system

Abstract

The system according to this embodiment aims to translate the content of a web page into multiple languages ​​in real time. [Solution] The system according to this embodiment comprises an acquisition unit, an analysis unit, and a translation unit. The acquisition unit acquires the content of a web page. The analysis unit analyzes the content acquired by the acquisition unit. The translation unit translates the content analyzed by the analysis unit into multiple languages.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to accurately translate the content of a web page into multiple languages in real time.

[0005] The system according to an embodiment aims to translate the content of a web page into multiple languages in real time.

Means for Solving the Problems

[0006] The system according to an embodiment includes an acquisition unit, an analysis unit, and a translation unit. The acquisition unit acquires the content of a web page. The analysis unit analyzes the content acquired by the acquisition unit. The translation unit translates the content analyzed by the analysis unit into multiple languages based thereon.

Effects of the Invention

[0007] The system according to this embodiment can translate the content of a web page into multiple languages ​​in real time. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An AI assistant automatic translation system according to an embodiment of the present invention is a system that translates the content of a web page into multiple languages ​​in real time. This AI assistant automatic translation system acquires, analyzes, and translates the content of a web page into multiple languages. In this process, it refers to a dictionary memory unit to support accurate translation of technical terms and proper nouns. It also includes a learning unit to improve the accuracy of translation based on user feedback. Furthermore, the translation unit operates as a browser extension and can accept the user's selection of a specific dictionary. In addition, the translation unit has a function to estimate the user's emotions and translate the web page based on the estimated emotions. The translated multiple languages ​​are displayed side by side for each predetermined unit of text, and the correspondence between each language is displayed in a way that can be visually understood. For example, the AI ​​assistant automatic translation system acquires the content of a web page. In this process, the acquisition unit acquires the HTML and text data of the web page. For example, it can acquire the content of various web pages, such as news articles and blog posts. Next, it analyzes the acquired content. The analysis unit analyzes the acquired HTML and text data to understand the structure and context of the text. For example, it analyzes the structure of paragraphs, headings, lists, etc., and grasps the meaning of the text. Based on the analyzed content, the system translates it into multiple languages. The translation unit translates the analyzed text into multiple languages ​​in real time. In this process, it refers to a dictionary memory unit to support accurate translation of specialized terms and proper nouns. For example, it refers to dictionaries corresponding to specialized fields such as medicine and law to perform accurate translations. Furthermore, it is equipped with a learning unit to improve translation accuracy based on user feedback. When a user provides feedback on the translation results, the learning unit learns from that feedback and improves the translation process. For example, if a user provides feedback that "this translation is inaccurate," the learning unit improves the translation algorithm based on that information. Because the translation unit operates as a browser extension, users can check the translation results in real time while browsing specific web pages. For example, by installing the extension in browsers such as Chrome or Firefox, the content of web pages can be automatically translated.The system also includes a reception section that accepts the user's selection of a specific dictionary. By selecting the dictionary they wish to use, users can obtain more accurate translation results. For example, they can choose from multiple dictionaries, such as medical dictionaries or technical dictionaries. Furthermore, the translation section has a function to estimate the user's emotions and translate the web page based on those emotions. For example, if a user inputs an emotional sentence, the translation result can be adjusted to take those emotions into account. The translated text in multiple languages ​​is displayed side by side for each predetermined unit of text, making the correspondence between each language visually easy to understand. This makes it easier for users to compare translation results and deepen their understanding. For example, by displaying the English and Japanese translation results side by side, users can check both languages ​​simultaneously. As a result, the AI ​​assistant automatic translation system can translate the content of web pages into multiple languages ​​in real time.

[0029] The AI ​​assistant automatic translation system according to this embodiment comprises an acquisition unit, an analysis unit, and a translation unit. The acquisition unit acquires the content of a web page. For example, the acquisition unit acquires the HTML or text data of a web page. The acquisition unit can acquire the content of various web pages, such as news articles or blog posts. The analysis unit analyzes the content acquired by the acquisition unit. For example, the analysis unit analyzes the acquired HTML or text data to understand the structure and context of the text. The analysis unit analyzes the structure, such as paragraphs, headings, and lists, to grasp the meaning of the text. The translation unit translates the content analyzed by the analysis unit into multiple languages. For example, the translation unit translates the analyzed text into multiple languages ​​in real time. The translation unit refers to a dictionary memory unit to support accurate translation of technical terms and proper nouns. The translation unit refers to dictionaries corresponding to specialized fields such as medicine and law to perform accurate translations. Some or all of the above-described processes in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can take the content analyzed by the analysis unit as input and perform translation using an AI model that translates into multiple languages. As a result, the AI ​​assistant automatic translation system according to this embodiment can translate the content of a web page into multiple languages ​​in real time.

[0030] The acquisition unit acquires the content of web pages. For example, the acquisition unit acquires HTML and text data of web pages. Specifically, the acquisition unit uses a web crawler to visit various web pages on the internet and collects HTML data from specified URLs. The web crawler can also automatically collect related pages by following links. The acquisition unit can acquire the content of various web pages, such as articles on news sites and blog posts. For example, it can collect the latest news articles from news sites and personal opinions and reviews from blogs. The acquisition unit temporarily stores the collected data and performs data preprocessing before passing it to the analysis unit. Preprocessing includes removing HTML tags and normalizing text. This allows the analysis unit to analyze the data efficiently. Furthermore, the acquisition unit also has a function to filter data based on specific keywords and topics. This allows the user to collect only specific information of interest. For example, it can prioritize the acquisition of information related to specific news topics or industries. The acquisition unit can periodically update the collected data to provide the latest information. As a result, the automatic translation system AI assistant according to the embodiment can always acquire the latest web page content and provide a foundation for real-time translation.

[0031] The analysis unit analyzes the content acquired by the acquisition unit. For example, the analysis unit analyzes acquired HTML and text data to understand the structure and context of the text. Specifically, the analysis unit uses natural language processing (NLP) techniques to tokenize text data, tag parts of speech, and perform syntactic analysis. Tokenization divides the text into words and phrases, and part of speech tagging identifies the part of speech of each word. Syntactic analysis analyzes the grammatical structure of the text, clarifying relationships such as subject, predicate, and object. The analysis unit analyzes the structure of paragraphs, headings, lists, etc., to grasp the meaning of the text. For example, it analyzes HTML tags to identify heading tags (h1, h2, h3, etc.) and list tags (ul, ol, li, etc.) to understand the hierarchical structure of the text. Furthermore, the analysis unit performs coreference analysis and semantic role labeling to understand the context. Coreference analysis identifies what pronouns and demonstratives in the text refer to, and semantic role labeling identifies the role that each word plays in the text. This allows the analysis unit to deeply understand the meaning of the text and provide accurate information to the translation unit. The analysis unit also has a filtering function that extracts important information from the acquired data and removes unnecessary information. This prepares the translation unit to perform translation work efficiently. The analysis unit stores the analysis results in a database so that they can be used for subsequent processing. As a result, the AI ​​assistant in this embodiment of the automatic translation system can accurately analyze the content of acquired web pages and provide a foundation for translation.

[0032] The translation unit translates the content analyzed by the analysis unit into multiple languages. For example, the translation unit translates the analyzed text into multiple languages ​​in real time. Specifically, the translation unit uses a neural machine translation (NMT) model to translate the analyzed text into the target language. The NMT model is trained using a large amount of translation data and can generate natural translations with high accuracy. The translation unit refers to a dictionary memory unit to support the accurate translation of technical terms and proper nouns. The dictionary memory unit contains dictionaries corresponding to specialized fields such as medicine and law, and by referring to these dictionaries, it can perform accurate translations of technical terms and proper nouns. For example, in the medical field, it is required to accurately translate technical terms such as drug names, disease names, and treatment methods. The translation unit utilizes these specialized dictionaries to provide accurate and consistent translations. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can take the content analyzed by the analysis unit as input and perform translation using an AI model that translates into multiple languages. The AI ​​model performs context-aware translation, understanding the meaning of the entire sentence rather than just individual words. This enables natural and fluent translations. Furthermore, the translation unit can collect user feedback and continuously improve the accuracy of the translation model. As a result, the AI ​​assistant automatic translation system according to this embodiment can translate the content of web pages into multiple languages ​​in real time and provide users with high-quality translations.

[0033] The translation unit can translate technical terms and proper nouns from dictionaries corresponding to the field to which the web page belongs, based on a dictionary memory unit that stores translations of technical terms and proper nouns. For example, the translation unit can refer to a dictionary specialized in the medical field to accurately translate technical terms. It can also refer to a dictionary specialized in the legal field to accurately translate proper nouns. Furthermore, it can refer to a dictionary specialized in the technical field to accurately translate technical terms. This enables accurate translation of technical terms and proper nouns. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input translations of technical terms and proper nouns into an AI model, and the AI ​​model can output the translation results.

[0034] The learning unit can learn the translation process based on user feedback on translations. For example, if a user provides feedback that "this translation is inaccurate," the learning unit will improve the translation algorithm based on that information. The learning unit can improve the accuracy of translations based on user feedback. For example, the learning unit can input user-provided feedback into an AI model, which can then update the translation algorithm. This allows for improved translation accuracy based on user feedback. Some or all of the above processes in the learning unit may be performed using AI, or without AI.

[0035] The translation tool can operate as a browser extension. For example, by installing an extension on a browser such as Chrome or Firefox, the translation tool can automatically translate the content of a webpage. The translation tool allows users to see the translation results in real time while browsing a specific webpage. The translation tool operates as a browser extension and can translate the content of a webpage in real time. This allows users to see the translation results in real time while browsing a specific webpage. Some or all of the above-described processes in the translation tool may be performed using AI, for example, or without AI.

[0036] The reception unit can accept the user's selection of a specific dictionary. For example, by allowing the user to select the dictionary they wish to use, the reception unit can obtain more accurate translation results. The reception unit can select from multiple dictionaries, such as medical dictionaries or technical dictionaries. By allowing the user to select a specific dictionary, the reception unit can improve the accuracy of the translation. This allows the user to obtain more accurate translation results by selecting the dictionary they wish to use. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI.

[0037] The translation unit can display multiple translated languages ​​side-by-side for each predetermined unit of text. For example, by displaying English and Japanese translation results side-by-side, the user can check both languages ​​simultaneously. The translation unit ensures that the correspondence between each language is displayed in a visually understandable manner. This makes it easier for the user to compare translation results and deepen their understanding. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input multiple translated languages ​​into an AI model, which can then visually display the correspondence between each language.

[0038] The acquisition unit can analyze the user's past browsing history and select the optimal acquisition method. For example, the acquisition unit can prioritize acquiring web pages that the user has frequently visited in the past. The acquisition unit can predict web pages that the user will visit at a specific time based on the user's past browsing history and acquire them in advance. The acquisition unit can analyze the user's browsing patterns and propose the optimal acquisition method. This allows the system to select the optimal acquisition method based on the user's past browsing history. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's past browsing history data into a generating AI, which can then select the optimal acquisition method.

[0039] The acquisition unit can filter web pages based on the user's current areas of interest when acquiring them. For example, the acquisition unit can prioritize acquiring web pages related to topics the user is currently interested in. The acquisition unit can filter highly relevant web pages based on the user's current search keywords. The acquisition unit can analyze the user's social media activity and acquire web pages based on their areas of interest. This allows the acquisition of highly relevant web pages based on the user's current areas of interest. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's current areas of interest data into a generating AI, which can then filter highly relevant web pages.

[0040] The acquisition unit can prioritize the acquisition of highly relevant pages based on the user's geographical location information when acquiring web pages. For example, if the user is in a specific region, the acquisition unit will prioritize the acquisition of web pages related to that region. The acquisition unit can prioritize the acquisition of web pages that contain information about locations close to the user's current location. The acquisition unit can acquire web pages that contain local news and event information based on the user's geographical location information. This allows the acquisition of highly relevant web pages based on the user's geographical location information. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's geographical location information data into a generating AI, which can then prioritize the acquisition of highly relevant web pages.

[0041] The acquisition unit can analyze a user's social media activity when acquiring web pages and acquire relevant pages. For example, the acquisition unit can acquire web pages related to articles shared by the user on social media. The acquisition unit can acquire relevant web pages based on the content of posts from accounts that the user follows. The acquisition unit can analyze a user's social media activity history and acquire web pages related to topics of interest. This allows the acquisition of relevant web pages based on the user's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's social media activity data into a generating AI, and the generating AI can acquire relevant web pages.

[0042] The analysis unit can adjust the level of detail of the analysis based on the importance of the text during analysis. For example, the analysis unit can perform a detailed analysis on important texts and a concise analysis on less important texts. The analysis unit can adjust the display order of the analysis results based on the importance of the texts. The analysis unit can perform a particularly detailed analysis on texts containing important keywords. This allows the level of detail of the analysis to be adjusted based on the importance of the texts. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input text importance data into a generating AI, which can then adjust the level of detail of the analysis based on the importance.

[0043] The analysis unit can apply different analysis algorithms depending on the category of the text during analysis. For example, the analysis unit can apply a news-specific analysis algorithm to news articles. For technical documents, it can apply an analysis algorithm specialized for technical terminology. For entertainment articles, it can apply an entertainment-specific analysis algorithm. This allows the analysis unit to apply the most suitable analysis algorithm according to the category of the text. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input text category data into a generating AI, which can then apply an analysis algorithm appropriate to the category.

[0044] The analysis unit can determine the priority of analysis based on the submission date of the documents during analysis. For example, the analysis unit can prioritize the analysis of the most recent documents. The analysis unit can lower the priority of analysis for older documents. The analysis unit can adjust the display order of the analysis results based on the submission date. This allows the analysis priority to be determined based on the submission date of the documents. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the document submission date data into a generating AI, and the generating AI can determine the analysis priority based on the submission date.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the texts during analysis. For example, the analysis unit may prioritize the analysis of texts with high relevance. The analysis unit may lower the priority of analysis for texts with low relevance. The analysis unit can also adjust the display order of the analysis results based on the relevance of the texts. This allows the order of analysis to be adjusted based on the relevance of the texts. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit may input text relevance data into a generating AI, which can then adjust the order of analysis based on the relevance.

[0046] The translation unit can adjust the level of detail of the translation based on the importance of the text during translation. For example, the translation unit can provide detailed translations for important texts and concise translations for less important texts. The translation unit can also adjust the display order of the translation results based on the importance of the texts. The translation unit can provide particularly detailed translations for texts containing important keywords. This allows for adjustment of the level of detail of the translation based on the importance of the texts. Some or all of the above processes in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input text importance data into a generating AI, which can then adjust the level of detail of the translation based on the importance.

[0047] The translation unit can apply different translation algorithms depending on the category of the text during translation. For example, the translation unit can apply a news-specific translation algorithm to news articles. For technical documents, it can apply a translation algorithm specialized for technical terminology. For entertainment articles, it can apply an entertainment-specific translation algorithm. This allows the translation unit to apply the most suitable translation algorithm according to the category of the text. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input text category data into a generating AI, and the generating AI can apply a translation algorithm appropriate to the category.

[0048] The translation department can determine translation priorities based on the submission date of the documents during the translation process. For example, the department may prioritize the translation of the most recent documents. The department may lower the translation priority of older documents. The department may also adjust the display order of the translation results based on the submission date. This allows the department to determine translation priorities based on the submission date of the documents. Some or all of the above processes in the translation department may be performed using AI, for example, or not using AI. For example, the translation department may input document submission date data into a generating AI, which can then determine translation priorities based on the submission date.

[0049] The translation unit can adjust the order of translations based on the relevance of the sentences during translation. For example, the translation unit may prioritize translating sentences that are highly relevant. The translation unit may lower the translation priority of sentences that are less relevant. The translation unit can also adjust the display order of the translation results based on the relevance of the sentences. This allows the order of translations to be adjusted based on the relevance of the sentences. Some or all of the above processes in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit may input sentence relevance data into a generating AI, which can then adjust the order of translations based on relevance.

[0050] The dictionary memory unit can add custom dictionaries based on the user's past translation history. For example, the dictionary memory unit can add specialized terms and proper nouns that the user has translated in the past to the custom dictionary. The dictionary memory unit can add phrases and expressions that the user frequently uses to the custom dictionary. The dictionary memory unit can analyze the user's translation history and create custom dictionaries specialized in specific fields. This allows custom dictionaries to be added based on the user's past translation history. Some or all of the above processes in the dictionary memory unit may be performed using AI, for example, or not using AI. For example, the dictionary memory unit can input the user's translation history data into a generating AI, which can then create a custom dictionary.

[0051] The dictionary memory unit can add specialized dictionaries specific to particular fields. For example, the dictionary memory unit can add specialized dictionaries specific to the medical field. The dictionary memory unit can add specialized dictionaries specific to the legal field. The dictionary memory unit can add specialized dictionaries specific to the technology field. By adding specialized dictionaries specific to particular fields, the accuracy of translation of specialized terminology is improved. Some or all of the above processing in the dictionary memory unit may be performed using AI, for example, or without AI. For example, the dictionary memory unit can input specialized dictionary data specific to a particular field into a generating AI, and the generating AI can add the specialized dictionary.

[0052] The dictionary memory unit can prioritize the use of dictionaries that are highly relevant based on the user's geographical location information. For example, if the user is in a specific region, the dictionary memory unit will prioritize the use of dictionaries related to that region. The dictionary memory unit can prioritize the use of dictionaries that contain information about places close to the user's current location. The dictionary memory unit can prioritize the use of dictionaries that contain regional terminology based on the user's geographical location information. This allows for the priority use of dictionaries that are highly relevant based on the user's geographical location information. Some or all of the above processing in the dictionary memory unit may be performed using AI, for example, or without AI. For example, the dictionary memory unit can input the user's geographical location information data into a generating AI, which can then prioritize the use of dictionaries that are highly relevant.

[0053] The dictionary memory unit can analyze the user's social media activity and use relevant dictionaries. For example, the dictionary memory unit can use dictionaries related to articles the user has shared on social media. The dictionary memory unit can use relevant dictionaries based on the content of posts from accounts the user follows. The dictionary memory unit can analyze the user's social media activity history and use dictionaries related to topics of interest. This allows the dictionary memory unit to use relevant dictionaries based on the user's social media activity. Some or all of the above processing in the dictionary memory unit may be performed using AI, for example, or without AI. For example, the dictionary memory unit can input the user's social media activity data into a generating AI, which can then use relevant dictionaries.

[0054] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can analyze past learning data and adjust the parameters of the learning algorithm. The learning unit can improve the accuracy of the learning algorithm by referring to past learning data. This allows the learning algorithm to be optimized based on past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input past learning data into a generating AI, which can then optimize the learning algorithm.

[0055] The learning unit can weight the training data based on the submission date of the translation history. For example, the learning unit can give a higher weight to the most recent translation history. The learning unit can give a lower weight to older translation history submissions. The learning unit can adjust the weighting of the training data based on the submission date. This allows the training data to be weighted based on the submission date of the translation history. Some or all of the above processing in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input the translation history submission date data into a generating AI, and the generating AI can weight the training data based on the submission date.

[0056] The reception unit can suggest the most suitable dictionary by referring to the user's past dictionary selection history. For example, the reception unit can suggest the most suitable dictionary based on the dictionary the user has selected in the past. The reception unit can analyze the user's past dictionary selection history and suggest dictionaries specialized in a particular field. The reception unit can suggest the most suitable dictionary by referring to the user's dictionary selection history. This allows the reception unit to suggest the most suitable dictionary based on the user's past dictionary selection history. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the user's dictionary selection history data into a generating AI, which can then suggest the most suitable dictionary.

[0057] The reception unit can suggest the most suitable dictionary based on the user's device information. For example, if the user is using a smartphone, the reception unit can suggest a dictionary that matches the screen size. If the user is using a tablet, the reception unit can suggest a dictionary optimized for a larger screen. If the user is using a smartwatch, the reception unit can suggest a concise and highly visible dictionary. This allows the system to suggest the most suitable dictionary based on the user's device information. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the user's device information data into a generating AI, which can then suggest the most suitable dictionary.

[0058] The display unit can select the optimal display method by referring to the user's past display history. For example, the display unit can select the optimal display method based on the display method previously selected by the user. The display unit can analyze the user's past display history and select a display method specialized for a particular field. The display unit can select the optimal display method by referring to the user's display history. This allows the display unit to select the optimal display method based on the user's past display history. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the user's display history data into a generating AI, which can then select the optimal display method.

[0059] The display unit can select the optimal display method based on the user's device information. For example, if the user is using a smartphone, the display unit can provide a display method that matches the screen size. If the user is using a tablet, the display unit can provide a display method optimized for a larger screen. If the user is using a smartwatch, the display unit can provide a concise and highly visible display method. This allows the optimal display method to be selected based on the user's device information. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input user device information data into a generating AI, which can then select the optimal display method.

[0060] The display unit can provide a multilingual display according to the user's language settings. For example, the display unit can automatically set the display language based on the language settings of the user's device. The display unit can provide a language switching function if the user uses multiple languages. The display unit can provide a display in a specific language if the user selects a particular language. This allows the display to be provided in a multilingual format according to the user's language settings. Some or all of the above-described processes in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the user's language setting data into a generating AI, and the generating AI can provide a multilingual display.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] The data acquisition unit can analyze the user's past browsing history and select the optimal acquisition method. For example, it can prioritize the acquisition of web pages that the user has frequently visited in the past. Furthermore, it can predict web pages that the user will visit at specific times based on their past browsing history and acquire them in advance. It can also analyze the user's browsing patterns and suggest the optimal acquisition method. This allows the system to select the optimal acquisition method based on the user's past browsing history.

[0063] The analysis unit can apply different analysis algorithms depending on the category of the text. For example, a news-specific analysis algorithm can be applied to news articles. A technical analysis algorithm specialized for technical terminology can be applied to technical documents. Furthermore, an entertainment-specific analysis algorithm can be applied to entertainment articles. This allows the system to apply the most suitable analysis algorithm according to the category of the text.

[0064] The translation unit can adjust the level of detail in translations based on the importance of the text. For example, it can provide detailed translations for important sentences and concise translations for less important ones. Furthermore, it can adjust the display order of translation results based on the importance of the text. In addition, it can provide particularly detailed translations for sentences containing important keywords. This allows for adjusting the level of detail in translations based on the importance of the text.

[0065] The dictionary memory unit can add specialized dictionaries focused on specific fields. For example, it can add specialized dictionaries for the medical field, for the legal field, or for the technical field. This allows for the addition of specialized dictionaries focused on specific fields, thereby improving the accuracy of translations of technical terms.

[0066] The learning unit can optimize the learning algorithm by referring to past training data. For example, it can select the optimal learning algorithm based on past training data. Furthermore, it can analyze past training data and adjust the parameters of the learning algorithm. It can also improve the accuracy of the learning algorithm by referring to past training data. In this way, the learning algorithm can be optimized based on past training data.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The retrieval unit retrieves the content of the web page. For example, the retrieval unit retrieves the HTML and text data of the web page. The retrieval unit can retrieve the content of various web pages, such as news articles and blog posts. Step 2: The analysis unit analyzes the content acquired by the acquisition unit. For example, the analysis unit analyzes the acquired HTML and text data to understand the structure and context of the text. The analysis unit analyzes the structure of paragraphs, headings, lists, etc., to grasp the meaning of the text. Step 3: The translation unit translates the content analyzed by the analysis unit into multiple languages. For example, the translation unit translates the analyzed text into multiple languages ​​in real time. The translation unit consults the dictionary memory unit to support accurate translation of technical terms and proper nouns. The translation unit consults dictionaries corresponding to specialized fields such as medicine and law to perform accurate translations. Some or all of the above processes in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can use an AI model that takes the content analyzed by the analysis unit as input and translates it into multiple languages ​​to perform the translation.

[0069] (Example of form 2) An AI assistant automatic translation system according to an embodiment of the present invention is a system that translates the content of a web page into multiple languages ​​in real time. This AI assistant automatic translation system acquires, analyzes, and translates the content of a web page into multiple languages. In this process, it refers to a dictionary memory unit to support accurate translation of technical terms and proper nouns. It also includes a learning unit to improve the accuracy of translation based on user feedback. Furthermore, the translation unit operates as a browser extension and can accept the user's selection of a specific dictionary. In addition, the translation unit has a function to estimate the user's emotions and translate the web page based on the estimated emotions. The translated multiple languages ​​are displayed side by side for each predetermined unit of text, and the correspondence between each language is displayed in a way that can be visually understood. For example, the AI ​​assistant automatic translation system acquires the content of a web page. In this process, the acquisition unit acquires the HTML and text data of the web page. For example, it can acquire the content of various web pages, such as news articles and blog posts. Next, it analyzes the acquired content. The analysis unit analyzes the acquired HTML and text data to understand the structure and context of the text. For example, it analyzes the structure of paragraphs, headings, lists, etc., and grasps the meaning of the text. Based on the analyzed content, the system translates it into multiple languages. The translation unit translates the analyzed text into multiple languages ​​in real time. In this process, it refers to a dictionary memory unit to support accurate translation of specialized terms and proper nouns. For example, it refers to dictionaries corresponding to specialized fields such as medicine and law to perform accurate translations. Furthermore, it is equipped with a learning unit to improve translation accuracy based on user feedback. When a user provides feedback on the translation results, the learning unit learns from that feedback and improves the translation process. For example, if a user provides feedback that "this translation is inaccurate," the learning unit improves the translation algorithm based on that information. Because the translation unit operates as a browser extension, users can check the translation results in real time while browsing specific web pages. For example, by installing the extension in browsers such as Chrome or Firefox, the content of web pages can be automatically translated.The system also includes a reception section that accepts the user's selection of a specific dictionary. By selecting the dictionary they wish to use, users can obtain more accurate translation results. For example, they can choose from multiple dictionaries, such as medical dictionaries or technical dictionaries. Furthermore, the translation section has a function to estimate the user's emotions and translate the web page based on those emotions. For example, if a user inputs an emotional sentence, the translation result can be adjusted to take those emotions into account. The translated text in multiple languages ​​is displayed side by side for each predetermined unit of text, making the correspondence between each language visually easy to understand. This makes it easier for users to compare translation results and deepen their understanding. For example, by displaying the English and Japanese translation results side by side, users can check both languages ​​simultaneously. As a result, the AI ​​assistant automatic translation system can translate the content of web pages into multiple languages ​​in real time.

[0070] The AI ​​assistant automatic translation system according to this embodiment comprises an acquisition unit, an analysis unit, and a translation unit. The acquisition unit acquires the content of a web page. For example, the acquisition unit acquires the HTML or text data of a web page. The acquisition unit can acquire the content of various web pages, such as news articles or blog posts. The analysis unit analyzes the content acquired by the acquisition unit. For example, the analysis unit analyzes the acquired HTML or text data to understand the structure and context of the text. The analysis unit analyzes the structure, such as paragraphs, headings, and lists, to grasp the meaning of the text. The translation unit translates the content analyzed by the analysis unit into multiple languages. For example, the translation unit translates the analyzed text into multiple languages ​​in real time. The translation unit refers to a dictionary memory unit to support accurate translation of technical terms and proper nouns. The translation unit refers to dictionaries corresponding to specialized fields such as medicine and law to perform accurate translations. Some or all of the above-described processes in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can take the content analyzed by the analysis unit as input and perform translation using an AI model that translates into multiple languages. As a result, the AI ​​assistant automatic translation system according to this embodiment can translate the content of a web page into multiple languages ​​in real time.

[0071] The acquisition unit acquires the content of web pages. For example, the acquisition unit acquires HTML and text data of web pages. Specifically, the acquisition unit uses a web crawler to visit various web pages on the internet and collects HTML data from specified URLs. The web crawler can also automatically collect related pages by following links. The acquisition unit can acquire the content of various web pages, such as articles on news sites and blog posts. For example, it can collect the latest news articles from news sites and personal opinions and reviews from blogs. The acquisition unit temporarily stores the collected data and performs data preprocessing before passing it to the analysis unit. Preprocessing includes removing HTML tags and normalizing text. This allows the analysis unit to analyze the data efficiently. Furthermore, the acquisition unit also has a function to filter data based on specific keywords and topics. This allows the user to collect only specific information of interest. For example, it can prioritize the acquisition of information related to specific news topics or industries. The acquisition unit can periodically update the collected data to provide the latest information. As a result, the automatic translation system AI assistant according to the embodiment can always acquire the latest web page content and provide a foundation for real-time translation.

[0072] The analysis unit analyzes the content acquired by the acquisition unit. For example, the analysis unit analyzes acquired HTML and text data to understand the structure and context of the text. Specifically, the analysis unit uses natural language processing (NLP) techniques to tokenize text data, tag parts of speech, and perform syntactic analysis. Tokenization divides the text into words and phrases, and part of speech tagging identifies the part of speech of each word. Syntactic analysis analyzes the grammatical structure of the text, clarifying relationships such as subject, predicate, and object. The analysis unit analyzes the structure of paragraphs, headings, lists, etc., to grasp the meaning of the text. For example, it analyzes HTML tags to identify heading tags (h1, h2, h3, etc.) and list tags (ul, ol, li, etc.) to understand the hierarchical structure of the text. Furthermore, the analysis unit performs coreference analysis and semantic role labeling to understand the context. Coreference analysis identifies what pronouns and demonstratives in the text refer to, and semantic role labeling identifies the role that each word plays in the text. This allows the analysis unit to deeply understand the meaning of the text and provide accurate information to the translation unit. The analysis unit also has a filtering function that extracts important information from the acquired data and removes unnecessary information. This prepares the translation unit to perform translation work efficiently. The analysis unit stores the analysis results in a database so that they can be used for subsequent processing. As a result, the AI ​​assistant in this embodiment of the automatic translation system can accurately analyze the content of acquired web pages and provide a foundation for translation.

[0073] The translation unit translates the content analyzed by the analysis unit into multiple languages. For example, the translation unit translates the analyzed text into multiple languages ​​in real time. Specifically, the translation unit uses a neural machine translation (NMT) model to translate the analyzed text into the target language. The NMT model is trained using a large amount of translation data and can generate natural translations with high accuracy. The translation unit refers to a dictionary memory unit to support the accurate translation of technical terms and proper nouns. The dictionary memory unit contains dictionaries corresponding to specialized fields such as medicine and law, and by referring to these dictionaries, it can perform accurate translations of technical terms and proper nouns. For example, in the medical field, it is required to accurately translate technical terms such as drug names, disease names, and treatment methods. The translation unit utilizes these specialized dictionaries to provide accurate and consistent translations. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can take the content analyzed by the analysis unit as input and perform translation using an AI model that translates into multiple languages. The AI ​​model performs context-aware translation, understanding the meaning of the entire sentence rather than just individual words. This enables natural and fluent translations. Furthermore, the translation unit can collect user feedback and continuously improve the accuracy of the translation model. As a result, the AI ​​assistant automatic translation system according to this embodiment can translate the content of web pages into multiple languages ​​in real time and provide users with high-quality translations.

[0074] The translation unit can translate technical terms and proper nouns from dictionaries corresponding to the field to which the web page belongs, based on a dictionary memory unit that stores translations of technical terms and proper nouns. For example, the translation unit can refer to a dictionary specialized in the medical field to accurately translate technical terms. It can also refer to a dictionary specialized in the legal field to accurately translate proper nouns. Furthermore, it can refer to a dictionary specialized in the technical field to accurately translate technical terms. This enables accurate translation of technical terms and proper nouns. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input translations of technical terms and proper nouns into an AI model, and the AI ​​model can output the translation results.

[0075] The learning unit can learn the translation process based on user feedback on translations. For example, if a user provides feedback that "this translation is inaccurate," the learning unit will improve the translation algorithm based on that information. The learning unit can improve the accuracy of translations based on user feedback. For example, the learning unit can input user-provided feedback into an AI model, which can then update the translation algorithm. This allows for improved translation accuracy based on user feedback. Some or all of the above processes in the learning unit may be performed using AI, or without AI.

[0076] The translation tool can operate as a browser extension. For example, by installing an extension on a browser such as Chrome or Firefox, the translation tool can automatically translate the content of a webpage. The translation tool allows users to see the translation results in real time while browsing a specific webpage. The translation tool operates as a browser extension and can translate the content of a webpage in real time. This allows users to see the translation results in real time while browsing a specific webpage. Some or all of the above-described processes in the translation tool may be performed using AI, for example, or without AI.

[0077] The reception unit can accept the user's selection of a specific dictionary. For example, by allowing the user to select the dictionary they wish to use, the reception unit can obtain more accurate translation results. The reception unit can select from multiple dictionaries, such as medical dictionaries or technical dictionaries. By allowing the user to select a specific dictionary, the reception unit can improve the accuracy of the translation. This allows the user to obtain more accurate translation results by selecting the dictionary they wish to use. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI.

[0078] The translation unit can estimate the user's emotions and translate the web page based on those emotions. For example, if the user inputs an emotional text, the translation unit can adjust the translation result to take those emotions into account. By estimating the user's emotions and adjusting the translation result based on those emotions, the translation unit can provide a more appropriate translation. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for the provision of translation results that are appropriate to the user's emotions. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input user emotion data into a generative AI, and the generative AI can output a translation result based on the emotions.

[0079] The translation unit can display multiple translated languages ​​side-by-side for each predetermined unit of text. For example, by displaying English and Japanese translation results side-by-side, the user can check both languages ​​simultaneously. The translation unit ensures that the correspondence between each language is displayed in a visually understandable manner. This makes it easier for the user to compare translation results and deepen their understanding. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input multiple translated languages ​​into an AI model, which can then visually display the correspondence between each language.

[0080] The acquisition unit can estimate the user's emotions and adjust the timing of web page acquisition based on the estimated emotions. For example, if the user is stressed, the acquisition unit can delay web page acquisition and wait until the user is relaxed. If the user is focused, the acquisition unit can acquire web pages immediately to minimize interruption to their work. If the user is in a hurry, the acquisition unit can prioritize web page acquisition and provide information quickly. This allows the timing of web page acquisition to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the acquisition unit may be performed using AI or not using AI. For example, the acquisition unit can input user emotion data into a generative AI, which can then adjust the timing of web page acquisition based on the emotions.

[0081] The acquisition unit can analyze the user's past browsing history and select the optimal acquisition method. For example, the acquisition unit can prioritize acquiring web pages that the user has frequently visited in the past. The acquisition unit can predict web pages that the user will visit at a specific time based on the user's past browsing history and acquire them in advance. The acquisition unit can analyze the user's browsing patterns and propose the optimal acquisition method. This allows the system to select the optimal acquisition method based on the user's past browsing history. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's past browsing history data into a generating AI, which can then select the optimal acquisition method.

[0082] The acquisition unit can filter web pages based on the user's current areas of interest when acquiring them. For example, the acquisition unit can prioritize acquiring web pages related to topics the user is currently interested in. The acquisition unit can filter highly relevant web pages based on the user's current search keywords. The acquisition unit can analyze the user's social media activity and acquire web pages based on their areas of interest. This allows the acquisition of highly relevant web pages based on the user's current areas of interest. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's current areas of interest data into a generating AI, which can then filter highly relevant web pages.

[0083] The retrieval unit can estimate the user's emotions and determine the priority of web pages to retrieve based on the estimated emotions. For example, if the user is relaxed, the retrieval unit may prioritize retrieving entertainment-related web pages. If the user is focused, the retrieval unit may prioritize retrieving web pages related to work or learning. If the user is in a hurry, the retrieval unit may prioritize retrieving web pages containing important information. This allows the retrieval unit to determine the priority of web pages to retrieve according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or not using AI. For example, the retrieval unit can input user emotion data into a generative AI, which can then determine the priority of web pages based on the emotions.

[0084] The acquisition unit can prioritize the acquisition of highly relevant pages based on the user's geographical location information when acquiring web pages. For example, if the user is in a specific region, the acquisition unit will prioritize the acquisition of web pages related to that region. The acquisition unit can prioritize the acquisition of web pages that contain information about locations close to the user's current location. The acquisition unit can acquire web pages that contain local news and event information based on the user's geographical location information. This allows the acquisition of highly relevant web pages based on the user's geographical location information. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's geographical location information data into a generating AI, which can then prioritize the acquisition of highly relevant web pages.

[0085] The acquisition unit can analyze a user's social media activity when acquiring web pages and acquire relevant pages. For example, the acquisition unit can acquire web pages related to articles shared by the user on social media. The acquisition unit can acquire relevant web pages based on the content of posts from accounts that the user follows. The acquisition unit can analyze a user's social media activity history and acquire web pages related to topics of interest. This allows the acquisition of relevant web pages based on the user's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's social media activity data into a generating AI, and the generating AI can acquire relevant web pages.

[0086] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the user is relaxed, the analysis unit can provide detailed analysis results. If the user is in a hurry, the analysis unit can provide concise analysis results that get straight to the point. If the user is excited, the analysis unit can provide analysis results with visually stimulating effects. This allows the presentation of the analysis to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input the user's emotion data into a generative AI, which can then adjust the presentation of the analysis based on the emotion.

[0087] The analysis unit can adjust the level of detail of the analysis based on the importance of the text during analysis. For example, the analysis unit can perform a detailed analysis on important texts and a concise analysis on less important texts. The analysis unit can adjust the display order of the analysis results based on the importance of the texts. The analysis unit can perform a particularly detailed analysis on texts containing important keywords. This allows the level of detail of the analysis to be adjusted based on the importance of the texts. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input text importance data into a generating AI, which can then adjust the level of detail of the analysis based on the importance.

[0088] The analysis unit can apply different analysis algorithms depending on the category of the text during analysis. For example, the analysis unit can apply a news-specific analysis algorithm to news articles. For technical documents, it can apply an analysis algorithm specialized for technical terminology. For entertainment articles, it can apply an entertainment-specific analysis algorithm. This allows the analysis unit to apply the most suitable analysis algorithm according to the category of the text. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input text category data into a generating AI, which can then apply an analysis algorithm appropriate to the category.

[0089] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the user is relaxed, the analysis unit can provide detailed analysis results. If the user is in a hurry, the analysis unit can provide concise analysis results that get straight to the point. If the user is excited, the analysis unit can provide analysis results with visually stimulating effects. This allows the length of the analysis to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input the user's emotion data into a generative AI, which can then adjust the length of the analysis based on the emotion.

[0090] The analysis unit can determine the priority of analysis based on the submission date of the documents during analysis. For example, the analysis unit can prioritize the analysis of the most recent documents. The analysis unit can lower the priority of analysis for older documents. The analysis unit can adjust the display order of the analysis results based on the submission date. This allows the analysis priority to be determined based on the submission date of the documents. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the document submission date data into a generating AI, and the generating AI can determine the analysis priority based on the submission date.

[0091] The analysis unit can adjust the order of analysis based on the relevance of the texts during analysis. For example, the analysis unit may prioritize the analysis of texts with high relevance. The analysis unit may lower the priority of analysis for texts with low relevance. The analysis unit can also adjust the display order of the analysis results based on the relevance of the texts. This allows the order of analysis to be adjusted based on the relevance of the texts. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit may input text relevance data into a generating AI, which can then adjust the order of analysis based on the relevance.

[0092] The translation unit can estimate the user's emotions and adjust the translation's expression based on those emotions. For example, if the user is relaxed, the translation unit can provide a detailed translation. If the user is in a hurry, the translation unit can provide a concise translation that gets straight to the point. If the user is excited, the translation unit can provide a translation with visually stimulating effects. This allows the translation's expression to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using AI, or not using AI. For example, the translation unit can input user emotion data into the generative AI, which can then adjust the translation's expression based on the emotion.

[0093] The translation unit can adjust the level of detail of the translation based on the importance of the text during translation. For example, the translation unit can provide detailed translations for important texts and concise translations for less important texts. The translation unit can also adjust the display order of the translation results based on the importance of the texts. The translation unit can provide particularly detailed translations for texts containing important keywords. This allows for adjustment of the level of detail of the translation based on the importance of the texts. Some or all of the above processes in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input text importance data into a generating AI, which can then adjust the level of detail of the translation based on the importance.

[0094] The translation unit can apply different translation algorithms depending on the category of the text during translation. For example, the translation unit can apply a news-specific translation algorithm to news articles. For technical documents, it can apply a translation algorithm specialized for technical terminology. For entertainment articles, it can apply an entertainment-specific translation algorithm. This allows the translation unit to apply the most suitable translation algorithm according to the category of the text. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input text category data into a generating AI, and the generating AI can apply a translation algorithm appropriate to the category.

[0095] The translation unit can estimate the user's emotions and adjust the translation length based on the estimated emotions. For example, if the user is relaxed, the translation unit can provide a detailed translation. If the user is in a hurry, the translation unit can provide a concise translation that gets straight to the point. If the user is excited, the translation unit can provide a translation with visually stimulating effects. This allows the translation length to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using AI or not using AI. For example, the translation unit can input user emotion data into a generative AI, which can then adjust the translation length based on the emotion.

[0096] The translation department can determine translation priorities based on the submission date of the documents during the translation process. For example, the department may prioritize the translation of the most recent documents. The department may lower the translation priority of older documents. The department may also adjust the display order of the translation results based on the submission date. This allows the department to determine translation priorities based on the submission date of the documents. Some or all of the above processes in the translation department may be performed using AI, for example, or not using AI. For example, the translation department may input document submission date data into a generating AI, which can then determine translation priorities based on the submission date.

[0097] The translation unit can adjust the order of translations based on the relevance of the sentences during translation. For example, the translation unit may prioritize translating sentences that are highly relevant. The translation unit may lower the translation priority of sentences that are less relevant. The translation unit can also adjust the display order of the translation results based on the relevance of the sentences. This allows the order of translations to be adjusted based on the relevance of the sentences. Some or all of the above processes in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit may input sentence relevance data into a generating AI, which can then adjust the order of translations based on relevance.

[0098] The dictionary memory unit can estimate the user's emotions and select a dictionary based on the estimated emotions. For example, if the user is relaxed, the dictionary memory unit can select a detailed dictionary. If the user is in a hurry, the dictionary memory unit can select a concise dictionary. If the user is excited, the dictionary memory unit can select a visually stimulating dictionary. This allows for the selection of the optimal dictionary according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the dictionary memory unit may be performed using AI, for example, or without AI. For example, the dictionary memory unit can input user emotion data into a generative AI, which can then select a dictionary based on the emotions.

[0099] The dictionary memory unit can add custom dictionaries based on the user's past translation history. For example, the dictionary memory unit can add specialized terms and proper nouns that the user has translated in the past to the custom dictionary. The dictionary memory unit can add phrases and expressions that the user frequently uses to the custom dictionary. The dictionary memory unit can analyze the user's translation history and create custom dictionaries specialized in specific fields. This allows custom dictionaries to be added based on the user's past translation history. Some or all of the above processes in the dictionary memory unit may be performed using AI, for example, or not using AI. For example, the dictionary memory unit can input the user's translation history data into a generating AI, which can then create a custom dictionary.

[0100] The dictionary memory unit can add specialized dictionaries specific to particular fields. For example, the dictionary memory unit can add specialized dictionaries specific to the medical field. The dictionary memory unit can add specialized dictionaries specific to the legal field. The dictionary memory unit can add specialized dictionaries specific to the technology field. By adding specialized dictionaries specific to particular fields, the accuracy of translation of specialized terminology is improved. Some or all of the above processing in the dictionary memory unit may be performed using AI, for example, or without AI. For example, the dictionary memory unit can input specialized dictionary data specific to a particular field into a generating AI, and the generating AI can add the specialized dictionary.

[0101] The dictionary memory unit can estimate the user's emotions and determine dictionary priorities based on the estimated emotions. For example, if the user is relaxed, the dictionary memory unit will prioritize detailed dictionaries. If the user is in a hurry, the dictionary memory unit will prioritize concise dictionaries. If the user is excited, the dictionary memory unit will prioritize visually stimulating dictionaries. This allows for the prioritization of dictionaries according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dictionary memory unit may be performed using AI, or not using AI. For example, the dictionary memory unit can input user emotion data into a generative AI, which can then determine dictionary priorities based on the emotions.

[0102] The dictionary memory unit can prioritize the use of dictionaries that are highly relevant based on the user's geographical location information. For example, if the user is in a specific region, the dictionary memory unit will prioritize the use of dictionaries related to that region. The dictionary memory unit can prioritize the use of dictionaries that contain information about places close to the user's current location. The dictionary memory unit can prioritize the use of dictionaries that contain regional terminology based on the user's geographical location information. This allows for the priority use of dictionaries that are highly relevant based on the user's geographical location information. Some or all of the above processing in the dictionary memory unit may be performed using AI, for example, or without AI. For example, the dictionary memory unit can input the user's geographical location information data into a generating AI, which can then prioritize the use of dictionaries that are highly relevant.

[0103] The dictionary memory unit can analyze the user's social media activity and use relevant dictionaries. For example, the dictionary memory unit can use dictionaries related to articles the user has shared on social media. The dictionary memory unit can use relevant dictionaries based on the content of posts from accounts the user follows. The dictionary memory unit can analyze the user's social media activity history and use dictionaries related to topics of interest. This allows the dictionary memory unit to use relevant dictionaries based on the user's social media activity. Some or all of the above processing in the dictionary memory unit may be performed using AI, for example, or without AI. For example, the dictionary memory unit can input the user's social media activity data into a generating AI, which can then use relevant dictionaries.

[0104] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is relaxed, the learning unit can select detailed training data. If the user is in a hurry, the learning unit can select concise training data. If the user is excited, the learning unit can select visually stimulating training data. This allows for the selection of optimal training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input user emotion data into a generative AI, which can then select training data based on the emotions.

[0105] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can analyze past learning data and adjust the parameters of the learning algorithm. The learning unit can improve the accuracy of the learning algorithm by referring to past learning data. This allows the learning algorithm to be optimized based on past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input past learning data into a generating AI, which can then optimize the learning algorithm.

[0106] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, the learning unit can increase the learning frequency when the user is relaxed. It can decrease the learning frequency when the user is in a hurry. It can adjust the learning frequency when the user is excited. This allows the learning frequency to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input user emotion data into a generative AI, and the generative AI can adjust the learning frequency based on the emotions.

[0107] The learning unit can weight the training data based on the submission date of the translation history. For example, the learning unit can give a higher weight to the most recent translation history. The learning unit can give a lower weight to older translation history submissions. The learning unit can adjust the weighting of the training data based on the submission date. This allows the training data to be weighted based on the submission date of the translation history. Some or all of the above processing in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input the translation history submission date data into a generating AI, and the generating AI can weight the training data based on the submission date.

[0108] The reception unit can estimate the user's emotions and adjust the dictionary selection method based on the estimated emotions. For example, if the user is relaxed, the reception unit can select a detailed dictionary. If the user is in a hurry, the reception unit can select a concise dictionary. If the user is excited, the reception unit can select a visually stimulating dictionary. This allows the dictionary selection method to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can input the user's emotion data into the generative AI, which can then adjust the dictionary selection method based on the emotion.

[0109] The reception unit can suggest the most suitable dictionary by referring to the user's past dictionary selection history. For example, the reception unit can suggest the most suitable dictionary based on the dictionary the user has selected in the past. The reception unit can analyze the user's past dictionary selection history and suggest dictionaries specialized in a particular field. The reception unit can suggest the most suitable dictionary by referring to the user's dictionary selection history. This allows the reception unit to suggest the most suitable dictionary based on the user's past dictionary selection history. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the user's dictionary selection history data into a generating AI, which can then suggest the most suitable dictionary.

[0110] The reception unit can estimate the user's emotions and determine dictionary priorities based on the estimated emotions. For example, if the user is relaxed, the reception unit will prioritize detailed dictionaries. If the user is in a hurry, the reception unit will prioritize concise dictionaries. If the user is excited, the reception unit will prioritize visually stimulating dictionaries. This allows the system to prioritize dictionaries according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI or not using AI. For example, the reception unit can input user emotion data into a generative AI, which can then determine dictionary priorities based on the emotions.

[0111] The reception unit can suggest the most suitable dictionary based on the user's device information. For example, if the user is using a smartphone, the reception unit can suggest a dictionary that matches the screen size. If the user is using a tablet, the reception unit can suggest a dictionary optimized for a larger screen. If the user is using a smartwatch, the reception unit can suggest a concise and highly visible dictionary. This allows the system to suggest the most suitable dictionary based on the user's device information. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the user's device information data into a generating AI, which can then suggest the most suitable dictionary.

[0112] The display unit can estimate the user's emotions and adjust how the translation results are displayed based on the estimated emotions. For example, if the user is relaxed, the display unit can display detailed translation results. If the user is in a hurry, the display unit can display concise translation results that get straight to the point. If the user is excited, the display unit can display translation results with visually stimulating effects. This allows the display method of the translation results to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the display unit may be performed using AI, for example, or not using AI. For example, the display unit can input the user's emotion data into the generative AI, and the generative AI can adjust how the translation results are displayed based on the emotion.

[0113] The display unit can select the optimal display method by referring to the user's past display history. For example, the display unit can select the optimal display method based on the display method previously selected by the user. The display unit can analyze the user's past display history and select a display method specialized for a particular field. The display unit can select the optimal display method by referring to the user's display history. This allows the display unit to select the optimal display method based on the user's past display history. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the user's display history data into a generating AI, which can then select the optimal display method.

[0114] The display unit can estimate the user's emotions and adjust the display order of translation results based on the estimated emotions. For example, if the user is relaxed, the display unit can prioritize displaying detailed translation results. If the user is in a hurry, the display unit can prioritize displaying concise translation results. If the user is excited, the display unit can prioritize displaying translation results with visually stimulating effects. This allows the display order of translation results to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the display unit may be performed using AI, or not using AI. For example, the display unit can input user emotion data into a generative AI, which can then adjust the display order of translation results based on the emotions.

[0115] The display unit can select the optimal display method based on the user's device information. For example, if the user is using a smartphone, the display unit can provide a display method that matches the screen size. If the user is using a tablet, the display unit can provide a display method optimized for a larger screen. If the user is using a smartwatch, the display unit can provide a concise and highly visible display method. This allows the optimal display method to be selected based on the user's device information. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input user device information data into a generating AI, which can then select the optimal display method.

[0116] The display unit can provide a multilingual display according to the user's language settings. For example, the display unit can automatically set the display language based on the language settings of the user's device. The display unit can provide a language switching function if the user uses multiple languages. The display unit can provide a display in a specific language if the user selects a particular language. This allows the display to be provided in a multilingual format according to the user's language settings. Some or all of the above-described processes in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the user's language setting data into a generating AI, and the generating AI can provide a multilingual display.

[0117] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0118] The retrieval unit can estimate the user's emotions and adjust how web pages are retrieved based on those emotions. For example, if the user is stressed, the retrieval unit can delay retrieving web pages and wait until the user is relaxed. If the user is focused, the retrieval unit can retrieve web pages immediately to minimize interruption to their work. Furthermore, if the user is in a hurry, the retrieval unit can prioritize retrieving web pages and provide information quickly. In this way, the method of retrieving web pages can be adjusted according to the user's emotions.

[0119] The analysis unit can estimate the user's emotions and adjust the level of detail in the analysis based on the estimated emotions. For example, if the user is relaxed, the analysis unit can provide detailed analysis results. If the user is in a hurry, the analysis unit can provide concise analysis results that get straight to the point. Furthermore, if the user is excited, the analysis unit can provide analysis results with visually stimulating effects. In this way, the level of detail in the analysis can be adjusted according to the user's emotions.

[0120] The translation unit can estimate the user's emotions and adjust the translation's expression based on those emotions. For example, if the user is relaxed, the translation unit can provide a detailed translation. If the user is in a hurry, the translation unit can provide a concise translation that gets straight to the point. Furthermore, if the user is excited, the translation unit can provide a translation with visually stimulating effects. This allows the translation's expression to be adjusted according to the user's emotions.

[0121] The dictionary memory unit can estimate the user's emotions and select a dictionary based on those emotions. For example, if the user is relaxed, the dictionary memory unit can select a detailed dictionary. If the user is in a hurry, the dictionary memory unit can select a concise dictionary. Furthermore, if the user is excited, the dictionary memory unit can select a visually stimulating dictionary. This allows the system to select the most appropriate dictionary according to the user's emotions.

[0122] The display unit can estimate the user's emotions and adjust how the translation results are displayed based on those emotions. For example, if the user is relaxed, the display unit can show a detailed translation. If the user is in a hurry, the display unit can show a concise translation that gets straight to the point. Furthermore, if the user is excited, the display unit can show a translation with visually stimulating effects. This allows the display method of the translation results to be adjusted according to the user's emotions.

[0123] The data acquisition unit can analyze the user's past browsing history and select the optimal acquisition method. For example, it can prioritize the acquisition of web pages that the user has frequently visited in the past. Furthermore, it can predict web pages that the user will visit at specific times based on their past browsing history and acquire them in advance. It can also analyze the user's browsing patterns and suggest the optimal acquisition method. This allows the system to select the optimal acquisition method based on the user's past browsing history.

[0124] The analysis unit can apply different analysis algorithms depending on the category of the text. For example, a news-specific analysis algorithm can be applied to news articles. A technical analysis algorithm specialized for technical terminology can be applied to technical documents. Furthermore, an entertainment-specific analysis algorithm can be applied to entertainment articles. This allows the system to apply the most suitable analysis algorithm according to the category of the text.

[0125] The translation unit can adjust the level of detail in translations based on the importance of the text. For example, it can provide detailed translations for important sentences and concise translations for less important ones. Furthermore, it can adjust the display order of translation results based on the importance of the text. In addition, it can provide particularly detailed translations for sentences containing important keywords. This allows for adjusting the level of detail in translations based on the importance of the text.

[0126] The dictionary memory unit can add specialized dictionaries focused on specific fields. For example, it can add specialized dictionaries for the medical field, for the legal field, or for the technical field. This allows for the addition of specialized dictionaries focused on specific fields, thereby improving the accuracy of translations of technical terms.

[0127] The learning unit can optimize the learning algorithm by referring to past training data. For example, it can select the optimal learning algorithm based on past training data. Furthermore, it can analyze past training data and adjust the parameters of the learning algorithm. It can also improve the accuracy of the learning algorithm by referring to past training data. In this way, the learning algorithm can be optimized based on past training data.

[0128] The following briefly describes the processing flow for example form 2.

[0129] Step 1: The retrieval unit retrieves the content of the web page. For example, the retrieval unit retrieves the HTML and text data of the web page. The retrieval unit can retrieve the content of various web pages, such as news articles and blog posts. Step 2: The analysis unit analyzes the content acquired by the acquisition unit. For example, the analysis unit analyzes the acquired HTML and text data to understand the structure and context of the text. The analysis unit analyzes the structure of paragraphs, headings, lists, etc., to grasp the meaning of the text. Step 3: The translation unit translates the content analyzed by the analysis unit into multiple languages. For example, the translation unit translates the analyzed text into multiple languages ​​in real time. The translation unit consults the dictionary memory unit to support accurate translation of technical terms and proper nouns. The translation unit consults dictionaries corresponding to specialized fields such as medicine and law to perform accurate translations. Some or all of the above processes in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can use an AI model that takes the content analyzed by the analysis unit as input and translates it into multiple languages ​​to perform the translation.

[0130] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0131] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0132] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0133] For example, the acquisition unit is implemented in either the data processing unit 12 or the smart device 14. For example, the specific processing unit 290 of the data processing unit 12 can perform the process of acquiring HTML and text data from a web page. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and analyzes the acquired data to understand the structure and context of the text. The translation unit is implemented, for example, by the control unit 46A of the smart device 14, and translates the analyzed text into multiple languages ​​in real time. The dictionary storage unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and supports accurate translation of technical terms and proper nouns. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and improves the accuracy of translation based on user feedback. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0134] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0135] As shown in Figure 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.

[0136] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0137] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0138] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0140] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0141] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0142] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0143] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0144] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0145] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0146] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0147] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0148] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0149] For example, the acquisition unit is implemented in either the data processing unit 12 or the smart glasses 214. For example, the specific processing unit 290 of the data processing unit 12 can perform the process of acquiring HTML and text data from a web page. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and analyzes the acquired data to understand the structure and context of the text. The translation unit is implemented, for example, by the control unit 46A of the smart glasses 214, and translates the analyzed text into multiple languages ​​in real time. The dictionary storage unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and supports accurate translation of technical terms and proper nouns. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and improves the accuracy of translation based on user feedback. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0150] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0151] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0152] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0153] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0154] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0156] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0157] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0159] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0160] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0163] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0164] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] For example, the acquisition unit is implemented in either the data processing unit 12 or the headset terminal 314. For example, the specific processing unit 290 of the data processing unit 12 can perform processing to acquire HTML and text data of a web page. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and analyzes the acquired data to understand the structure and context of the text. The translation unit is implemented, for example, by the control unit 46A of the headset terminal 314, and translates the analyzed text into multiple languages ​​in real time. The dictionary storage unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and supports accurate translation of technical terms and proper nouns. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and improves the accuracy of translation based on user feedback. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0166] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0167] As shown in Figure 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.

[0168] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0169] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0170] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0171] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0172] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0173] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0174] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0175] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0176] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0177] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0178] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0179] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0180] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0181] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0182] For example, the acquisition unit is implemented in either the data processing unit 12 or the robot 414. For example, the specific processing unit 290 of the data processing unit 12 can perform the process of acquiring HTML and text data from a web page. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and analyzes the acquired data to understand the structure and context of the text. The translation unit is implemented, for example, by the control unit 46A of the robot 414, and translates the analyzed text into multiple languages ​​in real time. The dictionary storage unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and supports accurate translation of technical terms and proper nouns. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and improves the accuracy of translation based on user feedback. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0183] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0184] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0185] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0186] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0187] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0188] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0189] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0190] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0191] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0192] 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.

[0193] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0194] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0195] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0196] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0197] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0198] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0199] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0200] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0201] (Note 1) A retrieval unit that retrieves the content of a web page, An analysis unit analyzes the contents acquired by the acquisition unit, A translation unit that translates the content analyzed by the aforementioned analysis unit into multiple languages, Equipped with A system characterized by the following features. (Note 2) The aforementioned translation department, Based on the dictionary memory unit that stores translations of technical terms and proper nouns, Translate technical terms and proper nouns from a dictionary corresponding to the field to which the aforementioned webpage belongs. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a learning unit that learns the translation process based on user feedback on translations. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned translation department, It operates as a browser extension. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a reception section that accepts the user's selection of a specific dictionary. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned translation department, To estimate the user's emotions, Translate web pages based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned translation department, For each sentence in a predetermined unit, Display the translated text in multiple languages ​​side by side. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, To estimate the user's emotions, Adjust the timing of web page retrieval based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, By analyzing the user's past browsing history, Select the optimal acquisition method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition unit is, When retrieving a web page, Filter based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The acquisition unit is, To estimate the user's emotions, The priority of web pages to retrieve is determined based on the estimated user's sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 12) The acquisition unit is, When retrieving a web page, The system prioritizes retrieving pages that are highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The acquisition unit is, When retrieving a web page, Analyze users' social media activity, Get related pages The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, To estimate the user's emotions, The analysis is presented in a way that reflects the estimated user's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During the analysis, Adjust the level of detail in the analysis based on the importance of the text. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During the analysis, Apply different analysis algorithms depending on the category of the text. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, To estimate the user's emotions, Adjust the length of the analysis based on the estimated user's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During the analysis, Prioritize analysis based on the submission date of the documents. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During the analysis, Adjust the order of analysis based on the relevance of the text. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned translation department, To estimate the user's emotions, The translation style is adjusted based on the estimated user's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned translation department, When translating, Adjust the level of detail in the translation based on the importance of the text. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned translation department, When translating, Apply different translation algorithms depending on the category of the text. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned translation department, To estimate the user's emotions, Adjust the translation length based on the estimated user's sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned translation department, When translating, Translation priorities are determined based on the submission date of the documents. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned translation department, When translating, Adjust the order of translations based on the relevance of the text. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned dictionary storage unit is To estimate the user's emotions, Dictionary selection is performed based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned dictionary storage unit is Add a custom dictionary based on the user's past translation history. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned dictionary storage unit is Add specialized dictionaries focused on specific fields. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned dictionary storage unit is To estimate the user's emotions, Dictionary priorities are determined based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned dictionary storage unit is The system prioritizes the use of relevant dictionaries based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned dictionary storage unit is Analyze users' social media activity, Use relevant dictionaries The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned learning unit, To estimate the user's emotions, The training data is selected based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned learning unit, When learning, Optimize the learning algorithm by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned learning unit, To estimate the user's emotions, The learning frequency is adjusted based on the estimated user's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned learning unit, The training data is weighted based on when the translation history was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned reception unit is To estimate the user's emotions, The dictionary selection method is adjusted based on the estimated user's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned reception unit is The system suggests the most suitable dictionary by referring to the user's past dictionary selection history. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned reception unit is To estimate the user's emotions, Dictionary priorities are determined based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned reception unit is The system suggests the optimal dictionary based on the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned display unit is To estimate the user's emotions, The way translation results are displayed is adjusted based on the estimated user's sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned display unit is The system selects the optimal display method by referring to the user's past viewing history. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned display unit is To estimate the user's emotions, The display order of translation results is adjusted based on the estimated user's sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned display unit is The optimal display method is selected based on the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 44) The aforementioned display unit is Provides multilingual display based on the user's language settings. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0202] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A retrieval unit that retrieves the content of a web page, An analysis unit analyzes the contents acquired by the acquisition unit, The system includes a translation unit that translates the content analyzed by the analysis unit into multiple languages. A system characterized by the following features.

2. The aforementioned translation department, Based on the dictionary memory unit that stores translations of technical terms and proper nouns, Translate technical terms and proper nouns from a dictionary corresponding to the field to which the aforementioned webpage belongs. The system according to feature 1.

3. It includes a learning unit that learns the translation process based on user feedback on translations. The system according to feature 1.

4. The aforementioned translation department, It operates as a browser extension. The system according to feature 1.

5. It includes a reception section that accepts the user's selection of a specific dictionary. The system according to feature 1.

6. The aforementioned translation department, To estimate the user's emotions, Translate web pages based on estimated user sentiment. The system according to feature 1.

7. The aforementioned translation department, For each sentence in a predetermined unit, Display the translated text in multiple languages ​​side by side. The system according to feature 1.

8. The acquisition unit is, To estimate the user's emotions, Adjust the timing of web page retrieval based on estimated user sentiment. The system according to feature 1.

9. The acquisition unit is, By analyzing the user's past browsing history, Select the optimal acquisition method. The system according to feature 1.

Images