System

Abstract

An object of the system according to the embodiment is to continue the conversation with the deceased.SOLUTION: A system according to an embodiment includes a data collection part, an analysis part, a personality reproduction part, and a dialogue generation part. The data collection unit collects data provided by a user. The analysis unit analyzes the data collected by the data collection unit. The personality reproducing section reproduces the personality of the deceased based on the data analyzed by the analyzing section. The dialogue generation section generates a dialogue based on the personality of the deceased reproduced by the personality reproduction section.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 there is no way to continue communicating with the deceased, making it difficult to ease the grief caused by separation.

[0005] The system of the embodiment aims to continue the dialogue with the deceased. [Means for solving the problem]

[0006] The system according to the embodiment includes a data collection unit, an analysis unit, a personality reproduction unit, and a dialogue generation unit. The data collection unit collects data provided by a user. The analysis unit analyzes the data collected by the data collection unit. The personality reproduction unit reproduces the personality of the deceased person based on the data analyzed by the analysis unit. The dialogue generation unit generates dialogue based on the personality of the deceased person reproduced by the personality reproduction unit. [Effects of the Invention]

[0007] The system according to the embodiment allows for continued dialogue with the deceased. [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) An AI service according to an embodiment of the present invention is a system for continuing to communicate with loved ones even after they have passed away. The system recreates the personality of the deceased using data such as memorable photos, letters, and voice recordings, allowing users to continue to converse with the deceased. In this way, the AI ​​service can ease the sadness caused by parting.

[0029] An AI service according to an embodiment includes a data collection unit, an analysis unit, a personality reproduction unit, and a dialogue generation unit. The data collection unit collects data provided by a user. For example, the data collection unit collects data such as memorable photos, letters, and voice recordings provided by the user. The data collection unit can also collect online data and social media posts. The analysis unit analyzes the collected data. For example, it analyzes photos to extract facial features and analyzes the contents of letters to understand vocabulary and thought patterns. It can also learn the tone of voice and speaking style from voice recordings. The personality reproduction unit recreates the personality of the deceased based on the analyzed data. For example, it creates an avatar based on a photo of the deceased and generates dialogue that sounds as if the deceased were actually speaking based on information learned from letters and voice recordings. The dialogue generation unit generates dialogue based on the recreated personality of the deceased. For example, it generates responses that reflect the personality of the deceased in response to questions and conversation content input by the user. This allows the AI ​​service according to an embodiment to continue a dialogue with the deceased. For example, if a user asks, "How was your day today?", the AI ​​service will generate a response that reflects the personality of the deceased person, such as, "Today was a great day. How was it for you?"

[0030] The data collection unit also collects online data, such as the deceased's social media posts or blog articles, to perform a more detailed personality analysis. The data collection unit, for example, collects the deceased's social media posts and analyzes the personality from the content of the posts and comments. For example, the frequency and content of posts can be used to identify the deceased's interests. The data collection unit also analyzes the deceased's blog posts and recreates the personality from the writing style and themes. For example, the deceased's thought patterns can be extracted from the blog's themes and writing style. The data collection unit also collects the deceased's online chat history and analyzes the personality from the content of the conversations and the way they are expressed. For example, the deceased's communication style can be identified from the chat interactions. This makes it possible to perform a more detailed personality analysis using online data.

[0031] The data collection unit analyzes the deceased's handwriting and reproduces the characteristics of the handwriting and writing style, thereby enabling a more realistic reproduction of the letter. For example, the data collection unit scans the deceased's handwriting and extracts the characteristics of the characters using handwriting analysis technology. For example, it analyzes the shape and pressure of the characters to reproduce the deceased's writing style. The data collection unit also generates a digital letter that imitates the deceased's handwriting based on the results of the handwriting analysis. For example, it creates a letter that reproduces the deceased's characteristic character shapes. The data collection unit also analyzes the deceased's handwriting and learns writing patterns. For example, it reproduces the writing style of specific characters and the connection of consecutive characters. This makes it possible to reproduce a more realistic letter by analyzing the handwriting.

[0032] The data collection unit can also collect data about the hobbies and interests of the deceased, thereby diversifying the content of the conversation. For example, the data collection unit collects data about the hobbies of the deceased and reflects this in the content of the conversation. For example, a dialogue is generated based on information about the music and movies that the deceased liked. The data collection unit also analyzes data about the interests of the deceased and incorporates related topics into the conversation. For example, it can provide topics about science, technology, and sports that the deceased were interested in. The data collection unit can also find common topics with the user based on the hobbies and interests of the deceased, thereby diversifying the conversation. For example, sharing stories about a common hobby. In this way, by collecting data about hobbies and interests, the content of the conversation can be diversified.

[0033] The data collection unit can collect interviews from the deceased's friends and family and add information from a third-party perspective. For example, the data collection unit interviews the deceased's friends and family to collect information about the deceased's episodes and personality. For example, it listens to reminiscences and details about specific events. The data collection unit also analyzes the interview content and reflects the information from a third-party perspective in recreating the deceased's personality. For example, it recreates the deceased's characteristics based on the testimony of friends and family. The data collection unit also recreates the deceased's personality in more detail based on the information obtained from the interviews. For example, it generates dialogue that incorporates the opinions of friends and family. In this way, adding information from a third-party perspective makes it possible to recreate a more detailed personality.

[0034] The personality reproducing unit can reproduce not only the deceased's tone of voice or speaking style, but also their unique gestures or facial expressions. For example, the personality reproducing unit may analyze an audio recording of the deceased and reproduce their tone of voice and speaking style. For example, it may imitate the deceased's distinctive speaking style. The personality reproducing unit may also analyze a photograph or video of the deceased and reproduce their unique gestures and facial expressions. For example, it may reproduce the deceased's smile or hand movements. The personality reproducing unit may also integrate the deceased's tone of voice, speaking style, gestures, and facial expressions to generate more realistic dialogue. For example, it may reproduce the facial expressions and movements of the deceased when they spoke. This allows for more realistic dialogue by reproducing the tone of voice, speaking style, gestures, and facial expressions.

[0035] The personality reproducing unit can learn the past behavioral patterns of the deceased and reproduce their reactions in specific situations. For example, the personality reproducing unit analyzes the past behavioral patterns of the deceased and learns their reactions in specific situations. For example, it reproduces how the deceased behaved in a specific event. The personality reproducing unit also generates dialogue in specific situations based on the behavioral patterns of the deceased. For example, it reproduces how the deceased spoke about a specific topic. The personality reproducing unit also learns the past behavioral patterns of the deceased and generates dialogue based on the results. For example, it reproduces how the deceased reacted in a specific emotional state. In this way, by learning past behavioral patterns, it is possible to reproduce reactions in specific situations.

[0036] The personality reproduction unit can combine and use multiple generative AI models to reproduce the personality of the deceased. For example, the personality reproduction unit combines different generative AI models to reproduce the personality of the deceased. For example, it integrates a voice generation model and a text generation model. The personality reproduction unit also uses multiple generative AI models to reproduce the personality of the deceased in more detail. For example, it combines an emotion estimation model and a behavior pattern model. The personality reproduction unit also combines different generative AI models to reproduce the multifaceted personality of the deceased. For example, it generates dialogue that integrates the voice, facial expressions, and behavior of the deceased. In this way, by combining multiple generative AI models, it is possible to reproduce a more detailed personality.

[0037] The dialogue generation unit can learn the past dialogue history of the deceased and realize a more consistent conversation. The dialogue generation unit, for example, analyzes the past dialogue history of the deceased and generates a consistent conversation. For example, it generates the next response based on the content of the past dialogue. The dialogue generation unit also learns the past dialogue history and reproduces the speaking style and expressions of the deceased. For example, it reproduces specific phrases and expressions. The dialogue generation unit also realizes a consistent conversation with the user based on the dialogue history of the deceased. For example, it provides the next topic based on the content of the previous dialogue. In this way, by learning the past dialogue history, a more consistent conversation is possible.

[0038] The dialogue generation unit can incorporate humor and jokes that reflect the personality of the deceased, generating natural conversations. The dialogue generation unit, for example, learns the deceased's style of humor and jokes and incorporates them into the conversation. For example, it reproduces jokes that the deceased often used. The dialogue generation unit also extracts humor and joke patterns from the deceased's past conversations and incorporates them into natural conversations. For example, it reproduces jokes used in specific situations. The dialogue generation unit also generates dialogues that reflect the deceased's humor, making conversations with the user more enjoyable. For example, it incorporates humorous phrases that the deceased often used. In this way, incorporating humor and jokes enables more natural conversations.

[0039] The dialogue generation unit can automatically record the content of a conversation so that the user can review it later. For example, the dialogue generation unit automatically records the content of a conversation with the user and saves it so that it can be reviewed later. For example, it saves the text of the conversation and makes it accessible to the user. The dialogue generation unit also records the content of the conversation and provides a function that allows the user to search for a specific conversation. For example, it searches for past conversations using specific keywords. The dialogue generation unit also automatically records the content of the conversation and provides an interface that allows the user to review it later. For example, it displays the dialogue history in chronological order. In this way, by automatically recording the content of the conversation, the user can review it later.

[0040] The dialogue generation unit can add a function that allows multiple users to share a dialogue with the deceased and enjoy a conversation together. The dialogue generation unit, for example, provides a function that allows multiple users to share a dialogue with the deceased. For example, it allows family and friends to participate in the dialogue together. The dialogue generation unit also uses the shared dialogue function to allow multiple users to enjoy a dialogue with the deceased at the same time. For example, the dialogue can be conducted in a group chat format. The dialogue generation unit also provides a function that allows multiple users to share a dialogue with the deceased and jointly reminisce about memories. For example, to celebrate a specific event or anniversary together. This allows multiple users to share a dialogue and enjoy a conversation together.

[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 data collection unit can also collect data about the user's lifestyle habits and reflect this in conversations with the deceased. For example, the data collection unit can collect information such as the user's daily routines, favorite foods, and favorite places, and the deceased can mention these in the conversations. The data collection unit can also collect data about the user's health status and generate conversations in which the deceased expresses concern for the user's health. For example, the data collection unit can generate conversations in which the deceased praises the user for starting to exercise. This enables conversations based on the user's lifestyle habits and health status, providing a more personalized experience.

[0043] The data collection unit can also collect data about the user's hobbies and interests and reflect this in the dialogue with the deceased. For example, it can collect information about the user's favorite music and movies and generate a dialogue in which the deceased talks about them. It can also collect information about topics the user was interested in and generate a dialogue in which the deceased talks about those topics. It can also collect information about books the user recently read or movies they recently watched and generate a dialogue in which the deceased shares their thoughts about them. This enables dialogue based on the user's hobbies and interests, providing a more personalized experience.

[0044] The data collection unit can learn from the user's past dialogue history to realize a more consistent conversation. For example, it can generate the next response based on the content of the past dialogue. It can also remember what the user has previously said and continue the dialogue based on that. Furthermore, when the user wants to talk about a specific topic, it can refer to the past dialogue history to provide related topics. In this way, learning from the past dialogue history enables a more consistent conversation and provides a natural dialogue experience for the user.

[0045] The data collection unit can collect interviews from the user's friends and family and add information from a third-party perspective. For example, it can interview friends and family to collect information about the user's anecdotes and personality. It can also analyze the interview content and reflect the information from a third-party perspective in the personality reproduction of the deceased. Furthermore, it can generate dialogue in which the deceased talks about the user based on the information obtained from the interview. By adding information from a third-party perspective, it is possible to reproduce the personality in more detail, providing the user with a more realistic dialogue experience.

[0046] The data collection unit can also collect data about the user's lifestyle habits and reflect this in conversations with the deceased. For example, the data collection unit can collect information such as the user's daily routines, favorite foods, and favorite places, and the deceased can mention these in the conversations. The data collection unit can also collect data about the user's health status and generate conversations in which the deceased expresses concern for the user's health. For example, the data collection unit can generate conversations in which the deceased praises the user for starting to exercise. This enables conversations based on the user's lifestyle habits and health status, providing a more personalized experience.

[0047] The data collection unit can also collect data about the user's hobbies and interests and reflect this in the dialogue with the deceased. For example, it can collect information about the user's favorite music and movies and generate a dialogue in which the deceased talks about them. It can also collect information about topics the user was interested in and generate a dialogue in which the deceased talks about those topics. It can also collect information about books the user recently read or movies they recently watched and generate a dialogue in which the deceased shares their thoughts about them. This enables dialogue based on the user's hobbies and interests, providing a more personalized experience.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The data collection unit collects data provided by the user. For example, it collects data such as memorable photos, letters, and audio recordings provided by the user. The data collection unit can also collect online data and social media posts. Step 2: The analysis unit analyzes the collected data. For example, it can analyze photos to extract facial features, analyze the contents of letters to understand vocabulary and thought patterns, or learn tone of voice and speaking style from audio recordings. Step 3: The personality reconstruction unit recreates the deceased person's personality based on the analyzed data, for example, creating an avatar generated from a photo of the deceased and generating dialogue that sounds like the deceased was actually speaking based on information learned from letters and voice recordings. Step 4: The dialogue generation unit generates a dialogue based on the recreated personality of the deceased. For example, it generates a response that reflects the personality of the deceased in response to questions and conversations entered by the user. This allows the user to continue the dialogue with the deceased.

[0050] (Example 2) An AI service according to an embodiment of the present invention is a system for continuing to communicate with loved ones even after they have passed away. The system recreates the personality of the deceased using data such as memorable photos, letters, and voice recordings, allowing users to continue to converse with the deceased. In this way, the AI ​​service can ease the sadness caused by parting.

[0051] An AI service according to an embodiment includes a data collection unit, an analysis unit, a personality reproduction unit, and a dialogue generation unit. The data collection unit collects data provided by a user. For example, the data collection unit collects data such as memorable photos, letters, and voice recordings provided by the user. The data collection unit can also collect online data and social media posts. The analysis unit analyzes the collected data. For example, it analyzes photos to extract facial features and analyzes the contents of letters to understand vocabulary and thought patterns. It can also learn the tone of voice and speaking style from voice recordings. The personality reproduction unit recreates the personality of the deceased based on the analyzed data. For example, it creates an avatar based on a photo of the deceased and generates dialogue that sounds as if the deceased were actually speaking based on information learned from letters and voice recordings. The dialogue generation unit generates dialogue based on the recreated personality of the deceased. For example, it generates responses that reflect the personality of the deceased in response to questions and conversation content input by the user. This allows the AI ​​service according to an embodiment to continue a dialogue with the deceased. For example, if a user asks, "How was your day today?", the AI ​​service will generate a response that reflects the personality of the deceased person, such as, "Today was a great day. How was it for you?"

[0052] The data collection unit can use the emotion estimation function to estimate the emotional state of the deceased from the collected data and recreate a personality that reflects those emotions. The data collection unit, for example, analyzes the deceased's letters and diary and uses the emotion estimation function to estimate the emotional state at the time. For example, emotions such as joy and sadness can be extracted from the content of the letters and the deceased's emotions can be recreated. The data collection unit can also analyze the deceased's audio recordings and estimate emotions from the tone of voice and speaking style. For example, emotions can be identified based on the pitch and speed of the voice and dialogue that reflects the deceased's emotions can be generated. The data collection unit can also analyze photographs of the deceased and estimate emotions from facial expressions. For example, emotions can be identified based on smiling and crying expressions and a personality recreated that reflects those emotions. This enables a more realistic personality recreate that reflects the deceased's emotional state.

[0053] The data collection unit also collects online data, such as the deceased's social media posts or blog articles, to perform a more detailed personality analysis. The data collection unit, for example, collects the deceased's social media posts and analyzes the personality from the content of the posts and comments. For example, the frequency and content of posts can be used to identify the deceased's interests. The data collection unit also analyzes the deceased's blog posts and recreates the personality from the writing style and themes. For example, the deceased's thought patterns can be extracted from the blog's themes and writing style. The data collection unit also collects the deceased's online chat history and analyzes the personality from the content of the conversations and the way they are expressed. For example, the deceased's communication style can be identified from the chat interactions. This makes it possible to perform a more detailed personality analysis using online data.

[0054] The data collection unit analyzes the deceased's handwriting and reproduces the characteristics of the handwriting and writing style, thereby enabling a more realistic reproduction of the letter. For example, the data collection unit scans the deceased's handwriting and extracts the characteristics of the characters using handwriting analysis technology. For example, it analyzes the shape and pressure of the characters to reproduce the deceased's writing style. The data collection unit also generates a digital letter that imitates the deceased's handwriting based on the results of the handwriting analysis. For example, it creates a letter that reproduces the deceased's characteristic character shapes. The data collection unit also analyzes the deceased's handwriting and learns writing patterns. For example, it reproduces the writing style of specific characters and the connection of consecutive characters. This makes it possible to reproduce a more realistic letter by analyzing the handwriting.

[0055] The data collection unit can also collect data about the hobbies and interests of the deceased, thereby diversifying the content of the conversation. For example, the data collection unit collects data about the hobbies of the deceased and reflects this in the content of the conversation. For example, a dialogue is generated based on information about the music and movies that the deceased liked. The data collection unit also analyzes data about the interests of the deceased and incorporates related topics into the conversation. For example, it can provide topics about science, technology, and sports that the deceased were interested in. The data collection unit can also find common topics with the user based on the hobbies and interests of the deceased, thereby diversifying the conversation. For example, sharing stories about a common hobby. In this way, by collecting data about hobbies and interests, the content of the conversation can be diversified.

[0056] The data collection unit can collect interviews from the deceased's friends and family and add information from a third-party perspective. For example, the data collection unit interviews the deceased's friends and family to collect information about the deceased's episodes and personality. For example, it listens to reminiscences and details about specific events. The data collection unit also analyzes the interview content and reflects the information from a third-party perspective in recreating the deceased's personality. For example, it recreates the deceased's characteristics based on the testimony of friends and family. The data collection unit also recreates the deceased's personality in more detail based on the information obtained from the interviews. For example, it generates dialogue that incorporates the opinions of friends and family. In this way, adding information from a third-party perspective makes it possible to recreate a more detailed personality.

[0057] The data collection unit can use the emotion estimation function to evaluate the emotional value of data provided by the user and prioritize analysis of important data. The data collection unit, for example, performs emotion estimation on data provided by the user and identifies data with high emotional value. For example, it prioritizes analysis of letters and photos with high emotion scores. The data collection unit also selects important data based on the emotion estimation results and reflects it in recreating the personality of the deceased. For example, it generates dialogue based on emotionally strong episodes. The data collection unit also evaluates the emotional value of data provided by the user and generates dialogue that reflects the emotions of the deceased. For example, it recreates emotionally important events. In this way, by prioritizing analysis of data with high emotional value, it is possible to generate more emotionally satisfying dialogue.

[0058] The personality reproducing unit can use the emotion estimation function to generate dialogue that reflects the emotional state of the deceased in real time. The personality reproducing unit, for example, estimates the emotional state of the deceased in real time and generates dialogue based on the result. For example, it reproduces dialogue when the deceased was happy. The personality reproducing unit also uses the emotion estimation function to generate responses that reflect the emotions of the deceased. For example, it reproduces dialogue when the deceased was sad. The personality reproducing unit also analyzes the emotional state of the deceased in real time and generates dialogue that reflects those emotions. For example, it reproduces dialogue when the deceased was surprised. In this way, by reflecting the emotional state of the deceased in real time, more empathetic dialogue is possible.

[0059] The personality reproducing unit can reproduce not only the deceased's tone of voice or speaking style, but also their unique gestures or facial expressions. For example, the personality reproducing unit may analyze an audio recording of the deceased and reproduce their tone of voice and speaking style. For example, it may imitate the deceased's distinctive speaking style. The personality reproducing unit may also analyze a photograph or video of the deceased and reproduce their unique gestures and facial expressions. For example, it may reproduce the deceased's smile or hand movements. The personality reproducing unit may also integrate the deceased's tone of voice, speaking style, gestures, and facial expressions to generate more realistic dialogue. For example, it may reproduce the facial expressions and movements of the deceased when they spoke. This allows for more realistic dialogue by reproducing the tone of voice, speaking style, gestures, and facial expressions.

[0060] The personality reproducing unit can learn the past behavioral patterns of the deceased and reproduce their reactions in specific situations. For example, the personality reproducing unit analyzes the past behavioral patterns of the deceased and learns their reactions in specific situations. For example, it reproduces how the deceased behaved in a specific event. The personality reproducing unit also generates dialogue in specific situations based on the behavioral patterns of the deceased. For example, it reproduces how the deceased spoke about a specific topic. The personality reproducing unit also learns the past behavioral patterns of the deceased and generates dialogue based on the results. For example, it reproduces how the deceased reacted in a specific emotional state. In this way, by learning past behavioral patterns, it is possible to reproduce reactions in specific situations.

[0061] The personality reproduction unit can combine and use multiple generative AI models to reproduce the personality of the deceased. For example, the personality reproduction unit combines different generative AI models to reproduce the personality of the deceased. For example, it integrates a voice generation model and a text generation model. The personality reproduction unit also uses multiple generative AI models to reproduce the personality of the deceased in more detail. For example, it combines an emotion estimation model and a behavior pattern model. The personality reproduction unit also combines different generative AI models to reproduce the multifaceted personality of the deceased. For example, it generates dialogue that integrates the voice, facial expressions, and behavior of the deceased. In this way, by combining multiple generative AI models, it is possible to reproduce a more detailed personality.

[0062] The personality reproduction unit uses the emotion estimation function to generate responses from the deceased that correspond to the user's emotional state, thereby enabling a more empathetic dialogue. The personality reproduction unit, for example, analyzes the user's emotional state in real time and generates responses from the deceased based on the results. For example, it provides words of comfort when the user is sad. The personality reproduction unit also uses the emotion estimation function to generate responses from the deceased that correspond to the user's emotions. For example, it provides words of empathy when the user is happy. The personality reproduction unit also adjusts the responses of the deceased based on the user's emotional state, enabling a more empathetic dialogue. For example, it provides words of encouragement when the user is feeling anxious. In this way, a more empathetic dialogue can be achieved by generating responses that correspond to the user's emotional state.

[0063] The dialogue generation unit can use the emotion estimation function to analyze the user's emotional state in real time and generate a response from the deceased accordingly. The dialogue generation unit, for example, analyzes the user's emotional state in real time and generates a response from the deceased based on the results. For example, it provides calm words when the user is angry. The dialogue generation unit also uses the emotion estimation function to generate a response from the deceased according to the user's emotions. For example, it provides words of comfort when the user is sad. The dialogue generation unit also adjusts the response of the deceased based on the user's emotional state to achieve a more empathetic dialogue. For example, it provides words of empathy when the user is happy. In this way, by analyzing the user's emotional state in real time and generating a response accordingly, a more empathetic dialogue is possible.

[0064] The dialogue generation unit can learn the past dialogue history of the deceased and realize a more consistent conversation. The dialogue generation unit, for example, analyzes the past dialogue history of the deceased and generates a consistent conversation. For example, it generates the next response based on the content of the past dialogue. The dialogue generation unit also learns the past dialogue history and reproduces the speaking style and expressions of the deceased. For example, it reproduces specific phrases and expressions. The dialogue generation unit also realizes a consistent conversation with the user based on the dialogue history of the deceased. For example, it provides the next topic based on the content of the previous dialogue. In this way, by learning the past dialogue history, a more consistent conversation is possible.

[0065] The dialogue generation unit can incorporate humor and jokes that reflect the personality of the deceased, generating natural conversations. The dialogue generation unit, for example, learns the deceased's style of humor and jokes and incorporates them into the conversation. For example, it reproduces jokes that the deceased often used. The dialogue generation unit also extracts humor and joke patterns from the deceased's past conversations and incorporates them into natural conversations. For example, it reproduces jokes used in specific situations. The dialogue generation unit also generates dialogues that reflect the deceased's humor, making conversations with the user more enjoyable. For example, it incorporates humorous phrases that the deceased often used. In this way, incorporating humor and jokes enables more natural conversations.

[0066] The dialogue generation unit can automatically record the content of a conversation so that the user can review it later. For example, the dialogue generation unit automatically records the content of a conversation with the user and saves it so that it can be reviewed later. For example, it saves the text of the conversation and makes it accessible to the user. The dialogue generation unit also records the content of the conversation and provides a function that allows the user to search for a specific conversation. For example, it searches for past conversations using specific keywords. The dialogue generation unit also automatically records the content of the conversation and provides an interface that allows the user to review it later. For example, it displays the dialogue history in chronological order. In this way, by automatically recording the content of the conversation, the user can review it later.

[0067] The dialogue generation unit can add a function that allows multiple users to share a dialogue with the deceased and enjoy a conversation together. The dialogue generation unit, for example, provides a function that allows multiple users to share a dialogue with the deceased. For example, it allows family and friends to participate in the dialogue together. The dialogue generation unit also uses the shared dialogue function to allow multiple users to enjoy a dialogue with the deceased at the same time. For example, the dialogue can be conducted in a group chat format. The dialogue generation unit also provides a function that allows multiple users to share a dialogue with the deceased and jointly reminisce about memories. For example, to celebrate a specific event or anniversary together. This allows multiple users to share a dialogue and enjoy a conversation together.

[0068] The dialogue generation unit can use the emotion estimation function to suggest a conversation topic that will provide the user with the most emotional satisfaction. For example, the dialogue generation unit uses the emotion estimation function to identify a topic that will provide the user with the most emotional satisfaction and incorporate it into the dialogue. For example, it suggests a topic that will bring joy to the user. The dialogue generation unit also analyzes the user's emotional state in real time and suggests an optimal topic based on the results. For example, it provides a topic that will relax the user. The dialogue generation unit also selects a topic that will provide the user with the most emotional satisfaction based on the emotion estimation data and generates a dialogue. For example, it suggests a topic that the user is interested in. In this way, by suggesting a conversation topic that will provide the user with the most emotional satisfaction, it is possible to have a more emotionally satisfying dialogue.

[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 data collection unit can also collect data about the user's lifestyle habits and reflect this in conversations with the deceased. For example, the data collection unit can collect information such as the user's daily routines, favorite foods, and favorite places, and the deceased can mention these in the conversations. The data collection unit can also collect data about the user's health status and generate conversations in which the deceased expresses concern for the user's health. For example, the data collection unit can generate conversations in which the deceased praises the user for starting to exercise. This enables conversations based on the user's lifestyle habits and health status, providing a more personalized experience.

[0071] The data collection unit can estimate the user's emotional state and generate a response from the deceased that corresponds to that emotion. For example, when the user is sad, a dialogue can be generated in which the deceased offers words of comfort. When the user is happy, a dialogue can be generated in which the deceased offers words of sympathy. Furthermore, when the user is stressed, a dialogue can be generated in which the deceased suggests ways to relax. This enables a dialogue that corresponds to the user's emotional state, providing a more empathetic experience.

[0072] The data collection unit can also collect data about the user's hobbies and interests and reflect this in the dialogue with the deceased. For example, it can collect information about the user's favorite music and movies and generate a dialogue in which the deceased talks about them. It can also collect information about topics the user was interested in and generate a dialogue in which the deceased talks about those topics. It can also collect information about books the user recently read or movies they recently watched and generate a dialogue in which the deceased shares their thoughts about them. This enables dialogue based on the user's hobbies and interests, providing a more personalized experience.

[0073] The data collection unit can learn from the user's past dialogue history to realize a more consistent conversation. For example, it can generate the next response based on the content of the past dialogue. It can also remember what the user has previously said and continue the dialogue based on that. Furthermore, when the user wants to talk about a specific topic, it can refer to the past dialogue history to provide related topics. In this way, learning from the past dialogue history enables a more consistent conversation and provides a natural dialogue experience for the user.

[0074] The data collection unit can analyze the user's emotional state in real time and generate responses from the deceased based on the results. For example, when the user is angry, a dialogue can be generated in which the deceased speaks calmly. When the user is sad, a dialogue can be generated in which the deceased speaks comforting words. Furthermore, when the user is happy, a dialogue can be generated in which the deceased speaks sympathetic words. This allows for more empathetic dialogue by analyzing the user's emotional state in real time and generating responses accordingly.

[0075] The data collection unit can collect interviews from the user's friends and family and add information from a third-party perspective. For example, it can interview friends and family to collect information about the user's anecdotes and personality. It can also analyze the interview content and reflect the information from a third-party perspective in the personality reproduction of the deceased. Furthermore, it can generate dialogue in which the deceased talks about the user based on the information obtained from the interview. By adding information from a third-party perspective, it is possible to reproduce the personality in more detail, providing the user with a more realistic dialogue experience.

[0076] The data collection unit can estimate the user's emotional state and generate a response from the deceased that corresponds to that emotion. For example, when the user is sad, a dialogue can be generated in which the deceased offers words of comfort. When the user is happy, a dialogue can be generated in which the deceased offers words of sympathy. Furthermore, when the user is stressed, a dialogue can be generated in which the deceased suggests ways to relax. This enables a dialogue that corresponds to the user's emotional state, providing a more empathetic experience.

[0077] The data collection unit can also collect data about the user's lifestyle habits and reflect this in conversations with the deceased. For example, the data collection unit can collect information such as the user's daily routines, favorite foods, and favorite places, and the deceased can mention these in the conversations. The data collection unit can also collect data about the user's health status and generate conversations in which the deceased expresses concern for the user's health. For example, the data collection unit can generate conversations in which the deceased praises the user for starting to exercise. This enables conversations based on the user's lifestyle habits and health status, providing a more personalized experience.

[0078] The data collection unit can also collect data about the user's hobbies and interests and reflect this in the dialogue with the deceased. For example, it can collect information about the user's favorite music and movies and generate a dialogue in which the deceased talks about them. It can also collect information about topics the user was interested in and generate a dialogue in which the deceased talks about those topics. It can also collect information about books the user recently read or movies they recently watched and generate a dialogue in which the deceased shares their thoughts about them. This enables dialogue based on the user's hobbies and interests, providing a more personalized experience.

[0079] The data collection unit can analyze the user's emotional state in real time and generate responses from the deceased based on the results. For example, when the user is angry, a dialogue can be generated in which the deceased speaks calmly. When the user is sad, a dialogue can be generated in which the deceased speaks comforting words. Furthermore, when the user is happy, a dialogue can be generated in which the deceased speaks sympathetic words. This allows for more empathetic dialogue by analyzing the user's emotional state in real time and generating responses accordingly.

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

[0081] Step 1: The data collection unit collects data provided by the user. For example, it collects data such as memorable photos, letters, and audio recordings provided by the user. The data collection unit can also collect online data and social media posts. Step 2: The analysis unit analyzes the collected data. For example, it can analyze photos to extract facial features, analyze the contents of letters to understand vocabulary and thought patterns, or learn tone of voice and speaking style from audio recordings. Step 3: The personality reconstruction unit recreates the deceased person's personality based on the analyzed data, for example, creating an avatar generated from a photo of the deceased and generating dialogue that sounds like the deceased was actually speaking based on information learned from letters and voice recordings. Step 4: The dialogue generation unit generates a dialogue based on the recreated personality of the deceased. For example, it generates a response that reflects the personality of the deceased in response to questions and conversations entered by the user. This allows the user to continue the dialogue with the deceased.

[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 a 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 type 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 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform 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 data collection unit that collects data provided by a user; an analysis unit that analyzes the data collected by the data collection unit; a personality reproducing unit that reproduces the personality of the deceased person based on the data analyzed by the analyzing unit; a dialogue generation unit that generates a dialogue based on the personality of the deceased person reproduced by the personality reproduction unit; A system characterized by:

2. The data collection unit Estimate the emotional state of the deceased from the collected data and recreate a personality that reflects those emotions.

2. The system of claim 1.

3. The data collection unit Online data such as at least one social media post or blog post by the deceased will also be collected to conduct a more detailed personality analysis.

2. The system of claim 1.

4. The data collection unit By analyzing the handwriting of the deceased and recreating the characteristics of the handwriting and writing style, we can recreate letters that are more realistic.

2. The system of claim 1.

5. The data collection unit Data on the deceased's hobbies and interests will also be collected to diversify the content of conversations.

2. The system of claim 1.

Images