System

Abstract

An object of the system according to the embodiment is to digitize analog literature materials and reproduce wording and thought patterns of each era.SOLUTION: A system includes a literature digitalization part, a generation AI learning part, a language model part, and a chat part. The literature digitizing unit digitizes the analog literature material. The generated AI learning unit learns the documents digitized by the document digitizing unit. The language model unit reproduces the wording and thought pattern of each period based on the content learned by the generative AI learning unit. The chat unit interacts with the user using the wording and thought pattern reproduced by the language model unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has not been able to adequately digitize analog documents and reproduce the language and thought patterns of each era, making it difficult to gain a deep understanding of historical context.

[0005] The system according to the embodiment aims to digitize analog documentary materials and reproduce the language and thought patterns of each era. [Means for solving the problem]

[0006] The system according to the embodiment includes a document digitization unit, a generative AI learning unit, a language model unit, and a chat unit. The document digitization unit digitizes analog document materials. The generative AI learning unit learns the documents digitized by the document digitization unit. The language model unit reproduces the language and thought patterns of each era based on the content learned by the generative AI learning unit. The chat unit interacts with users using the language and thought patterns reproduced by the language model unit. [Effects of the Invention]

[0007] The system according to the embodiment can digitize analog documentary materials and reproduce the language and thought patterns of each era. [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 nonvolatile storage devices that store various programs, various parameters, etc. Examples of nonvolatile 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The Time Machine Chat AI system, an embodiment of the present invention, is a pseudo-time travel AI service centered on a Japanese large-scale language model (LLM) rooted in the historical context from the Heian period to the early Heisei period. This system digitizes a vast amount of analog documents from before the widespread use of the Internet. A generative AI system that learns historical contexts such as culture, art, and politics recreates the language and thought patterns of people from each era. This language model also enables mutual translation of Japanese from ancient to modern times. Users can experience an immersive experience through chat. This system can be used as a tool for researchers to analyze history from new perspectives, to help film and drama scriptwriters enhance the realism of their works through historical research, and as entertainment for general users to enjoy historical experiences for educational and recreational purposes. This allows the Time Machine Chat AI system to connect history with the present and provide an innovative service that brings history closer to people through dialogue with people from the past.

[0029] The time machine chat AI system according to the embodiment includes a document digitization unit, a generative AI learning unit, a language model unit, and a chat unit. The document digitization unit digitizes analog document materials. For example, it scans handwritten manuscripts and saves them as image data. It can also scan books and magazines and convert them into digital data. It can also convert printed documents into text data using OCR technology. The generative AI learning unit learns the digitized documents. For example, the generative AI analyzes and learns the content of the document using a text generation AI (e.g., LLM). The generative AI can also learn the content of the document from multiple perspectives using a multimodal generative AI. The generative AI can also extract and learn important parts of the document. The language model unit reproduces the language and thought patterns of each era based on the content learned by the generative AI learning unit. For example, the language model unit reproduces the language and etiquette of aristocrats in the Heian period. It can also reproduce the commercial terminology and trading practices of merchants in the Edo period. The language model unit can also translate modern Japanese into Heian-period language. The chat unit converses with the user using the language and thought patterns reproduced by the language model unit. For example, it can simulate a user conversing with an aristocrat from the Heian period. It can also simulate a user doing business with a merchant from the Edo period. It can also allow a user to converse by translating modern Japanese into language from the Heian period. In this way, the time machine chat AI system according to the embodiment allows a user to experience the language and thought patterns of each era.

[0030] The document digitization department can use generative AI to automatically classify the contents of documents and organize them by era. For example, the document digitization department scans document materials, and generative AI automatically converts them into text data. The document contents are then analyzed and classified by era, such as the Heian period, Edo period, and Meiji period. The document digitization department also uses an algorithm to automatically classify the contents of documents using generative AI and organize them by era. For example, the generative AI analyzes the contents of documents and classifies them based on specific keywords or phrases. The document digitization department also builds a system that automatically classifies the contents of documents using generative AI and organizes them by era. For example, the generative AI analyzes the contents of documents and classifies them into categories by era. This allows the contents of documents to be efficiently classified and organized by era.

[0031] The generative AI learning unit can automatically annotate digitized documents, explaining their background and important points. For example, the generative AI learning unit analyzes digitized documents and annotates important keywords and phrases. For example, it adds annotations about historical events and people. The generative AI learning unit also uses an algorithm to automatically add annotations that explain the background and important points of documents. For example, the generative AI analyzes the content of documents and adds annotations based on specific keywords and phrases. The generative AI learning unit also builds a system that automatically adds annotations that explain the background and important points of documents. For example, the generative AI analyzes the content of documents and adds annotations about the background and important points. This makes it possible to automatically explain the background and important points of documents.

[0032] The generative AI learning unit can convert digitized documents into audio data and provide an audio historical experience. The generative AI learning unit, for example, analyzes digitized documents and converts them into audio data using speech synthesis technology. For example, it can reproduce documents from the Heian period in audio and play them for the user. The generative AI learning unit also converts digitized documents into audio data and uses an algorithm to provide an audio historical experience. For example, the generative AI analyzes the contents of the documents and converts them into audio data. The generative AI learning unit also builds a system that converts digitized documents into audio data and provides an audio historical experience. For example, the generative AI analyzes the contents of the documents and converts them into audio data, which is then provided to the user. This allows for an audio historical experience to be provided.

[0033] The generative AI learning unit can compare documents from different eras and automatically extract similarities and differences. For example, the generative AI learning unit analyzes documents from different eras and automatically extracts similarities and differences. For example, it compares the differences between the political systems of the Heian and Edo periods. The generative AI learning unit also uses an algorithm to compare documents from different eras and automatically extract similarities and differences. For example, the generative AI analyzes the content of the documents and extracts similarities and differences based on specific keywords and phrases. The generative AI learning unit also builds a system that compares documents from different eras and automatically extracts similarities and differences. For example, the generative AI analyzes the content of the documents and extracts similarities and differences. This makes it possible to automatically extract similarities and differences between documents from different eras.

[0034] When recreating the language usage and thought patterns of each era, the language model unit can recreate language specialized for specific people or occupations. For example, the generative AI in the language model unit recreates the language and etiquette of aristocrats in the Heian period. For example, it simulates the language used in aristocratic daily conversations and in official settings. The language model unit also uses an algorithm to recreate language specialized for specific people or occupations. For example, the generative AI recreates language based on a specific person or occupation. The language model unit also builds a system that recreates language specialized for specific people or occupations. For example, the generative AI recreates language based on a specific person or occupation. This makes it possible to recreate language specialized for specific people or occupations.

[0035] The language model unit can simulate the social issues and events of the time and reflect their influence in order to recreate the language and thought patterns of each era. For example, the generation AI simulates social issues and events of the Heian period and recreates language and thought patterns that reflect their influence. For example, it recreates political maneuvering among aristocrats. The language model unit also uses an algorithm to simulate social issues and events of the time and reflect their influence. For example, the generation AI simulates social issues and events and reflects their influence. The language model unit also builds a system that simulates social issues and events of the time and reflects their influence. For example, the generation AI simulates social issues and events and reflects their influence. This makes it possible to recreate language and thought patterns that reflect the social issues and events of the time.

[0036] When reproducing the language usage and thought patterns of each era, the language model unit can also reproduce the language usage of different regions and cultural spheres. For example, the generation AI in the language model unit reproduces not only the language usage of aristocrats in the Heian period, but also the language usage of rural peasants. For example, it simulates a conversation between an aristocrat and a peasant. The language model unit also uses algorithms to reproduce the language usage of different regions and cultural spheres. For example, the generation AI reproduces language usage based on the region or cultural sphere. The language model unit also builds a system that reproduces the language usage of different regions and cultural spheres. For example, the generation AI reproduces language usage based on the region or cultural sphere. This makes it possible to reproduce the language usage of different regions and cultural spheres.

[0037] The language usage and thought patterns reproduced by the language model unit can be used as educational materials to improve the quality of history education. For example, the language model unit uses the language usage and thought patterns of the Heian period reproduced by the generative AI as teaching materials to improve the quality of history education. For example, it creates teaching materials to learn about the lives and culture of aristocrats. The language model unit also uses an algorithm to use the reproduced language and thought patterns as educational materials. For example, it creates teaching materials based on the language usage and thought patterns reproduced by the generative AI. The language model unit also builds a system that uses the reproduced language and thought patterns as educational materials. For example, it creates teaching materials based on the language usage and thought patterns reproduced by the generative AI. This can be used to improve the quality of history education.

[0038] The language model unit can refer to relevant historical background when performing mutual translation of Japanese to understand the context and provide an appropriate translation. For example, when the generation AI translates classical texts from the Heian period into modern Japanese, the language model unit understands the context and refers to relevant historical background. For example, the translation takes into account the culture and customs of the Heian period. The language model unit also uses an algorithm that refers to relevant historical background to understand the context and provide an appropriate translation. For example, the generation AI analyzes the context and refers to the historical background. The language model unit also builds a system that refers to relevant historical background to understand the context and provide an appropriate translation. For example, the generation AI analyzes the context and refers to the historical background. This makes it possible to provide an appropriate translation that takes the context and historical background into consideration.

[0039] The language model unit can automatically annotate the translation results and explain the intention and background of the translation. For example, when the generation AI translates classical Japanese from the Heian period into modern Japanese, the language model unit annotates the translation results. For example, it adds annotations explaining the meaning of specific expressions and terms in the classical Japanese. The language model unit also uses an algorithm to automatically annotate the translation results and explain the intention and background of the translation. For example, the generation AI analyzes the translation results and adds annotations. The language model unit also builds a system that automatically annotates the translation results and explains the intention and background of the translation. For example, the generation AI analyzes the translation results and adds annotations. This makes it possible to automatically add annotations explaining the intention and background of the translation.

[0040] The language model unit enables translation between different languages ​​when performing mutual translation of Japanese, thereby promoting historical understanding from a global perspective. For example, the generative AI not only translates classical Heian period texts into modern Japanese, but also translates them into different languages ​​such as English and French. For example, it understands the culture and customs of the Heian period in multiple languages. The language model unit also enables translation between different languages ​​and uses algorithms that promote historical understanding from a global perspective. For example, the generative AI translates into different languages. The language model unit also enables translation between different languages, building a system that promotes historical understanding from a global perspective. For example, the generative AI translates into different languages. This makes it possible to promote historical understanding from a global perspective through translation between different languages.

[0041] The language model unit can automatically convert translated documents into audio data and provide audio translation results. For example, the language model unit uses an algorithm to automatically convert translated documents into audio data and provide audio translation results. For example, the generation AI translates classical Heian period text into modern Japanese and converts the translation results into audio data. For example, the language model unit recreates the culture and customs of the Heian period through audio. The language model unit also uses an algorithm to automatically convert translated documents into audio data and provide audio translation results. For example, the generation AI converts the translation results into audio data. The language model unit also builds a system to automatically convert translated documents into audio data and provide audio translation results. For example, the generation AI converts the translation results into audio data. This allows the translation results to be provided audio.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The Time Machine Chat AI system can also analyze the user's speech rate and intonation to provide audio feedback tailored to the language and thought patterns of each era. For example, it can recreate the relaxed speech of a Heian-period aristocrat or the lively speech of an Edo-period merchant. It can also analyze the user's speech data and convert it into the appropriate language and intonation of the era, allowing users to have a more realistic historical experience.

[0044] The document digitization unit can also automatically summarize the contents of documents and provide them to users. For example, it can extract the main points of long documents and display them as short summaries. It can also highlight important parts of documents, allowing users to efficiently grasp the contents of documents.

[0045] The generative AI learning unit can compare documents from different eras and automatically extract similarities and differences. For example, it can compare the differences in political systems between the Heian and Edo periods. It can also compare the cultural transitions between the Meiji and Showa periods. This makes it possible to automatically extract similarities and differences between documents from different eras.

[0046] The generative AI learning unit can convert digitized documents into audio data and provide an audio historical experience. For example, it can reproduce audio documents from the Heian period and let users listen to them. It can also reproduce audio of merchant transactions from the Edo period. This allows for an audio historical experience.

[0047] When recreating the language and thought patterns of each era, the language model can also recreate language specialized for specific people or occupations. For example, it can recreate the language and etiquette of aristocrats in the Heian period. It can also recreate the commercial terminology and trading practices of merchants in the Edo period. This allows it to recreate language specialized for specific people or occupations.

[0048] When performing mutual translation between Japanese languages, the language model unit can understand the context and refer to relevant historical background to provide an appropriate translation. For example, when translating classical texts from the Heian period into modern Japanese, the language model unit understands the context and refers to relevant historical background. Similarly, when translating documents from the Edo period, the language model unit can take historical background into consideration. This allows the system to provide an appropriate translation that takes into account the context and historical background.

[0049] The processing flow of the first embodiment will be briefly explained below.

[0050] Step 1: The Document Digitization Department digitizes analog document materials. For example, handwritten manuscripts are scanned and saved as image data. It can also scan books and magazines and convert them into digital data. It can also convert printed documents into text data using OCR technology. Step 2: The generative AI learning unit learns the digitized document. For example, the generative AI can analyze and learn the content of the document using text generation AI (e.g., LLM). The generative AI can also use multimodal generative AI to learn the content of the document from multiple angles. The generative AI can also extract and learn important parts of the document. Step 3: The language modeling unit recreates the language and thought patterns of each era based on the content learned by the generative AI learning unit. For example, the language modeling unit recreates the language and etiquette of aristocrats in the Heian period. It can also recreate the commercial jargon and trading practices of merchants in the Edo period. The language modeling unit can also translate modern Japanese into Heian-period language. Step 4: The chat unit converses with the user using the language and thought patterns reproduced by the language model unit. For example, it can simulate the user conversing with a Heian-period aristocrat. It can also simulate the user conducting business with a merchant from the Edo period. It can also translate modern Japanese into Heian-period language and converse with the user.

[0051] (Example 2) The Time Machine Chat AI system, an embodiment of the present invention, is a pseudo-time travel AI service centered on a Japanese large-scale language model (LLM) rooted in the historical context from the Heian period to the early Heisei period. This system digitizes a vast amount of analog documents from before the widespread use of the Internet. A generative AI system that learns historical contexts such as culture, art, and politics recreates the language and thought patterns of people from each era. This language model also enables mutual translation of Japanese from ancient to modern times. Users can experience an immersive experience through chat. This system can be used as a tool for researchers to analyze history from new perspectives, to help film and drama scriptwriters enhance the realism of their works through historical research, and as entertainment for general users to enjoy historical experiences for educational and recreational purposes. This allows the Time Machine Chat AI system to connect history with the present and provide an innovative service that brings history closer to people through dialogue with people from the past.

[0052] The time machine chat AI system according to the embodiment includes a document digitization unit, a generative AI learning unit, a language model unit, and a chat unit. The document digitization unit digitizes analog document materials. For example, it scans handwritten manuscripts and saves them as image data. It can also scan books and magazines and convert them into digital data. It can also convert printed documents into text data using OCR technology. The generative AI learning unit learns the digitized documents. For example, the generative AI analyzes and learns the content of the document using a text generation AI (e.g., LLM). The generative AI can also learn the content of the document from multiple perspectives using a multimodal generative AI. The generative AI can also extract and learn important parts of the document. The language model unit reproduces the language and thought patterns of each era based on the content learned by the generative AI learning unit. For example, the language model unit reproduces the language and etiquette of aristocrats in the Heian period. It can also reproduce the commercial terminology and trading practices of merchants in the Edo period. The language model unit can also translate modern Japanese into Heian-period language. The chat unit converses with the user using the language and thought patterns reproduced by the language model unit. For example, it can simulate a user conversing with an aristocrat from the Heian period. It can also simulate a user doing business with a merchant from the Edo period. It can also allow a user to converse by translating modern Japanese into language from the Heian period. In this way, the time machine chat AI system according to the embodiment allows a user to experience the language and thought patterns of each era.

[0053] The document digitization department can use generative AI to automatically classify the contents of documents and organize them by era. For example, the document digitization department scans document materials, and generative AI automatically converts them into text data. The document contents are then analyzed and classified by era, such as the Heian period, Edo period, and Meiji period. The document digitization department also uses an algorithm to automatically classify the contents of documents using generative AI and organize them by era. For example, the generative AI analyzes the contents of documents and classifies them based on specific keywords or phrases. The document digitization department also builds a system that automatically classifies the contents of documents using generative AI and organizes them by era. For example, the generative AI analyzes the contents of documents and classifies them into categories by era. This allows the contents of documents to be efficiently classified and organized by era.

[0054] The generative AI learning unit can automatically annotate digitized documents, explaining their background and important points. For example, the generative AI learning unit analyzes digitized documents and annotates important keywords and phrases. For example, it adds annotations about historical events and people. The generative AI learning unit also uses an algorithm to automatically add annotations that explain the background and important points of documents. For example, the generative AI analyzes the content of documents and adds annotations based on specific keywords and phrases. The generative AI learning unit also builds a system that automatically adds annotations that explain the background and important points of documents. For example, the generative AI analyzes the content of documents and adds annotations about the background and important points. This makes it possible to automatically explain the background and important points of documents.

[0055] The generative AI learning unit can use the emotion estimation function to estimate the emotions people felt at the time regarding the content of a document and classify the document based on those emotions. For example, the generative AI learning unit analyzes digitized documents and uses the emotion estimation function to estimate the emotions people felt at the time regarding the content of the document. For example, it classifies emotions such as joy, sadness, and anger. The generative AI learning unit also uses the emotion estimation function to estimate the emotions people felt at the time regarding the content of the document and uses an algorithm to classify the document based on those emotions. For example, the generative AI analyzes the content of a document and classifies it based on specific emotions. The generative AI learning unit also uses the emotion estimation function to estimate the emotions people felt at the time regarding the content of the document and builds a system to classify documents based on those emotions. For example, the generative AI analyzes the content of a document and classifies it into categories based on emotions. This makes it possible to classify documents based on the emotions people felt at the time.

[0056] The generative AI learning unit can convert digitized documents into audio data and provide an audio historical experience. The generative AI learning unit, for example, analyzes digitized documents and converts them into audio data using speech synthesis technology. For example, it can reproduce documents from the Heian period in audio and play them for the user. The generative AI learning unit also converts digitized documents into audio data and uses an algorithm to provide an audio historical experience. For example, the generative AI analyzes the contents of the documents and converts them into audio data. The generative AI learning unit also builds a system that converts digitized documents into audio data and provides an audio historical experience. For example, the generative AI analyzes the contents of the documents and converts them into audio data, which is then provided to the user. This allows for an audio historical experience to be provided.

[0057] The generative AI learning unit can compare documents from different eras and automatically extract similarities and differences. For example, the generative AI learning unit analyzes documents from different eras and automatically extracts similarities and differences. For example, it compares the differences between the political systems of the Heian and Edo periods. The generative AI learning unit also uses an algorithm to compare documents from different eras and automatically extract similarities and differences. For example, the generative AI analyzes the content of the documents and extracts similarities and differences based on specific keywords and phrases. The generative AI learning unit also builds a system that compares documents from different eras and automatically extracts similarities and differences. For example, the generative AI analyzes the content of the documents and extracts similarities and differences. This makes it possible to automatically extract similarities and differences between documents from different eras.

[0058] The generative AI learning unit can use the emotion estimation function to collect modern users' emotional reactions to the content of a document and evaluate the importance of the document based on those reactions. The generative AI learning unit, for example, analyzes digitized documents and uses the emotion estimation function to collect modern users' emotional reactions. For example, it records the emotion scores of users who read the document. The generative AI learning unit also uses the emotion estimation function to collect modern users' emotional reactions to the content of the document and uses an algorithm to evaluate the importance of the document based on those reactions. For example, the generative AI analyzes the content of the document and evaluates the importance based on the user's emotion score. The generative AI learning unit also uses the emotion estimation function to collect modern users' emotional reactions to the content of the document and builds a system to evaluate the importance of the document based on those reactions. For example, the generative AI analyzes the content of the document and evaluates the importance based on the user's emotion score. This makes it possible to evaluate the importance of a document based on the emotional reactions of modern users.

[0059] When recreating the language usage and thought patterns of each era, the language model unit can recreate language specialized for specific people or occupations. For example, the generative AI in the language model unit recreates the language and etiquette of aristocrats in the Heian period. For example, it simulates the language used in aristocratic daily conversations and in official settings. The language model unit also uses an algorithm to recreate language specialized for specific people or occupations. For example, the generative AI recreates language based on a specific person or occupation. The language model unit also builds a system that recreates language specialized for specific people or occupations. For example, the generative AI recreates language based on a specific person or occupation. This makes it possible to recreate language specialized for specific people or occupations.

[0060] The language model unit can simulate the social issues and events of the time and reflect their influence in order to recreate the language and thought patterns of each era. For example, the generation AI simulates social issues and events of the Heian period and recreates language and thought patterns that reflect their influence. For example, it recreates political maneuvering among aristocrats. The language model unit also uses an algorithm to simulate social issues and events of the time and reflect their influence. For example, the generation AI simulates social issues and events and reflects their influence. The language model unit also builds a system that simulates social issues and events of the time and reflects their influence. For example, the generation AI simulates social issues and events and reflects their influence. This makes it possible to recreate language and thought patterns that reflect the social issues and events of the time.

[0061] The language model unit uses the emotion estimation function to recreate the emotions of people in each era and can generate dialogue based on those emotions. In the language model unit, for example, a generation AI recreates the emotions of aristocrats in the Heian period and generates dialogue based on those emotions. For example, it simulates dialogue between aristocrats expressing joy and sadness. The language model unit also uses the emotion estimation function to recreate the emotions of people in each era and uses an algorithm to generate dialogue based on those emotions. For example, the generation AI analyzes emotions and generates dialogue based on those emotions. The language model unit also builds a system that recreates the emotions of people in each era and generates dialogue based on those emotions. For example, the generation AI analyzes emotions and generates dialogue based on those emotions. This makes it possible to generate dialogue based on the emotions of people in each era.

[0062] When reproducing the language usage and thought patterns of each era, the language model unit can also reproduce the language usage of different regions and cultural spheres. For example, the generation AI in the language model unit reproduces not only the language usage of aristocrats in the Heian period, but also the language usage of rural peasants. For example, it simulates a conversation between an aristocrat and a peasant. The language model unit also uses algorithms to reproduce the language usage of different regions and cultural spheres. For example, the generation AI reproduces language usage based on the region or cultural sphere. The language model unit also builds a system that reproduces the language usage of different regions and cultural spheres. For example, the generation AI reproduces language usage based on the region or cultural sphere. This makes it possible to reproduce the language usage of different regions and cultural spheres.

[0063] The language usage and thought patterns reproduced by the language model unit can be used as educational materials to improve the quality of history education. For example, the language model unit uses the language usage and thought patterns of the Heian period reproduced by the generative AI as teaching materials to improve the quality of history education. For example, it creates teaching materials to learn about the lives and culture of aristocrats. The language model unit also uses an algorithm to use the reproduced language and thought patterns as educational materials. For example, it creates teaching materials based on the language usage and thought patterns reproduced by the generative AI. The language model unit also builds a system that uses the reproduced language and thought patterns as educational materials. For example, it creates teaching materials based on the language usage and thought patterns reproduced by the generative AI. This can be used to improve the quality of history education.

[0064] The language model unit can use the emotion estimation function to analyze the emotions felt by a user during a conversation in real time and generate dialogue content corresponding to those emotions. For example, the language model unit uses a generation AI to analyze the user's emotions in real time and generate dialogue content corresponding to those emotions. For example, if the user is happy, it provides an enjoyable topic. The language model unit also uses an algorithm to analyze the emotions felt by a user during a conversation in real time and generate dialogue content corresponding to those emotions using the emotion estimation function. For example, the generation AI analyzes emotions and generates dialogue based on those emotions. The language model unit also builds a system that uses the emotion estimation function to analyze the emotions felt by a user during a conversation in real time and generates dialogue content corresponding to those emotions. For example, the generation AI analyzes emotions and generates dialogue based on those emotions. This makes it possible to generate dialogue content corresponding to the user's emotions in real time.

[0065] The language model unit can refer to relevant historical background when performing mutual translation of Japanese to understand the context and provide an appropriate translation. For example, when the generation AI translates classical texts from the Heian period into modern Japanese, the language model unit understands the context and refers to relevant historical background. For example, the translation takes into account the culture and customs of the Heian period. The language model unit also uses an algorithm that refers to relevant historical background to understand the context and provide an appropriate translation. For example, the generation AI analyzes the context and refers to the historical background. The language model unit also builds a system that refers to relevant historical background to understand the context and provide an appropriate translation. For example, the generation AI analyzes the context and refers to the historical background. This makes it possible to provide an appropriate translation that takes the context and historical background into consideration.

[0066] The language model unit can automatically annotate the translation results and explain the intention and background of the translation. For example, when the generation AI translates classical Japanese from the Heian period into modern Japanese, the language model unit annotates the translation results. For example, it adds annotations explaining the meaning of specific expressions and terms in the classical Japanese. The language model unit also uses an algorithm to automatically annotate the translation results and explain the intention and background of the translation. For example, the generation AI analyzes the translation results and adds annotations. The language model unit also builds a system that automatically annotates the translation results and explains the intention and background of the translation. For example, the generation AI analyzes the translation results and adds annotations. This makes it possible to automatically add annotations explaining the intention and background of the translation.

[0067] The language model unit uses the emotion estimation function to preserve the emotional nuances of documents translated and can provide emotion-based translations. For example, when the generation AI translates classical texts from the Heian period into modern Japanese, the language model unit preserves emotional nuances using the emotion estimation function. For example, a translation that reflects emotions such as joy and sadness is provided. The language model unit also uses an algorithm to preserve the emotional nuances of documents translated using the emotion estimation function and provide emotion-based translations. For example, the generation AI analyzes emotions and performs translations based on those emotions. The language model unit also builds a system that preserves the emotional nuances of documents translated using the emotion estimation function and provides emotion-based translations. For example, the generation AI analyzes emotions and performs translations based on those emotions. This makes it possible to provide translations that preserve emotional nuances.

[0068] The language model unit enables translation between different languages ​​when performing mutual translation of Japanese, thereby promoting historical understanding from a global perspective. For example, the generative AI not only translates classical Heian period texts into modern Japanese, but also translates them into different languages ​​such as English and French. For example, it understands the culture and customs of the Heian period in multiple languages. The language model unit also enables translation between different languages ​​and uses algorithms that promote historical understanding from a global perspective. For example, the generative AI translates into different languages. The language model unit also enables translation between different languages, building a system that promotes historical understanding from a global perspective. For example, the generative AI translates into different languages. This makes it possible to promote historical understanding from a global perspective through translation between different languages.

[0069] The language model unit can automatically convert translated documents into audio data and provide audio translation results. For example, the language model unit uses an algorithm to automatically convert translated documents into audio data and provide audio translation results. For example, the generation AI translates classical Heian period text into modern Japanese and converts the translation results into audio data. For example, the language model unit recreates the culture and customs of the Heian period through audio. The language model unit also uses an algorithm to automatically convert translated documents into audio data and provide audio translation results. For example, the generation AI converts the translation results into audio data. The language model unit also builds a system to automatically convert translated documents into audio data and provide audio translation results. For example, the generation AI converts the translation results into audio data. This allows the translation results to be provided audio.

[0070] The language model unit can collect users' emotional reactions to documents translated using the emotion estimation function and improve the quality of the translation based on those reactions. For example, the language model unit uses a generation AI to translate classical Heian period texts into modern Japanese and collects users' emotional reactions using the emotion estimation function. For example, the language model unit improves the quality of the translation based on the user's emotional score. The language model unit also uses an algorithm to collect users' emotional reactions to documents translated using the emotion estimation function and improve the quality of the translation based on those reactions. For example, the generation AI analyzes users' emotions and improves the quality of the translation based on those emotions. The language model unit also uses the emotion estimation function to collect users' emotional reactions to documents translated and builds a system to improve the quality of the translation based on those reactions. For example, the generation AI analyzes users' emotions and improves the quality of the translation based on those emotions. This makes it possible to improve the quality of the translation based on the users' emotional reactions.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The Time Machine Chat AI system can also analyze the user's speech rate and intonation to provide audio feedback tailored to the language and thought patterns of each era. For example, it can recreate the relaxed speech of a Heian-period aristocrat or the lively speech of an Edo-period merchant. It can also analyze the user's speech data and convert it into the appropriate language and intonation of the era, allowing users to have a more realistic historical experience.

[0073] The document digitization unit can also automatically summarize the contents of documents and provide them to users. For example, it can extract the main points of long documents and display them as short summaries. It can also highlight important parts of documents, allowing users to efficiently grasp the contents of documents.

[0074] The generative AI learning unit uses its emotion estimation function to estimate the emotions felt by people at the time regarding the contents of a document, and can evaluate the importance of the document based on those emotions. For example, it can estimate the emotions felt by aristocrats toward a document from the Heian period and evaluate the importance of the document based on those emotions. It can also estimate the emotions felt by merchants from the Edo period and evaluate the importance of the document based on those emotions. This makes it possible to evaluate the importance of documents based on emotions.

[0075] The generative AI learning unit can compare documents from different eras and automatically extract similarities and differences. For example, it can compare the differences in political systems between the Heian and Edo periods. It can also compare the cultural transitions between the Meiji and Showa periods. This makes it possible to automatically extract similarities and differences between documents from different eras.

[0076] The generative AI learning unit uses its emotion estimation function to collect the emotional reactions of modern users to the content of a document and evaluate the importance of the document based on those reactions. For example, it can record the emotional scores of users who read a document and evaluate the importance of the document based on those scores. It can also improve the content of the document based on the users' emotional reactions. This makes it possible to evaluate the importance of a document based on the emotional reactions of modern users.

[0077] The generative AI learning unit can convert digitized documents into audio data and provide an audio historical experience. For example, it can reproduce audio documents from the Heian period and let users listen to them. It can also reproduce audio of merchant transactions from the Edo period. This allows for an audio historical experience.

[0078] The language model unit can use the emotion estimation function to recreate the emotions of people from each era and generate dialogue based on those emotions. For example, it can recreate the emotions of aristocrats from the Heian period and generate dialogue based on those emotions. It can also recreate the emotions of merchants from the Edo period and generate dialogue based on those emotions. This makes it possible to generate dialogue based on the emotions of people from each era.

[0079] When recreating the language and thought patterns of each era, the language model can also recreate language specialized for specific people or occupations. For example, it can recreate the language and etiquette of aristocrats in the Heian period. It can also recreate the commercial terminology and trading practices of merchants in the Edo period. This allows it to recreate language specialized for specific people or occupations.

[0080] The language model unit uses the emotion estimation function to analyze the emotions felt by the user during a conversation in real time, and can generate dialogue content that corresponds to those emotions. For example, if the user is happy, it can provide a fun topic. Also, if the user is sad, it can generate dialogue content that comforts the user. This makes it possible to generate dialogue content that corresponds to the user's emotions in real time.

[0081] When performing mutual translation between Japanese languages, the language model unit can understand the context and refer to relevant historical background to provide an appropriate translation. For example, when translating classical texts from the Heian period into modern Japanese, the language model unit understands the context and refers to relevant historical background. Similarly, when translating documents from the Edo period, the language model unit can take historical background into consideration. This allows the system to provide an appropriate translation that takes into account the context and historical background.

[0082] The processing flow of the second embodiment will be briefly explained below.

[0083] Step 1: The Document Digitization Department digitizes analog document materials. For example, handwritten manuscripts are scanned and saved as image data. It can also scan books and magazines and convert them into digital data. It can also convert printed documents into text data using OCR technology. Step 2: The generative AI learning unit learns the digitized document. For example, the generative AI can analyze and learn the content of the document using text generation AI (e.g., LLM). The generative AI can also use multimodal generative AI to learn the content of the document from multiple angles. The generative AI can also extract and learn important parts of the document. Step 3: The language modeling unit recreates the language and thought patterns of each era based on the content learned by the generative AI learning unit. For example, the language modeling unit recreates the language and etiquette of aristocrats in the Heian period. It can also recreate the commercial jargon and trading practices of merchants in the Edo period. The language modeling unit can also translate modern Japanese into Heian-period language. Step 4: The chat unit converses with the user using the language and thought patterns reproduced by the language model unit. For example, it can simulate the user conversing with a Heian-period aristocrat. It can also simulate the user conducting business with a merchant from the Edo period. It can also translate modern Japanese into Heian-period language and converse with the user.

[0084] 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.

[0085] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0086] 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.

[0087] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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).

[0093] 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.

[0094] 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.

[0095] 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.

[0096] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0097] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0098] 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.

[0099] 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.

[0100] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0101] 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.

[0102] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0103] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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).

[0108] 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.

[0109] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0110] 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.

[0111] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0112] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0113] 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.

[0114] 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.

[0115] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] 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.

[0117] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0118] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0128] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0129] 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.

[0130] 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.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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."

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0151] 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 document digitization department that digitizes analog document materials; a generation AI learning unit that learns the documents digitized by the document digitization unit; a language model unit that reproduces the language and thought patterns of each era based on the content learned by the generation AI learning unit; a chat unit that converses with a user using the language and thought patterns reproduced by the language model unit. A system characterized by:

2. The document digitization unit The generative AI is used to automatically classify the contents of documents and organize them by era.

2. The system of claim 1.

3. The generation AI learning unit The digitized documents will be converted into audio data to provide an audio historical experience.

2. The system of claim 1.

4. The language model unit When recreating the language and thought patterns of each era, we recreate the language that is specific to certain people or professions.

2. The system of claim 1.

5. The language model unit When translating between Japanese and English, refer to historical background to understand the context and provide an appropriate translation.

2. The system of claim 1.

6. The generation AI learning unit Using the emotion estimation function, we estimate the emotions people felt at the time regarding the content of the document, and classify the document based on those emotions.

2. The system of claim 1.

7. The language model unit Using emotion estimation functionality to recreate the emotions of people from different eras and generate dialogue based on those emotions 2. The system of claim 1.

8. The language model unit Using emotion estimation functionality to collect the user's emotional response to the translated document and improve the quality of the translation based on the response.

2. The system of claim 1.

Images