated using voice synthesis technology. In this way, a voice tone based on the emotion of a character can be generated.

[0069] The audio conversion unit can automatically add background sounds and sound effects when converting verbalized visual information into audio, thereby enhancing the sense of realism. For example, when the generation AI converts verbalized visual information into audio, the audio conversion unit can automatically add background sounds to enhance the sense of realism. For example, natural sounds and environmental sounds according to the scene are added. The audio conversion unit can also automatically add sound effects. For example, gunshots and explosions are added in action scenes. The audio conversion unit can also automatically add music. For example, moving music is added in moving scenes. In this way, background sounds and sound effects can be automatically added, enhancing the sense of realism.

[0070] When converting verbalized visual information into audio, the audio conversion unit can generate characters with different voices for each character to provide explanations. For example, when the generation AI converts verbalized visual information into audio, the audio conversion unit can generate characters with different voices to provide explanations for each character. For example, different voices are used for male characters and female characters. The audio conversion unit can also generate characters with different voices by changing the pitch or tone of the voice. For example, different voices are used for child characters and adult characters. The audio conversion unit can also generate characters with different voices by changing the accent or dialect. For example, dialects for each region are used. This allows explanations to be provided in different voices for each character.

[0071] The speech conversion unit supports multiple languages ​​when converting verbalized visual information into speech, making it possible to accommodate international users. For example, the speech conversion unit builds a system that supports multiple languages ​​when the generation AI converts verbalized visual information into speech. For example, it supports languages ​​such as English, French, and Chinese. The speech conversion unit can also generate speech using different speech synthesis technologies for each language. For example, it can use English speech synthesis technology and Japanese speech synthesis technology. The speech conversion unit can also automatically switch languages ​​based on the user's language settings. For example, it generates speech according to the language set by the user. This makes it possible to support multiple languages ​​and accommodate international users.

[0072] The speech conversion unit can allow the user to adjust the speed and pitch of the speech when converting verbalized visual information into speech. For example, the speech conversion unit provides a function that allows the user to adjust the speed of the speech when the generation AI converts verbalized visual information into speech. For example, the playback speed can be increased or decreased. The speech conversion unit can also provide a function that allows the user to adjust the pitch of the speech. For example, the pitch of the speech can be changed. The speech conversion unit can also adjust the speed and pitch of the speech through a user interface. For example, the adjustment can be made using a slider or button. This allows the user to adjust the speed and pitch of the speech.

[0073] When converting verbalized visual information into speech, the speech conversion unit uses an emotion estimation function to adjust the speech tone in real time according to the user's emotions, thereby providing a more emotional experience. For example, when the generation AI converts verbalized visual information into speech, the speech conversion unit uses the emotion estimation function to adjust the speech tone in real time according to the user's emotions. For example, if the user is excited, the speech conversion unit raises the speech tone. The speech conversion unit can also analyze the user's emotions and adjust the speech tone based on the emotions. For example, if the user is relaxed, the speech conversion unit calms the speech tone. The speech conversion unit can also monitor the user's emotions in real time and adjust the speech tone. For example, the speech conversion unit analyzes the user's facial expressions and tone of voice and adjusts the speech tone. This allows the speech tone to be adjusted in real time according to the user's emotions, thereby providing a more emotional experience.

[0074] When integrating auditory information and vocalized visual information, the integration unit can set the priority of information based on the importance of each scene. For example, when the generation AI integrates auditory information and vocalized visual information, the integration unit sets the priority of information based on the importance of each scene. For example, important lines and action scenes are given priority. The integration unit can also analyze the importance of a scene and set the priority of information based on that importance. For example, the importance is evaluated based on the length of the scene and the number of characters. The integration unit can also adjust the priority of information based on user settings. For example, information is provided according to the importance set by the user. This makes it possible to set the priority of information based on the importance of each scene.

[0075] The integration unit can seamlessly integrate background sounds and sound effects when integrating auditory information with audio-enabled visual information, thereby generating natural audio content. For example, when the generation AI integrates auditory information with audio-enabled visual information, the integration unit seamlessly integrates background sounds to generate natural audio content. For example, environmental sounds according to the scene are added. The integration unit can also seamlessly integrate sound effects. For example, in action scenes, gunshots and explosions are naturally integrated. The integration unit can also synchronize audio and background sounds to seamlessly integrate them. For example, the integration unit can align the timing of audio and background sounds to integrate them. This allows background sounds and sound effects to be seamlessly integrated, thereby generating natural audio content.

[0076] The integration unit can add audio effects to emphasize the emotional tone of a scene when integrating auditory information and vocalized visual information. For example, when the generation AI integrates auditory information and vocalized visual information, the integration unit adds audio effects to emphasize the emotional tone of a scene. For example, music or sound effects to increase tension are added. The integration unit can also analyze the emotional tone of a scene and add audio effects based on the tone. For example, emotional music is added in an emotional scene. The integration unit can also adjust the type and intensity of audio effects and add them. For example, the intensity of the audio effect is adjusted to emphasize the emotional tone of the scene. This makes it possible to add audio effects to emphasize the emotional tone of the scene.

[0077] The integration unit can also accommodate content of different genres when integrating auditory information and audiovisual visual information. For example, when the generative AI integrates auditory information and audiovisual visual information, the integration unit builds a system that can accommodate content of different genres. For example, it verbalizes and audiovisualizes the visual information of documentaries and anime. The integration unit can also use different visual information analysis methods for each genre. For example, documentaries can emphasize factual information, while anime can emphasize the emotions of the characters. The integration unit can also use different audio effects for each genre. For example, action movies can use powerful sound effects, while romance movies can use moving music. This makes it possible to accommodate content of different genres.

[0078] The integration unit can adjust the level of detail of the information according to the user's preferences when integrating auditory information and vocalized visual information. For example, the integration unit builds a system that can adjust the level of detail of the information according to the user's preferences when the generation AI integrates auditory information and vocalized visual information. For example, it makes it possible to select between a detailed explanation and a concise explanation. The integration unit can also adjust the level of detail of the information based on the user's settings. For example, it provides information according to the level of detail set by the user. The integration unit can also adjust the granularity of the information to be provided. For example, it provides a detailed explanation for each scene or an overall overview. This makes it possible to adjust the level of detail of the information according to the user's preferences.

[0079] When integrating auditory information and vocalized visual information, the integration unit uses an emotion estimation function to adjust the priority of information in real time according to the user's emotions, thereby providing a more personalized experience. For example, when the generation AI integrates auditory information and vocalized visual information, the integration unit uses the emotion estimation function to adjust the priority of information in real time according to the user's emotions. For example, if the user is excited, action scenes are prioritized. The integration unit can also analyze the user's emotions and adjust the priority of information based on those emotions. For example, if the user is relaxed, relaxing scenes are prioritized. The integration unit can also monitor the user's emotions in real time and adjust the priority of information. For example, it can analyze the user's facial expressions and tone of voice and adjust the priority of information. This allows the priority of information to be adjusted in real time according to the user's emotions, thereby providing a more personalized experience.

[0080] When providing audio content, the system can recommend personalized content based on the user's viewing history. For example, when a generative AI provides audio content, the system analyzes the user's viewing history and builds a system that recommends personalized content. For example, recommendations may be made based on genres or themes viewed in the past. The system can also analyze the user's interests based on the user's viewing history and recommend related content. For example, if the user has watched a lot of action movies, action movies may be recommended. The system can also update the user's viewing history in real time and recommend content based on the latest information. For example, new content may be recommended based on recently viewed content. This makes it possible to recommend personalized content based on the user's viewing history.

[0081] The system can add an offline playback function when providing audio content, making it possible to use the content even without an internet connection. For example, when a generative AI provides audio content, the system can add an offline playback function to build a system that can be used even without an internet connection. For example, offline playback can be made possible by downloading the content in advance. The system can also provide storage for offline playback. For example, the system can store the audio content in the device. The system can also display the available playback time for offline playback. For example, the system can display the remaining time available for offline playback. This allows the offline playback function to be added, making it possible to use the content even without an internet connection.

[0082] The system can collect user feedback in real time when providing audio content and continuously improve the quality of the content. For example, when a generative AI provides audio content, the system collects user feedback in real time and builds a system that continuously improves the quality of the content. For example, improvements are made based on user ratings and comments. The system can also analyze user feedback and identify areas for improvement. For example, it can analyze areas with low user ratings and propose improvements. The system can also diversify the methods for collecting feedback. For example, it can collect feedback through surveys, real-time ratings, comments, etc. This makes it possible to collect user feedback in real time and continuously improve the quality of the content.

[0083] The system can support different devices when providing audio content. For example, the system builds a system that supports different devices when a generative AI provides audio content. For example, it enables playback on smart speakers and wearable devices. The system can also provide an interface optimized for each device. For example, it can provide an app for smartphones and a skill for smart speakers. The system can also synchronize between devices. For example, playback can be started on a smartphone and continued on a smart speaker. This allows it to support different devices.

[0084] The system can add a chapter function when providing audio content so that the user can proceed at their own pace. For example, a system can be constructed that adds a chapter function when a generative AI provides audio content so that the user can proceed at their own pace. For example, the system can provide chapters separated by scenes. The system can also provide an interface that makes it easy to move between chapters. For example, the system can display a chapter list and jump to a selected chapter. The system can also allow the user to customize how chapters are divided. For example, the user can set chapters at any point. This makes it possible to add a chapter function that allows the user to proceed at their own pace.

[0085] When providing audio content, the system uses an emotion estimation function to recommend content based on the user's emotions, thereby providing more interesting content. For example, a system is constructed in which, when a generative AI provides audio content, the system uses the emotion estimation function to recommend content based on the user's emotions. For example, if the user is excited, the system recommends action movies. The system can also analyze the user's emotions and recommend content based on those emotions. For example, if the user is relaxed, the system can recommend relaxing music. The system can also monitor the user's emotions in real time and recommend content. For example, the system can analyze the user's facial expressions and tone of voice and recommend appropriate content. This allows the emotion estimation function to recommend content based on the user's emotions, providing more interesting content.

[0086] The system can utilize natural language processing technology in the user interface to make voice guide navigation more intuitive. For example, when a generation AI designs a user interface, the system utilizes natural language processing technology to make voice guide navigation more intuitive. For example, the system analyzes a user's voice commands and performs appropriate operations. The system can also generate the content of the voice guide using natural language processing technology. For example, the system can provide appropriate answers to the user's questions. The system can also customize the voice guide navigation according to the user's usage situation. For example, the system can prioritize the display of functions that the user uses frequently. In this way, natural language processing technology can be utilized to make voice guide navigation more intuitive.

[0087] The system can introduce an operation method using haptic feedback into the user interface, thereby enabling operation without relying on vision. For example, when a generating AI designs a user interface, the system can introduce an operation method using haptic feedback, thereby enabling operation without relying on vision. For example, feedback can be provided by vibration when a button is pressed. The system can also diversify the types of haptic feedback. For example, pressure feedback or temperature feedback can be provided. The system can also adjust the intensity of the haptic feedback. For example, the system can allow the user to set the feedback intensity. This allows an operation method using haptic feedback to be introduced, enabling operation without relying on vision.

[0088] The system can learn the user's usage status in the user interface and provide individually optimized operation methods. For example, when a generative AI designs a user interface, the system learns the user's usage status and builds a system that provides individually optimized operation methods. For example, the system may suggest the optimal operation method based on the user's operation history. The system can also monitor the user's usage status in real time and adjust the operation method. For example, the system may prioritize displaying functions that the user uses frequently. The system can also customize the operation method based on the user's settings. For example, the system adjusts the interface according to the operation method set by the user. This makes it possible to learn the user's usage status and provide individually optimized operation methods.

[0089] The system can provide customizable settings in a user interface to accommodate users with different disabilities. For example, when a generative AI designs a user interface, the system builds a system that provides customizable settings to accommodate users with different disabilities. For example, it provides audio guides for the visually impaired and subtitles for the hearing impaired. The system can also customize the interface according to a user's disability. For example, it adjusts color contrast for users with color blindness. The system can also provide customizable options based on the user's settings. For example, it adjusts the interface according to the disability set by the user. This makes it possible to provide customizable settings to accommodate users with different disabilities.

[0090] The system can learn the characteristics of a user's voice to improve the accuracy of voice commands in a user interface. For example, when a generative AI designs a user interface, the system builds a system that learns the characteristics of a user's voice to improve the accuracy of voice commands. For example, the system analyzes the tone and accent of the user's voice. The system can also improve the accuracy of voice command recognition based on the characteristics of the user's voice. For example, the system analyzes the pitch and speed of the user's voice to improve the accuracy of voice command recognition. The system can also learn the characteristics of the user's voice in real time and adjust the accuracy of voice commands. For example, the system adjusts the accuracy of voice command recognition according to changes in the user's voice. In this way, the system can learn the characteristics of the user's voice to improve the accuracy of voice commands.

[0091] The system can use an emotion estimation function in a user interface to adjust the interface design in real time according to the user's emotions, providing a more comfortable user experience. For example, when a generative AI designs a user interface, the system uses the emotion estimation function to build a system that adjusts the interface design in real time according to the user's emotions. For example, if the user is feeling stressed, the interface is simplified. The system can also analyze the user's emotions and adjust the interface design based on those emotions. For example, if the user is relaxed, the interface is changed to a more relaxing design. The system can also monitor the user's emotions in real time and adjust the interface design. For example, the system can analyze the user's facial expressions and tone of voice and adjust the interface design. This allows the emotion estimation function to adjust the interface design in real time according to the user's emotions, providing a more comfortable user experience.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] When analyzing the visual information of a video, the visual information analysis unit can verbalize details of the clothing and accessories of the characters. For example, it can describe the color, design, and brand name of the clothing worn by the characters. The visual information analysis unit can also verbalize the type and characteristics of accessories worn by the characters. For example, it can describe the design and material of necklaces and watches. The visual information analysis unit can also track changes in the clothing and accessories of the characters and verbalize those changes. For example, it can describe the changes in clothing and accessories that differ from scene to scene. This makes it possible to verbalize details of the clothing and accessories of the characters and complement the visual information.

[0094] When analyzing the visual information of a video, the visual information analysis unit can infer the relationships between characters and add an explanation based on those relationships. For example, if characters A and B are close friends, the unit will explain their relationship. The visual information analysis unit can also infer relationships from the characters' actions and conversations. For example, if character A is speaking to B in a friendly manner, the unit will explain that closeness. The visual information analysis unit can also track changes in the relationships between characters and explain those changes. For example, the unit can explain the process by which the relationship between characters A and B changes from friends to lovers. This makes it possible to provide a detailed explanation based on the relationships between characters.

[0095] When analyzing the visual information of a video, the visual information analysis unit can verbalize the geographical information of the scene. For example, it can explain the place name and characteristics of the location where the scene was shot. The visual information analysis unit can also verbalize the geographical background of the scene in detail. For example, if the scene was shot in a mountainous area, it can explain the name and altitude of the mountain. The visual information analysis unit can also track geographical changes in the scene and verbalize those changes. For example, it can explain the process of the scene moving from a city to a rural area. This allows the geographical information of the scene to be verbalized in detail to complement the visual information.

[0096] When analyzing the visual information of a video, the visual information analysis unit can estimate the health status of a character and add an explanation based on that health status. For example, if a character is tired, the cause and effects of that fatigue can be explained. The visual information analysis unit can also estimate the health status from the character's movements and facial expressions. For example, if a character is coughing, the cause of the cough can be explained. The visual information analysis unit can also track changes in the character's health status and explain those changes. For example, it can explain the process by which a character recovers from an illness. This makes it possible to provide a detailed explanation based on the character's health status.

[0097] When analyzing the visual information of a video, the visual information analysis unit can verbalize the cultural background of a scene. For example, it can explain the cultural meaning of the buildings and costumes that appear in the scene. The visual information analysis unit can also verbalize the cultural background of a scene in detail. For example, if the scene depicts a specific festival or traditional event, it can explain the history and meaning of that festival or event. The visual information analysis unit can also track the cultural changes in the scene and verbalize those changes. For example, it can explain the process by which the scene goes back in time from the present day. This allows the cultural background of the scene to be verbalized in detail to complement the visual information.

[0098] When analyzing the visual information of a video, the visual information analysis unit can infer the psychological state of a character and add an explanation based on that psychological state. For example, if a character is nervous, the cause and effect of that tension can be explained. The visual information analysis unit can also infer the psychological state from the character's behavior and facial expression. For example, if a character looks anxious, the cause of that anxiety can be explained. The visual information analysis unit can also track changes in the character's psychological state and explain those changes. For example, it can explain the process by which a character becomes relieved. This makes it possible to provide a detailed explanation based on the character's psychological state.

[0099] When analyzing the visual information of a video, the visual information analysis unit can verbalize the historical background of a scene. For example, it can explain the historical events and background of the era in which the scene is depicted. The visual information analysis unit can also verbalize the historical background of a scene in detail. For example, if the scene depicts a specific war or incident, it can explain the details of that war or incident. The visual information analysis unit can also track the historical changes of a scene and verbalize those changes. For example, it can explain the process by which the scene progresses from the past to the present. This allows the historical background of the scene to be verbalized in detail to complement the visual information.

[0100] When analyzing the visual information of a video, the visual information analysis unit can estimate the social position of a character and add an explanation based on that position. For example, if a character is a leader, the background and influence of that leadership can be explained. The visual information analysis unit can also estimate the social position from the character's actions and conversations. For example, if a character is giving instructions to another character, the background of those instructions can be explained. The visual information analysis unit can also track changes in the character's social position and explain those changes. For example, the process by which a character is promoted can be explained. This makes it possible to provide a detailed explanation based on the character's social position.

[0101] When analyzing the visual information of a video, the visual information analysis unit can verbalize the environmental elements of a scene. For example, it can explain the characteristics of the natural environment or urban environment that appears in the scene. The visual information analysis unit can also verbalize the environmental elements of a scene in detail. For example, if a scene is shot in a forest or on the beach, it can explain the details of the natural environment. The visual information analysis unit can also track environmental changes in a scene and verbalize those changes. For example, if a scene depicts the change of seasons, it can explain the change of seasons. This makes it possible to verbalize the environmental elements of a scene in detail and complement the visual information.

[0102] When analyzing the visual information of a video, the visual information analysis unit can infer the motivation of a character and add an explanation based on that motivation. For example, if a character is trying to achieve something, the unit will explain their goal and motivation. The visual information analysis unit can also infer motivation from a character's actions and conversations. For example, if a character is making an effort, the unit will explain the reason for that effort. The visual information analysis unit can also track changes in a character's motivation and explain those changes. For example, the unit will explain the process by which a character achieves their goal. This makes it possible to provide a detailed explanation based on the character's motivation.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The visual information analysis unit analyzes the visual information in the video. For example, it analyzes the facial expressions and movements of the characters, the background scenery, etc. It can also extract and analyze visual information for each frame of the video. For example, it can analyze the position and movement of the characters in each frame of the video. Step 2: The verbalization unit verbalizes the visual information analyzed by the visual information analysis unit. For example, it verbalizes information such as "Character A is smiling and talking to Character B" or "A beautiful sunset is spreading in the background." It can also generate sentences from visual information using natural language processing technology. Step 3: The speech conversion unit converts the visual information verbalized by the verbalization unit into speech, for example, by using speech synthesis technology or text-to-speech technology. Step 4: The integration unit integrates the visual and auditory information converted into audio by the audio conversion unit. For example, in a movie scene, the dialogue of a character and the visual information of that scene can be simultaneously provided as audio. It is also possible to integrate the audio visual information and the dialogue in a timely manner.

[0105] 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.

[0106] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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 a data format such as voice data and text data. 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0107] 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.

[0108] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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).

[0114] 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.

[0115] 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.

[0116] 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.

[0117] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0118] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0119] 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.

[0120] 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.

[0121] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0122] 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.

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

[0124] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0131] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0133] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0135] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0149] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0150] 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.

[0151] 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.

[0152] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] 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."

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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. [Explanation of symbols]

[0172] 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 visual information analysis unit that analyzes visual information of the video; a verbalization unit that verbalizes the visual information analyzed by the visual information analysis unit; a speech conversion unit that converts the visual information verbalized by the verbalization unit into speech; an integration unit that integrates the visual information and the auditory information converted into audio by the audio conversion unit; A system characterized by:

2. The visual information analysis unit Inferring the emotions of characters and adding detailed descriptions based on those emotions 2. The system of claim 1.

3. The visual information analysis unit Simultaneously analyze information from different camera angles and viewpoints to provide explanations from multiple perspectives 2. The system of claim 1.

4. The voice conversion unit When converting the verbalized visual information into audio, an audio tone is generated based on the emotions of the characters.

2. The system of claim 1.

5. The integration unit When integrating the auditory information and the vocalized visual information, the information is prioritized based on the importance of each scene.

2. The system of claim 1.

6. The integration unit When integrating the auditory information with the voiced visual information, emotion estimation is used to adjust the priority of information in real time according to the user's emotions, providing a more personalized experience.

2. The system of claim 1.

7. The system comprises: When providing audio content, the emotion estimation function is used to recommend content according to the user's emotions, and more interesting content is provided.

2. The system of claim 1.

8. The system comprises: In user interfaces, emotion estimation functionality is used to adjust interface design in real time according to the user's emotions, providing a more comfortable user experience.

2. The system of claim 1.

Images