system

Abstract

The system according to the embodiment aims to reproduce the thoughts and speaking style of the deceased and enable dialogue. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, a generation unit, and a response unit. The collection unit collects data on the deceased while they were alive. The analysis unit analyzes the data collected by the collection unit and learns the speech patterns and thought patterns of the deceased. The generation unit generates an AI model for interacting with the deceased based on the data learned by the analysis unit. The response unit enables the AI ​​model generated by the generation unit to respond to questions from the user.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the problem that it is not possible to converse with the deceased, making it difficult to reproduce the deceased's thoughts and speaking style.

[0005] The system according to the embodiment aims to reproduce the thoughts and speaking style of the deceased and enable dialogue. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a response unit. The collection unit collects data on the deceased during their lifetime. The analysis unit analyzes the data collected by the collection unit and learns the speech patterns and thought patterns of the deceased. The generation unit generates an AI model for interacting with the deceased based on the data learned by the analysis unit. The response unit enables the AI ​​model generated by the generation unit to respond to questions from the user. [Effects of the Invention]

[0007] The system according to the embodiment can reproduce the thoughts and speech patterns of the deceased, enabling dialogue. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A deceased person dialogue system according to an embodiment of the present invention provides the experience of interacting with the deceased based on data from the deceased's lifetime. This deceased person dialogue system collects data from the deceased's lifetime, analyzes it using AI, learns the deceased's speech patterns and thought patterns, and generates an AI model for dialogue with the deceased. For example, data such as letters and diaries written by the deceased, social media posts, audio recordings, and video messages is collected. The AI ​​then analyzes the collected data and learns the deceased's speech patterns and thought patterns. Furthermore, an AI model for dialogue with the deceased is generated based on the learned data. This AI model can respond to questions from a user in the same way as the deceased would. For example, if a user asks, "What is your favorite food?", the AI ​​model will respond, based on the deceased's data, with, "My favorite food is curry." In this way, an experience of conversing with the deceased is provided. This mechanism allows users to reminisce about their memories with the deceased by interacting with an AI model that reproduces the deceased's speech patterns and thought patterns. Furthermore, an AI model that has learned the deceased's speech patterns and thought patterns can also be used as a means of conveying the deceased's wishes and thoughts. For example, the AI ​​model can convey what the deceased wanted to say and their wishes while they were alive. This allows the deceased's wishes and thoughts to be passed on through dialogue with the deceased. This allows the deceased dialogue system to provide the experience of interacting with the deceased based on data from their life.

[0029] The deceased person dialogue system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a response unit. The collection unit collects data from the deceased's life. Data from the deceased's life includes, but is not limited to, letters, diaries, social media posts, audio recordings, and video messages. The collection unit, for example, scans letters and diaries written by the deceased and saves them as digital data. The collection unit can also collect content posted by the deceased on social media, audio recordings, and video messages. For example, the collection unit scans letters and diaries written by the deceased and saves them as digital data. Next, the analysis unit analyzes the collected data to learn the deceased's speaking style and thought patterns. The analysis unit analyzes, for example, the writing style and wording of letters and diaries written by the deceased, the content of social media posts, and the speaking style of audio recordings. For example, the analysis unit analyzes the writing style and wording of letters and diaries written by the deceased to learn the deceased's speaking style and thought patterns. The analysis unit can also analyze content posted by the deceased on social media and the speaking style of audio recordings. Next, the generation unit generates an AI model for interacting with the deceased based on the learned data. For example, the generation unit generates an AI model for interacting with the deceased based on data learned from the deceased's speaking style and thought patterns. For example, the generation unit generates an AI model for interacting with the deceased based on data learned from the deceased's speaking style and thought patterns. Next, the response unit causes the AI ​​model generated by the generation unit to respond to questions from the user. For example, the response unit responds to questions from the user in a manner similar to how the deceased would respond. For example, if the user asks, "What is your favorite food?", the response unit responds, based on the data of the deceased, with "My favorite food is curry." As a result, the deceased dialogue system according to the embodiment can provide an experience of interacting with the deceased based on data from the deceased's life.

[0030] The collection unit may collect at least one of letters or diaries written by the deceased, posts on social media, audio recordings, and video messages. For example, the collection unit may scan letters or diaries written by the deceased and save them as digital data. The collection unit may also collect posts on social media by the deceased, audio recordings, video messages, and the like. For example, the collection unit may scan letters or diaries written by the deceased before they died and save them as digital data. In this way, by collecting data in various formats, the deceased's speaking style and thought patterns can be more accurately learned.

[0031] The analysis unit can analyze the collected data and learn the speaking style and thought patterns of the deceased. For example, the analysis unit can analyze the writing style and language used in letters and diaries written by the deceased to learn the speaking style and thought patterns of the deceased. The analysis unit can also analyze content posted by the deceased on social media and the speaking style of audio recordings. For example, the analysis unit can analyze the writing style and language used in letters and diaries written by the deceased to learn the speaking style and thought patterns of the deceased. In this way, by learning the speaking style and thought patterns of the deceased, more natural conversations become possible.

[0032] The generation unit can generate an AI model for interacting with the deceased based on the learned data. The generation unit generates an AI model for interacting with the deceased based on, for example, data learned from the speech pattern and thought patterns of the deceased. For example, the generation unit generates an AI model for interacting with the deceased based on data learned from the speech pattern and thought patterns of the deceased. In this way, by generating an AI model based on the learned data, it is possible to provide the experience of interacting with the deceased.

[0033] The response unit can respond to questions from the user in the same way that the deceased would. For example, if the user asks, "What is your favorite food?", the response unit will respond with, "My favorite food is curry," based on the data of the deceased. This allows the AI ​​model to respond to questions from the user in the same way that the deceased would.

[0034] The collection unit can analyze the deceased's past data submission history and select the appropriate collection method. For example, the collection unit will prioritize collecting data from social media platforms that the deceased frequently used. In addition, if the deceased left behind many letters or diaries, the collection unit can prioritize digitizing and collecting that data. For example, if the deceased left behind many audio recordings, the collection unit will prioritize collecting audio data and use it for analysis. This allows the optimal collection method to be selected by analyzing the deceased's past data submission history.

[0035] When collecting data, the collection unit can filter the data based on the living situation and areas of interest of the deceased. For example, if the deceased had a particular hobby or interest, the collection unit will prioritize collecting data related to that area. Furthermore, if the deceased engaged in a particular activity during a particular period, the collection unit can also focus on collecting data from that period. For example, if the deceased frequently visited a particular place, the collection unit will prioritize collecting data related to that place. In this way, by filtering the data based on the living situation and areas of interest of the deceased, more relevant data can be collected.

[0036] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the deceased. For example, if the deceased frequently visited a particular place, the collection unit can prioritize collecting data related to that place. Furthermore, if the deceased lived in a particular area, the collection unit can also focus on collecting data related to that area. For example, if the deceased left a lot of data from travel destinations, the collection unit can prioritize collecting data related to those travel destinations. In this way, by taking into account the geographical location information of the deceased, highly relevant data can be prioritized.

[0037] When collecting data, the collection unit can analyze the social media activities of the deceased and collect relevant data. For example, the collection unit can prioritize collecting data from social media platforms where the deceased frequently posted. In addition, if the deceased frequently used a particular hashtag, the collection unit can also focus on collecting data related to that hashtag. For example, if the deceased participated in a particular group or community, the collection unit can prioritize collecting data related to that group or community. This allows for efficient collection of relevant data by analyzing the social media activities of the deceased.

[0038] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit performs a detailed analysis of data related to important events or occurrences. The analysis unit can also perform a simplified analysis of everyday data. For example, the analysis unit may focus on analyzing data related to events that were turning points in the life of the deceased. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data.

[0039] During analysis, the analysis unit can apply different analysis algorithms depending on the data category. For example, the analysis unit applies a natural language processing algorithm to text data. The analysis unit can also apply a voice recognition algorithm to audio data. For example, the analysis unit applies a video analysis algorithm to video data. This improves analysis accuracy by applying an appropriate analysis algorithm depending on the data category.

[0040] During analysis, the analysis unit can determine the priority of analysis based on the time of data submission. For example, the analysis unit prioritizes analysis of data from a period when the deceased frequently submitted data during their lifetime. The analysis unit can also prioritize analysis of data related to specific events or occurrences of the deceased. For example, the analysis unit prioritizes analysis of data from a period when the deceased was emotionally stable. This enables efficient analysis by determining the priority of analysis based on the time of data submission.

[0041] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the data. For example, the analysis unit may prioritize analyzing data related to turning points in the deceased's life. The analysis unit may also analyze data related to the deceased's hobbies and interests next. For example, the analysis unit may analyze everyday data last. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the data.

[0042] The generation unit can adjust the level of detail of the AI ​​model based on the importance of the data during generation. For example, the generation unit generates a detailed AI model based on data related to important events or occurrences. The generation unit can also generate a simplified AI model based on everyday data. For example, the generation unit generates a focused AI model based on data related to a turning point in the life of a deceased person. In this way, by adjusting the level of detail of the AI ​​model based on the importance of the data, it is possible to generate an AI model that reflects important information in more detail.

[0043] During generation, the generation unit can apply different generation algorithms depending on the data category. For example, the generation unit applies a natural language generation algorithm to text data. The generation unit can also apply a voice synthesis algorithm to audio data. For example, the generation unit applies a video generation algorithm to video data. This improves generation accuracy by applying an appropriate generation algorithm depending on the data category.

[0044] At the time of generation, the generation unit can determine the priority of AI models based on the time of data submission. For example, the generation unit may generate AI models with priority based on data from a period when the deceased frequently submitted data during their lifetime. The generation unit may also generate AI models with priority based on data related to specific events or occurrences of the deceased. For example, the generation unit may generate AI models with priority based on data from a period when the deceased was emotionally stable. This enables efficient model generation by determining the priority of AI models based on the time of data submission.

[0045] During generation, the generation unit can adjust the order of AI models based on the relevance of the data. For example, the generation unit may prioritize generating an AI model based on data related to a turning point in the deceased's life. The generation unit may also generate an AI model next based on data related to the deceased's hobbies and interests. For example, the generation unit may generate an AI model last based on everyday data. This allows for efficient model generation by adjusting the order of AI models based on the relevance of the data.

[0046] When responding, the response unit can adjust the level of detail in the response based on the importance of the question. For example, the response unit provides a detailed response to an important question. The response unit can also provide a brief response to an everyday question. For example, the response unit provides a focused response to a question related to a turning point in the life of the deceased. This allows for efficient responses by adjusting the level of detail in the response based on the importance of the question.

[0047] When responding, the response unit can apply different response algorithms depending on the category of the question. For example, the response unit can apply a sentiment analysis algorithm to an emotional question. The response unit can also apply an information retrieval algorithm to a fact-checking question. For example, the response unit can apply a natural language generation algorithm to a question requesting an opinion. This improves response accuracy by applying an appropriate response algorithm depending on the question category.

[0048] When responding, the response unit can determine the priority of the response based on the time when the question was submitted. For example, the response unit prioritizes responses to the most recent questions. The response unit can also prioritize responses to questions related to important events or occurrences. For example, the response unit prioritizes questions based on the emotional stability of the deceased. This allows for efficient responses by prioritizing responses based on the time when the question was submitted.

[0049] When responding, the response unit can adjust the order of responses based on the relevance of the questions. For example, the response unit may prioritize responses to questions related to turning points in the life of the deceased. The response unit may also next respond to questions related to the hobbies and interests of the deceased. For example, the response unit may respond to everyday questions last. This allows for efficient responses by adjusting the order of responses based on the relevance of the questions.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] When collecting data about the deceased, the collection unit can also determine the priority of the data by taking into account the deceased's social relationships. For example, it can prioritize collection of the deceased's interactions with close friends and family. Also, if the deceased belonged to a specific group or community, it can focus on collecting data related to that group or community. This allows for the collection of data based on the deceased's social relationships, providing a richer conversation experience.

[0052] When collecting data on the deceased during their lifetime, the collection unit can also adjust the timing of data collection taking into account the health condition of the deceased. For example, data from periods when the deceased was healthy can be collected preferentially. Data from periods when the deceased was ill can also be avoided. In this way, by adjusting the timing of data collection based on the health condition of the deceased, more appropriate data can be collected.

[0053] The generator can also have a voice synthesis function that reproduces the voice of the deceased based on data from the deceased's lifetime. For example, it can analyze the deceased's voice recordings and learn the characteristics of their voice. It can also generate a voice synthesis model that reproduces the deceased's voice based on the learned data. This allows for the reproduction of the deceased's voice, providing a more realistic conversation experience.

[0054] When collecting data about the deceased, the collection unit can expand the scope of data collection by taking into account the deceased's hobbies and interests. For example, if the deceased left a lot of data about a particular hobby, the collection unit can focus on collecting data related to that hobby. It can also collect data related to areas in which the deceased was interested. This allows for a richer interaction experience by expanding the scope of data collection based on the deceased's hobbies and interests.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The collection department collects the deceased's life data, which includes letters, diaries, social media posts, audio recordings, video messages, etc. The collection department scans this data and stores it as digital data. Step 2: The analysis unit analyzes the collected data and learns the deceased's speech style and thought patterns. The analysis unit analyzes the writing style and vocabulary of letters and diaries, the content of social media posts, and the speaking style of audio recordings. Step 3: The generation unit generates an AI model for interacting with the deceased based on the data learned by the analysis unit. The generation unit generates an AI model based on data learned from the deceased's speaking style and thought patterns. Step 4: The response unit uses the AI ​​model generated by the generation unit to respond to questions from the user. The response unit responds to questions from the user in the same way that the deceased person would.

[0057] (Example 2) A deceased person dialogue system according to an embodiment of the present invention provides the experience of interacting with the deceased based on data from the deceased's lifetime. This deceased person dialogue system collects data from the deceased's lifetime, analyzes it using AI, learns the deceased's speech patterns and thought patterns, and generates an AI model for dialogue with the deceased. For example, data such as letters and diaries written by the deceased, social media posts, audio recordings, and video messages is collected. The AI ​​then analyzes the collected data and learns the deceased's speech patterns and thought patterns. Furthermore, an AI model for dialogue with the deceased is generated based on the learned data. This AI model can respond to questions from a user in the same way as the deceased would. For example, if a user asks, "What is your favorite food?", the AI ​​model will respond, based on the deceased's data, with, "My favorite food is curry." In this way, an experience of conversing with the deceased is provided. This mechanism allows users to reminisce about their memories with the deceased by interacting with an AI model that reproduces the deceased's speech patterns and thought patterns. Furthermore, an AI model that has learned the deceased's speech patterns and thought patterns can also be used as a means of conveying the deceased's wishes and thoughts. For example, the AI ​​model can convey what the deceased wanted to say and their wishes while they were alive. This allows the deceased's wishes and thoughts to be passed on through dialogue with the deceased. This allows the deceased dialogue system to provide the experience of interacting with the deceased based on data from their life.

[0058] The deceased person dialogue system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a response unit. The collection unit collects data from the deceased's life. Data from the deceased's life includes, but is not limited to, letters, diaries, social media posts, audio recordings, and video messages. The collection unit, for example, scans letters and diaries written by the deceased and saves them as digital data. The collection unit can also collect content posted by the deceased on social media, audio recordings, and video messages. For example, the collection unit scans letters and diaries written by the deceased and saves them as digital data. Next, the analysis unit analyzes the collected data to learn the deceased's speaking style and thought patterns. The analysis unit analyzes, for example, the writing style and wording of letters and diaries written by the deceased, the content of social media posts, and the speaking style of audio recordings. For example, the analysis unit analyzes the writing style and wording of letters and diaries written by the deceased to learn the deceased's speaking style and thought patterns. The analysis unit can also analyze content posted by the deceased on social media and the speaking style of audio recordings. Next, the generation unit generates an AI model for interacting with the deceased based on the learned data. For example, the generation unit generates an AI model for interacting with the deceased based on data learned from the deceased's speaking style and thought patterns. For example, the generation unit generates an AI model for interacting with the deceased based on data learned from the deceased's speaking style and thought patterns. Next, the response unit causes the AI ​​model generated by the generation unit to respond to questions from the user. For example, the response unit responds to questions from the user in a manner similar to how the deceased would respond. For example, if the user asks, "What is your favorite food?", the response unit responds, based on the data of the deceased, with "My favorite food is curry." As a result, the deceased dialogue system according to the embodiment can provide an experience of interacting with the deceased based on data from the deceased's life.

[0059] The collection unit may collect at least one of letters or diaries written by the deceased, posts on social media, audio recordings, and video messages. For example, the collection unit may scan letters or diaries written by the deceased and save them as digital data. The collection unit may also collect posts on social media by the deceased, audio recordings, video messages, and the like. For example, the collection unit may scan letters or diaries written by the deceased before they died and save them as digital data. In this way, by collecting data in various formats, the deceased's speaking style and thought patterns can be more accurately learned.

[0060] The analysis unit can analyze the collected data and learn the speaking style and thought patterns of the deceased. For example, the analysis unit can analyze the writing style and language used in letters and diaries written by the deceased to learn the speaking style and thought patterns of the deceased. The analysis unit can also analyze content posted by the deceased on social media and the speaking style of audio recordings. For example, the analysis unit can analyze the writing style and language used in letters and diaries written by the deceased to learn the speaking style and thought patterns of the deceased. In this way, by learning the speaking style and thought patterns of the deceased, more natural conversations become possible.

[0061] The generation unit can generate an AI model for interacting with the deceased based on the learned data. The generation unit generates an AI model for interacting with the deceased based on, for example, data learned from the speech pattern and thought patterns of the deceased. For example, the generation unit generates an AI model for interacting with the deceased based on data learned from the speech pattern and thought patterns of the deceased. In this way, by generating an AI model based on the learned data, it is possible to provide the experience of interacting with the deceased.

[0062] The response unit can respond to questions from the user in the same way that the deceased would. For example, if the user asks, "What is your favorite food?", the response unit will respond with, "My favorite food is curry," based on the data of the deceased. This allows the AI ​​model to respond to questions from the user in the same way that the deceased would.

[0063] The collection unit can estimate the emotions of the deceased and adjust the timing of data collection based on the estimated emotions of the deceased. For example, the collection unit avoids data from periods when the deceased was stressed and prioritizes collecting data from periods when the deceased was relaxed. Furthermore, if the deceased had an emotional reaction to a particular event or occurrence, the collection unit can also focus on collecting data from that period. For example, the collection unit prioritizes collecting data from periods when the deceased was emotionally stable and collects data with little emotional fluctuation. In this way, by adjusting the timing of data collection based on the emotions of the deceased, more appropriate data can be collected.

[0064] The collection unit can analyze the deceased's past data submission history and select the appropriate collection method. For example, the collection unit will prioritize collecting data from social media platforms that the deceased frequently used. In addition, if the deceased left behind many letters or diaries, the collection unit can prioritize digitizing and collecting that data. For example, if the deceased left behind many audio recordings, the collection unit will prioritize collecting audio data and use it for analysis. This allows the optimal collection method to be selected by analyzing the deceased's past data submission history.

[0065] When collecting data, the collection unit can filter the data based on the living situation and areas of interest of the deceased. For example, if the deceased had a particular hobby or interest, the collection unit will prioritize collecting data related to that area. Furthermore, if the deceased engaged in a particular activity during a particular period, the collection unit can also focus on collecting data from that period. For example, if the deceased frequently visited a particular place, the collection unit will prioritize collecting data related to that place. In this way, by filtering the data based on the living situation and areas of interest of the deceased, more relevant data can be collected.

[0066] The collection unit can estimate the emotions of the deceased and determine the priority of data to be collected based on the estimated emotions of the deceased. For example, the collection unit prioritizes collecting data from periods when the deceased was emotionally stable. Furthermore, if the deceased reacted emotionally to a particular event or occurrence, the collection unit can also focus on collecting data from that period. For example, the collection unit prioritizes collecting data from periods when the deceased was relaxed. In this way, by determining the priority of data based on the emotions of the deceased, more important data can be collected preferentially.

[0067] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the deceased. For example, if the deceased frequently visited a particular place, the collection unit can prioritize collecting data related to that place. Furthermore, if the deceased lived in a particular area, the collection unit can also focus on collecting data related to that area. For example, if the deceased left a lot of data from travel destinations, the collection unit can prioritize collecting data related to those travel destinations. In this way, by taking into account the geographical location information of the deceased, highly relevant data can be prioritized.

[0068] When collecting data, the collection unit can analyze the social media activities of the deceased and collect relevant data. For example, the collection unit can prioritize collecting data from social media platforms where the deceased frequently posted. In addition, if the deceased frequently used a particular hashtag, the collection unit can also focus on collecting data related to that hashtag. For example, if the deceased participated in a particular group or community, the collection unit can prioritize collecting data related to that group or community. This allows for efficient collection of relevant data by analyzing the social media activities of the deceased.

[0069] The analysis unit can estimate the emotions of the deceased and adjust the expression method of the analysis based on the estimated emotions of the deceased. For example, the analysis unit can use soft expressions when analyzing data from a period when the deceased was relaxed. The analysis unit can also use careful expressions when analyzing data from a period when the deceased was stressed. For example, the analysis unit can use neutral expressions when analyzing data from a period when the deceased was emotionally stable. In this way, by adjusting the expression method of the analysis based on the emotions of the deceased, more appropriate analysis results can be obtained.

[0070] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit performs a detailed analysis of data related to important events or occurrences. The analysis unit can also perform a simplified analysis of everyday data. For example, the analysis unit may focus on analyzing data related to events that were turning points in the life of the deceased. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data.

[0071] During analysis, the analysis unit can apply different analysis algorithms depending on the data category. For example, the analysis unit applies a natural language processing algorithm to text data. The analysis unit can also apply a voice recognition algorithm to audio data. For example, the analysis unit applies a video analysis algorithm to video data. This improves analysis accuracy by applying an appropriate analysis algorithm depending on the data category.

[0072] The analysis unit can estimate the emotions of the deceased and adjust the length of the analysis based on the estimated emotions of the deceased. For example, the analysis unit can perform a detailed analysis of data from periods when the deceased was relaxed. The analysis unit can also perform a simplified analysis of data from periods when the deceased was stressed. For example, the analysis unit can analyze data from periods when the deceased was emotionally stable with a medium level of detail. In this way, by adjusting the length of the analysis based on the emotions of the deceased, more appropriate analysis results can be obtained.

[0073] During analysis, the analysis unit can determine the priority of analysis based on the time of data submission. For example, the analysis unit prioritizes analysis of data from a period when the deceased frequently submitted data during their lifetime. The analysis unit can also prioritize analysis of data related to specific events or occurrences of the deceased. For example, the analysis unit prioritizes analysis of data from a period when the deceased was emotionally stable. This enables efficient analysis by determining the priority of analysis based on the time of data submission.

[0074] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the data. For example, the analysis unit may prioritize analyzing data related to turning points in the deceased's life. The analysis unit may also analyze data related to the deceased's hobbies and interests next. For example, the analysis unit may analyze everyday data last. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the data.

[0075] The generation unit can estimate the emotions of the deceased and adjust the expression method of the generated AI model based on the estimated emotions of the deceased. For example, the generation unit can generate an AI model that uses soft expressions based on data from a time when the deceased was relaxed. The generation unit can also generate an AI model that uses careful expressions based on data from a time when the deceased was stressed. For example, the generation unit can generate an AI model that uses neutral expressions based on data from a time when the deceased was emotionally stable. This allows for more natural conversation by adjusting the expression method of the AI ​​model based on the emotions of the deceased.

[0076] The generation unit can adjust the level of detail of the AI ​​model based on the importance of the data during generation. For example, the generation unit generates a detailed AI model based on data related to important events or occurrences. The generation unit can also generate a simplified AI model based on everyday data. For example, the generation unit generates a focused AI model based on data related to a turning point in the life of a deceased person. In this way, by adjusting the level of detail of the AI ​​model based on the importance of the data, it is possible to generate an AI model that reflects important information in more detail.

[0077] During generation, the generation unit can apply different generation algorithms depending on the data category. For example, the generation unit applies a natural language generation algorithm to text data. The generation unit can also apply a voice synthesis algorithm to audio data. For example, the generation unit applies a video generation algorithm to video data. This improves generation accuracy by applying an appropriate generation algorithm depending on the data category.

[0078] The generation unit can estimate the emotions of the deceased and adjust the length of the generated AI model based on the estimated emotions of the deceased. For example, the generation unit can generate a longer AI model based on data from a period when the deceased was relaxed. The generation unit can also generate a shorter AI model based on data from a period when the deceased was feeling stressed. For example, the generation unit can generate a medium-length AI model based on data from a period when the deceased was emotionally stable. This allows for adjusting the length of the AI ​​model based on the emotions of the deceased to provide a more appropriate dialogue experience.

[0079] At the time of generation, the generation unit can determine the priority of AI models based on the time of data submission. For example, the generation unit may generate AI models with priority based on data from a period when the deceased frequently submitted data during their lifetime. The generation unit may also generate AI models with priority based on data related to specific events or occurrences of the deceased. For example, the generation unit may generate AI models with priority based on data from a period when the deceased was emotionally stable. This enables efficient model generation by determining the priority of AI models based on the time of data submission.

[0080] During generation, the generation unit can adjust the order of AI models based on the relevance of the data. For example, the generation unit may prioritize generating an AI model based on data related to a turning point in the deceased's life. The generation unit may also generate an AI model next based on data related to the deceased's hobbies and interests. For example, the generation unit may generate an AI model last based on everyday data. This allows for efficient model generation by adjusting the order of AI models based on the relevance of the data.

[0081] The response unit can estimate the emotions of the deceased and adjust the way the response is expressed based on the estimated emotions of the deceased. For example, the response unit can respond with softer expressions based on data from a time when the deceased was relaxed. The response unit can also respond with more careful expressions based on data from a time when the deceased was stressed. For example, the response unit can respond with neutral expressions based on data from a time when the deceased was emotionally stable. This allows for more natural dialogue by adjusting the way the response is expressed based on the emotions of the deceased.

[0082] When responding, the response unit can adjust the level of detail in the response based on the importance of the question. For example, the response unit provides a detailed response to an important question. The response unit can also provide a brief response to an everyday question. For example, the response unit provides a focused response to a question related to a turning point in the life of the deceased. This allows for efficient responses by adjusting the level of detail in the response based on the importance of the question.

[0083] When responding, the response unit can apply different response algorithms depending on the category of the question. For example, the response unit can apply a sentiment analysis algorithm to an emotional question. The response unit can also apply an information retrieval algorithm to a fact-checking question. For example, the response unit can apply a natural language generation algorithm to a question requesting an opinion. This improves response accuracy by applying an appropriate response algorithm depending on the question category.

[0084] The response unit can estimate the emotions of the deceased and adjust the length of the response based on the estimated emotions of the deceased. For example, the response unit can provide a longer response based on data from a period when the deceased was relaxed. The response unit can also provide a shorter response based on data from a period when the deceased was stressed. For example, the response unit can provide a medium-length response based on data from a period when the deceased was emotionally stable. This allows for a more appropriate dialogue experience by adjusting the length of the response based on the emotions of the deceased.

[0085] When responding, the response unit can determine the priority of the response based on the time when the question was submitted. For example, the response unit prioritizes responses to the most recent questions. The response unit can also prioritize responses to questions related to important events or occurrences. For example, the response unit prioritizes questions based on the emotional stability of the deceased. This allows for efficient responses by prioritizing responses based on the time when the question was submitted.

[0086] When responding, the response unit can adjust the order of responses based on the relevance of the questions. For example, the response unit may prioritize responses to questions related to turning points in the life of the deceased. The response unit may also next respond to questions related to the hobbies and interests of the deceased. For example, the response unit may respond to everyday questions last. This allows for efficient responses by adjusting the order of responses based on the relevance of the questions. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and response 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 collects data about the deceased person's life using the camera 42 and microphone 38B of the smart device 14 and stores the data as digital data using the control unit 46A. The analysis unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected data to learn the deceased person's speaking style and thought patterns. The generation unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and generates an AI model based on the learned data. The response unit, for example, is realized by the control unit 46A of the smart device 14 and the AI ​​model responds to questions from the user. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and response 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 collects data about the deceased person's life using the camera 42 and microphone 238 of the smart glasses 214 and stores the data as digital data using the control unit 46A. The analysis unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected data to learn the deceased person's speaking style and thought patterns. The generation unit, for example, is realized by the specific processing unit 290 of the data processing device 12 and generates an AI model based on the learned data. The response unit, for example, is realized by the control unit 46A of the smart glasses 214 and the AI ​​model responds to questions from the user. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and response 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 collects data about the deceased person's life using the camera 42 and microphone 238 of the headset-type terminal 314 and stores the data as digital data using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data to learn the deceased person's speaking style and thought patterns. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an AI model based on the learned data. The response unit is realized, for example, by the control unit 46A of the headset-type terminal 314, and the AI ​​model responds to questions from the user. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and response 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 collects data about the deceased person's life using the camera 42 and microphone 238 of the robot 414 and stores the data as digital data using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data to learn the deceased person's speaking style and thought patterns. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an AI model based on the learned data. The response unit is realized, for example, by the control unit 46A of the robot 414, and the AI ​​model responds to questions from the user.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] When collecting data about the deceased, the collection unit can also determine the priority of the data by taking into account the deceased's social relationships. For example, it can prioritize collection of the deceased's interactions with close friends and family. Also, if the deceased belonged to a specific group or community, it can focus on collecting data related to that group or community. This allows for the collection of data based on the deceased's social relationships, providing a richer conversation experience.

[0089] The analysis unit can also estimate the emotions of the deceased and determine the priorities of analysis based on the estimated emotions of the deceased. For example, it can prioritize analysis of data from a period when the deceased was emotionally stable. Also, if the deceased had an emotional reaction to a particular event or occurrence, it can focus analysis on data from that period. In this way, by determining the priorities of analysis based on the emotions of the deceased, more appropriate analysis results can be obtained.

[0090] The generation unit can also estimate the emotions of the deceased and adjust the response speed of the generated AI model based on the estimated emotions of the deceased. For example, an AI model with a slower response speed can be generated based on data from a time when the deceased was relaxed. Alternatively, an AI model with a faster response speed can be generated based on data from a time when the deceased was stressed. This allows for more natural conversations by adjusting the response speed of the AI ​​model based on the emotions of the deceased.

[0091] The response unit can also estimate the user's emotions and adjust the content of the response based on the estimated user emotions. For example, if the user is sad, the response unit can provide a comforting response. If the user is happy, the response unit can provide a sympathetic response. By adjusting the content of the response based on the user's emotions, a more emotionally sensitive conversation experience can be provided.

[0092] When collecting data on the deceased during their lifetime, the collection unit can also adjust the timing of data collection taking into account the health condition of the deceased. For example, data from periods when the deceased was healthy can be collected preferentially. Data from periods when the deceased was ill can also be avoided. In this way, by adjusting the timing of data collection based on the health condition of the deceased, more appropriate data can be collected.

[0093] The analysis unit can estimate the emotions of the deceased and adjust the accuracy of the analysis based on the estimated emotions of the deceased. For example, it can analyze data from periods when the deceased was relaxed in detail. It can also analyze data from periods when the deceased was stressed in a simplified manner. By adjusting the accuracy of the analysis based on the emotions of the deceased, more appropriate analysis results can be obtained.

[0094] The generator can also have a voice synthesis function that reproduces the voice of the deceased based on data from the deceased's lifetime. For example, it can analyze the deceased's voice recordings and learn the characteristics of their voice. It can also generate a voice synthesis model that reproduces the deceased's voice based on the learned data. This allows for the reproduction of the deceased's voice, providing a more realistic conversation experience.

[0095] The response unit can also estimate the user's emotions and adjust the tone of the response based on the estimated user's emotions. For example, if the user is depressed, the response unit can respond in a gentle tone. If the user is excited, the response unit can respond in a cheerful tone. In this way, by adjusting the tone of the response based on the user's emotions, a more emotionally sensitive conversation experience can be provided.

[0096] When collecting data about the deceased, the collection unit can expand the scope of data collection by taking into account the deceased's hobbies and interests. For example, if the deceased left a lot of data about a particular hobby, the collection unit can focus on collecting data related to that hobby. It can also collect data related to areas in which the deceased was interested. This allows for a richer interaction experience by expanding the scope of data collection based on the deceased's hobbies and interests.

[0097] The analysis unit can also estimate the emotions of the deceased and select an analysis method based on the estimated emotions of the deceased. For example, when analyzing data from a period when the deceased was relaxed, an emotion analysis algorithm can be applied. Also, when analyzing data from a period when the deceased was stressed, a more careful analysis method can be selected. In this way, by selecting an analysis method based on the emotions of the deceased, more appropriate analysis results can be obtained.

[0098] The processing flow of the second embodiment will be briefly explained below.

[0099] Step 1: The collection department collects the deceased's life data, which includes letters, diaries, social media posts, audio recordings, video messages, etc. The collection department scans this data and stores it as digital data. Step 2: The analysis unit analyzes the collected data and learns the deceased's speech style and thought patterns. The analysis unit analyzes the writing style and vocabulary of letters and diaries, the content of social media posts, and the speaking style of audio recordings. Step 3: The generation unit generates an AI model for interacting with the deceased based on the data learned by the analysis unit. The generation unit generates an AI model based on data learned from the deceased's speaking style and thought patterns. Step 4: The response unit uses the AI ​​model generated by the generation unit to respond to questions from the user. The response unit responds to questions from the user in the same way that the deceased person would.

[0100] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0101] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0102] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0103] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0104] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0105] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0106] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0107] 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.

[0108] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0109] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0110] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0111] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0112] 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.

[0113] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0114] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0115] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0116] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0117] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0118] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0119] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0122] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0123] 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.

[0124] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0125] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0126] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0127] 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.

[0128] 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.

[0129] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0130] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0131] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0132] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0133] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0134] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0135] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] 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.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] 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.

[0145] 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.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0154] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0155] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0156] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0157] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0158] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0159] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0160] 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.

[0161] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0162] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0163] 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.

[0164] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0165] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0166] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0167] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0168] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0169] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0170] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0171] [Explanation of symbols]

[0172] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection department that collects data on the deceased during their lifetime; an analysis unit that analyzes the data collected by the collection unit and learns the speaking style and thought patterns of the deceased; A generation unit that generates an AI model for interacting with the deceased based on the data learned by the analysis unit; A response unit that causes the AI ​​model generated by the generation unit to respond to a question from a user. A system characterized by:

2. The collecting unit Collect at least one of the following data: letters or diaries written by the deceased, social media posts, audio recordings, or video messages The system of claim 1 .

3. The analysis unit Analyze the collected data to learn the speech patterns and thought patterns of the deceased The system of claim 1 .

4. The generation unit Based on the learned data, an AI model is generated to communicate with the deceased. The system of claim 1 .

5. The response unit Respond to user questions as if the deceased were answering them The system of claim 1 .

6. The collecting unit To provide a method for estimating the emotions of the deceased and adjusting the timing of data collection based on the estimated emotions of the deceased. The system of claim 1 .

7. The collecting unit Analyze the deceased person's past data submission history and select the appropriate collection method The system of claim 1 .

8. The collecting unit When collecting data, filter it based on the deceased's life circumstances and areas of interest. The system of claim 1 .

Images