system

Abstract

The system according to the embodiment aims to provide dialogue by imitating a particular personality. [Solution] A system according to an embodiment includes a data collection unit, a learning unit, an imitation unit, and a providing unit. The data collection unit collects voice data or text data. The learning unit performs machine learning and deep learning using the data collected by the data collection unit. The imitation unit imitates a personality using a model learned by the learning unit. The providing unit provides a dialogue with the personality imitated by the imitation unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have not adequately provided interactions that mimic a specific personality, and there is room for improvement.

[0005] The system according to the embodiment aims to provide dialogue by imitating a particular personality. [Means for solving the problem]

[0006] A system according to an embodiment includes a data collection unit, a learning unit, an imitation unit, and a providing unit. The data collection unit collects voice data or text data. The learning unit performs machine learning and deep learning using the data collected by the data collection unit. The imitation unit imitates a personality using a model learned by the learning unit. The providing unit provides a dialogue with the personality imitated by the imitation unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide dialogue by imitating a particular personality. [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 personality mimicry system according to an embodiment of the present invention uses technologies such as natural language processing, machine learning, and deep learning to learn large amounts of data and human speech patterns and communication styles, thereby mimicking a specific personality. In this system, a user collects voice data and text data of a deceased person or a celebrity, and a learning unit uses the collected data to perform machine learning and deep learning to learn the speech patterns and communication styles. The mimicry unit uses the learned model to mimic a specific personality, and a providing unit provides the user with a dialogue with the mimicked personality. This system can provide emotional fulfillment to surviving family members by mimicking the personality of a deceased person, and can also provide paid services to fans by mimicking the personality of a celebrity. For example, a data collection unit collects voice data and text data of a deceased person or a celebrity, and a learning unit uses the collected data to perform machine learning and deep learning to learn the speech patterns and communication styles. The mimicry unit uses the learned model to mimic a specific personality, and a providing unit provides the user with a dialogue with the mimicked personality. In this way, the personality imitation system can provide a sense of spiritual fulfillment to the surviving family members by imitating the personality of the deceased, and can also provide paid services to fans by imitating the personality of a celebrity.

[0029] The personality mimicry system according to the embodiment includes a data collection unit, a learning unit, a mimicry unit, and a providing unit. The data collection unit collects audio data or text data. The audio data includes, for example, audio file formats (MP3, WAV, etc.), and the text data includes, for example, text file formats (TXT, DOC, etc.), but is not limited to these examples. The data collection unit collects, for example, audio data or text data of deceased individuals or famous people. For example, the data collection unit can collect interview audio, lecture audio, and everyday conversation audio. The data collection unit can also collect text data such as books, blogs, and social media posts. The learning unit uses the collected data for machine learning and deep learning to learn speech patterns and communication styles. For machine learning, algorithms such as neural networks and support vector machines are used. For deep learning, algorithms such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are used. For example, the learning unit uses the collected audio data to learn speech patterns, and uses the collected text data to learn communication styles. The mimicry unit mimics a specific personality using the learned model. The mimicry unit, for example, generates voice using the learned speech pattern and generates text using the learned communication style. The provision unit provides a user with a dialogue with the mimicked personality. The provision unit provides a dialogue experience to the user using, for example, a voice dialogue system or a text chat system. As a result, the personality mimicry system according to the embodiment can provide a system that mimics a specific personality by collecting, learning, imitating, and providing voice data and text data.

[0030] The data collection unit can collect audio data or text data of a specific person. For example, the data collection unit collects audio data or text data of a deceased person or a famous person. For example, the data collection unit can collect interview audio, lecture audio, everyday conversation audio, etc. The data collection unit can also collect text data such as books, blogs, and social media posts. In this way, collecting audio data or text data of a deceased person or a famous person can provide data for imitating a specific personality.

[0031] The learning unit can perform machine learning and deep learning using the collected data to learn speech patterns or communication styles. The learning unit, for example, learns speech patterns using collected voice data and learns communication styles using collected text data. Algorithms such as neural networks and support vector machines are used for machine learning. Algorithms such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are used for deep learning. This makes it possible to learn speech patterns and communication styles by performing machine learning and deep learning using the collected data.

[0032] The mimicry unit can mimic a specific personality using the trained model. For example, the mimicry unit generates voice using the trained speech patterns and generates text using the trained communication style. In this way, the mimicry unit can mimic a specific personality using the trained model.

[0033] The providing unit can provide the user with a dialogue with the imitated personality. The providing unit provides the user with a dialogue experience by using, for example, a voice dialogue system or a text chat system. In this way, the dialogue with the imitated personality can be provided to the user with a dialogue experience.

[0034] When collecting data, the data collection unit can select a data collection method taking into consideration the specific conditions of the person being collected. For example, if the person being collected leads a busy life, the data collection unit prioritizes data that can be collected in a short period of time. In addition, if the person being collected participates in many events, the data collection unit can also collect utterances at the events. In addition, if the person being collected spends a lot of time at home, the data collection unit can also collect conversation data within the home. This makes it possible to select a more appropriate data collection method by taking into consideration the living environment and activity history of the person being collected.

[0035] The data collection unit can filter data based on specific conditions of the person being collected when collecting data. For example, the data collection unit collects utterances made by the person being collected at a specific event. The data collection unit can also collect utterances made by the person being collected in a specific situation. The data collection unit can also collect utterances made by the person being collected at a specific time period. This makes it possible to collect more relevant data by filtering data based on specific events or situations of the person being collected.

[0036] When collecting data, the data collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the person being collected. For example, if the person being collected lives in a specific area, the data collection unit collects utterances made in that area. The data collection unit can also collect utterances made by the person being collected in a specific location. This allows highly relevant data to be prioritized by taking into account the geographical location information of the person being collected.

[0037] During data collection, the data collection unit can analyze the social media activities of the person being collected and collect related data. For example, the data collection unit collects comments made by the person being collected on social media. The data collection unit can also collect comments made by the person being collected on social media. This makes it possible to collect related data by analyzing the social media activities of the person being collected.

[0038] During learning, the learning unit can evaluate the quality of the collected data and select the optimal dataset. For example, the learning unit can remove noise from the voice data and select clear voice data. The learning unit can also correct typos in the text data and select accurate text data. The learning unit can also check the consistency of the data and select highly reliable data. In this way, the quality of the collected data can be evaluated to select the optimal dataset.

[0039] During learning, the learning unit can customize the learning model based on the specific speech patterns and communication styles of the person being collected. For example, if the person being collected has a specific speech pattern, the learning unit learns that pattern. Furthermore, if the person being collected has a specific communication style, the learning unit can also learn that style. Furthermore, if the person being collected has a specific speech pattern or communication style, the learning unit can also learn that pattern or style. In this way, by customizing the learning model based on the specific speech patterns and communication styles of the person being collected, more accurate learning can be performed.

[0040] During learning, the learning unit can weight the learning data by referring to the past utterance history of the person to be collected. For example, the learning unit may learn by placing emphasis on phrases that the person to be collected has frequently used in the past. The learning unit may also learn by placing emphasis on important utterances that the person to be collected has made in the past. The learning unit may also learn by placing emphasis on content that the person to be collected has made in the past on a specific topic. In this way, by referring to the past utterance history of the person to be collected, the learning data can be weighted, enabling more accurate learning.

[0041] During learning, the learning unit can improve the accuracy of the learning model by referring to literature related to the person being collected. The learning unit learns by referring to, for example, books and papers written by the person being collected. The learning unit can also learn by referring to what the person being collected said in an interview. The learning unit can also learn by referring to what the person being collected said in a performance. In this way, by referring to literature related to the person being collected, the accuracy of the learning model can be improved.

[0042] During imitation, the imitation unit can customize the imitation model based on the specific speech pattern or communication style of the person being collected. For example, if the person being collected has a specific speech pattern, the imitation unit imitates that pattern. Furthermore, if the person being collected has a specific communication style, the imitation unit can also imitate that style. Furthermore, if the person being collected has a specific speech pattern or communication style, the imitation unit can also imitate that pattern or style. In this way, by customizing the imitation model based on the specific speech pattern or communication style of the person being collected, more accurate imitation can be performed.

[0043] During imitation, the imitation unit can improve the accuracy of the imitation based on specific conditions of the person to be collected. For example, the imitation unit imitates what the person to be collected says at a specific event. The imitation unit can also imitate what the person to be collected says in a specific situation. The imitation unit can also imitate what the person to be collected says at a specific time period. This allows for more accurate imitation by improving the accuracy of the imitation based on specific events and situations of the person to be collected.

[0044] When imitating, the imitating unit can improve the accuracy of the imitating by taking into account the geographical location information of the person to be collected. For example, if the person to be collected lives in a specific area, the imitating unit imitates utterances made in that area. The imitating unit can also imitate utterances made by the person to be collected in a specific location. In this way, the accuracy of the imitating can be improved by taking into account the geographical location information of the person to be collected.

[0045] The imitation unit can analyze the social media activity of the person to be collected during imitation, thereby improving the accuracy of the imitation. For example, the imitation unit imitates the social media posts of the person to be collected. The imitation unit can also imitate the social media posts of the person to be collected. In this way, by analyzing the social media activity of the person to be collected, the accuracy of the imitation can be improved.

[0046] When providing the dialogue, the providing unit can select the optimal dialogue method by referring to the user's past dialogue history. For example, the providing unit can preferentially provide a dialogue style that the user has preferred in the past. The providing unit can also avoid a dialogue style that the user has avoided in the past. The providing unit can also refer to the content of conversations the user has had in the past on a specific topic. In this way, the optimal dialogue method can be selected by referring to the user's past dialogue history.

[0047] The providing unit can select the optimal dialogue method by taking into consideration the user's geographical location information when providing the dialogue. For example, if the user is in a specific area, the providing unit can provide dialogue related to the area. Furthermore, if the user is in a specific location, the providing unit can also provide dialogue related to the location. In this way, the optimal dialogue method can be selected by taking into consideration the user's geographical location information.

[0048] The providing unit can analyze the user's social media activity and customize the content of the dialogue when providing the dialogue. For example, the providing unit provides the dialogue by referring to the user's comments on social media. The providing unit can also provide the dialogue by referring to the user's comments on social media. In this way, the content of the dialogue can be customized by analyzing the user's social media activity.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The data collection unit can also analyze the user's past interaction history and adjust the type of data to be collected. For example, if the user has frequently interacted with a particular topic in the past, data related to that topic can be collected preferentially. Also, for topics that the user has avoided in the past, collection of data related to that topic can be refrained from. Furthermore, if the user has liked the comments of a particular person in the past, data related to that person can be collected. This makes it possible to collect more relevant data based on the user's past interaction history.

[0051] The providing unit can customize the content of the dialogue taking into account the user's geographical location information. For example, if the user is in a specific area, topics related to that area can be provided. If the user is traveling, information related to the travel destination can be provided. Furthermore, if the user is at home, topics related to the home can be provided. This makes it possible to provide more relevant dialogue based on the user's geographical location information.

[0052] The data collection unit can analyze the social media activity of the person being collected and adjust the type of data to be collected. For example, if the person being collected frequently posts about a particular topic, data related to that topic can be collected preferentially. Also, if the person being collected attends a particular event, data related to that event can be collected. Furthermore, if the person being collected uses a particular hashtag, data related to that hashtag can be collected. This allows for more relevant data to be collected based on the social media activity of the person being collected.

[0053] The learning unit can prioritize learning data related to a specific theme from the collected data. For example, if the person being collected is interested in environmental issues, data related to environmental issues can be prioritized for learning. Also, if the person being collected is interested in health, data related to health can be prioritized for learning. Furthermore, if the person being collected is interested in technology, data related to technology can be prioritized for learning. This makes it possible to learn more appropriate data based on the interests of the person being collected.

[0054] The providing unit can customize the content of the dialogue by referring to the user's past dialogue history. For example, if the user has frequently conversed about a particular topic in the past, topics related to that topic can be provided. Also, for topics that the user has avoided in the past, topics related to that topic can be refrained from. Furthermore, if the user has liked the comments of a particular person in the past, topics related to that person can be provided. This makes it possible to provide more relevant dialogue based on the user's past dialogue history.

[0055] The data collection unit can adjust the type of data to be collected taking into account the geographic location information of the person being collected. For example, if the person being collected lives in a particular area, data related to that area can be collected preferentially. Also, if the person being collected frequently visits a particular place, data related to that place can be collected. Furthermore, if the person being collected participates in a particular event, data related to that event can be collected. This makes it possible to collect more relevant data based on the geographic location information of the person being collected.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The data collection unit collects audio data or text data. Audio data includes, for example, audio file formats (MP3, WAV, etc.), and text data includes, for example, text file formats (TXT, DOC, etc.). The data collection unit collects audio data or text data of deceased individuals or famous people. For example, data such as interview audio, lecture audio, everyday conversation audio, books, blogs, and social media posts may be collected. Step 2: The learning unit uses the collected data to perform machine learning and deep learning. Machine learning uses algorithms such as neural networks and support vector machines, while deep learning uses convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The learning unit uses the collected voice data to learn speech patterns and the collected text data to learn communication styles. Step 3: The mimic uses the trained model to mimic a specific personality. The mimic generates speech using the trained speech patterns and text using the trained communication style. Step 4: The providing unit provides the user with a dialogue with the imitated personality. The providing unit provides the user with a dialogue experience using a voice dialogue system or a text chat system.

[0058] (Example 2) A personality mimicry system according to an embodiment of the present invention uses technologies such as natural language processing, machine learning, and deep learning to learn large amounts of data and human speech patterns and communication styles, thereby mimicking a specific personality. In this system, a user collects voice data and text data of deceased individuals or celebrities, and a learning unit uses the collected data to perform machine learning and deep learning to learn the speech patterns and communication styles. The mimicry unit uses the learned model to mimic a specific personality, and a providing unit provides the user with a dialogue with the mimicked personality. This system can provide emotional fulfillment to surviving family members by mimicking the personality of a deceased individual, and can also provide paid services to fans by mimicking the personality of a celebrity. For example, a data collection unit collects voice data and text data of deceased individuals or celebrities, and a learning unit uses the collected data to perform machine learning and deep learning to learn the speech patterns and communication styles. The mimicry unit uses the learned model to mimic a specific personality, and a providing unit provides the user with a dialogue with the mimicked personality. In this way, the personality imitation system can provide a sense of spiritual fulfillment to the surviving family members by imitating the personality of the deceased, and can also provide paid services to fans by imitating the personality of a celebrity.

[0059] The personality mimicry system according to the embodiment includes a data collection unit, a learning unit, a mimicry unit, and a providing unit. The data collection unit collects audio data or text data. The audio data includes, for example, audio file formats (MP3, WAV, etc.), and the text data includes, for example, text file formats (TXT, DOC, etc.), but is not limited to these examples. The data collection unit collects, for example, audio data or text data of deceased individuals or famous people. For example, the data collection unit can collect interview audio, lecture audio, and everyday conversation audio. The data collection unit can also collect text data such as books, blogs, and social media posts. The learning unit uses the collected data for machine learning and deep learning to learn speech patterns and communication styles. For machine learning, algorithms such as neural networks and support vector machines are used. For deep learning, algorithms such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are used. For example, the learning unit uses the collected audio data to learn speech patterns, and uses the collected text data to learn communication styles. The mimicry unit mimics a specific personality using the learned model. The mimicry unit, for example, generates voice using the learned speech pattern and generates text using the learned communication style. The provision unit provides a user with a dialogue with the mimicked personality. The provision unit provides a dialogue experience to the user using, for example, a voice dialogue system or a text chat system. As a result, the personality mimicry system according to the embodiment can provide a system that mimics a specific personality by collecting, learning, imitating, and providing voice data and text data.

[0060] The data collection unit can collect audio data or text data of a specific person. For example, the data collection unit collects audio data or text data of a deceased person or a famous person. For example, the data collection unit can collect interview audio, lecture audio, everyday conversation audio, etc. The data collection unit can also collect text data such as books, blogs, and social media posts. In this way, collecting audio data or text data of a deceased person or a famous person can provide data for imitating a specific personality.

[0061] The learning unit can perform machine learning and deep learning using the collected data to learn speech patterns or communication styles. The learning unit, for example, learns speech patterns using collected voice data and learns communication styles using collected text data. Algorithms such as neural networks and support vector machines are used for machine learning. Algorithms such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are used for deep learning. This makes it possible to learn speech patterns and communication styles by performing machine learning and deep learning using the collected data.

[0062] The mimicry unit can mimic a specific personality using the trained model. For example, the mimicry unit generates voice using the trained speech patterns and generates text using the trained communication style. In this way, the mimicry unit can mimic a specific personality using the trained model.

[0063] The providing unit can provide the user with a dialogue with the imitated personality. The providing unit provides the user with a dialogue experience by using, for example, a voice dialogue system or a text chat system. In this way, the dialogue with the imitated personality can be provided to the user with a dialogue experience.

[0064] The data collection unit can estimate the user's emotions and adjust the type of data to be collected based on the estimated user emotions. For example, if the user is sad, the data collection unit can prioritize collecting audio data of the deceased. Furthermore, if the user is excited, the data collection unit can also collect the latest interviews and statements of celebrities. Furthermore, if the user is relaxed, the data collection unit can also collect everyday conversation data. By adjusting the type of data to be collected based on the user's emotions, more appropriate data can be collected. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0065] When collecting data, the data collection unit can select a data collection method taking into consideration the specific conditions of the person being collected. For example, if the person being collected leads a busy life, the data collection unit prioritizes data that can be collected in a short period of time. In addition, if the person being collected participates in many events, the data collection unit can also collect utterances at the events. In addition, if the person being collected spends a lot of time at home, the data collection unit can also collect conversation data within the home. This makes it possible to select a more appropriate data collection method by taking into consideration the living environment and activity history of the person being collected.

[0066] The data collection unit can filter data based on specific conditions of the person being collected when collecting data. For example, the data collection unit collects utterances made by the person being collected at a specific event. The data collection unit can also collect utterances made by the person being collected in a specific situation. The data collection unit can also collect utterances made by the person being collected at a specific time period. This makes it possible to collect more relevant data by filtering data based on specific events or situations of the person being collected.

[0067] The data collection unit can estimate the user's emotions and prioritize the data to be collected based on the estimated user emotions. For example, if the user is sad, the data collection unit can prioritize collecting audio data of a deceased person. Furthermore, if the user is excited, the data collection unit can also collect the latest interviews and statements of celebrities. Furthermore, if the user is relaxed, the data collection unit can also collect everyday conversation data. By prioritizing the data to be collected based on the user's emotions, more appropriate data can be collected preferentially. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0068] When collecting data, the data collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the person being collected. For example, if the person being collected lives in a specific area, the data collection unit collects utterances made in that area. The data collection unit can also collect utterances made by the person being collected in a specific location. This allows highly relevant data to be prioritized by taking into account the geographical location information of the person being collected.

[0069] During data collection, the data collection unit can analyze the social media activities of the person being collected and collect related data. For example, the data collection unit collects comments made by the person being collected on social media. The data collection unit can also collect comments made by the person being collected on social media. This makes it possible to collect related data by analyzing the social media activities of the person being collected.

[0070] The learning unit can estimate the user's emotions and adjust the parameters of the learning algorithm based on the estimated user emotions. For example, if the user is sad, the learning unit learns a speech pattern that soothes the emotion. The learning unit can also learn an energetic speech pattern if the user is excited. The learning unit can also learn a calm speech pattern if the user is relaxed. This allows for more appropriate learning by adjusting the parameters of the learning algorithm based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0071] During learning, the learning unit can evaluate the quality of the collected data and select the optimal dataset. For example, the learning unit can remove noise from the voice data and select clear voice data. The learning unit can also correct typos in the text data and select accurate text data. The learning unit can also check the consistency of the data and select highly reliable data. In this way, the quality of the collected data can be evaluated to select the optimal dataset.

[0072] During learning, the learning unit can customize the learning model based on the specific speech patterns and communication styles of the person being collected. For example, if the person being collected has a specific speech pattern, the learning unit learns that pattern. Furthermore, if the person being collected has a specific communication style, the learning unit can also learn that style. Furthermore, if the person being collected has a specific speech pattern or communication style, the learning unit can also learn that pattern or style. In this way, by customizing the learning model based on the specific speech patterns and communication styles of the person being collected, more accurate learning can be performed.

[0073] The learning unit can estimate the user's emotions and determine learning priorities based on the estimated user emotions. For example, if the user is sad, the learning unit prioritizes learning speech patterns that soothe the emotions. Also, if the user is excited, the learning unit can prioritize learning energetic speech patterns. Also, if the user is relaxed, the learning unit can prioritize learning calm speech patterns. This allows for more appropriate learning by determining learning priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0074] During learning, the learning unit can weight the learning data by referring to the past utterance history of the person to be collected. For example, the learning unit may learn by placing emphasis on phrases that the person to be collected has frequently used in the past. The learning unit may also learn by placing emphasis on important utterances that the person to be collected has made in the past. The learning unit may also learn by placing emphasis on content that the person to be collected has made in the past on a specific topic. In this way, by referring to the past utterance history of the person to be collected, the learning data can be weighted, enabling more accurate learning.

[0075] During learning, the learning unit can improve the accuracy of the learning model by referring to literature related to the person being collected. The learning unit learns by referring to, for example, books and papers written by the person being collected. The learning unit can also learn by referring to what the person being collected said in an interview. The learning unit can also learn by referring to what the person being collected said in a performance. In this way, by referring to literature related to the person being collected, the accuracy of the learning model can be improved.

[0076] The mimicry unit can estimate the user's emotions and adjust the expression style of the mimicked personality based on the estimated user emotions. For example, if the user is sad, the mimicry unit can mimic the user in a gentle tone. If the user is excited, the mimicry unit can mimic the user in an energetic tone. If the user is relaxed, the mimicry unit can mimic the user in a gentle tone. This allows for more appropriate mimicry by adjusting the expression style of the mimicked personality based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0077] During imitation, the imitation unit can customize the imitation model based on the specific speech pattern or communication style of the person being collected. For example, if the person being collected has a specific speech pattern, the imitation unit imitates that pattern. Furthermore, if the person being collected has a specific communication style, the imitation unit can also imitate that style. Furthermore, if the person being collected has a specific speech pattern or communication style, the imitation unit can also imitate that pattern or style. In this way, by customizing the imitation model based on the specific speech pattern or communication style of the person being collected, more accurate imitation can be performed.

[0078] During imitation, the imitation unit can improve the accuracy of the imitation based on specific conditions of the person to be collected. For example, the imitation unit imitates what the person to be collected says at a specific event. The imitation unit can also imitate what the person to be collected says in a specific situation. The imitation unit can also imitate what the person to be collected says at a specific time period. This allows for more accurate imitation by improving the accuracy of the imitation based on specific events and situations of the person to be collected.

[0079] The mimicry unit can estimate the user's emotions and determine the priority of personalities to imitate based on the estimated user emotions. For example, if the user is sad, the mimicry unit can prioritize imitating the personality of a deceased person. Also, if the user is excited, the mimicry unit can prioritize imitating the personality of a famous person. Also, if the user is relaxed, the mimicry unit can mimic everyday conversation. This allows for more appropriate imitations by determining the priority of personalities to imitate based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0080] When imitating, the imitating unit can improve the accuracy of the imitating by taking into account the geographical location information of the person to be collected. For example, if the person to be collected lives in a specific area, the imitating unit imitates utterances made in that area. The imitating unit can also imitate utterances made by the person to be collected in a specific location. In this way, the accuracy of the imitating can be improved by taking into account the geographical location information of the person to be collected.

[0081] The imitation unit can analyze the social media activity of the person to be collected during imitation, thereby improving the accuracy of the imitation. For example, the imitation unit imitates the social media posts of the person to be collected. The imitation unit can also imitate the social media posts of the person to be collected. In this way, by analyzing the social media activity of the person to be collected, the accuracy of the imitation can be improved.

[0082] The providing unit can estimate the user's emotions and adjust the way the dialogue is expressed based on the estimated user's emotions. For example, if the user is sad, the providing unit can provide the dialogue in a gentle tone. Also, if the user is excited, the providing unit can provide the dialogue in an energetic tone. Also, if the user is relaxed, the providing unit can provide the dialogue in a gentle tone. In this way, by adjusting the way the dialogue is expressed based on the user's emotions, it is possible to provide a more appropriate dialogue. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0083] When providing the dialogue, the providing unit can select the optimal dialogue method by referring to the user's past dialogue history. For example, the providing unit can preferentially provide a dialogue style that the user has preferred in the past. The providing unit can also avoid a dialogue style that the user has avoided in the past. The providing unit can also refer to the content of conversations the user has had in the past on a specific topic. In this way, the optimal dialogue method can be selected by referring to the user's past dialogue history.

[0084] The providing unit can estimate the user's emotions and determine the priority of dialogues based on the estimated user's emotions. For example, if the user is sad, the providing unit can prioritize providing dialogues that soothe the emotions. Furthermore, if the user is excited, the providing unit can prioritize providing energetic dialogues. Furthermore, if the user is relaxed, the providing unit can prioritize providing calm dialogues. In this way, by determining the priority of dialogues based on the user's emotions, more appropriate dialogues can be provided. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0085] The providing unit can select the optimal dialogue method by taking into consideration the user's geographical location information when providing the dialogue. For example, if the user is in a specific area, the providing unit can provide dialogue related to the area. Furthermore, if the user is in a specific location, the providing unit can also provide dialogue related to the location. In this way, the optimal dialogue method can be selected by taking into consideration the user's geographical location information.

[0086] The providing unit can analyze the user's social media activity and customize the content of the dialogue when providing the dialogue. For example, the providing unit provides the dialogue by referring to the user's comments on social media. The providing unit can also provide the dialogue by referring to the user's comments on social media. In this way, the content of the dialogue can be customized by analyzing the user's social media activity. === Hard Collateral 1-1 === Each of the multiple elements, including the data collection unit, learning unit, imitation unit, and provision 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 data collection unit collects voice data and text data using the camera 42 and microphone 38B of the smart device 14. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs machine learning and deep learning using the collected data. The imitation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and imitates a specific personality using the learned model. The provision unit is realized, for example, by the control unit 46A of the smart device 14 and provides the user with a dialogue with the imitated personality. === Hard Collateral 1-2 === Each of the multiple elements, including the data collection unit, learning unit, imitation unit, and provision 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 data collection unit collects voice data and text data using the camera 42 and microphone 238 of the smart glasses 214. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and performs machine learning and deep learning using the collected data. The imitation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and imitates a specific personality using the learned model. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214, and provides the user with a dialogue with the imitated personality. === Hard Collateral 1-3 === Each of the multiple elements including the data collection unit, learning unit, imitation unit, and provision 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 data collection unit collects voice data and text data using the camera 42 and microphone 238 of the headset type terminal 314. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and performs machine learning and deep learning using the collected data. The imitation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and imitates a specific personality using a learned model. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314, and provides the user with a dialogue with the imitated personality. === Hard Collateral 1-4 === Each of the multiple elements including the data collection unit, learning unit, imitation unit, and provision unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the data collection unit collects voice data and text data using the camera 42 and microphone 238 of the robot 414. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and performs machine learning and deep learning using the collected data. The imitation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and imitates a specific personality using a learned model. The provision unit is realized, for example, by the control unit 46A of the robot 414, and provides the user with a dialogue with the imitated personality.

[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] The data collection unit can also analyze the user's past interaction history and adjust the type of data to be collected. For example, if the user has frequently interacted with a particular topic in the past, data related to that topic can be collected preferentially. Also, for topics that the user has avoided in the past, collection of data related to that topic can be refrained from. Furthermore, if the user has liked the comments of a particular person in the past, data related to that person can be collected. This makes it possible to collect more relevant data based on the user's past interaction history.

[0089] The learning unit can prioritize learning data that includes specific emotions from the collected data. For example, if the user is sad, speech patterns that express sadness can be prioritized for learning. Also, if the user is happy, speech patterns that express joy can be prioritized for learning. Furthermore, if the user is angry, speech patterns that express anger can be prioritized for learning. This makes it possible to learn more appropriate speech patterns based on the user's emotions.

[0090] The mimicry unit can estimate the user's emotions and adjust the speech rate of the imitated personality based on the estimated user's emotions. For example, if the user is relaxed, the imitator can imitate the user at a slower speech rate. If the user is excited, the imitator can imitate the user at a faster speech rate. Furthermore, if the user is sad, the imitator can imitate the user at a calmer speech rate. This allows for more natural dialogue by adjusting the speech rate based on the user's emotions.

[0091] The providing unit can customize the content of the dialogue taking into account the user's geographical location information. For example, if the user is in a specific area, topics related to that area can be provided. If the user is traveling, information related to the travel destination can be provided. Furthermore, if the user is at home, topics related to the home can be provided. This makes it possible to provide more relevant dialogue based on the user's geographical location information.

[0092] The data collection unit can analyze the social media activity of the person being collected and adjust the type of data to be collected. For example, if the person being collected frequently posts about a particular topic, data related to that topic can be collected preferentially. Also, if the person being collected attends a particular event, data related to that event can be collected. Furthermore, if the person being collected uses a particular hashtag, data related to that hashtag can be collected. This allows for more relevant data to be collected based on the social media activity of the person being collected.

[0093] The learning unit can prioritize learning data related to a specific theme from the collected data. For example, if the person being collected is interested in environmental issues, data related to environmental issues can be prioritized for learning. Also, if the person being collected is interested in health, data related to health can be prioritized for learning. Furthermore, if the person being collected is interested in technology, data related to technology can be prioritized for learning. This makes it possible to learn more appropriate data based on the interests of the person being collected.

[0094] The mimicry unit can estimate the user's emotions and adjust the gestures of the mimicking character based on the estimated user's emotions. For example, if the user is relaxed, the mimicry unit can mimic a calm gesture. If the user is excited, the mimicry unit can mimic a lively gesture. Furthermore, if the user is sad, the mimicry unit can mimic a subdued gesture. This allows for more natural interaction by adjusting the gestures based on the user's emotions.

[0095] The providing unit can customize the content of the dialogue by referring to the user's past dialogue history. For example, if the user has frequently conversed about a particular topic in the past, topics related to that topic can be provided. Also, for topics that the user has avoided in the past, topics related to that topic can be refrained from. Furthermore, if the user has liked the comments of a particular person in the past, topics related to that person can be provided. This makes it possible to provide more relevant dialogue based on the user's past dialogue history.

[0096] The data collection unit can adjust the type of data to be collected taking into account the geographic location information of the person being collected. For example, if the person being collected lives in a particular area, data related to that area can be collected preferentially. Also, if the person being collected frequently visits a particular place, data related to that place can be collected. Furthermore, if the person being collected participates in a particular event, data related to that event can be collected. This makes it possible to collect more relevant data based on the geographic location information of the person being collected.

[0097] The providing unit can estimate the user's emotions and adjust the tone of the dialogue based on the estimated user's emotions. For example, if the user is sad, the dialogue can be provided in a gentle tone. If the user is excited, the dialogue can be provided in an energetic tone. Furthermore, if the user is relaxed, the dialogue can be provided in a calm tone. In this way, by adjusting the tone of the dialogue based on the user's emotions, it is possible to provide a more appropriate dialogue.

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

[0099] Step 1: The data collection unit collects audio data or text data. Audio data includes, for example, audio file formats (MP3, WAV, etc.), and text data includes, for example, text file formats (TXT, DOC, etc.). The data collection unit collects audio data or text data of deceased individuals or famous people. For example, data such as interview audio, lecture audio, everyday conversation audio, books, blogs, and social media posts may be collected. Step 2: The learning unit uses the collected data to perform machine learning and deep learning. Machine learning uses algorithms such as neural networks and support vector machines, while deep learning uses convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The learning unit uses the collected voice data to learn speech patterns and the collected text data to learn communication styles. Step 3: The mimic uses the trained model to mimic a specific personality. The mimic generates speech using the trained speech patterns and text using the trained communication style. Step 4: The providing unit provides the user with a dialogue with the imitated personality. The providing unit provides the user with a dialogue experience using a voice dialogue system or a text chat system.

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

[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 data collection unit that collects voice data or text data; a learning unit that performs machine learning and deep learning using the data collected by the data collection unit; an imitating unit that imitates a personality using the model learned by the learning unit; a providing unit that provides a dialogue with the personality imitated by the imitating unit; Equipped with A system characterized by:

2. The data collection unit Collecting voice or text data from a specific person 2. The system of claim 1.

3. The learning unit Use machine learning and deep learning to learn speech patterns or communication styles using collected data 2. The system of claim 1.

4. The mimicking portion is Using trained models to mimic specific personalities 2. The system of claim 1.

5. The providing unit Providing users with interaction with an imitated personality 2. The system of claim 1.

6. The data collection unit Inferring user sentiment and adjusting the type of data collected based on the estimated user sentiment 2. The system of claim 1.

7. The data collection unit When collecting data, choose a method of collecting data taking into account the specific conditions of the person being collected.

2. The system of claim 1.

8. The data collection unit When collecting data, filter the data based on specific criteria for the person being collected 2. The system of claim 1.

Images