System

Abstract

An object of the system according to the embodiment is to make it possible to obtain advice from the deceased or the master even after death.SOLUTION: A system according to an embodiment includes a deep fake video generation unit, an advice derivation unit, and a negative utterance exclusion unit. The deep fake image generation unit may generate a deep fake image using photos or voices captured from a plurality of angles during life. The advice derivation unit derives advice based on a questionnaire of a plurality of concepts. The negative utterance exclusion unit excludes a negative utterance and leads the user to act forward.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 technology has the problem that it is not possible to receive advice from deceased loved ones or teachers after death, resulting in the loss of spiritual support.

[0005] The system according to the embodiment aims to enable people to receive advice from deceased loved ones or teachers even after death. [Means for solving the problem]

[0006] The system according to the embodiment includes a deepfake video generation unit, an advice derivation unit, and a negative comment exclusion unit. The deepfake video generation unit generates deepfake video using photographs and audio taken from multiple angles during the subject's lifetime. The advice derivation unit derives advice based on a questionnaire covering multiple perspectives. The negative comment exclusion unit excludes negative comments and encourages the subject to take positive action. [Effects of the Invention]

[0007] The system according to the embodiment can enable advice from deceased loved ones or teachers to be obtained even after death. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The consultation tool according to an embodiment of the present invention is a system that generates deepfake video using photographs and audio taken from multiple angles during a person's lifetime, creating a video that looks exactly like the person. This system provides advice based on a questionnaire covering various perspectives, filters out negative comments, and encourages positive behavior. This allows the consultation tool to provide a function for parent-child and teacher-student relationships, even after death.

[0029] The consultation tool according to the embodiment includes a deepfake video generation unit, an advice derivation unit, and a negative comment exclusion unit. The deepfake video generation unit generates deepfake video using photos and audio captured from multiple angles during a person's lifetime. For example, the generation AI receives photos and audio data taken during a person's lifetime as input and generates a video that looks exactly like the person based on the input. The generation AI analyzes the photo and audio data using deep learning technology to create realistic videos. For example, when a parent's photo or audio is input, the generation AI generates a video of the parent and makes it move as if they were alive. The advice derivation unit derives advice based on a questionnaire covering various perspectives. For example, the generation AI analyzes questionnaire data filled out by the person during their lifetime and generates appropriate advice for the relevant person. For example, based on questionnaire data filled out by a master during their lifetime, the master can give positive advice to their disciple, such as "If you keep trying, you will surely succeed." The negative comment exclusion unit excludes negative comments when generating advice. For example, the generation AI generates positive messages such as "Don't give up even if you fail," and excludes negative content when generating advice. As a result, the consultation tool according to the embodiment can provide a function for parent-child or master-disciple relationships to receive consultation even after death. For example, even after a parent passes away, a child can receive advice through the parent's video and behave positively. Also, even after a master passes away, a disciple can receive advice through the master's video and continue to grow.

[0030] The deepfake video generation unit can analyze the person's handwritten text or diary entries, in addition to video and audio data from before death, to generate more realistic deepfake videos. For example, the deepfake video generation unit scans letters or diaries written before death and converts them into text data using character recognition technology. The generation AI then analyzes the text data and learns the person's unique phrasing and expressions, reflecting them in the video. The deepfake video generation unit also digitizes the person's handwritten notes and notebooks, and the generation AI analyzes their contents. For example, it learns specific phrases and wording and reproduces them as natural conversations when generating the video. The deepfake video generation unit can also analyze the person's blogs and social media posts, in addition to video and audio data from before death, and the generation AI learns from their contents. This allows the person's thoughts and opinions to be more accurately reproduced in the video. This allows for the generation of more realistic deepfake videos.

[0031] The deepfake video generation unit learns the person's unique gesture or facial expression patterns and reproduces them, allowing it to generate more natural-looking videos. For example, the deepfake video generation unit analyzes video data from the person's life to extract the person's unique gesture and facial expression patterns. For example, it learns characteristics such as smiles and hand movements and reflects them in the generated video. The deepfake video generation unit also uses the person's video data to utilize deep learning technology to model unique facial expression changes and movement patterns. This makes the generated video more natural and realistic. The deepfake video generation unit also learns from video from the person's life what gestures and facial expressions the person would make in specific situations, and the generation AI reproduces those patterns. For example, it incorporates facial expressions of surprise or thoughtful gestures into the video. This allows it to generate more natural-looking deepfake videos.

[0032] The deepfake video generation unit can combine the deepfake video with devices that reproduce not only the person's voice but also their unique scent or tactile sensation, providing an experience that appeals to all five senses. For example, the deepfake video generation unit uses a device that reproduces the person's unique scent in addition to the deepfake video. For example, the scent of a perfume often used by the person can be reproduced and provided along with the video. The deepfake video generation unit can also combine the deepfake video with a tactile device to reproduce the feel of the person's hand or the sensation of a hug. For example, a device that provides tactile feedback can be used to link with the video. The deepfake video generation unit can also build a system that integrates video, audio, scent, and tactile sensations, allowing the user to experience the experience with all five senses. For example, while watching the video, the user can hear the person's voice, smell the scent, and feel the sensation of touch with a tactile device. This can provide an experience that appeals to all five senses.

[0033] The deepfake video generation unit can make deepfake videos multilingual for users of different cultures or languages, promoting international use. For example, the deepfake video generation unit adds multilingual support to deepfake videos to enable them to be used by users of different languages. For example, it automatically translates the audio of the video and displays subtitles. The deepfake video generation unit also customizes the content of the deepfake video for users of different cultures. For example, it incorporates expressions that match cultural backgrounds and customs. The deepfake video generation unit also integrates voice recognition and translation technology to provide multilingual deepfake videos, incorporating real-time translated audio into the video. For example, it supports multiple languages ​​such as English, French, and Chinese. This promotes international use.

[0034] The advice derivation unit can analyze the contents of letters or emails written by the individual in addition to questionnaire data from before death, to derive more specific and personalized advice. For example, the advice derivation unit scans letters or emails written before death and converts them into text data using character recognition technology. The generation AI then analyzes the text data and learns the individual's unique phrases and expressions, reflecting them in the advice. The advice derivation unit also digitizes handwritten notes and notebooks written by the individual, and the generation AI analyzes their contents. For example, it learns specific phrases and wording and reproduces them as natural conversation when generating advice. The advice derivation unit also analyzes the contents of letters or emails written before death, and the generation AI generates personalized advice based on those contents. For example, it provides specific advice tailored to a specific situation. This makes it possible to provide more specific and personalized advice.

[0035] The advice derivation unit can learn the person's past behavioral history or decision-making patterns and generate advice based on that. For example, the advice derivation unit stores the person's behavioral history and decision-making patterns during their lifetime in a database, and the generation AI analyzes that data. For example, advice is generated based on past experiences of success and failure. The advice derivation unit also analyzes the person's past behavioral history, and the generation AI learns those patterns. For example, appropriate advice is provided based on behavioral patterns in specific situations. The advice derivation unit also analyzes the person's decision-making patterns during their lifetime, and the generation AI generates advice based on those patterns. For example, advice is provided that takes into account the reasons and results of past decisions. This makes it possible to provide advice based on the person's past behavioral history and decision-making patterns.

[0036] The advice derivation unit can customize the content of advice according to the user's life stage or situation and provide it at a more appropriate time. For example, the advice derivation unit stores the user's life stage and situation in a database, and the generation AI customizes the advice based on that data. For example, it provides academic advice to students. The advice derivation unit also builds a system that analyzes the user's current situation and generates advice according to that situation. For example, it provides advice on interview preparation to a user who is job-hunting. The advice derivation unit also develops a system that dynamically adjusts the content of advice according to the user's life stage. For example, it provides advice on married life to a newlywed user. This makes it possible to provide advice according to the user's life stage and situation.

[0037] The advice derivation unit can generate multidisciplinary advice that incorporates the opinions of experts in different fields and provide it to the user. For example, the advice derivation unit stores the opinions of experts in different fields in a database, and the generation AI generates advice based on that data. For example, it integrates the opinions of experts in medicine, law, psychology, etc. To generate multidisciplinary advice, the advice derivation unit also collects the opinions of experts in different fields in real time, and the generation AI analyzes that data. For example, it provides advice that combines the opinions of multiple experts. The advice derivation unit also builds a system that provides comprehensive advice to the user based on the opinions of experts in different fields. For example, it provides advice that integrates health management and career planning. This makes it possible to provide advice that incorporates the opinions of experts in different fields.

[0038] The negative comment elimination unit can develop algorithms that not only filter out negative comments but also convert them into positive ones. For example, the negative comment elimination unit will develop an algorithm that detects negative comments and converts them into positive ones. For example, it will convert "I might fail" into "It's a challenge to succeed." The negative comment elimination unit will also use a generative AI to analyze negative comments and convert their content into positive expressions. For example, it will convert "It's a difficult problem" into "It's a problem worth solving." The negative comment elimination unit will also develop an algorithm that uses natural language processing technology to convert negative comments into positive ones. For example, it will convert "It's impossible" into "It's worthwhile." This will convert negative comments into positive ones.

[0039] The negative comment filtering unit can also apply the negative comment filtering function to other communication tools to promote overall positive communication. For example, the negative comment filtering unit integrates the negative comment filtering function into a chat app and analyzes messages sent by users in real time to filter out negative content. For example, if negative words are detected during a chat, they are automatically converted into positive expressions. The negative comment filtering unit also introduces the negative comment filtering function into a social media platform and analyzes the content of posts to filter out negative comments. For example, if a post contains negative content, a warning is displayed before the post, prompting the user to change it to a more positive expression. The negative comment filtering unit also applies the negative comment filtering function to business communication tools to keep workplace communication positive. For example, it analyzes the content of emails and messages and converts negative expressions into positive expressions. This promotes overall positive communication.

[0040] The negative comment elimination unit provides a function for excluding negative comments in a manner specialized for specific environments, such as educational settings or workplaces, thereby realizing a less stressful environment. For example, in educational settings, the negative comment elimination unit introduces a function for excluding negative comments to maintain positive communication between students. For example, it excludes negative comments in chats and forums during online classes. In addition, in workplace environments, the negative comment elimination unit introduces a function for excluding negative comments to maintain positive communication between employees. For example, it analyzes the content of internal emails and messages and converts negative expressions into positive ones. Furthermore, the negative comment elimination unit provides a function for excluding negative comments specialized for specific environments in order to reduce stress in educational settings or workplaces. For example, in educational settings, it considers the mental health of students, and in workplaces, it provides a function for reducing employee stress. This allows for a less stressful environment to be realized in specific environments, such as educational settings or workplaces.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The deepfake video generation unit can make deepfake videos multilingual for users of different cultures or languages, promoting international use. For example, it can automatically translate the audio in the video and display subtitles. It can also customize the content of deepfake videos for users of different cultures. For example, it can incorporate expressions that match cultural backgrounds and customs. Furthermore, to provide multilingual deepfake videos, it can integrate speech recognition and translation technology and incorporate real-time translated audio into the video, promoting international use.

[0043] The deepfake video generation unit can combine the deepfake video with devices that reproduce not only the person's voice but also their unique scent or texture, providing an experience that appeals to all five senses. For example, in addition to the deepfake video, a device that reproduces the person's unique scent can be used. For example, the scent of a perfume that the person often wears can be reproduced and provided along with the video. A tactile device can also be combined to reproduce the feel of the person's hand or the sensation of a hug. For example, a device that provides tactile feedback can be used in conjunction with the video. Furthermore, a system that integrates video, audio, scent, and touch can be built, allowing the user to experience it with all five senses. This can provide an experience that appeals to all five senses.

[0044] The advice derivation unit can analyze the contents of letters or emails written by the deceased person in addition to questionnaire data from before death, to derive more specific and personalized advice. For example, letters or emails written before death can be scanned and converted into text data using character recognition technology. The generation AI then analyzes the text data and learns the person's unique phrases and expressions, which are then reflected in the advice. Handwritten notes and notebooks can also be digitized and their contents analyzed by the generation AI. For example, specific phrases and wording can be learned and reproduced as natural conversation when generating advice. Furthermore, the content of letters and emails can be analyzed, and the generation AI can generate personalized advice based on that content. This makes it possible to provide more specific and personalized advice.

[0045] The advice derivation unit can learn the individual's past behavioral history or decision-making patterns and generate advice based on that. For example, the individual's behavioral history and decision-making patterns from that time are stored in a database, and the generation AI analyzes that data. For example, advice is generated based on past experiences of success and failure. Past behavioral history can also be analyzed, and the generation AI can learn those patterns. For example, appropriate advice is provided based on behavioral patterns in specific situations. Furthermore, decision-making patterns can be analyzed, and the generation AI can generate advice based on those patterns. This makes it possible to provide advice based on the individual's past behavioral history and decision-making patterns.

[0046] The advice derivation unit can generate multidisciplinary advice that incorporates the opinions of experts from different fields and provide it to the user. For example, the opinions of experts from different fields can be stored in a database, and the generation AI can generate advice based on that data. For example, the opinions of experts in medicine, law, psychology, etc. can be integrated. In addition, to generate multidisciplinary advice, the opinions of experts from different fields can be collected in real time, and the generation AI can analyze that data. For example, advice that combines the opinions of multiple experts can be provided. Furthermore, a system can be built that provides comprehensive advice to users based on the opinions of experts from different fields. This makes it possible to provide advice that incorporates the opinions of experts from different fields.

[0047] The processing flow of the first embodiment will be briefly explained below.

[0048] Step 1: The deepfake video generation unit generates deepfake videos using photos and audio taken from multiple angles before the person's death. For example, the generation AI receives as input photos taken before the person's death and audio recordings, and uses them to generate videos that look exactly like the person. The generation AI uses deep learning technology to analyze the photos and audio data and create realistic videos. For example, if a photo or audio of a parent is input, the generation AI will generate an image of that parent and make them act as if they were alive. Step 2: The advice derivation unit derives advice based on a questionnaire with various perspectives. For example, the generation AI analyzes the questionnaire data that the person answered before they died and generates appropriate advice for the relevant person. For example, based on the questionnaire data that a master answered before they died, it could give positive advice to a disciple such as "If you keep trying, you will surely succeed." Step 3: The negative comment filter filters out negative comments when generating advice. For example, when generating advice, the AI ​​generates positive messages such as "Don't give up even if you fail," and filters out negative content.

[0049] (Example 2) The consultation tool according to an embodiment of the present invention is a system that generates deepfake video using photographs and audio taken from multiple angles during a person's lifetime, creating a video that looks exactly like the person. This system provides advice based on a questionnaire covering various perspectives, filters out negative comments, and encourages positive behavior. This allows the consultation tool to provide a function for parent-child and teacher-student relationships, even after death.

[0050] The consultation tool according to the embodiment includes a deepfake video generation unit, an advice derivation unit, and a negative comment exclusion unit. The deepfake video generation unit generates deepfake video using photos and audio captured from multiple angles during a person's lifetime. For example, the generation AI receives photos and audio data taken during a person's lifetime as input and generates a video that looks exactly like the person based on the input. The generation AI analyzes the photo and audio data using deep learning technology to create realistic videos. For example, when a parent's photo or audio is input, the generation AI generates a video of the parent and makes it move as if they were alive. The advice derivation unit derives advice based on a questionnaire covering various perspectives. For example, the generation AI analyzes questionnaire data filled out by the person during their lifetime and generates appropriate advice for the relevant person. For example, based on questionnaire data filled out by a master during their lifetime, the master can give positive advice to their disciple, such as "If you keep trying, you will surely succeed." The negative comment exclusion unit excludes negative comments when generating advice. For example, the generation AI generates positive messages such as "Don't give up even if you fail," and excludes negative content when generating advice. As a result, the consultation tool according to the embodiment can provide a function for parent-child or master-disciple relationships to receive consultation even after death. For example, even after a parent passes away, a child can receive advice through the parent's video and behave positively. Also, even after a master passes away, a disciple can receive advice through the master's video and continue to grow.

[0051] The deepfake video generation unit can analyze the person's handwritten text or diary entries, in addition to video and audio data from before death, to generate more realistic deepfake videos. For example, the deepfake video generation unit scans letters or diaries written before death and converts them into text data using character recognition technology. The generation AI then analyzes the text data and learns the person's unique phrasing and expressions, reflecting them in the video. The deepfake video generation unit also digitizes the person's handwritten notes and notebooks, and the generation AI analyzes their contents. For example, it learns specific phrases and wording and reproduces them as natural conversations when generating the video. The deepfake video generation unit can also analyze the person's blogs and social media posts, in addition to video and audio data from before death, and the generation AI learns from their contents. This allows the person's thoughts and opinions to be more accurately reproduced in the video. This allows for the generation of more realistic deepfake videos.

[0052] The deepfake video generation unit learns the person's unique gesture or facial expression patterns and reproduces them, allowing it to generate more natural-looking videos. For example, the deepfake video generation unit analyzes video data from the person's life to extract the person's unique gesture and facial expression patterns. For example, it learns characteristics such as smiles and hand movements and reflects them in the generated video. The deepfake video generation unit also uses the person's video data to utilize deep learning technology to model unique facial expression changes and movement patterns. This makes the generated video more natural and realistic. The deepfake video generation unit also learns from video from the person's life what gestures and facial expressions the person would make in specific situations, and the generation AI reproduces those patterns. For example, it incorporates facial expressions of surprise or thoughtful gestures into the video. This allows it to generate more natural-looking deepfake videos.

[0053] The deepfake video generation unit can use the emotion estimation function to generate deepfake video with facial expressions or tones that correspond to the user's emotional state. The deepfake video generation unit, for example, analyzes the user's emotional state in real time and adjusts the facial expressions and tone of the deepfake video based on the results. For example, if the user is sad, the facial expression of the video is made gentler. The deepfake video generation unit also uses the emotion estimation function to calculate the user's emotional score and change the tone and facial expression of the video according to the score. For example, if the user is excited, the tone of the video is made brighter. The deepfake video generation unit also analyzes the user's emotional state and builds a system that dynamically adjusts the facial expressions and tone of the deepfake video based on the data. For example, if the user is relaxed, the facial expression of the video is made gentler. This makes it possible to generate deepfake video that corresponds to the user's emotional state.

[0054] The deepfake video generation unit can combine the deepfake video with devices that reproduce not only the person's voice but also their unique scent or tactile sensation, providing an experience that appeals to all five senses. For example, the deepfake video generation unit uses a device that reproduces the person's unique scent in addition to the deepfake video. For example, the scent of a perfume often used by the person can be reproduced and provided along with the video. The deepfake video generation unit can also combine the deepfake video with a tactile device to reproduce the feel of the person's hand or the sensation of a hug. For example, a device that provides tactile feedback can be used to link with the video. The deepfake video generation unit can also build a system that integrates video, audio, scent, and tactile sensations, allowing the user to experience the experience with all five senses. For example, while watching the video, the user can hear the person's voice, smell the scent, and feel the sensation of touch with a tactile device. This can provide an experience that appeals to all five senses.

[0055] The deepfake video generation unit can make deepfake videos multilingual for users of different cultures or languages, promoting international use. For example, the deepfake video generation unit adds multilingual support to deepfake videos to enable them to be used by users of different languages. For example, it automatically translates the audio of the video and displays subtitles. The deepfake video generation unit also customizes the content of the deepfake video for users of different cultures. For example, it incorporates expressions that match cultural backgrounds and customs. The deepfake video generation unit also integrates voice recognition and translation technology to provide multilingual deepfake videos, incorporating real-time translated audio into the video. For example, it supports multiple languages ​​such as English, French, and Chinese. This promotes international use.

[0056] The deepfake video generation unit uses an emotion estimation function to analyze a user's emotional response in real time when watching a video and dynamically adjust the content of the video. For example, the deepfake video generation unit builds a system that analyzes a user's emotional response in real time when watching a video and dynamically adjusts the content of the video based on the results. For example, if the user is moved, the tone of the video is emphasized. The deepfake video generation unit also uses the emotion estimation function to analyze the user's emotion score and change the content of the video according to the score. For example, if the user is sad, the content of the video is changed to an encouraging message. The deepfake video generation unit also develops a system that adjusts the video scenario and expression in real time based on the user's emotional response data. For example, if the user is relaxed, the content of the video is changed to a calmer one. This allows the content of the video to be dynamically adjusted according to the user's emotional response.

[0057] The advice derivation unit can analyze the contents of letters or emails written by the individual in addition to questionnaire data from before death, to derive more specific and personalized advice. For example, the advice derivation unit scans letters or emails written before death and converts them into text data using character recognition technology. The generation AI then analyzes the text data and learns the individual's unique phrases and expressions, reflecting them in the advice. The advice derivation unit also digitizes handwritten notes and notebooks written by the individual, and the generation AI analyzes their contents. For example, it learns specific phrases and wording and reproduces them as natural conversation when generating advice. The advice derivation unit also analyzes the contents of letters or emails written before death, and the generation AI generates personalized advice based on those contents. For example, it provides specific advice tailored to a specific situation. This makes it possible to provide more specific and personalized advice.

[0058] The advice derivation unit can learn the person's past behavioral history or decision-making patterns and generate advice based on that. For example, the advice derivation unit stores the person's behavioral history and decision-making patterns during their lifetime in a database, and the generation AI analyzes that data. For example, advice is generated based on past experiences of success and failure. The advice derivation unit also analyzes the person's past behavioral history, and the generation AI learns those patterns. For example, appropriate advice is provided based on behavioral patterns in specific situations. The advice derivation unit also analyzes the person's decision-making patterns during their lifetime, and the generation AI generates advice based on those patterns. For example, advice is provided that takes into account the reasons and results of past decisions. This makes it possible to provide advice based on the person's past behavioral history and decision-making patterns.

[0059] The advice derivation unit can use the emotion estimation function to generate advice in real time according to the user's current emotional state. The advice derivation unit, for example, builds a system that analyzes the user's emotional state in real time and generates advice based on the results. For example, if the user is depressed, it provides an encouraging message. The advice derivation unit also uses the emotion estimation function to analyze the user's emotion score and generate advice according to the score. For example, if the user is excited, it provides advice to stay calm. The advice derivation unit also develops a system that generates advice in real time based on the user's emotional response data. For example, if the user is relaxed, it provides advice to maintain relaxation. This makes it possible to provide advice in real time according to the user's current emotional state.

[0060] The advice derivation unit can customize the content of advice according to the user's life stage or situation and provide it at a more appropriate time. For example, the advice derivation unit stores the user's life stage and situation in a database, and the generation AI customizes the advice based on that data. For example, it provides academic advice to students. The advice derivation unit also builds a system that analyzes the user's current situation and generates advice according to that situation. For example, it provides advice on interview preparation to a user who is job-hunting. The advice derivation unit also develops a system that dynamically adjusts the content of advice according to the user's life stage. For example, it provides advice on married life to a newlywed user. This makes it possible to provide advice according to the user's life stage and situation.

[0061] The advice derivation unit can generate multidisciplinary advice that incorporates the opinions of experts in different fields and provide it to the user. For example, the advice derivation unit stores the opinions of experts in different fields in a database, and the generation AI generates advice based on that data. For example, it integrates the opinions of experts in medicine, law, psychology, etc. To generate multidisciplinary advice, the advice derivation unit also collects the opinions of experts in different fields in real time, and the generation AI analyzes that data. For example, it provides advice that combines the opinions of multiple experts. The advice derivation unit also builds a system that provides comprehensive advice to the user based on the opinions of experts in different fields. For example, it provides advice that integrates health management and career planning. This makes it possible to provide advice that incorporates the opinions of experts in different fields.

[0062] The advice derivation unit uses the emotion estimation function to analyze the emotional response of the user when receiving advice, and can continuously improve the content of the advice. The advice derivation unit, for example, analyzes the emotional response of the user when receiving advice in real time, and builds a system that improves the content of the advice based on that data. For example, it prioritizes providing advice that receives a lot of positive responses. The advice derivation unit also uses the emotion estimation function to analyze the user's emotion score, and adjusts the content of the advice according to that score. For example, it modifies advice that receives a lot of negative responses. The advice derivation unit also develops a system that continuously improves the content of the advice based on the user's emotional response data. For example, it improves the quality of the advice based on user feedback. This makes it possible to continuously improve the content of the advice based on the user's emotional response.

[0063] The negative comment elimination unit can develop algorithms that not only filter out negative comments but also convert them into positive ones. For example, the negative comment elimination unit will develop an algorithm that detects negative comments and converts them into positive ones. For example, it will convert "I might fail" into "It's a challenge to succeed." The negative comment elimination unit will also use a generative AI to analyze negative comments and convert their content into positive expressions. For example, it will convert "It's a difficult problem" into "It's a problem worth solving." The negative comment elimination unit will also develop an algorithm that uses natural language processing technology to convert negative comments into positive ones. For example, it will convert "It's impossible" into "It's worthwhile." This will convert negative comments into positive ones.

[0064] In addition to excluding negative comments, the negative comment excluding unit can provide positive feedback that takes into account the user's psychological state. For example, the negative comment excluding unit builds a system that analyzes the user's psychological state in real time and provides positive feedback based on the results. For example, if the user is feeling down, it provides an encouraging message. The negative comment excluding unit not only excludes negative comments but also generates positive feedback according to the user's psychological state. For example, if the user is feeling stressed, it provides advice on how to relax. The negative comment excluding unit also develops a system that takes into account the user's psychological state and converts negative comments into positive feedback. For example, if the user is feeling anxious, it provides a message that gives a sense of security. This makes it possible to provide positive feedback that takes into account the user's psychological state.

[0065] The negative comment excluding unit can use the emotion estimation function to generate an optimal positive message according to the user's emotional state. The negative comment excluding unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and builds a system that generates an optimal positive message based on the results. For example, if the user is sad, it provides an encouraging message. The negative comment excluding unit also analyzes the user's emotion score and generates a positive message according to the score. For example, if the user is excited, it provides advice to stay calm. The negative comment excluding unit also develops a system that generates a positive message in real time based on the user's emotional response data. For example, if the user is relaxed, it provides a message to help the user stay relaxed. This makes it possible to provide an optimal positive message according to the user's emotional state.

[0066] The negative comment filtering unit can also apply the negative comment filtering function to other communication tools to promote overall positive communication. For example, the negative comment filtering unit integrates the negative comment filtering function into a chat app and analyzes messages sent by users in real time to filter out negative content. For example, if negative words are detected during a chat, they are automatically converted into positive expressions. The negative comment filtering unit also introduces the negative comment filtering function into a social media platform and analyzes the content of posts to filter out negative comments. For example, if a post contains negative content, a warning is displayed before the post, prompting the user to change it to a more positive expression. The negative comment filtering unit also applies the negative comment filtering function to business communication tools to keep workplace communication positive. For example, it analyzes the content of emails and messages and converts negative expressions into positive expressions. This promotes overall positive communication.

[0067] The negative comment elimination unit provides a function for excluding negative comments in a manner specialized for specific environments, such as educational settings or workplaces, thereby realizing a less stressful environment. For example, in educational settings, the negative comment elimination unit introduces a function for excluding negative comments to maintain positive communication between students. For example, it excludes negative comments in chats and forums during online classes. In addition, in workplace environments, the negative comment elimination unit introduces a function for excluding negative comments to maintain positive communication between employees. For example, it analyzes the content of internal emails and messages and converts negative expressions into positive ones. Furthermore, the negative comment elimination unit provides a function for excluding negative comments specialized for specific environments in order to reduce stress in educational settings or workplaces. For example, in educational settings, it considers the mental health of students, and in workplaces, it provides a function for reducing employee stress. This allows for a less stressful environment to be realized in specific environments, such as educational settings or workplaces.

[0068] The negative comment excluding unit can use the emotion estimation function to analyze the emotional reaction of a user when receiving a negative comment and improve the function based on that data. For example, the negative comment excluding unit uses the emotion estimation function to build a system that analyzes the emotional reaction of a user when receiving a negative comment in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The negative comment excluding unit also improves the negative comment excluding function based on the user's emotional response data. For example, when a negative comment is detected, it provides an optimal positive message taking into account the user's emotional response. The negative comment excluding unit also collects user emotional response data and develops a system that continuously improves the negative comment excluding function based on that data. For example, it improves the accuracy of the function based on user feedback. This makes it possible to improve the negative comment excluding function based on the user's emotional response.

[0069] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0070] The consultation tool can be equipped with an emotion estimation function for providing appropriate advice according to the user's emotional state. For example, if the user is feeling stressed, the tool can provide advice to relax. If the user is excited, the tool can provide advice to stay calm. Furthermore, if the user is sad, the tool can provide an encouraging message. In this way, appropriate advice can be provided according to the user's emotional state.

[0071] The deepfake video generator can dynamically adjust the tone and facial expression of the video according to the user's emotional state. For example, if the user is relaxed, the facial expression of the video can be made calmer. If the user is excited, the tone of the video can be made brighter. Furthermore, if the user is sad, the facial expression of the video can be made gentler. This makes it possible to provide a video that matches the user's emotional state.

[0072] The deepfake video generator can dynamically adjust the content of the video according to the user's emotional state. For example, if the user is emotional, the tone of the video can be emphasized. If the user is sad, the content of the video can be changed to an encouraging message. Furthermore, if the user is relaxed, the content of the video can be changed to a calmer one. This makes it possible to provide a video that matches the user's emotional state.

[0073] The advice deriving unit can generate appropriate advice in real time according to the emotional state of the user. For example, if the user is depressed, an encouraging message can be provided. If the user is excited, advice to stay calm can be provided. Furthermore, if the user is relaxed, advice to maintain relaxation can be provided. In this way, appropriate advice can be provided according to the emotional state of the user.

[0074] The negative comment elimination unit can generate an optimal positive message according to the emotional state of the user. For example, if the user is sad, an encouraging message can be provided. If the user is excited, advice to stay calm can be provided. Furthermore, if the user is relaxed, a message to help the user maintain relaxation can be provided. In this way, it is possible to provide an optimal positive message according to the emotional state of the user.

[0075] The deepfake video generation unit can make deepfake videos multilingual for users of different cultures or languages, promoting international use. For example, it can automatically translate the audio in the video and display subtitles. It can also customize the content of deepfake videos for users of different cultures. For example, it can incorporate expressions that match cultural backgrounds and customs. Furthermore, to provide multilingual deepfake videos, it can integrate speech recognition and translation technology and incorporate real-time translated audio into the video, promoting international use.

[0076] The deepfake video generation unit can combine the deepfake video with devices that reproduce not only the person's voice but also their unique scent or texture, providing an experience that appeals to all five senses. For example, in addition to the deepfake video, a device that reproduces the person's unique scent can be used. For example, the scent of a perfume that the person often wears can be reproduced and provided along with the video. A tactile device can also be combined to reproduce the feel of the person's hand or the sensation of a hug. For example, a device that provides tactile feedback can be used in conjunction with the video. Furthermore, a system that integrates video, audio, scent, and touch can be built, allowing the user to experience it with all five senses. This can provide an experience that appeals to all five senses.

[0077] The advice derivation unit can analyze the contents of letters or emails written by the deceased person in addition to questionnaire data from before death, to derive more specific and personalized advice. For example, letters or emails written before death can be scanned and converted into text data using character recognition technology. The generation AI then analyzes the text data and learns the person's unique phrases and expressions, which are then reflected in the advice. Handwritten notes and notebooks can also be digitized and their contents analyzed by the generation AI. For example, specific phrases and wording can be learned and reproduced as natural conversation when generating advice. Furthermore, the content of letters and emails can be analyzed, and the generation AI can generate personalized advice based on that content. This makes it possible to provide more specific and personalized advice.

[0078] The advice derivation unit can learn the individual's past behavioral history or decision-making patterns and generate advice based on that. For example, the individual's behavioral history and decision-making patterns from that time are stored in a database, and the generation AI analyzes that data. For example, advice is generated based on past experiences of success and failure. Past behavioral history can also be analyzed, and the generation AI can learn those patterns. For example, appropriate advice is provided based on behavioral patterns in specific situations. Furthermore, decision-making patterns can be analyzed, and the generation AI can generate advice based on those patterns. This makes it possible to provide advice based on the individual's past behavioral history and decision-making patterns.

[0079] The advice derivation unit can generate multidisciplinary advice that incorporates the opinions of experts from different fields and provide it to the user. For example, the opinions of experts from different fields can be stored in a database, and the generation AI can generate advice based on that data. For example, the opinions of experts in medicine, law, psychology, etc. can be integrated. In addition, to generate multidisciplinary advice, the opinions of experts from different fields can be collected in real time, and the generation AI can analyze that data. For example, advice that combines the opinions of multiple experts can be provided. Furthermore, a system can be built that provides comprehensive advice to users based on the opinions of experts from different fields. This makes it possible to provide advice that incorporates the opinions of experts from different fields.

[0080] The processing flow of the second embodiment will be briefly explained below.

[0081] Step 1: The deepfake video generation unit generates deepfake videos using photos and audio taken from multiple angles before the person's death. For example, the generation AI receives as input photos taken before the person's death and audio recordings, and uses them to generate videos that look exactly like the person. The generation AI uses deep learning technology to analyze the photos and audio data and create realistic videos. For example, if a photo or audio of a parent is input, the generation AI will generate an image of that parent and make them act as if they were alive. Step 2: The advice derivation unit derives advice based on a questionnaire with various perspectives. For example, the generation AI analyzes the questionnaire data that the person answered before they died and generates appropriate advice for the relevant person. For example, based on the questionnaire data that a master answered before they died, it could give positive advice to a disciple such as "If you keep trying, you will surely succeed." Step 3: The negative comment filter filters out negative comments when generating advice. For example, when generating advice, the AI ​​generates positive messages such as "Don't give up even if you fail," and filters out negative content.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0086] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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).

[0091] 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.

[0092] 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.

[0093] 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.

[0094] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0095] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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).

[0106] 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.

[0107] 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.

[0108] 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.

[0109] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0110] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0116] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0126] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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."

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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]

[0149] 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 deepfake video generation unit that generates deepfake video using photographs and audio from multiple angles obtained during the person's lifetime; an advice derivation unit that derives advice based on a questionnaire of multiple ways of thinking; A negative comment excluding unit that excludes negative comments and guides users to take positive action. A system characterized by:

2. The deep fake video generation unit In addition to video and audio data from the person's life, the system analyzes the person's handwritten text or diary data to generate more realistic deepfake video.

2. The system of claim 1.

3. The deep fake video generation unit By learning and reproducing the unique gestures or facial expressions of the individual, more natural-looking images can be generated.

2. The system of claim 1.

4. The deep fake video generation unit Generate deepfake video with facial expressions or tones that correspond to the user's emotional state 2. The system of claim 1.

5. The deep fake video generation unit Deepfake video is combined with devices that reproduce not only the person's voice but also their unique scent or texture, providing an experience that appeals to all five senses.

2. The system of claim 1.

Images