System

Abstract

To provide a system that reproduces the personality of the deceased and makes a simulated conversation.SOLUTION: A system according to the embodiment comprises a collection unit, a learning unit, and a conversation unit. The collection unit collects at least one piece of personality information out of antemortem conversation data or behavioral patterns and hobbies and preferences. The learning unit learns the information collected by the collection unit, and reproduces the personality of the deceased. The conversation unit makes simulated conversations based on the information learned by the learning unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology is unable to simulate a conversation with a deceased person, and there is room for improvement.

[0005] The system according to the embodiment aims to recreate the personality of a deceased person and conduct a simulated conversation. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a learning unit, and a conversation unit. The collection unit collects at least one of conversation data from the person's life or personality information such as behavioral patterns and hobbies and preferences. The learning unit learns the information collected by the collection unit and reproduces the personality of the person. The conversation unit holds a pseudo-conversation based on the information learned by the learning unit. Effect of the Invention

[0007] The system according to the embodiment is capable of recreating the personality of a deceased person and conducting a simulated conversation with the person. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The personality reproduction system according to the embodiment of the present invention is a system that collects personality information such as conversation data, behavior patterns, and hobbies and preferences of a person before death, makes AI learn the collected information, and conducts a simulated conversation even after the person dies. This personality reproduction system collects personality information such as conversation data, behavior patterns, and hobbies and preferences of a person before death, and makes AI learn the collected information. The AI ​​reproduces the personality of the person based on the learned information. Finally, the AI ​​conducts a simulated conversation even after the person dies. For example, when a family member or friend talks to the AI, the AI ​​responds by reproducing the tone and manner of speech of the person. This system allows you to enjoy a conversation with the person even after they die. For example, as a collection unit, it collects personality information such as conversation data, behavior patterns, and hobbies and preferences before death. For example, it collects daily conversations, SNS posts, and information about hobbies. Next, as a learning unit, it makes the AI ​​learn the collected information. The AI ​​reproduces the personality of the person based on the collected information. For example, it learns a person's tone of voice, speaking style, hobbies, and preferences. Finally, as the conversation section, the AI ​​simulates a conversation. For example, when a family member or friend speaks to the AI, the AI ​​responds by recreating that person's tone of voice and speaking style. This system allows you to enjoy conversations with that person even after they have passed away. This personality reproduction system allows you to enjoy conversations with that person even after they have passed away.

[0029] The personality reproduction system according to the embodiment includes a collection unit, a learning unit, and a conversation unit. The collection unit collects personality information such as conversation data, behavioral patterns, and hobbies and preferences from the person's lifetime. The conversation data from the person's lifetime includes, for example, voice data, text data, and the like, but is not limited to such examples. The collection unit collects, for example, information on daily conversations, SNS posts, and hobbies. For example, conversations at home, conversations at work, and SNS post contents can be collected. The behavioral patterns include, for example, daily movement history, activity logs, and the like, but are not limited to such examples. The hobbies and preferences include, for example, music preferences, sports hobbies, and the like, but are not limited to such examples. The learning unit learns the information collected by the collection unit and reproduces the personality of the person. The learning unit learns the tone of speech, speaking style, and hobbies and preferences based on the collected information, for example, using a machine learning algorithm. For example, the learning unit can learn the characteristics of the tone of speech and speaking style, and patterns of hobbies and preferences. The conversation unit conducts a pseudo-conversation based on the information learned by the learning unit. For example, when a family member or friend speaks to the conversation unit, the conversation unit responds by reproducing the tone and manner of speech of the person. For example, the conversation unit can reproduce the voice of the person using a voice synthesis technology. The conversation unit can also generate the contents of the conversation using a natural language processing technology. In this way, the personality reproduction system according to the embodiment can enjoy a conversation with the person even after the person has passed away. A part or all of the above-mentioned processing in the conversation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversation unit can conduct a conversation using an AI model that receives the contents of a conversation by a family member or friend and responds by reproducing the tone and manner of speech of the person.

[0030] The collection unit collects personality information such as conversation data, behavioral patterns, and hobbies and preferences from the person's lifetime. Specifically, the conversation data from the person's lifetime includes voice data and text data, which are collected from conversations at home, conversations at work, and SNS posts. For example, conversations at home are collected through microphones and smart speakers installed in the home, and conversations at work are collected from communication tools and recording data of meetings at the workplace. SNS posts are collected from posts and messages published by users. The behavioral patterns include daily movement history and activity logs, which are collected from GPS data and fitness tracker data of a smartphone. For example, the GPS data of a smartphone is used to record the places visited by the user and the route of movement, and the fitness tracker data is used to grasp the user's exercise habits and activity level. The hobbies and preferences include music preferences and sports preferences, which are collected from the playback history of a music streaming service and the participation history of sporting events. For example, the playback history of a music streaming service is analyzed to identify the music genres and artists that the user prefers, and the sports and activities in which the user is interested are grasped based on the participation history of sporting events. This allows the collection department to collect a wide range of personality information from various data sources and build a detailed profile of the person. Furthermore, the collection department can centrally manage these data and link them with other systems and departments as necessary. For example, the collected data is stored on a cloud server and made accessible to the learning department and conversation department. In addition, by adjusting the frequency and accuracy of data collection, flexible responses according to specific situations and conditions are possible. This allows the collection department to collect data efficiently and effectively and improve the performance of the entire system.

[0031] The learning unit learns the information collected by the collection unit and reproduces the personality of the person. Specifically, a machine learning algorithm is used to learn the tone of speech, speech style, and hobbies and preferences based on the collected information. For example, to learn the characteristics of the tone of speech and speech style, natural language processing technology is used to analyze text data, and voice recognition technology is applied using voice data. This makes it possible to extract the person's frequently used phrases, unique expressions, and tone and rhythm of voice. To learn the patterns of hobbies and preferences, the collected music playback history and sports participation history are analyzed to identify the user's preferences and interests. For example, the music playback history is classified using a clustering algorithm to identify the music genres and artists that the user prefers. In addition, the sports participation history is analyzed to understand the sporting events and activities that the user regularly participates in. The learning unit integrates these pieces of information to build a model for reproducing the person's personality. For example, a recurrent neural network (RNN) or a transformer model using deep learning is used to train a model that understands the flow and context of a conversation and generates natural responses. In addition, the learning unit can continually retrain the model as the collected data updates to reflect the latest information, allowing the learning unit to accurately recreate the person's personality and adapt in real time.

[0032] The conversation unit has a pseudo-conversation based on the information learned by the learning unit. Specifically, when a family member or friend speaks to the user, the conversation unit responds by reproducing the tone and manner of speech of the person. For example, the conversation unit can reproduce the voice of the person using voice synthesis technology. Text-to-speech (TTS) technology is used for the voice synthesis technology, and the characteristics of the person's voice are reproduced based on the voice data learned by the learning unit. Furthermore, the conversation unit generates the content of the conversation using natural language processing technology. For example, the content spoken by the family member or friend is received as input, the content is analyzed using natural language understanding (NLU) technology, and an appropriate response is generated. The generated response is output as a voice using voice synthesis technology. This allows the conversation unit to realize a natural conversation with the family member or friend. Furthermore, the conversation unit can understand the context of the conversation and respond at an appropriate time. For example, a more natural conversation is realized by analyzing the flow of the conversation and incorporating appropriate intervals and emotional expressions. Furthermore, the conversation unit can collect user feedback and continuously improve the quality of the conversation. For example, the content of the response and the quality of the voice can be adjusted based on the feedback provided by the user to provide a more satisfying conversation experience. This allows the conversation unit to reproduce the personality of the person based on the information learned by the learning unit, enabling natural conversations with family and friends.

[0033] The collection unit can collect information on daily conversations, SNS posts, and hobbies. The collection unit, for example, collects daily conversations. For example, it can collect conversations at home, conversations at work, and the like. The collection unit can also collect SNS posts. For example, it can collect SNS post contents, comments, the number of likes, and the like. Furthermore, the collection unit can also collect information on hobbies. For example, it can collect blog articles and forum posts related to hobbies. As a result, by collecting information on daily conversations, SNS posts, and hobbies, more detailed personality information can be obtained. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the SNS post contents into AI and have the AI ​​execute analysis of the post contents.

[0034] The learning unit can learn the tone of speech, speech style, and hobbies and preferences based on the collected information. The learning unit, for example, learns the collected tone of speech and speech style. For example, it can learn speech characteristics, intonation, speaking speed, and word choice. The learning unit can also learn the collected hobbies and preferences. For example, it can learn favorite music genres, favorite movies, and sports hobbies. As a result, by learning the tone of speech, speech style, and hobbies and preferences based on the collected information, it is possible to reproduce a more natural conversation. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the collected conversation data into AI and cause AI to learn the tone of speech and speech style.

[0035] When a family member or friend speaks to the conversation unit, the conversation unit can respond by reproducing the person's tone and manner of speech. For example, when a family member or friend speaks to the conversation unit, the conversation unit responds by reproducing the person's tone and manner of speech. For example, the conversation unit can reproduce the person's voice using voice synthesis technology. The conversation unit can also generate the content of the conversation using natural language processing technology. As a result, when a family member or friend speaks to the conversation unit, the conversation unit can enjoy a conversation with the person even after the person has passed away by reproducing the person's tone and manner of speech in response. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can input the content spoken to by the family member or friend into AI and have a conversation using an AI model that reproduces the person's tone and manner of speech and responds.

[0036] The collection unit can select an appropriate data collection method based on the user's living environment and daily behavior patterns at the time of collection. The collection unit selects the optimal data collection method, for example, by taking into consideration the user's living environment and daily behavior patterns. For example, if the user spends a lot of time at home, the collection unit focuses on collecting conversations and behavior patterns at home. If the user goes out a lot, the collection unit can also collect behavior patterns and conversations while out. If the user spends a lot of time at work, the collection unit can also collect conversations and behavior patterns at work. This allows for more effective data collection by selecting the optimal data collection method by taking into consideration the user's living environment and daily behavior patterns. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's living environment data into AI and cause AI to select the optimal data collection method.

[0037] The collection unit can identify important events and anniversaries of the user's past at the time of collection, and collect data related thereto with priority. The collection unit, for example, identifies important events and anniversaries of the user's past, and collects data related thereto with priority. For example, data on conversations and events related to the user's birthday is collected. Data on conversations and events related to the user's wedding anniversary can also be collected. Data on important events related to the family, such as the birthdays and graduation ceremonies of the user's children, can also be collected. This allows more meaningful data to be collected by identifying important events and anniversaries of the user's past and collecting data related thereto with priority. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's past event data into AI, and cause AI to execute collection of related data.

[0038] The collection unit can preferentially collect highly relevant data based on the geographical location information of the user at the time of collection. The collection unit, for example, preferentially collects highly relevant data taking into account the geographical location information of the user. For example, when the user is traveling, conversations and behavior patterns at the travel destination are collected. In addition, when the user lives in a specific area, conversations and behavior patterns related to the area can also be collected. In addition, when the user frequently visits a specific place, conversations and behavior patterns at the place can also be collected. As a result, more appropriate data can be collected by preferentially collecting highly relevant data taking into account the geographical location information of the user. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the geographical location information of the user to AI and cause the AI ​​to collect highly relevant data.

[0039] The collection unit can analyze the user's social media activity and collect related data at the time of collection. The collection unit, for example, analyzes the user's social media activity and collects related data. For example, it collects the contents of social media that the user frequently posts. It can also collect posts that the user likes or comments on. It can also collect information on accounts and groups that the user follows. In this way, by analyzing the user's social media activity and collecting related data, more detailed personality information can be obtained. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's social media data into AI and have the AI ​​execute the collection of related data.

[0040] The learning unit can adjust the level of detail of the learning based on the importance of the collected data during learning. The learning unit, for example, adjusts the level of detail of the learning based on the importance of the collected data. For example, data related to important events and anniversaries is preferentially learned. Data related to the user's hobbies and preferences can also be learned in detail. Data related to the user's daily behavioral patterns can also be learned in detail. This allows for more effective learning by adjusting the level of detail of the learning based on the importance of the collected data. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the collected data to AI and cause the AI ​​to adjust the level of detail of the learning.

[0041] The learning unit can apply different learning algorithms according to different aspects of the user's personality during learning. The learning unit applies different learning algorithms according to different aspects of the user's personality, for example. For example, different learning algorithms are applied according to the user's tone of voice and speaking style. Different learning algorithms can also be applied according to the user's hobbies and preferences. Different learning algorithms can also be applied according to the user's behavioral patterns. This allows for more accurate learning by applying different learning algorithms according to different aspects of the user's personality. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI or may be performed without using AI. For example, the learning unit can input the user's personality data into AI and cause the AI ​​to apply different learning algorithms.

[0042] The learning unit can weight the learning based on the submission time of the collected data during learning. The learning unit weights the learning based on the submission time of the collected data, for example. For example, the learning unit preferentially learns recently collected data. In addition, data related to important events and anniversaries can be preferentially learned. In addition, data related to the user's hobbies and preferences can be learned in detail. As a result, more effective learning is possible by weighting the learning based on the submission time of the collected data. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the collected data to an AI and cause the AI ​​to perform the weighting of the learning.

[0043] The learning unit can improve the accuracy of learning by referring to the user's related literature and past history during learning. The learning unit improves the accuracy of learning, for example, by referring to the user's related literature and past history. For example, the learning unit learns by referring to books and articles that the user has read in the past. The learning unit can also learn by referring to events and activities that the user has participated in in the past. The learning unit can also learn by referring to trips that the user has taken in the past and places that the user has visited. This allows for more accurate learning by improving the accuracy of learning by referring to the user's related literature and past history. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's past history data into AI and cause AI to improve the accuracy of learning.

[0044] The conversation unit can generate an optimal response by referring to the user's past conversation history during a conversation. The conversation unit, for example, generates an optimal response by referring to the user's past conversation history during a conversation. For example, based on the content that the user has talked about in the past, related topics are provided. The conversation can also be advanced based on topics that the user has shown interest in in the past. An appropriate response can also be generated based on topics that the user has avoided in the past. This allows for a more natural conversation by generating an optimal response by referring to the user's past conversation history. A part or all of the above-mentioned processing in the conversation unit may be performed, for example, using AI, or may be performed without using AI. For example, the conversation unit can input the user's past conversation history into AI and cause the AI ​​to generate an optimal response.

[0045] The conversation unit can customize the content of the conversation based on the user's current situation and environment during the conversation. The conversation unit customizes the content of the conversation based on the user's current situation and environment during the conversation, for example. For example, when the user is at home, the conversation unit provides topics about the home. When the user is out, the conversation unit can provide topics about the outside. When the user is at work, the conversation unit can provide topics about the workplace. This enables a more appropriate conversation by customizing the content of the conversation based on the user's current situation and environment. A part or all of the above-mentioned processing in the conversation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversation unit can input the user's current situation data into the AI ​​and have the AI ​​execute the customization of the content of the conversation.

[0046] The conversation unit can provide appropriate conversation content based on the geographical location information of the user during conversation. The conversation unit, for example, provides optimal conversation content taking into account the geographical location information of the user during conversation. For example, when the user is traveling, the conversation unit provides topics at the travel destination. Also, when the user lives in a specific area, the conversation unit can provide topics related to the area. Also, when the user frequently visits a specific place, the conversation unit can provide topics at the place. This allows for more relevant conversation by providing optimal conversation content taking into account the geographical location information of the user. Part or all of the above-mentioned processing in the conversation unit may be performed, for example, using AI or may be performed without using AI. For example, the conversation unit can input the geographical location information of the user to AI and cause the AI ​​to provide appropriate conversation content.

[0047] The conversation unit can generate related conversation content by analyzing the user's social media activity during the conversation. The conversation unit, for example, generates related conversation content by analyzing the user's social media activity during the conversation. For example, the conversation unit provides related topics based on the content recently posted by the user. The conversation can also be advanced based on posts that the user has liked or commented on. Appropriate topics can also be provided based on information on accounts and groups that the user follows. This enables more detailed conversation by analyzing the user's social media activity and generating related conversation content. Part or all of the above-mentioned processing in the conversation unit may be performed, for example, using AI, or may be performed without using AI. For example, the conversation unit can input the user's social media data into AI and cause the AI ​​to generate related conversation content.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The collection unit can dynamically adjust the type and frequency of data to be collected based on the user's living environment and daily behavioral patterns. For example, if the user spends a lot of time at home, the collection unit can focus on conversations and behavioral patterns at home. If the user goes out a lot, the collection unit can also collect behavioral patterns and conversations while out. Furthermore, if the user spends a lot of time at work, the collection unit can also collect conversations and behavioral patterns at work. This makes it possible to collect optimal data according to the user's living environment and behavioral patterns, and obtain more detailed personality information.

[0050] The learning unit can adjust the level of detail of the learning based on the importance of the collected data. For example, data related to important events and anniversaries is preferentially learned. Data related to the user's hobbies and preferences can also be learned in detail. Furthermore, data related to the user's daily behavioral patterns can also be learned in detail. This allows for more effective learning by adjusting the level of detail of the learning based on the importance of the collected data.

[0051] The conversation unit can generate an optimal response by referring to the user's past conversation history. For example, it can provide related topics based on the content of past conversations by the user. It can also advance the conversation based on topics that the user has shown interest in in the past. It can also generate an appropriate response based on topics that the user has avoided in the past. This allows for a more natural conversation by generating an optimal response by referring to the user's past conversation history.

[0052] The collection unit can identify important events and anniversaries of the user's past and collect data related thereto with priority. For example, data on conversations and events related to the user's birthday can be collected. Data on conversations and events related to the user's wedding anniversary can also be collected. Furthermore, data on important events related to the family, such as the birthdays and graduation ceremonies of the user's children, can also be collected. In this way, by identifying important events and anniversaries of the user's past and collecting data related thereto with priority, more meaningful data can be collected.

[0053] The conversation unit can customize the content of the conversation based on the user's current situation and environment during the conversation. For example, when the user is at home, the conversation unit can provide topics about the home. When the user is out, the conversation unit can provide topics about the outside. When the user is at work, the conversation unit can provide topics about the workplace. This allows for more appropriate conversation by customizing the content of the conversation based on the user's current situation and environment.

[0054] The process flow of the first embodiment will be briefly described below.

[0055] Step 1: The collection unit collects personality information such as conversation data, behavioral patterns, hobbies, and preferences from the time of death. For example, information on daily conversations, SNS posts, and hobbies is collected. Specifically, this includes conversations at home, conversations at work, SNS posts, daily movement history, activity logs, music preferences, sports hobbies, etc. Step 2: The learning unit learns the information collected by the collection unit and recreates the person's personality. For example, it uses machine learning algorithms to learn the person's tone of voice, speaking style, and hobbies and preferences. Step 3: The conversation unit conducts a simulated conversation based on the information learned by the learning unit. For example, when a family member or friend speaks to the robot, the robot responds by reproducing that person's tone and manner of speaking. The robot can generate the person's voice and conversation content using speech synthesis technology and natural language processing technology.

[0056] (Example 2) The personality reproduction system according to the embodiment of the present invention is a system that collects personality information such as conversation data, behavior patterns, and hobbies and preferences of a person before death, makes AI learn the collected information, and conducts a simulated conversation even after the person dies. This personality reproduction system collects personality information such as conversation data, behavior patterns, and hobbies and preferences of a person before death, and makes AI learn the collected information. The AI ​​reproduces the personality of the person based on the learned information. Finally, the AI ​​conducts a simulated conversation even after the person dies. For example, when a family member or friend talks to the AI, the AI ​​responds by reproducing the tone and manner of speech of the person. This system allows you to enjoy a conversation with the person even after they die. For example, as a collection unit, it collects personality information such as conversation data, behavior patterns, and hobbies and preferences before death. For example, it collects daily conversations, SNS posts, and information about hobbies. Next, as a learning unit, it makes the AI ​​learn the collected information. The AI ​​reproduces the personality of the person based on the collected information. For example, it learns a person's tone of voice, speaking style, hobbies, and preferences. Finally, as the conversation section, the AI ​​simulates a conversation. For example, when a family member or friend speaks to the AI, the AI ​​responds by recreating that person's tone of voice and speaking style. This system allows you to enjoy conversations with that person even after they have passed away. This personality reproduction system allows you to enjoy conversations with that person even after they have passed away.

[0057] The personality reproduction system according to the embodiment includes a collection unit, a learning unit, and a conversation unit. The collection unit collects personality information such as conversation data, behavioral patterns, and hobbies and preferences from the person's lifetime. The conversation data from the person's lifetime includes, for example, voice data, text data, and the like, but is not limited to such examples. The collection unit collects, for example, information on daily conversations, SNS posts, and hobbies. For example, conversations at home, conversations at work, and SNS post contents can be collected. The behavioral patterns include, for example, daily movement history, activity logs, and the like, but are not limited to such examples. The hobbies and preferences include, for example, music preferences, sports hobbies, and the like, but are not limited to such examples. The learning unit learns the information collected by the collection unit and reproduces the personality of the person. The learning unit learns the tone of speech, speaking style, and hobbies and preferences based on the collected information, for example, using a machine learning algorithm. For example, the learning unit can learn the characteristics of the tone of speech and speaking style, and patterns of hobbies and preferences. The conversation unit conducts a pseudo-conversation based on the information learned by the learning unit. For example, when a family member or friend speaks to the conversation unit, the conversation unit responds by reproducing the tone and manner of speech of the person. For example, the conversation unit can reproduce the voice of the person using a voice synthesis technology. The conversation unit can also generate the contents of the conversation using a natural language processing technology. In this way, the personality reproduction system according to the embodiment can enjoy a conversation with the person even after the person has passed away. A part or all of the above-mentioned processing in the conversation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversation unit can conduct a conversation using an AI model that receives the contents of a conversation by a family member or friend and responds by reproducing the tone and manner of speech of the person.

[0058] The collection unit collects personality information such as conversation data, behavioral patterns, and hobbies and preferences from the person's lifetime. Specifically, the conversation data from the person's lifetime includes voice data and text data, which are collected from conversations at home, conversations at work, and SNS posts. For example, conversations at home are collected through microphones and smart speakers installed in the home, and conversations at work are collected from communication tools and recording data of meetings at the workplace. SNS posts are collected from posts and messages published by users. The behavioral patterns include daily movement history and activity logs, which are collected from GPS data and fitness tracker data of a smartphone. For example, the GPS data of a smartphone is used to record the places visited by the user and the route of movement, and the fitness tracker data is used to grasp the user's exercise habits and activity level. The hobbies and preferences include music preferences and sports preferences, which are collected from the playback history of a music streaming service and the participation history of sporting events. For example, the playback history of a music streaming service is analyzed to identify the music genres and artists that the user prefers, and the sports and activities in which the user is interested are grasped based on the participation history of sporting events. This allows the collection department to collect a wide range of personality information from various data sources and build a detailed profile of the person. Furthermore, the collection department can centrally manage these data and link them with other systems and departments as necessary. For example, the collected data is stored on a cloud server and made accessible to the learning department and conversation department. In addition, by adjusting the frequency and accuracy of data collection, flexible responses according to specific situations and conditions are possible. This allows the collection department to collect data efficiently and effectively and improve the performance of the entire system.

[0059] The learning unit learns the information collected by the collection unit and reproduces the personality of the person. Specifically, a machine learning algorithm is used to learn the tone of speech, speech style, and hobbies and preferences based on the collected information. For example, to learn the characteristics of the tone of speech and speech style, natural language processing technology is used to analyze text data, and voice recognition technology is applied using voice data. This makes it possible to extract the person's frequently used phrases, unique expressions, and tone and rhythm of voice. To learn the patterns of hobbies and preferences, the collected music playback history and sports participation history are analyzed to identify the user's preferences and interests. For example, the music playback history is classified using a clustering algorithm to identify the music genres and artists that the user prefers. In addition, the sports participation history is analyzed to understand the sporting events and activities that the user regularly participates in. The learning unit integrates these pieces of information to build a model for reproducing the person's personality. For example, a recurrent neural network (RNN) or a transformer model using deep learning is used to train a model that understands the flow and context of a conversation and generates natural responses. In addition, the learning unit can continually retrain the model as the collected data updates to reflect the latest information, allowing the learning unit to accurately recreate the person's personality and adapt in real time.

[0060] The conversation unit has a pseudo-conversation based on the information learned by the learning unit. Specifically, when a family member or friend speaks to the user, the conversation unit responds by reproducing the tone and manner of speech of the person. For example, the conversation unit can reproduce the voice of the person using voice synthesis technology. Text-to-speech (TTS) technology is used for the voice synthesis technology, and the characteristics of the person's voice are reproduced based on the voice data learned by the learning unit. Furthermore, the conversation unit generates the content of the conversation using natural language processing technology. For example, the content spoken by the family member or friend is received as input, the content is analyzed using natural language understanding (NLU) technology, and an appropriate response is generated. The generated response is output as a voice using voice synthesis technology. This allows the conversation unit to realize a natural conversation with the family member or friend. Furthermore, the conversation unit can understand the context of the conversation and respond at an appropriate time. For example, a more natural conversation is realized by analyzing the flow of the conversation and incorporating appropriate intervals and emotional expressions. Furthermore, the conversation unit can collect user feedback and continuously improve the quality of the conversation. For example, the content of the response and the quality of the voice can be adjusted based on the feedback provided by the user to provide a more satisfying conversation experience. This allows the conversation unit to reproduce the personality of the person based on the information learned by the learning unit, enabling natural conversations with family and friends.

[0061] The collection unit can collect information on daily conversations, SNS posts, and hobbies. The collection unit, for example, collects daily conversations. For example, it can collect conversations at home, conversations at work, and the like. The collection unit can also collect SNS posts. For example, it can collect SNS post contents, comments, the number of likes, and the like. Furthermore, the collection unit can also collect information on hobbies. For example, it can collect blog articles and forum posts related to hobbies. As a result, by collecting information on daily conversations, SNS posts, and hobbies, more detailed personality information can be obtained. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the SNS post contents into AI and have the AI ​​execute analysis of the post contents.

[0062] The learning unit can learn the tone of speech, speech style, and hobbies and preferences based on the collected information. The learning unit, for example, learns the collected tone of speech and speech style. For example, it can learn speech characteristics, intonation, speaking speed, and word choice. The learning unit can also learn the collected hobbies and preferences. For example, it can learn favorite music genres, favorite movies, and sports hobbies. As a result, by learning the tone of speech, speech style, and hobbies and preferences based on the collected information, it is possible to reproduce a more natural conversation. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the collected conversation data into AI and cause AI to learn the tone of speech and speech style.

[0063] When a family member or friend speaks to the conversation unit, the conversation unit can respond by reproducing the person's tone and manner of speech. For example, when a family member or friend speaks to the conversation unit, the conversation unit responds by reproducing the person's tone and manner of speech. For example, the conversation unit can reproduce the person's voice using voice synthesis technology. The conversation unit can also generate the content of the conversation using natural language processing technology. As a result, when a family member or friend speaks to the conversation unit, the conversation unit can enjoy a conversation with the person even after the person has passed away by reproducing the person's tone and manner of speech in response. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can input the content spoken to by the family member or friend into AI and have a conversation using an AI model that reproduces the person's tone and manner of speech and responds.

[0064] The collection unit can estimate the user's emotion and adjust the type of data to be collected based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and adjusts the type of data to be collected based on the estimated user's emotion. For example, if the user is sad, the emotion engine estimates it and preferentially collects data related to comforting words and memories. Also, if the user is happy, the emotion engine can estimate it and preferentially collect data related to fun events and hobbies. Also, if the user is stressed, the emotion engine can estimate it and preferentially collect data related to topics and hobbies that can relax. In this way, by adjusting the type of data to be collected based on the user's emotion, more appropriate data can be collected. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to an AI and cause the AI ​​to adjust the type of data to be collected.

[0065] The collection unit can select an appropriate data collection method based on the user's living environment and daily behavior patterns at the time of collection. The collection unit selects the optimal data collection method, for example, by taking into consideration the user's living environment and daily behavior patterns. For example, if the user spends a lot of time at home, the collection unit focuses on collecting conversations and behavior patterns at home. If the user goes out a lot, the collection unit can also collect behavior patterns and conversations while out. If the user spends a lot of time at work, the collection unit can also collect conversations and behavior patterns at work. This allows for more effective data collection by selecting the optimal data collection method by taking into consideration the user's living environment and daily behavior patterns. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's living environment data into AI and cause AI to select the optimal data collection method.

[0066] The collection unit can identify important events and anniversaries of the user's past at the time of collection, and collect data related thereto with priority. The collection unit, for example, identifies important events and anniversaries of the user's past, and collects data related thereto with priority. For example, data on conversations and events related to the user's birthday is collected. Data on conversations and events related to the user's wedding anniversary can also be collected. Data on important events related to the family, such as the birthdays and graduation ceremonies of the user's children, can also be collected. This allows more meaningful data to be collected by identifying important events and anniversaries of the user's past and collecting data related thereto with priority. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's past event data into AI, and cause AI to execute collection of related data.

[0067] The collection unit can estimate the user's emotion and determine the priority of data to be collected based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and determines the priority of data to be collected based on the estimated user's emotion. For example, if the user is sad, the emotion engine estimates and preferentially collects data related to comforting words and memories. Also, if the user is happy, the emotion engine can estimate and preferentially collect data related to fun events and hobbies. Also, if the user is stressed, the emotion engine can estimate and preferentially collect data related to topics and hobbies that can relax. In this way, by determining the priority of data to be collected based on the user's emotion, more important data can be preferentially collected. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input a user's emotional data into the AI ​​and have the AI ​​decide the priorities of the data to be collected.

[0068] The collection unit can preferentially collect highly relevant data based on the geographical location information of the user at the time of collection. The collection unit, for example, preferentially collects highly relevant data taking into account the geographical location information of the user. For example, when the user is traveling, conversations and behavior patterns at the travel destination are collected. In addition, when the user lives in a specific area, conversations and behavior patterns related to the area can also be collected. In addition, when the user frequently visits a specific place, conversations and behavior patterns at the place can also be collected. As a result, more appropriate data can be collected by preferentially collecting highly relevant data taking into account the geographical location information of the user. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the geographical location information of the user to AI and cause the AI ​​to collect highly relevant data.

[0069] The collection unit can analyze the user's social media activity and collect related data at the time of collection. The collection unit, for example, analyzes the user's social media activity and collects related data. For example, it collects the contents of social media that the user frequently posts. It can also collect posts that the user likes or comments on. It can also collect information on accounts and groups that the user follows. In this way, by analyzing the user's social media activity and collecting related data, more detailed personality information can be obtained. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's social media data into AI and have the AI ​​execute the collection of related data.

[0070] The learning unit can estimate the user's emotions and adjust the learning algorithm based on the estimated user's emotions. The learning unit, for example, estimates the user's emotions and adjusts the learning algorithm based on the estimated user's emotions. For example, if the user is sad, the emotion engine estimates the emotions and preferentially learns data related to comforting words and memories. Also, if the user is happy, the emotion engine can estimate the emotions and preferentially learn data related to fun events and hobbies. Also, if the user is stressed, the emotion engine can estimate the emotions and preferentially learn data related to topics and hobbies that can relax. This allows for more appropriate learning by adjusting the learning algorithm based on the user's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's emotion data to the AI ​​and cause the AI ​​to adjust the learning algorithm.

[0071] The learning unit can adjust the level of detail of the learning based on the importance of the collected data during learning. The learning unit, for example, adjusts the level of detail of the learning based on the importance of the collected data. For example, data related to important events and anniversaries is preferentially learned. Data related to the user's hobbies and preferences can also be learned in detail. Data related to the user's daily behavioral patterns can also be learned in detail. This allows for more effective learning by adjusting the level of detail of the learning based on the importance of the collected data. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the collected data to AI and cause the AI ​​to adjust the level of detail of the learning.

[0072] The learning unit can apply different learning algorithms according to different aspects of the user's personality during learning. The learning unit applies different learning algorithms according to different aspects of the user's personality, for example. For example, different learning algorithms are applied according to the user's tone of voice and speaking style. Different learning algorithms can also be applied according to the user's hobbies and preferences. Different learning algorithms can also be applied according to the user's behavioral patterns. This allows for more accurate learning by applying different learning algorithms according to different aspects of the user's personality. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI or may be performed without using AI. For example, the learning unit can input the user's personality data into AI and cause the AI ​​to apply different learning algorithms.

[0073] The learning unit can estimate the user's emotions and determine the learning priority based on the estimated user's emotions. The learning unit, for example, estimates the user's emotions and determines the learning priority based on the estimated user's emotions. For example, if the user is sad, the emotion engine estimates the emotions and preferentially learns data related to comforting words and memories. Also, if the user is happy, the emotion engine can estimate the emotions and preferentially learn data related to fun events and hobbies. Also, if the user is stressed, the emotion engine can estimate the emotions and preferentially learn data related to topics and hobbies that can relax. In this way, by determining the learning priority based on the user's emotions, more important data can be preferentially learned. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's emotion data to an AI and cause the AI ​​to execute the determination of the learning priority.

[0074] The learning unit can weight the learning based on the submission time of the collected data during learning. The learning unit weights the learning based on the submission time of the collected data, for example. For example, the learning unit preferentially learns recently collected data. In addition, data related to important events and anniversaries can be preferentially learned. In addition, data related to the user's hobbies and preferences can be learned in detail. As a result, more effective learning is possible by weighting the learning based on the submission time of the collected data. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the collected data to an AI and cause the AI ​​to perform the weighting of the learning.

[0075] The learning unit can improve the accuracy of learning by referring to the user's related literature and past history during learning. The learning unit improves the accuracy of learning, for example, by referring to the user's related literature and past history. For example, the learning unit learns by referring to books and articles that the user has read in the past. The learning unit can also learn by referring to events and activities that the user has participated in in the past. The learning unit can also learn by referring to trips that the user has taken in the past and places that the user has visited. This allows for more accurate learning by improving the accuracy of learning by referring to the user's related literature and past history. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's past history data into AI and cause AI to improve the accuracy of learning.

[0076] The conversation unit can estimate the user's emotion and adjust the tone and content of the conversation based on the estimated user's emotion. The conversation unit, for example, estimates the user's emotion and adjusts the tone and content of the conversation based on the estimated user's emotion. For example, if the user is sad, the emotion engine estimates it and a conversation about comforting words and memories can be held. Also, if the user is happy, the emotion engine can estimate it and a conversation about happy events and hobbies can be held. Also, if the user is stressed, the emotion engine can estimate it and a conversation about relaxing topics and hobbies can be held. This allows for a more appropriate conversation by adjusting the tone and content of the conversation based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the conversation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversation unit can input the user's emotion data into the AI ​​and cause the AI ​​to adjust the tone and content of the conversation.

[0077] The conversation unit can generate an optimal response by referring to the user's past conversation history during a conversation. The conversation unit, for example, generates an optimal response by referring to the user's past conversation history during a conversation. For example, based on the content that the user has talked about in the past, related topics are provided. The conversation can also be advanced based on topics that the user has shown interest in in the past. An appropriate response can also be generated based on topics that the user has avoided in the past. This allows for a more natural conversation by generating an optimal response by referring to the user's past conversation history. A part or all of the above-mentioned processing in the conversation unit may be performed, for example, using AI, or may be performed without using AI. For example, the conversation unit can input the user's past conversation history into AI and cause the AI ​​to generate an optimal response.

[0078] The conversation unit can customize the content of the conversation based on the user's current situation and environment during the conversation. The conversation unit customizes the content of the conversation based on the user's current situation and environment during the conversation, for example. For example, when the user is at home, the conversation unit provides topics about the home. When the user is out, the conversation unit can provide topics about the outside. When the user is at work, the conversation unit can provide topics about the workplace. This enables a more appropriate conversation by customizing the content of the conversation based on the user's current situation and environment. A part or all of the above-mentioned processing in the conversation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversation unit can input the user's current situation data into the AI ​​and have the AI ​​execute the customization of the content of the conversation.

[0079] The conversation unit can estimate the user's emotion and determine the priority of the conversation based on the estimated user's emotion. The conversation unit, for example, estimates the user's emotion and determines the priority of the conversation based on the estimated user's emotion. For example, if the user is sad, the emotion engine estimates it and prioritizes conversations about comforting words and memories. Also, if the user is happy, the emotion engine can estimate it and prioritize conversations about happy events and hobbies. Also, if the user is stressed, the emotion engine can estimate it and prioritize conversations about relaxing topics and hobbies. In this way, by determining the priority of the conversation based on the user's emotion, it is possible to prioritize more important conversations. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the conversation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversation unit can input the user's emotional data into the AI ​​and have the AI ​​decide the priorities of the conversation.

[0080] The conversation unit can provide appropriate conversation content based on the geographical location information of the user during conversation. The conversation unit, for example, provides optimal conversation content taking into account the geographical location information of the user during conversation. For example, when the user is traveling, the conversation unit provides topics at the travel destination. Also, when the user lives in a specific area, the conversation unit can provide topics related to the area. Also, when the user frequently visits a specific place, the conversation unit can provide topics at the place. This allows for more relevant conversation by providing optimal conversation content taking into account the geographical location information of the user. Part or all of the above-mentioned processing in the conversation unit may be performed, for example, using AI or may be performed without using AI. For example, the conversation unit can input the geographical location information of the user to AI and cause the AI ​​to provide appropriate conversation content.

[0081] The conversation unit can generate related conversation content by analyzing the user's social media activity during the conversation. The conversation unit, for example, generates related conversation content by analyzing the user's social media activity during the conversation. For example, the conversation unit provides related topics based on the content recently posted by the user. The conversation can also be advanced based on posts that the user has liked or commented on. Appropriate topics can also be provided based on information on accounts and groups that the user follows. This enables more detailed conversation by analyzing the user's social media activity and generating related conversation content. Part or all of the above-mentioned processing in the conversation unit may be performed, for example, using AI, or may be performed without using AI. For example, the conversation unit can input the user's social media data into AI and cause the AI ​​to generate related conversation content.

[0082] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0083] The personality reproduction system may further include an emotion estimation unit. The emotion estimation unit may estimate the user's emotion in real time and adjust the content and tone of the conversation based on the estimated emotion. For example, if the user is sad, the emotion estimation unit may preferentially generate a conversation about comforting words or memories. If the user is happy, the emotion estimation unit may provide a conversation about happy events or hobbies. Furthermore, if the user is stressed, the emotion estimation unit may also generate a conversation about relaxing topics or hobbies. This enables an appropriate conversation according to the user's emotion, realizing a more natural and friendly dialogue.

[0084] The collection unit can dynamically adjust the type and frequency of data to be collected based on the user's living environment and daily behavioral patterns. For example, if the user spends a lot of time at home, the collection unit can focus on conversations and behavioral patterns at home. If the user goes out a lot, the collection unit can also collect behavioral patterns and conversations while out. Furthermore, if the user spends a lot of time at work, the collection unit can also collect conversations and behavioral patterns at work. This makes it possible to collect optimal data according to the user's living environment and behavioral patterns, and obtain more detailed personality information.

[0085] The learning unit can adjust the level of detail of the learning based on the importance of the collected data. For example, data related to important events and anniversaries is preferentially learned. Data related to the user's hobbies and preferences can also be learned in detail. Furthermore, data related to the user's daily behavioral patterns can also be learned in detail. This allows for more effective learning by adjusting the level of detail of the learning based on the importance of the collected data.

[0086] The conversation unit can generate an optimal response by referring to the user's past conversation history. For example, it can provide related topics based on the content of past conversations by the user. It can also advance the conversation based on topics that the user has shown interest in in the past. It can also generate an appropriate response based on topics that the user has avoided in the past. This allows for a more natural conversation by generating an optimal response by referring to the user's past conversation history.

[0087] The collection unit can estimate the user's emotion and adjust the type of data to be collected based on the estimated user's emotion. For example, if the user is sad, the emotion engine can estimate and preferentially collect data related to comforting words and memories. Also, if the user is happy, the emotion engine can estimate and preferentially collect data related to happy events and hobbies. Furthermore, if the user is stressed, the emotion engine can estimate and preferentially collect data related to relaxing topics and hobbies. In this way, by adjusting the type of data to be collected based on the user's emotion, more appropriate data can be collected.

[0088] The collection unit can identify important events and anniversaries of the user's past and collect data related thereto with priority. For example, data on conversations and events related to the user's birthday can be collected. Data on conversations and events related to the user's wedding anniversary can also be collected. Furthermore, data on important events related to the family, such as the birthdays and graduation ceremonies of the user's children, can also be collected. In this way, by identifying important events and anniversaries of the user's past and collecting data related thereto with priority, more meaningful data can be collected.

[0089] The learning unit can estimate the user's emotions and adjust the learning algorithm based on the estimated user's emotions. For example, if the user is sad, the emotion engine can estimate the user's emotions and prioritize learning data related to comforting words and memories. Also, if the user is happy, the emotion engine can estimate the user's emotions and prioritize learning data related to happy events and hobbies. Furthermore, if the user is stressed, the emotion engine can estimate the user's emotions and prioritize learning data related to relaxing topics and hobbies. This allows for more appropriate learning by adjusting the learning algorithm based on the user's emotions.

[0090] The conversation unit can estimate the user's emotions and adjust the tone and content of the conversation based on the estimated user's emotions. For example, if the user is sad, the emotion engine can estimate the emotion and hold a conversation about words of comfort and memories. If the user is happy, the emotion engine can estimate the emotion and hold a conversation about happy events and hobbies. Furthermore, if the user is stressed, the emotion engine can estimate the emotion and hold a conversation about relaxing topics and hobbies. This allows for more appropriate conversation by adjusting the tone and content of the conversation based on the user's emotions.

[0091] The conversation unit can customize the content of the conversation based on the user's current situation and environment during the conversation. For example, when the user is at home, the conversation unit can provide topics about the home. When the user is out, the conversation unit can provide topics about the outside. When the user is at work, the conversation unit can provide topics about the workplace. This allows for more appropriate conversation by customizing the content of the conversation based on the user's current situation and environment.

[0092] The conversation unit can estimate the user's emotions and determine the priority of conversations based on the estimated user's emotions. For example, if the user is sad, the emotion engine can estimate the emotion and prioritize conversations about words of comfort and memories. Also, if the user is happy, the emotion engine can estimate the emotion and prioritize conversations about happy events and hobbies. Furthermore, if the user is stressed, the emotion engine can estimate the emotion and prioritize conversations about relaxing topics and hobbies. In this way, by determining the priority of conversations based on the user's emotions, more important conversations can be prioritized.

[0093] The process flow of the second embodiment will be briefly described below.

[0094] Step 1: The collection unit collects personality information such as conversation data, behavioral patterns, hobbies, and preferences from the time of death. For example, information on daily conversations, SNS posts, and hobbies is collected. Specifically, this includes conversations at home, conversations at work, SNS posts, daily movement history, activity logs, music preferences, sports hobbies, etc. Step 2: The learning unit learns the information collected by the collection unit and recreates the person's personality. For example, it uses machine learning algorithms to learn the person's tone of voice, speaking style, and hobbies and preferences. Step 3: The conversation unit conducts a simulated conversation based on the information learned by the learning unit. For example, when a family member or friend speaks to the robot, the robot responds by reproducing that person's tone and manner of speaking. The robot can generate the person's voice and conversation content using speech synthesis technology and natural language processing technology.

[0095] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0096] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0097] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0098] Each of the multiple elements including the collection unit, learning unit, and conversation unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit uses the camera 42 and microphone 38B of the smart device 14 to collect personality information such as conversation data, behavioral patterns, and hobbies and preferences from the person's life. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and AI reproduces the person's personality based on the collected information. The conversation unit is realized, for example, by the control unit 46A of the smart device 14, and when a family member or friend speaks to the person, it responds by reproducing the person's tone and manner of speaking. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0099] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0100] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0101] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0102] 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.

[0103] 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 the voice according to instructions from the processor 46.

[0104] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0105] 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 performed in a secure state.

[0106] Fig. 4 shows an example of 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.

[0107] 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.

[0108] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0109] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0110] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0111] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0112] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0113] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements including the collection unit, learning unit, and conversation unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit uses the camera 42 and microphone 238 of the smart glasses 214 to collect personality information such as conversation data, behavioral patterns, and hobbies and preferences from the person's life. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and AI reproduces the person's personality based on the collected information. The conversation unit is realized, for example, by the control unit 46A of the smart glasses 214, and when a family member or friend speaks to the person, it responds by reproducing the person's tone and manner of speaking. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0115] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0116] 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.

[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, the RAM 30, and the 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 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.

[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 the voice according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average 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 performed in a secure state.

[0122] 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.

[0123] 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.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0125] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0126] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0127] 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 voice indicating a user input for 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.

[0128] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0129] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements including the collection unit, learning unit, and conversation unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit uses the camera 42 and microphone 238 of the headset type terminal 314 to collect personality information such as conversation data, behavioral patterns, and hobbies and preferences from the person's life. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the AI ​​reproduces the person's personality based on the collected information. The conversation unit is realized, for example, by the control unit 46A of the headset type terminal 314, and when a family member or friend speaks to the conversation unit, the conversation unit responds by reproducing the person's tone and manner of speaking. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0131] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0132] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0134] 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.

[0135] 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 the voice according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0137] 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 performed in a secure state.

[0138] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0139] 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.

[0140] 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.

[0141] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0142] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0143] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0144] 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 a voice indicating a user input for 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.

[0145] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0146] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0147] Each of the multiple elements including the collection unit, learning unit, and conversation unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit uses the camera 42 and microphone 238 of the robot 414 to collect personality information such as conversation data, behavioral patterns, and hobbies and preferences from the person's life. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the AI ​​reproduces the person's personality based on the collected information. The conversation unit is realized, for example, by the control unit 46A of the robot 414, and when a family member or friend speaks to the robot, it responds by reproducing the person's tone and manner of speaking. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0148] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0149] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0150] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0151] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0152] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0153] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0154] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0155] 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.

[0156] 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 Universal Serial Bus (USB) 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.

[0157] In addition, 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 upon request from the data processing device 12.

[0158] 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.

[0159] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0160] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0161] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0162] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0163] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0164] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0165] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0166] (Appendix 1) A collection unit that collects at least one of personality information including conversation data, behavioral patterns, and hobbies and preferences during the person's lifetime; a learning unit that learns the information collected by the collecting unit and reproduces the personality of the person; a conversation unit that conducts a pseudo-conversation based on the information learned by the learning unit; Equipped A system characterized by: (Appendix 2) The collecting unit includes: Collect information about daily conversations, social media posts, and hobbies 2. The system of claim 1, (Appendix 3) The learning unit is Learn about your conversational tone, speaking style, hobbies, and preferences based on the information collected 2. The system of claim 1, (Appendix 4) The conversation unit includes: When a family member or friend talks to you, the robot responds by replicating that person's tone and manner of speaking. 2. The system of claim 1, (Appendix 5) The collecting unit includes: Inferring user sentiment and adjusting the type of data to be collected based on the inferred user sentiment 2. The system of claim 1, (Appendix 6) The collecting unit includes: At the time of collection, an appropriate data collection method is selected based on the user's living environment and daily behavior patterns. 2. The system of claim 1, (Appendix 7) The collecting unit includes: At the time of collection, identify important events or anniversaries in a user's past and prioritize collection of data related to those events or anniversaries. 2. The system of claim 1, (Appendix 8) The collecting unit includes: Infer user sentiment and prioritize data to be collected based on the inferred user sentiment 2. The system of claim 1, (Appendix 9) The collecting unit includes: At the time of collection, prioritize collection of relevant data based on the user's geographic location 2. The system of claim 1, (Appendix 10) The collecting unit includes: At the time of collection, analyze your social media activity and collect relevant data 2. The system of claim 1, (Appendix 11) The learning unit is Inferring user emotions and adjusting the learning algorithm based on the inferred user emotions 2. The system of claim 1, (Appendix 12) The learning unit is During training, adjust the granularity of training based on the importance of collected data 2. The system of claim 1, (Appendix 13) The learning unit is When training, different learning algorithms are applied depending on different aspects of the user's personality. 2. The system of claim 1, (Appendix 14) The learning unit is Estimate user emotions and determine learning priorities based on the estimated user emotions 2. The system of claim 1, (Appendix 15) The learning unit is During training, the training is weighted based on when the collected data was submitted. 2. The system of claim 1, (Appendix 16) The learning unit is When learning, the accuracy of learning is improved by referring to the user's related literature and past history. 2. The system of claim 1, (Appendix 17) The conversation unit includes: Infer user emotions and adjust the tone and content of conversations based on the inferred user emotions 2. The system of claim 1, (Appendix 18) The conversation unit includes: During a conversation, the system generates the best response by referencing the user's past conversation history 2. The system of claim 1, (Appendix 19) The conversation unit includes: During a conversation, customize the content of the conversation based on the user's current situation or environment 2. The system of claim 1, (Appendix 20) The conversation unit includes: Estimate user emotions and prioritize conversations based on the estimated user emotions 2. The system of claim 1, (Appendix 21) The conversation unit includes: During a conversation, provide the appropriate conversation content based on the user's geographic location 2. The system of claim 1, (Appendix 22) The conversation unit includes: During conversations, it analyzes the user's social media activity to generate relevant conversation content 2. The system of claim 1, [Explanation of symbols]

[0167] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that collects at least one of personality information including conversation data, behavioral patterns, and hobbies and preferences during the person's lifetime; a learning unit that learns the information collected by the collecting unit and reproduces the personality of the person; a conversation unit that conducts a pseudo-conversation based on the information learned by the learning unit; Equipped A system characterized by:

2. The collecting unit includes: Collect information about daily conversations, social media posts, and hobbies 2. The system of claim 1 .

3. The learning unit is Learn about your conversational tone, speaking style, hobbies, and preferences based on collected information 2. The system of claim 1 .

4. The conversation unit includes: When a family member or friend talks to you, the robot responds by replicating that person's tone and manner of speaking.

2. The system of claim 1 .

5. The collecting unit includes: Inferring user sentiment and adjusting the type of data collected based on the inferred user sentiment 2. The system of claim 1 .

6. The collecting unit includes: At the time of collection, an appropriate data collection method is selected based on the user's living environment and daily behavior patterns.

2. The system of claim 1 .

7. The collecting unit includes: At the time of collection, identify important events or anniversaries in a user's past and prioritize collection of data related to those events or anniversaries.

2. The system of claim 1 .

8. The collecting unit includes: Infer user sentiment and prioritize data to be collected based on the inferred user sentiment 2. The system of claim 1 .

Images