System

Abstract

An object of the system according to the embodiment is to accurately determine a context of Japanese and appropriately translate the context.SOLUTION: A system according to an embodiment includes a collection unit, an analysis unit, and a translation unit. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit and determines the context of the Japanese language. The translation unit performs translation based on the context determined by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it is difficult to accurately determine and translate the context of Japanese, and there is room for improvement.

[0005] The system according to the embodiment aims to accurately determine the context of Japanese and translate appropriately. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, and a translation unit. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit and determines the context of the Japanese text. The translation unit performs translation based on the context determined by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can accurately determine the context of Japanese and translate appropriately. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A translation system according to an embodiment of the present invention collects data, and a generation AI analyzes the context of Japanese text, determines its meaning, and performs translation. The translation system collects data, and a generation AI analyzes the context of Japanese text and determines its meaning, thereby providing an appropriate translation. For example, the translation system collects data from various sources, such as news articles and social media posts. The translation system then uses a generation AI to analyze the context of the collected data and determine its meaning. The input to the generation AI is the collected data itself, and the generation AI analyzes the context based on the collected data. For example, the generation AI receives a prompt such as "Please analyze the context of this sentence" and analyzes the context of the data. The translation system then translates the data into another language based on the context determined by the generation AI. The translation is not simply a word replacement, but rather an appropriate translation based on the context. For example, the generation AI receives a prompt such as "Please translate based on this context" and generates an appropriate translation. This allows the translation system to provide more natural and accurate translations. This allows the translation system to understand the context of Japanese text through accumulated data and provide appropriate translations. For example, by collecting data from various sources, such as news articles and social media posts, and analyzing the context, generative AI can provide more natural and accurate translations. Additionally, by incorporating user feedback, translation accuracy can be improved.

[0029] A translation system according to an embodiment includes a collection unit, an analysis unit, and a translation unit. The collection unit collects data. Examples of the data include, but are not limited to, news articles, social media posts, blogs, and forum posts. For example, the collection unit collects news articles from a specific news site. The collection unit can also collect social media posts from a specific platform. The collection unit can also periodically scan blog and forum posts to collect related data. For example, the collection unit collects data from popular blogs and scans forum posts to collect data. The analysis unit uses generative AI to analyze the data collected by the collection unit and determine the Japanese context. The analysis is performed using, for example, natural language processing technology or a machine learning algorithm, but is not limited to, examples. For example, the analysis unit analyzes the Japanese context using morphological analysis. The analysis unit can also analyze the context using grammatical analysis. The analysis unit can also analyze the context using semantic analysis. For example, the analysis unit analyzes the meaning of words using morphological analysis to determine the context. Grammatical analysis analyzes the structure of a sentence and determines the context. Semantic analysis analyzes the meaning of words and determines the context. The translation unit performs translation based on the context determined by the analysis unit. Translation may be performed using, for example, a translation memory or neural machine translation technology, but is not limited to these examples. For example, the translation unit uses a translation memory to refer to past translation results and perform an appropriate translation. The translation unit may also use neural machine translation technology to perform context-sensitive translation. The translation unit may also perform translation using an encoder-decoder model. For example, the translation unit uses a translation memory to refer to past translation results and perform an appropriate translation. Neural machine translation technology performs context-sensitive translation using a neural network. The encoder-decoder model encodes and decodes input sentences to perform translation. This allows the translation system according to the embodiment to understand the context of Japanese through accumulated data and perform appropriate translation. Some or all of the above-described processing in the translation unit may be performed using, for example, AI, or may be performed without AI.For example, the translation unit can perform the translation using an AI model that takes the context determined by the analysis unit as input and outputs a translation.

[0030] The collection unit can collect data including news articles and social media posts. For example, the collection unit collects news articles from a specific news site. For example, the collection unit collects articles using the RSS feed of the news site. The collection unit can also collect social media posts from a specific platform. For example, the collection unit collects posts using the social media API. The collection unit can also periodically scan blog and forum posts to collect related data. For example, the collection unit collects data from popular blogs and scans forum posts to collect data. This makes it possible to collect information from a variety of data sources. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the RSS feed of a news site into the generation AI and cause the generation AI to collect articles.

[0031] The analysis unit can analyze the context of Japanese using natural language processing technology or a machine learning algorithm. The analysis unit analyzes the context of Japanese using, for example, morphological analysis. For example, the analysis unit uses a morphological analysis tool to analyze the meaning of words and determine the context. The analysis unit can also analyze the context using grammatical analysis. For example, the analysis unit uses a grammatical analysis tool to analyze the structure of a sentence and determine the context. The analysis unit can also analyze the context using semantic analysis. For example, the analysis unit uses a semantic analysis tool to analyze the meaning of words and determine the context. This improves the accuracy of context analysis by using advanced algorithms. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input a morphological analysis tool into the generation AI and cause the generation AI to perform context analysis.

[0032] The translation unit can perform translation using a translation memory or neural machine translation technology. For example, the translation unit can refer to past translation results using a translation memory to perform an appropriate translation. For example, the translation unit can search past translation results stored in a translation memory and perform translation based on similar context. The translation unit can also perform context-sensitive translation using neural machine translation technology. For example, the translation unit can perform context-sensitive translation using a neural network. The translation unit can also perform translation using an encoder-decoder model. For example, the translation unit can encode and decode the input sentence to perform translation. This enables appropriate translation based on the context. Some or all of the above-mentioned processing in the translation unit can be performed using, for example, AI, or without AI. For example, the translation unit can input past translation results stored in a translation memory into a generation AI and have the generation AI perform an appropriate translation.

[0033] The reception unit can accept feedback from users. For example, the reception unit accepts feedback from users through an online form. For example, the reception unit collects user ratings and comments through a feedback form on a website. The reception unit can also accept feedback via email. For example, the reception unit receives feedback from users via email and reflects the feedback in the system. The reception unit can also accept feedback via telephone. For example, the reception unit receives feedback from users over the phone and reflects the feedback in the system. In this way, the accuracy of the system is improved by reflecting user feedback. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input feedback collected through an online form into a generation AI and have the generation AI analyze the feedback.

[0034] The management unit can translate proper nouns and technical terms using a technical dictionary. For example, the management unit translates proper nouns and technical terms using a technical dictionary. For example, the management unit references terms registered in the technical dictionary and performs appropriate translations. The management unit can also periodically update the technical dictionary and add new terms. For example, the management unit updates the technical dictionary and adds new terms based on user feedback. The management unit can also correct the contents of the technical dictionary to provide accurate translations. For example, the management unit periodically reviews the contents of the technical dictionary and corrects errors. This enables accurate translation of technical terms and proper nouns. Some or all of the above-described processing in the management unit can be performed using, or without, AI. For example, the management unit can input the contents of the technical dictionary into a generation AI and cause the generation AI to perform analysis to improve the accuracy of the translation.

[0035] The collection unit can include blog and forum posts in addition to news articles and social media posts as collection targets. For example, the collection unit collects data from popular blogs in addition to news articles and social media posts. For example, the collection unit collects articles using the RSS feed of a blog site. The collection unit can also periodically scan forum posts to collect related data. For example, the collection unit collects posts using the forum's API. The collection unit can also prioritize the collection of blog and forum posts related to topics of interest to a user. For example, the collection unit collects related blog and forum posts based on the user's interests. This enables information collection from a variety of data sources. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the RSS feed of a blog site into the generation AI and cause the generation AI to collect articles.

[0036] The collection unit can filter data based on specific keywords or topics when collecting data. The collection unit collects only relevant data based on, for example, keywords specified by a user. For example, the collection unit extracts relevant data using a keyword filtering algorithm. The collection unit can also preferentially collect data related to a specific topic and filter other data. For example, the collection unit extracts relevant data using a topic model. The collection unit can also preferentially collect data with high importance based on the frequency of keyword appearance. For example, the collection unit analyzes the frequency of keyword appearance and extracts data with high importance. This makes it possible to collect highly relevant data by filtering data based on specific keywords or topics. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input a keyword filtering algorithm to the generation AI and have the generation AI perform data filtering.

[0037] When collecting data, the collection unit can customize the data to be collected by referring to the user's past browsing history. The collection unit, for example, analyzes the user's past browsing history and prioritizes the collection of relevant data. For example, the collection unit analyzes the browser history and extracts relevant data. The collection unit can also collect data from sites the user frequently visits. For example, the collection unit prioritizes the collection of data from specific sites. The collection unit can also collect data that is likely to be of interest to the user based on the user's browsing history. For example, the collection unit analyzes the user's interests and extracts relevant data. This allows for the collection of more relevant data by referring to the user's past browsing history. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the browser history to a generation AI and cause the generation AI to extract relevant data.

[0038] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. The collection unit, for example, prioritizes collecting news articles related to the user's current location. For example, the collection unit identifies the user's current location using GPS data and collects related news articles. The collection unit can also collect local event information based on the user's geographical location. For example, the collection unit collects local event information based on the user's location information. The collection unit can also collect data related to nearby stores and services based on the user's location information. For example, the collection unit collects data related to nearby stores and services based on the user's location information. This makes it possible to collect highly relevant data by taking the user's geographical location information into account. Some or all of the above-described processing by the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input GPS data to a generation AI and cause the generation AI to collect related data.

[0039] The collection unit can analyze the user's social media activities and collect related data when collecting data. The collection unit, for example, collects posts from accounts the user follows on social media. For example, the collection unit collects posts from the followed accounts using a social media API. The collection unit can also analyze the content of the user's social media posts and collect related data. For example, the collection unit analyzes the content of the user's posts and extracts related data. The collection unit can also collect related data by referring to the activities of the user's friends on social media. For example, the collection unit analyzes the content of the user's friends' posts and extracts related data. In this way, highly relevant data can be collected by analyzing the user's social media activities. Some or all of the above-described processing by the collection unit can be performed using, for example, AI, or can be performed without using AI. For example, the collection unit can input social media APIs into the generation AI and cause the generation AI to collect related data.

[0040] The collection unit can customize the collection method by reflecting the user's past feedback when collecting data. The collection unit, for example, adjusts the type of data to collect based on feedback provided by the user in the past. For example, the collection unit analyzes the user's feedback and determines the type of data to collect. The collection unit can also adjust the collection frequency based on the user's feedback. For example, the collection unit adjusts the collection frequency based on the user's feedback. The collection unit can also select data sources to be collected by referring to the user's feedback. For example, the collection unit selects data sources to be collected based on the user's feedback. This allows the collection method to be optimized by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's feedback to the generation AI and cause the generation AI to customize the collection method.

[0041] During context analysis, the analysis unit can use an algorithm that analyzes the structure and grammar of a sentence in detail. For example, the analysis unit analyzes the structure of a sentence to clarify relationships such as the subject, predicate, and object. For example, the analysis unit analyzes the structure of a sentence using a syntax analysis tool. The analysis unit can also analyze the exact meaning of a sentence based on grammatical rules. For example, the analysis unit analyzes a sentence based on grammatical rules using a grammar analysis tool. The analysis unit can also combine the structure and grammar of a sentence to perform more accurate context analysis. For example, the analysis unit analyzes a sentence by combining syntax analysis and grammar analysis. This improves the accuracy of context analysis by analyzing the structure and grammar of the sentence in detail. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input a syntax analysis tool into the generation AI and cause the generation AI to analyze the structure of the sentence.

[0042] The analysis unit can improve the accuracy of the analysis by referring to past analysis results during context analysis. For example, the analysis unit stores past analysis results in a database and references them during a new analysis. For example, the analysis unit stores past analysis results in a database and references them using a search algorithm. The analysis unit can also adjust algorithm parameters based on past analysis results. For example, the analysis unit adjusts algorithm parameters based on past analysis results. The analysis unit can also analyze past analysis results and find common patterns to improve the analysis accuracy. For example, the analysis unit analyzes past analysis results and finds common patterns. By referring to past analysis results, the analysis accuracy is improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past analysis results into a generation AI and cause the generation AI to perform analysis to improve the analysis accuracy.

[0043] The analysis unit can customize analysis methods according to different genres or topics when analyzing context. For example, the analysis unit uses different analysis methods for news articles and social media posts. For example, the analysis unit uses a news-specific analysis method for news articles and a social media-specific analysis method for social media posts. The analysis unit can also use different analysis methods for technical documents and entertainment articles. For example, the analysis unit uses a technology-specific analysis method for technical documents and an entertainment-specific analysis method for entertainment articles. The analysis unit can also select the optimal analysis method for each topic to improve analysis accuracy. For example, the analysis unit uses a topic model to select the optimal analysis method for each topic. This improves analysis accuracy by customizing the analysis method according to different genres or topics. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input a topic model to a generation AI and have the generation AI select the optimal analysis method.

[0044] During context analysis, the analysis unit can adjust the analysis method according to the length and complexity of the sentence. For example, for short sentences, the analysis unit uses a simplified analysis method. For example, the analysis unit uses a simplified analysis algorithm for short sentences. The analysis unit can also use a detailed analysis method for long sentences. For example, the analysis unit uses a detailed analysis algorithm for long sentences. The analysis unit can also improve analysis accuracy by combining multiple analysis methods for complex sentences. For example, the analysis unit uses a combination of multiple analysis algorithms for complex sentences. In this way, analysis accuracy is improved by adjusting the analysis method according to the length and complexity of the sentence. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input a simplified analysis algorithm for short sentences to the generation AI and have the generation AI perform the analysis.

[0045] The analysis unit can improve the accuracy of the analysis by referring to a related external database during context analysis. The analysis unit, for example, refers to an external dictionary database to accurately analyze the meaning of a word. For example, the analysis unit refers to an external dictionary database via an API to analyze the meaning of a word. The analysis unit can also refer to an external knowledge base to analyze an appropriate meaning according to the context. For example, the analysis unit refers to an external knowledge base via an API to analyze the meaning according to the context. The analysis unit can also improve the analysis accuracy of specialized text by referring to an external terminology database. For example, the analysis unit refers to an external terminology database via an API to analyze specialized text. In this way, the analysis accuracy is improved by referring to the related external database. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input an external dictionary database into the generation AI and cause the generation AI to analyze the meaning of words.

[0046] During context analysis, the analysis unit can adjust the level of detail of the analysis results according to the user's level of expertise. For example, if the user is an expert, the analysis unit provides detailed analysis results. For example, the analysis unit evaluates the user's level of expertise based on survey results and past usage history and provides detailed analysis results. Furthermore, if the user is a general user, the analysis unit can also provide concise and easy-to-understand analysis results. For example, the analysis unit provides concise analysis results based on the user's level of expertise. Furthermore, the analysis unit can customize the display method of the analysis results according to the user's level of expertise. For example, the analysis unit customizes the display method of the analysis results based on the user's level of expertise. By adjusting the level of detail of the analysis results according to the user's level of expertise, it is possible to provide analysis results that are easy for the user to understand. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's level of expertise to the generation AI and cause the generation AI to adjust the level of detail of the analysis results.

[0047] The translation unit can apply different translation algorithms depending on the context during translation. For example, in the case of technical documents, the translation unit uses a translation algorithm specialized for technical terminology. For example, the translation unit translates technical documents using a technical terminology dictionary. In addition, the translation unit can also use a translation algorithm that emphasizes natural expression in the case of entertainment articles. For example, the translation unit uses a translation algorithm that emphasizes natural expression in the case of entertainment articles. In addition, the translation unit can also use a translation algorithm that emphasizes accuracy in the case of news articles. For example, the translation unit uses a translation algorithm that emphasizes accuracy in the case of news articles. In this way, by applying different translation algorithms depending on the context, translation accuracy is improved. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input a technical terminology dictionary into a generation AI for technical documents and have the generation AI perform the translation.

[0048] The translation unit can improve the accuracy of translation by referring to past translation results during translation. For example, the translation unit stores past translation results in a database and refers to them when performing a new translation. For example, the translation unit stores past translation results in a database and refers to them using a search algorithm. The translation unit can also adjust the parameters of the algorithm based on the past translation results. For example, the translation unit adjusts the parameters of the algorithm based on the past translation results. The translation unit can also analyze past translation results and find common patterns to improve translation accuracy. For example, the translation unit analyzes past translation results and finds common patterns. By referring to the past translation results, translation accuracy is improved. Some or all of the above-described processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input past translation results into a generation AI and have the generation AI perform analysis to improve translation accuracy.

[0049] During translation, the translation unit can use a translation method customized for specific technical terms and proper nouns. The translation unit, for example, uses a technical dictionary to perform an accurate translation. For example, the translation unit references terms registered in the technical dictionary to perform an appropriate translation. The translation unit can also use a customized method for performing an appropriate translation for proper nouns. For example, the translation unit uses a proper noun dictionary to perform translation. The translation unit can also improve translation accuracy by using a translation method specialized for a specific field. For example, the translation unit uses a technical dictionary specialized for a specific field to perform translation. In this way, translation accuracy is improved by using a translation method customized for specific technical terms and proper nouns. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input a technical dictionary into a generation AI and have the generation AI perform the translation.

[0050] During translation, the translation unit can determine the priority of translation based on the submission date of the text. For example, the translation unit prioritizes translating text with an approaching deadline. For example, the translation unit prioritizes translating text with an upcoming deadline based on the submission date and time. The translation unit can also postpone text with a more distant submission date and prioritize text with a higher urgency. For example, the translation unit prioritizes translating text with a higher urgency based on the submission date and time. The translation unit can also automatically adjust the translation schedule based on the submission date and time. For example, the translation unit automatically adjusts the translation schedule based on the submission date and time. In this way, by determining the priority of translation based on the submission date and time, text with a higher urgency can be translated with a higher priority. Some or all of the above-described processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input the submission date and time to the generation AI and have the generation AI determine the translation priority.

[0051] The translation unit can improve the accuracy of the translation by referring to related literature and materials during translation. For example, the translation unit can improve the translation accuracy of specialized content by referring to related literature. For example, the translation unit can search for related literature from a database and reflect it in the translation. The translation unit can also provide a consistent translation by referring to past materials. For example, the translation unit can search for past materials from a database and reflect it in the translation. The translation unit can also provide an accurate translation by referring to an external database. For example, the translation unit can refer to an external database through an API and reflect it in the translation. In this way, the translation accuracy is improved by referring to related literature and materials. Some or all of the above-mentioned processing in the translation unit may be performed using, or without, AI. For example, the translation unit can input related literature into the generation AI and have the generation AI perform analysis to improve the translation accuracy.

[0052] The translation unit can adjust the use of technical terms in the translation according to the user's level of expertise during translation. For example, if the user is an expert, the translation unit provides a translation that uses a lot of technical terms. For example, the translation unit evaluates the user's level of expertise based on survey results and past usage history and provides a translation that uses a lot of technical terms. In addition, if the user is a general user, the translation unit can provide a concise translation that avoids technical terms. For example, the translation unit provides a concise translation based on the user's level of expertise. In addition, the translation unit can adjust the level of detail of the translation according to the user's level of expertise. For example, the translation unit adjusts the level of detail of the translation based on the user's level of expertise. This allows for a more appropriate translation to be provided by adjusting the use of technical terms in the translation according to the user's level of expertise. Some or all of the above-described processing in the translation unit may be performed using, or without, AI. For example, the translation unit can input the user's level of expertise into a generation AI and have the generation AI adjust the use of technical terms in the translation.

[0053] When receiving feedback, the reception unit can select the optimal reception method by referring to the user's past feedback history. The reception unit, for example, prioritizes suggesting feedback methods that the user has used in the past. For example, the reception unit stores the user's past feedback history in a database and references it using a search algorithm. The reception unit can also predict and suggest a feedback method to be used in a specific time period based on the user's past feedback history. For example, the reception unit predicts a feedback method to be used in a specific time period based on the user's past feedback history. The reception unit can also analyze the user's past feedback history and select the optimal feedback method. For example, the reception unit analyzes the user's past feedback history and selects the optimal feedback method. In this way, the optimal feedback reception method can be provided by referring to the user's past feedback history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past feedback history into a generation AI and cause the generation AI to select the optimal feedback method.

[0054] The reception unit can filter the feedback content based on the user's current situation and interests when receiving the feedback. The reception unit, for example, prioritizes receiving relevant feedback content based on the user's current situation. For example, the reception unit evaluates the user's current situation based on survey results and past usage history, and prioritizes receiving related feedback content. The reception unit can also filter the feedback content based on the user's interests. For example, the reception unit filters the feedback content based on the user's interests. The reception unit can also customize the feedback content based on the user's current situation and interests. For example, the reception unit customizes the feedback content based on the user's current situation and interests. As a result, highly relevant feedback can be obtained by filtering the feedback content based on the user's current situation and interests. Some or all of the above-described processing in the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's current situation and interests to a generation AI and cause the generation AI to filter the feedback content.

[0055] When receiving feedback, the reception unit can prioritize receiving highly relevant feedback by taking into account the user's geographical location information. The reception unit, for example, prioritizes receiving feedback related to the user's current location. For example, the reception unit identifies the user's current location using GPS data and receives related feedback. The reception unit can also prioritize receiving regional feedback based on the user's geographical location. For example, the reception unit receives regional feedback based on the user's location information. The reception unit can also prioritize receiving feedback regarding nearby stores and services based on the user's location information. For example, the reception unit receives feedback regarding nearby stores and services based on the user's location information. In this way, highly relevant feedback can be obtained by taking the user's geographical location information into account. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input GPS data to the generation AI and cause the generation AI to receive related feedback.

[0056] The reception unit may analyze the user's social media activity and receive relevant feedback when receiving feedback. For example, the reception unit may preferentially receive feedback from accounts the user follows on social media. For example, the reception unit may receive feedback from the accounts the user follows using a social media API. The reception unit may also analyze the content of the user's social media posts and receive relevant feedback. For example, the reception unit may analyze the content of the user's posts and extract relevant feedback. The reception unit may also receive relevant feedback by referring to the activities of the user's friends on social media. For example, the reception unit may analyze the content of the user's friends' posts and extract relevant feedback. In this way, highly relevant feedback can be obtained by analyzing the user's social media activity. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input a social media API into the generation AI and cause the generation AI to receive relevant feedback.

[0057] When managing technical terms, the management unit can customize a technical dictionary according to a specific field or industry. The management unit, for example, uses a technical dictionary specialized for the medical field. For example, the management unit manages technical terms using a technical dictionary specialized for the medical field. The management unit can also use a technical dictionary specialized for a technical field. For example, the management unit manages technical terms using a technical dictionary specialized for a technical field. The management unit can also use a technical dictionary specialized for the legal field. For example, the management unit manages technical terms using a technical dictionary specialized for the legal field. In this way, by customizing the technical dictionary according to a specific field or industry, the accuracy of technical terminology management is improved. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input a technical dictionary specialized for a specific field or industry into the generation AI and have the generation AI manage the technical terminology.

[0058] The management unit can improve the accuracy of technical terms by referring to past translation results when managing technical terms. The management unit, for example, stores past translation results in a database and references them when managing new technical terms. For example, the management unit stores past translation results in a database and references them using a search algorithm. The management unit can also update the contents of the technical term dictionary based on past translation results. For example, the management unit updates the contents of the technical term dictionary based on past translation results. The management unit can also analyze past translation results and find common patterns to improve the accuracy of technical terms. For example, the management unit analyzes past translation results and finds common patterns. By referring to past translation results, the accuracy of technical terms is improved. Some or all of the above-mentioned processing in the management unit may be performed using AI, for example, or may be performed without using AI. For example, the management unit can input past translation results into a generation AI and have the generation AI perform analysis to improve the accuracy of technical terms.

[0059] During terminology management, the management unit can update the terminology dictionary by reflecting user feedback. The management unit, for example, updates the contents of the terminology dictionary based on user-provided feedback. For example, the management unit stores user feedback in a database and references it using a search algorithm. The management unit can also revise the definitions of terminology based on user feedback. For example, the management unit revises the definitions of terminology based on user feedback. The management unit can also improve the accuracy of the terminology dictionary by referring to user feedback. For example, the management unit analyzes user feedback and improves the accuracy of the terminology dictionary. As a result, the accuracy of the terminology dictionary is improved by reflecting user feedback. Some or all of the above-described processing in the management unit may be performed using AI, for example, or may be performed without using AI. For example, the management unit can input user feedback into a generation AI and cause the generation AI to update the terminology dictionary.

[0060] When managing technical terms, the management unit can prioritize managing highly relevant technical terms by taking into account the user's geographical location information. The management unit, for example, prioritizes managing technical terms related to the user's current location. For example, the management unit can identify the user's current location using GPS data and manage related technical terms. The management unit can also prioritize managing regional technical terms based on the user's geographical location. For example, the management unit manages regional technical terms based on the user's location information. The management unit can also prioritize managing technical terms related to nearby industries or fields based on the user's location information. For example, the management unit manages technical terms related to nearby industries or fields based on the user's location information. This makes it possible to manage highly relevant technical terms by taking into account the user's geographical location information. Some or all of the above-described processing in the management unit may be performed using AI, for example, or without AI. For example, the management unit can input GPS data into a generation AI and cause the generation AI to manage related technical terms.

[0061] When managing terminology, the management unit can analyze the user's social media activity and manage related terminology. For example, the management unit manages the terminology of accounts the user follows on social media. For example, the management unit manages the terminology of the accounts the user follows using a social media API. The management unit can also analyze the content of the user's social media posts and manage related terminology. For example, the management unit analyzes the content of the user's posts and extracts related terminology. The management unit can also manage related terminology by referring to the activities of the user's friends on social media. For example, the management unit analyzes the content of the user's friends' posts and extracts related terminology. In this way, highly relevant terminology can be managed by analyzing the user's social media activity. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input social media APIs into a generation AI and cause the generation AI to manage related terminology.

[0062] When managing technical terms, the management unit can determine the priority of technical terms by reflecting past user feedback. The management unit, for example, determines the priority of technical terms based on feedback provided by the user in the past. For example, the management unit stores user feedback in a database and references it using a search algorithm. The management unit can also adjust the importance of technical terms based on user feedback. For example, the management unit adjusts the importance of technical terms based on user feedback. The management unit can also customize the method of managing technical terms by referring to user feedback. For example, the management unit customizes the method of managing technical terms based on user feedback. This allows the priority of technical terms to be optimized by reflecting past user feedback. Some or all of the above-mentioned processing in the management unit may be performed using AI, for example, or may be performed without using AI. For example, the management unit can input user feedback into a generation AI and have the generation AI determine the priority of technical terms.

[0063] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0064] The translation system may further include a history reference unit that references the user's past translation history. The history reference unit stores the user's past translation results in a database and references them when creating a new translation. For example, if a user reuses a term from a technical document that they have previously translated, the history reference unit searches for that term and provides an appropriate translation. The history reference unit may also adjust algorithms to improve translation accuracy based on past translation results. For example, it may analyze past translation results and find common patterns to improve translation accuracy. Furthermore, the history reference unit may determine translation priorities based on the user's translation history. For example, it may prioritize translations of documents in fields that the user frequently translates. This improves translation accuracy and efficiency by utilizing past translation history.

[0065] The translation system can further include an expertise evaluation unit that evaluates the user's level of expertise. The expertise evaluation unit evaluates the user's level of expertise based on information provided by the user and past usage history. For example, if a user frequently translates technical documents, the expertise evaluation unit evaluates the user as an expert. The expertise evaluation unit can also adjust the level of detail of the translation depending on the user's level of expertise. For example, it can provide a detailed translation for experts and a concise translation for general users. Furthermore, the expertise evaluation unit can select an appropriate translation algorithm based on the user's level of expertise. For example, it can use a translation algorithm that uses a lot of technical terminology for experts and a concise translation algorithm for general users. This makes it possible to provide an appropriate translation according to the user's level of expertise.

[0066] The translation system may further include a location information analysis unit that takes into account the user's geographical location information. The location information analysis unit identifies the user's current location and prioritizes collecting data related to that location. For example, if the user is in Japan, news articles and social media posts related to Japan are prioritized. The location information analysis unit can also collect local event information and store information based on the user's location information. For example, if the user is in Tokyo, event information and store information for Tokyo are collected. The location information analysis unit can also determine translation priorities based on the user's location information. For example, if the user is in a hurry, nearby information is prioritized for translation. This allows the system to collect highly relevant data and provide appropriate translations by taking the user's geographical location information into account.

[0067] The translation system may further include a social media analysis unit that analyzes a user's social media activity. The social media analysis unit analyzes the accounts the user follows and the content of their posts to collect relevant data. For example, if a user follows technology accounts, technology-related posts will be collected preferentially. The social media analysis unit may also analyze the content of the user's posts and collect data based on the user's interests. For example, if a user frequently posts about entertainment, entertainment-related data will be collected preferentially. The social media analysis unit may also collect relevant data based on the activities of the user's friends. For example, it may collect posts shared by the user's friends. In this way, by analyzing the user's social media activity, highly relevant data can be collected and appropriate translations can be provided.

[0068] The processing flow of the first embodiment will be briefly explained below.

[0069] Step 1: The collection unit collects data. The data includes news articles, social media posts, blogs, forum posts, etc. The collection unit collects data from specific news sites and social media platforms, and periodically scans blog and forum posts to collect relevant data. Step 2: The analysis unit analyzes the data collected by the collection unit and determines the Japanese context. The analysis is performed using generative AI, natural language processing technology, machine learning algorithms, morphological analysis, grammatical analysis, semantic analysis, etc. For example, morphological analysis is used to analyze the meaning of words and determine the context. Grammatical analysis analyzes the structure of sentences, and semantic analysis analyzes the meaning of words to determine the context. Step 3: The translation unit performs translation based on the context determined by the analysis unit. Translation is performed using translation memory, neural machine translation technology, encoder-decoder models, etc. For example, a translation memory can be used to refer to past translation results and perform an appropriate translation. Neural machine translation technology uses a neural network to perform translation based on the context, and an encoder-decoder model encodes and decodes the input sentence to perform the translation.

[0070] (Example 2) A translation system according to an embodiment of the present invention collects data, and a generation AI analyzes the context of Japanese text, determines its meaning, and performs translation. The translation system collects data, and a generation AI analyzes the context of Japanese text and determines its meaning, thereby providing an appropriate translation. For example, the translation system collects data from various sources, such as news articles and social media posts. The translation system then uses a generation AI to analyze the context of the collected data and determine its meaning. The input to the generation AI is the collected data itself, and the generation AI analyzes the context based on the collected data. For example, the generation AI receives a prompt such as "Please analyze the context of this sentence" and analyzes the context of the data. The translation system then translates the data into another language based on the context determined by the generation AI. The translation is not simply a word replacement, but rather an appropriate translation based on the context. For example, the generation AI receives a prompt such as "Please translate based on this context" and generates an appropriate translation. This allows the translation system to provide more natural and accurate translations. This allows the translation system to understand the context of Japanese text through accumulated data and provide appropriate translations. For example, by collecting data from various sources, such as news articles and social media posts, and analyzing the context, generative AI can provide more natural and accurate translations. Additionally, by incorporating user feedback, translation accuracy can be improved.

[0071] A translation system according to an embodiment includes a collection unit, an analysis unit, and a translation unit. The collection unit collects data. Examples of the data include, but are not limited to, news articles, social media posts, blogs, and forum posts. For example, the collection unit collects news articles from a specific news site. The collection unit can also collect social media posts from a specific platform. The collection unit can also periodically scan blog and forum posts to collect related data. For example, the collection unit collects data from popular blogs and scans forum posts to collect data. The analysis unit uses generative AI to analyze the data collected by the collection unit and determine the Japanese context. The analysis is performed using, for example, natural language processing technology or a machine learning algorithm, but is not limited to, examples. For example, the analysis unit analyzes the Japanese context using morphological analysis. The analysis unit can also analyze the context using grammatical analysis. The analysis unit can also analyze the context using semantic analysis. For example, the analysis unit analyzes the meaning of words using morphological analysis to determine the context. Grammatical analysis analyzes the structure of a sentence and determines the context. Semantic analysis analyzes the meaning of words and determines the context. The translation unit performs translation based on the context determined by the analysis unit. Translation may be performed using, for example, a translation memory or neural machine translation technology, but is not limited to these examples. For example, the translation unit uses a translation memory to refer to past translation results and perform an appropriate translation. The translation unit may also use neural machine translation technology to perform context-sensitive translation. The translation unit may also perform translation using an encoder-decoder model. For example, the translation unit uses a translation memory to refer to past translation results and perform an appropriate translation. Neural machine translation technology performs context-sensitive translation using a neural network. The encoder-decoder model encodes and decodes input sentences to perform translation. This allows the translation system according to the embodiment to understand the context of Japanese through accumulated data and perform appropriate translation. Some or all of the above-described processing in the translation unit may be performed using, for example, AI, or may be performed without AI.For example, the translation unit can perform the translation using an AI model that takes the context determined by the analysis unit as input and outputs a translation.

[0072] The collection unit can collect data including news articles and social media posts. For example, the collection unit collects news articles from a specific news site. For example, the collection unit collects articles using the RSS feed of the news site. The collection unit can also collect social media posts from a specific platform. For example, the collection unit collects posts using the social media API. The collection unit can also periodically scan blog and forum posts to collect related data. For example, the collection unit collects data from popular blogs and scans forum posts to collect data. This makes it possible to collect information from a variety of data sources. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the RSS feed of a news site into the generation AI and cause the generation AI to collect articles.

[0073] The analysis unit can analyze the context of Japanese using natural language processing technology or a machine learning algorithm. The analysis unit analyzes the context of Japanese using, for example, morphological analysis. For example, the analysis unit uses a morphological analysis tool to analyze the meaning of words and determine the context. The analysis unit can also analyze the context using grammatical analysis. For example, the analysis unit uses a grammatical analysis tool to analyze the structure of a sentence and determine the context. The analysis unit can also analyze the context using semantic analysis. For example, the analysis unit uses a semantic analysis tool to analyze the meaning of words and determine the context. This improves the accuracy of context analysis by using advanced algorithms. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input a morphological analysis tool into the generation AI and cause the generation AI to perform context analysis.

[0074] The translation unit can perform translation using a translation memory or neural machine translation technology. For example, the translation unit can refer to past translation results using a translation memory to perform an appropriate translation. For example, the translation unit can search past translation results stored in a translation memory and perform translation based on similar context. The translation unit can also perform context-sensitive translation using neural machine translation technology. For example, the translation unit can perform context-sensitive translation using a neural network. The translation unit can also perform translation using an encoder-decoder model. For example, the translation unit can encode and decode the input sentence to perform translation. This enables appropriate translation based on the context. Some or all of the above-mentioned processing in the translation unit can be performed using, for example, AI, or without AI. For example, the translation unit can input past translation results stored in a translation memory into a generation AI and have the generation AI perform an appropriate translation.

[0075] The reception unit can accept feedback from users. For example, the reception unit accepts feedback from users through an online form. For example, the reception unit collects user ratings and comments through a feedback form on a website. The reception unit can also accept feedback via email. For example, the reception unit receives feedback from users via email and reflects the feedback in the system. The reception unit can also accept feedback via telephone. For example, the reception unit receives feedback from users over the phone and reflects the feedback in the system. In this way, the accuracy of the system is improved by reflecting user feedback. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input feedback collected through an online form into a generation AI and have the generation AI analyze the feedback.

[0076] The management unit can translate proper nouns and technical terms using a technical dictionary. For example, the management unit translates proper nouns and technical terms using a technical dictionary. For example, the management unit references terms registered in the technical dictionary and performs appropriate translations. The management unit can also periodically update the technical dictionary and add new terms. For example, the management unit updates the technical dictionary and adds new terms based on user feedback. The management unit can also correct the contents of the technical dictionary to provide accurate translations. For example, the management unit periodically reviews the contents of the technical dictionary and corrects errors. This enables accurate translation of technical terms and proper nouns. Some or all of the above-described processing in the management unit can be performed using, or without, AI. For example, the management unit can input the contents of the technical dictionary into a generation AI and cause the generation AI to perform analysis to improve the accuracy of the translation.

[0077] The collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit reduces the frequency of data collection to reduce the user's burden. For example, the collection unit captures the user's facial expressions with a camera and estimates the user's emotions using an emotion estimation algorithm. Furthermore, if the user is relaxed, the collection unit can increase the frequency of data collection to collect more data. For example, the collection unit records the user's voice and estimates the user's emotions using voice analysis technology. Furthermore, if the user is in a hurry, the collection unit can temporarily stop data collection and resume it later. For example, the collection unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This reduces the user's burden by adjusting the timing of data collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0078] The collection unit can include blog and forum posts in addition to news articles and social media posts as collection targets. For example, the collection unit collects data from popular blogs in addition to news articles and social media posts. For example, the collection unit collects articles using the RSS feed of a blog site. The collection unit can also periodically scan forum posts to collect related data. For example, the collection unit collects posts using the forum's API. The collection unit can also prioritize the collection of blog and forum posts related to topics of interest to a user. For example, the collection unit collects related blog and forum posts based on the user's interests. This enables information collection from a variety of data sources. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the RSS feed of a blog site into the generation AI and cause the generation AI to collect articles.

[0079] The collection unit can filter data based on specific keywords or topics when collecting data. The collection unit collects only relevant data based on, for example, keywords specified by a user. For example, the collection unit extracts relevant data using a keyword filtering algorithm. The collection unit can also preferentially collect data related to a specific topic and filter other data. For example, the collection unit extracts relevant data using a topic model. The collection unit can also preferentially collect data with high importance based on the frequency of keyword appearance. For example, the collection unit analyzes the frequency of keyword appearance and extracts data with high importance. This makes it possible to collect highly relevant data by filtering data based on specific keywords or topics. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input a keyword filtering algorithm to the generation AI and have the generation AI perform data filtering.

[0080] When collecting data, the collection unit can customize the data to be collected by referring to the user's past browsing history. The collection unit, for example, analyzes the user's past browsing history and prioritizes the collection of relevant data. For example, the collection unit analyzes the browser history and extracts relevant data. The collection unit can also collect data from sites the user frequently visits. For example, the collection unit prioritizes the collection of data from specific sites. The collection unit can also collect data that is likely to be of interest to the user based on the user's browsing history. For example, the collection unit analyzes the user's interests and extracts relevant data. This allows for the collection of more relevant data by referring to the user's past browsing history. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the browser history to a generation AI and cause the generation AI to extract relevant data.

[0081] The collection unit can estimate the user's emotions and prioritize the data to be collected based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit prioritizes collecting data that is relaxing. For example, the collection unit captures the user's facial expressions with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is excited, the collection unit can prioritize collecting data that is stimulating. For example, the collection unit records the user's voice and estimates the emotion using voice analysis technology. Furthermore, if the user is tired, the collection unit can prioritize collecting data that is simple and easy to understand. For example, the collection unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This allows for more appropriate data to be collected by prioritizing the data to be collected based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generative AI. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0082] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. The collection unit, for example, prioritizes collecting news articles related to the user's current location. For example, the collection unit identifies the user's current location using GPS data and collects related news articles. The collection unit can also collect local event information based on the user's geographical location. For example, the collection unit collects local event information based on the user's location information. The collection unit can also collect data related to nearby stores and services based on the user's location information. For example, the collection unit collects data related to nearby stores and services based on the user's location information. This makes it possible to collect highly relevant data by taking the user's geographical location information into account. Some or all of the above-described processing by the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input GPS data to a generation AI and cause the generation AI to collect related data.

[0083] The collection unit can analyze the user's social media activities and collect related data when collecting data. The collection unit, for example, collects posts from accounts the user follows on social media. For example, the collection unit collects posts from the followed accounts using a social media API. The collection unit can also analyze the content of the user's social media posts and collect related data. For example, the collection unit analyzes the content of the user's posts and extracts related data. The collection unit can also collect related data by referring to the activities of the user's friends on social media. For example, the collection unit analyzes the content of the user's friends' posts and extracts related data. In this way, highly relevant data can be collected by analyzing the user's social media activities. Some or all of the above-described processing by the collection unit can be performed using, for example, AI, or can be performed without using AI. For example, the collection unit can input social media APIs into the generation AI and cause the generation AI to collect related data.

[0084] The collection unit can customize the collection method by reflecting the user's past feedback when collecting data. The collection unit, for example, adjusts the type of data to collect based on feedback provided by the user in the past. For example, the collection unit analyzes the user's feedback and determines the type of data to collect. The collection unit can also adjust the collection frequency based on the user's feedback. For example, the collection unit adjusts the collection frequency based on the user's feedback. The collection unit can also select data sources to be collected by referring to the user's feedback. For example, the collection unit selects data sources to be collected based on the user's feedback. This allows the collection method to be optimized by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's feedback to the generation AI and cause the generation AI to customize the collection method.

[0085] The analysis unit can estimate the user's emotions and adjust the context analysis algorithm based on the estimated user emotions. For example, if the user is relaxed, the analysis unit uses an algorithm that performs detailed context analysis. For example, the analysis unit captures the user's facial expressions with a camera and estimates the user's emotions using an emotion estimation algorithm. Alternatively, if the user is in a hurry, the analysis unit can use an algorithm that performs simplified context analysis. For example, the analysis unit records the user's voice and estimates the user's emotions using voice analysis technology. Alternatively, if the user is excited, the analysis unit can use an algorithm that performs context analysis that emphasizes emotional factors. For example, the analysis unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This improves analysis accuracy by adjusting the context analysis algorithm 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 can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0086] During context analysis, the analysis unit can use an algorithm that analyzes the structure and grammar of a sentence in detail. For example, the analysis unit analyzes the structure of a sentence to clarify relationships such as the subject, predicate, and object. For example, the analysis unit analyzes the structure of a sentence using a syntax analysis tool. The analysis unit can also analyze the exact meaning of a sentence based on grammatical rules. For example, the analysis unit analyzes a sentence based on grammatical rules using a grammar analysis tool. The analysis unit can also combine the structure and grammar of a sentence to perform more accurate context analysis. For example, the analysis unit analyzes a sentence by combining syntax analysis and grammar analysis. This improves the accuracy of context analysis by analyzing the structure and grammar of the sentence in detail. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input a syntax analysis tool into the generation AI and cause the generation AI to analyze the structure of the sentence.

[0087] The analysis unit can improve the accuracy of the analysis by referring to past analysis results during context analysis. For example, the analysis unit stores past analysis results in a database and references them during a new analysis. For example, the analysis unit stores past analysis results in a database and references them using a search algorithm. The analysis unit can also adjust algorithm parameters based on past analysis results. For example, the analysis unit adjusts algorithm parameters based on past analysis results. The analysis unit can also analyze past analysis results and find common patterns to improve the analysis accuracy. For example, the analysis unit analyzes past analysis results and finds common patterns. By referring to past analysis results, the analysis accuracy is improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past analysis results into a generation AI and cause the generation AI to perform analysis to improve the analysis accuracy.

[0088] The analysis unit can customize analysis methods according to different genres or topics when analyzing context. For example, the analysis unit uses different analysis methods for news articles and social media posts. For example, the analysis unit uses a news-specific analysis method for news articles and a social media-specific analysis method for social media posts. The analysis unit can also use different analysis methods for technical documents and entertainment articles. For example, the analysis unit uses a technology-specific analysis method for technical documents and an entertainment-specific analysis method for entertainment articles. The analysis unit can also select the optimal analysis method for each topic to improve analysis accuracy. For example, the analysis unit uses a topic model to select the optimal analysis method for each topic. This improves analysis accuracy by customizing the analysis method according to different genres or topics. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input a topic model to a generation AI and have the generation AI select the optimal analysis method.

[0089] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit provides a simple, highly visible display method. For example, the analysis unit captures the user's facial expressions with a camera and estimates the user's emotions using an emotion estimation algorithm. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. For example, the analysis unit records the user's voice and estimates the user's emotions using voice analysis technology. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that focuses on the key points. For example, the analysis unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This allows the display method of the analysis results to be adjusted according to the user's emotions, thereby enabling a display that is easy for the user to view. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0090] During context analysis, the analysis unit can adjust the analysis method according to the length and complexity of the sentence. For example, for short sentences, the analysis unit uses a simplified analysis method. For example, the analysis unit uses a simplified analysis algorithm for short sentences. The analysis unit can also use a detailed analysis method for long sentences. For example, the analysis unit uses a detailed analysis algorithm for long sentences. The analysis unit can also improve analysis accuracy by combining multiple analysis methods for complex sentences. For example, the analysis unit uses a combination of multiple analysis algorithms for complex sentences. In this way, analysis accuracy is improved by adjusting the analysis method according to the length and complexity of the sentence. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input a simplified analysis algorithm for short sentences to the generation AI and have the generation AI perform the analysis.

[0091] The analysis unit can improve the accuracy of the analysis by referring to a related external database during context analysis. The analysis unit, for example, refers to an external dictionary database to accurately analyze the meaning of a word. For example, the analysis unit refers to an external dictionary database via an API to analyze the meaning of a word. The analysis unit can also refer to an external knowledge base to analyze an appropriate meaning according to the context. For example, the analysis unit refers to an external knowledge base via an API to analyze the meaning according to the context. The analysis unit can also improve the analysis accuracy of specialized text by referring to an external terminology database. For example, the analysis unit refers to an external terminology database via an API to analyze specialized text. In this way, the analysis accuracy is improved by referring to the related external database. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input an external dictionary database into the generation AI and cause the generation AI to analyze the meaning of words.

[0092] During context analysis, the analysis unit can adjust the level of detail of the analysis results according to the user's level of expertise. For example, if the user is an expert, the analysis unit provides detailed analysis results. For example, the analysis unit evaluates the user's level of expertise based on survey results and past usage history and provides detailed analysis results. Furthermore, if the user is a general user, the analysis unit can also provide concise and easy-to-understand analysis results. For example, the analysis unit provides concise analysis results based on the user's level of expertise. Furthermore, the analysis unit can customize the display method of the analysis results according to the user's level of expertise. For example, the analysis unit customizes the display method of the analysis results based on the user's level of expertise. By adjusting the level of detail of the analysis results according to the user's level of expertise, it is possible to provide analysis results that are easy for the user to understand. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's level of expertise to the generation AI and cause the generation AI to adjust the level of detail of the analysis results.

[0093] The translation unit can estimate the user's emotions and adjust the translation expression based on the estimated user emotions. For example, if the user is relaxed, the translation unit uses softer expressions in the translation. For example, the translation unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. Furthermore, if the user is in a hurry, the translation unit can use concise and direct expressions in the translation. For example, the translation unit records the user's voice and estimates the emotions using voice analysis technology. Furthermore, if the user is excited, the translation unit can emphasize emotional expressions in the translation. For example, the translation unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotions using an emotion estimation algorithm. This allows the translation expression to be adjusted according to the user's emotions, thereby providing a more appropriate translation. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generative AI. Some or all of the above-described processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit may input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0094] The translation unit can apply different translation algorithms depending on the context during translation. For example, in the case of technical documents, the translation unit uses a translation algorithm specialized for technical terminology. For example, the translation unit translates technical documents using a technical terminology dictionary. In addition, the translation unit can also use a translation algorithm that emphasizes natural expression in the case of entertainment articles. For example, the translation unit uses a translation algorithm that emphasizes natural expression in the case of entertainment articles. In addition, the translation unit can also use a translation algorithm that emphasizes accuracy in the case of news articles. For example, the translation unit uses a translation algorithm that emphasizes accuracy in the case of news articles. In this way, by applying different translation algorithms depending on the context, translation accuracy is improved. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input a technical terminology dictionary into a generation AI for technical documents and have the generation AI perform the translation.

[0095] The translation unit can improve the accuracy of translation by referring to past translation results during translation. For example, the translation unit stores past translation results in a database and refers to them when performing a new translation. For example, the translation unit stores past translation results in a database and refers to them using a search algorithm. The translation unit can also adjust the parameters of the algorithm based on the past translation results. For example, the translation unit adjusts the parameters of the algorithm based on the past translation results. The translation unit can also analyze past translation results and find common patterns to improve translation accuracy. For example, the translation unit analyzes past translation results and finds common patterns. By referring to the past translation results, translation accuracy is improved. Some or all of the above-described processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input past translation results into a generation AI and have the generation AI perform analysis to improve translation accuracy.

[0096] During translation, the translation unit can use a translation method customized for specific technical terms and proper nouns. The translation unit, for example, uses a technical dictionary to perform an accurate translation. For example, the translation unit references terms registered in the technical dictionary to perform an appropriate translation. The translation unit can also use a customized method for performing an appropriate translation for proper nouns. For example, the translation unit uses a proper noun dictionary to perform translation. The translation unit can also improve translation accuracy by using a translation method specialized for a specific field. For example, the translation unit uses a technical dictionary specialized for a specific field to perform translation. In this way, translation accuracy is improved by using a translation method customized for specific technical terms and proper nouns. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input a technical dictionary into a generation AI and have the generation AI perform the translation.

[0097] The translation unit can estimate the user's emotions and adjust the length of the translation based on the estimated user emotions. For example, if the user is in a hurry, the translation unit provides a short, concise translation. For example, the translation unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. Alternatively, if the user is relaxed, the translation unit can provide a longer translation with more detailed explanations. For example, the translation unit records the user's voice and estimates their emotions using voice analysis technology. Alternatively, if the user is excited, the translation unit can provide a translation that emphasizes emotional expressions. For example, the translation unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates their emotions using an emotion estimation algorithm. This allows the translation to be adjusted according to the user's emotions, thereby providing a more appropriate translation. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generative AI. Some or all of the above-described processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit may input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0098] During translation, the translation unit can determine the priority of translation based on the submission date of the text. For example, the translation unit prioritizes translating text with an approaching deadline. For example, the translation unit prioritizes translating text with an upcoming deadline based on the submission date and time. The translation unit can also postpone text with a more distant submission date and prioritize text with a higher urgency. For example, the translation unit prioritizes translating text with a higher urgency based on the submission date and time. The translation unit can also automatically adjust the translation schedule based on the submission date and time. For example, the translation unit automatically adjusts the translation schedule based on the submission date and time. In this way, by determining the priority of translation based on the submission date and time, text with a higher urgency can be translated with a higher priority. Some or all of the above-described processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input the submission date and time to the generation AI and have the generation AI determine the translation priority.

[0099] The translation unit can improve the accuracy of the translation by referring to related literature and materials during translation. For example, the translation unit can improve the translation accuracy of specialized content by referring to related literature. For example, the translation unit can search for related literature from a database and reflect it in the translation. The translation unit can also provide a consistent translation by referring to past materials. For example, the translation unit can search for past materials from a database and reflect it in the translation. The translation unit can also provide an accurate translation by referring to an external database. For example, the translation unit can refer to an external database through an API and reflect it in the translation. In this way, the translation accuracy is improved by referring to related literature and materials. Some or all of the above-mentioned processing in the translation unit may be performed using, or without, AI. For example, the translation unit can input related literature into the generation AI and have the generation AI perform analysis to improve the translation accuracy.

[0100] The translation unit can adjust the use of technical terms in the translation according to the user's level of expertise during translation. For example, if the user is an expert, the translation unit provides a translation that uses a lot of technical terms. For example, the translation unit evaluates the user's level of expertise based on survey results and past usage history and provides a translation that uses a lot of technical terms. In addition, if the user is a general user, the translation unit can provide a concise translation that avoids technical terms. For example, the translation unit provides a concise translation based on the user's level of expertise. In addition, the translation unit can adjust the level of detail of the translation according to the user's level of expertise. For example, the translation unit adjusts the level of detail of the translation based on the user's level of expertise. This allows for a more appropriate translation to be provided by adjusting the use of technical terms in the translation according to the user's level of expertise. Some or all of the above-described processing in the translation unit may be performed using, or without, AI. For example, the translation unit can input the user's level of expertise into a generation AI and have the generation AI adjust the use of technical terms in the translation.

[0101] The reception unit can estimate the user's emotions and adjust the feedback reception method based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit provides a simple feedback form. For example, the reception unit captures the user's facial expression with a camera and estimates the user's emotions using an emotion estimation algorithm. Alternatively, if the user is relaxed, the reception unit can provide a detailed feedback form. For example, the reception unit records the user's voice and estimates the user's emotions using voice analysis technology. Alternatively, if the user is in a hurry, the reception unit can prioritize voice input and quickly accept feedback. For example, the reception unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This allows for more appropriate feedback by adjusting the feedback reception method according to the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0102] When receiving feedback, the reception unit can select the optimal reception method by referring to the user's past feedback history. The reception unit, for example, prioritizes suggesting feedback methods that the user has used in the past. For example, the reception unit stores the user's past feedback history in a database and references it using a search algorithm. The reception unit can also predict and suggest a feedback method to be used in a specific time period based on the user's past feedback history. For example, the reception unit predicts a feedback method to be used in a specific time period based on the user's past feedback history. The reception unit can also analyze the user's past feedback history and select the optimal feedback method. For example, the reception unit analyzes the user's past feedback history and selects the optimal feedback method. In this way, the optimal feedback reception method can be provided by referring to the user's past feedback history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past feedback history into a generation AI and cause the generation AI to select the optimal feedback method.

[0103] The reception unit can filter the feedback content based on the user's current situation and interests when receiving the feedback. The reception unit, for example, prioritizes receiving relevant feedback content based on the user's current situation. For example, the reception unit evaluates the user's current situation based on survey results and past usage history, and prioritizes receiving related feedback content. The reception unit can also filter the feedback content based on the user's interests. For example, the reception unit filters the feedback content based on the user's interests. The reception unit can also customize the feedback content based on the user's current situation and interests. For example, the reception unit customizes the feedback content based on the user's current situation and interests. As a result, highly relevant feedback can be obtained by filtering the feedback content based on the user's current situation and interests. Some or all of the above-described processing in the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's current situation and interests to a generation AI and cause the generation AI to filter the feedback content.

[0104] The reception unit can estimate the user's emotions and prioritize feedback based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit prioritizes urgent feedback. For example, the reception unit captures the user's facial expression with a camera and estimates the user's emotions using an emotion estimation algorithm. Furthermore, if the user is relaxed, the reception unit can prioritize detailed feedback. For example, the reception unit records the user's voice and estimates the user's emotions using voice analysis technology. Furthermore, if the user is in a hurry, the reception unit can prioritize concise feedback. For example, the reception unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This allows for more appropriate feedback to be obtained by prioritizing feedback based on the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0105] When receiving feedback, the reception unit can prioritize receiving highly relevant feedback by taking into account the user's geographical location information. The reception unit, for example, prioritizes receiving feedback related to the user's current location. For example, the reception unit identifies the user's current location using GPS data and receives related feedback. The reception unit can also prioritize receiving regional feedback based on the user's geographical location. For example, the reception unit receives regional feedback based on the user's location information. The reception unit can also prioritize receiving feedback regarding nearby stores and services based on the user's location information. For example, the reception unit receives feedback regarding nearby stores and services based on the user's location information. In this way, highly relevant feedback can be obtained by taking the user's geographical location information into account. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input GPS data to the generation AI and cause the generation AI to receive related feedback.

[0106] The reception unit may analyze the user's social media activity and receive relevant feedback when receiving feedback. For example, the reception unit may preferentially receive feedback from accounts the user follows on social media. For example, the reception unit may receive feedback from the accounts the user follows using a social media API. The reception unit may also analyze the content of the user's social media posts and receive relevant feedback. For example, the reception unit may analyze the content of the user's posts and extract relevant feedback. The reception unit may also receive relevant feedback by referring to the activities of the user's friends on social media. For example, the reception unit may analyze the content of the user's friends' posts and extract relevant feedback. In this way, highly relevant feedback can be obtained by analyzing the user's social media activity. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input a social media API into the generation AI and cause the generation AI to receive relevant feedback.

[0107] The management unit can estimate the user's emotions and adjust the terminology management method based on the estimated user emotions. For example, if the user is feeling stressed, the management unit can provide a simple terminology management method. For example, the management unit can capture the user's facial expressions with a camera and estimate the user's emotions using an emotion estimation algorithm. Alternatively, if the user is relaxed, the management unit can provide a more detailed terminology management method. For example, the management unit can record the user's voice and estimate the user's emotions using voice analysis technology. Alternatively, if the user is in a hurry, the management unit can provide a method for quickly managing terminology. For example, the management unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the user's emotions using an emotion estimation algorithm. This allows for more appropriate terminology management by adjusting the terminology management method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0108] When managing technical terms, the management unit can customize a technical dictionary according to a specific field or industry. The management unit, for example, uses a technical dictionary specialized for the medical field. For example, the management unit manages technical terms using a technical dictionary specialized for the medical field. The management unit can also use a technical dictionary specialized for a technical field. For example, the management unit manages technical terms using a technical dictionary specialized for a technical field. The management unit can also use a technical dictionary specialized for the legal field. For example, the management unit manages technical terms using a technical dictionary specialized for the legal field. In this way, by customizing the technical dictionary according to a specific field or industry, the accuracy of technical terminology management is improved. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input a technical dictionary specialized for a specific field or industry into the generation AI and have the generation AI manage the technical terminology.

[0109] The management unit can improve the accuracy of technical terms by referring to past translation results when managing technical terms. The management unit, for example, stores past translation results in a database and references them when managing new technical terms. For example, the management unit stores past translation results in a database and references them using a search algorithm. The management unit can also update the contents of the technical term dictionary based on past translation results. For example, the management unit updates the contents of the technical term dictionary based on past translation results. The management unit can also analyze past translation results and find common patterns to improve the accuracy of technical terms. For example, the management unit analyzes past translation results and finds common patterns. By referring to past translation results, the accuracy of technical terms is improved. Some or all of the above-mentioned processing in the management unit may be performed using AI, for example, or may be performed without using AI. For example, the management unit can input past translation results into a generation AI and have the generation AI perform analysis to improve the accuracy of technical terms.

[0110] During terminology management, the management unit can update the terminology dictionary by reflecting user feedback. The management unit, for example, updates the contents of the terminology dictionary based on user-provided feedback. For example, the management unit stores user feedback in a database and references it using a search algorithm. The management unit can also revise the definitions of terminology based on user feedback. For example, the management unit revises the definitions of terminology based on user feedback. The management unit can also improve the accuracy of the terminology dictionary by referring to user feedback. For example, the management unit analyzes user feedback and improves the accuracy of the terminology dictionary. As a result, the accuracy of the terminology dictionary is improved by reflecting user feedback. Some or all of the above-described processing in the management unit may be performed using AI, for example, or may be performed without using AI. For example, the management unit can input user feedback into a generation AI and cause the generation AI to update the terminology dictionary.

[0111] The management unit can estimate the user's emotions and prioritize technical terms based on the estimated user emotions. For example, if the user is feeling stressed, the management unit prioritizes managing more important technical terms. For example, the management unit captures the user's facial expressions with a camera and estimates the user's emotions using an emotion estimation algorithm. The management unit can also prioritize detailed technical terms when the user is relaxed. For example, the management unit records the user's voice and estimates the user's emotions using voice analysis technology. The management unit can also prioritize concise technical terms when the user is in a hurry. For example, the management unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This enables more appropriate management by prioritizing technical terms according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0112] When managing technical terms, the management unit can prioritize managing highly relevant technical terms by taking into account the user's geographical location information. The management unit, for example, prioritizes managing technical terms related to the user's current location. For example, the management unit can identify the user's current location using GPS data and manage related technical terms. The management unit can also prioritize managing regional technical terms based on the user's geographical location. For example, the management unit manages regional technical terms based on the user's location information. The management unit can also prioritize managing technical terms related to nearby industries or fields based on the user's location information. For example, the management unit manages technical terms related to nearby industries or fields based on the user's location information. This makes it possible to manage highly relevant technical terms by taking into account the user's geographical location information. Some or all of the above-described processing in the management unit may be performed using AI, for example, or without AI. For example, the management unit can input GPS data into a generation AI and cause the generation AI to manage related technical terms.

[0113] When managing terminology, the management unit can analyze the user's social media activity and manage related terminology. For example, the management unit manages the terminology of accounts the user follows on social media. For example, the management unit manages the terminology of the accounts the user follows using a social media API. The management unit can also analyze the content of the user's social media posts and manage related terminology. For example, the management unit analyzes the content of the user's posts and extracts related terminology. The management unit can also manage related terminology by referring to the activities of the user's friends on social media. For example, the management unit analyzes the content of the user's friends' posts and extracts related terminology. In this way, highly relevant terminology can be managed by analyzing the user's social media activity. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input social media APIs into a generation AI and cause the generation AI to manage related terminology.

[0114] When managing technical terms, the management unit can determine the priority of technical terms by reflecting past user feedback. The management unit, for example, determines the priority of technical terms based on feedback provided by the user in the past. For example, the management unit stores user feedback in a database and references it using a search algorithm. The management unit can also adjust the importance of technical terms based on user feedback. For example, the management unit adjusts the importance of technical terms based on user feedback. The management unit can also customize the method of managing technical terms by referring to user feedback. For example, the management unit customizes the method of managing technical terms based on user feedback. This allows the priority of technical terms to be optimized by reflecting past user feedback. Some or all of the above-mentioned processing in the management unit may be performed using AI, for example, or may be performed without using AI. For example, the management unit can input user feedback into a generation AI and have the generation AI determine the priority of technical terms. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, and translation unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit can collect news articles and social media posts using the control unit 46A of the smart device 14. The analysis unit analyzes the context of the collected data using a generation AI by the specific processing unit 290 of the data processing device 12 and determines its meaning. The translation unit performs appropriate translation based on the context determined by the specific processing unit 290 of the data processing device 12. Some or all of the collection unit, analysis unit, and translation unit may also be realized by the control unit 46A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, and translation unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit can collect news articles and social media posts via the control unit 46A of the smart glasses 214. The analysis unit analyzes the context of the collected data using a generation AI by the specific processing unit 290 of the data processing device 12 to determine its meaning. The translation unit performs appropriate translation based on the context determined by the specific processing unit 290 of the data processing device 12. Some or all of the collection unit, analysis unit, and translation unit may also be realized by the control unit 46A of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, and translation unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit can collect news articles and social media posts by the control unit 46A of the headset type terminal 314. Furthermore, the analysis unit analyzes the context of the collected data using a generation AI by the specific processing unit 290 of the data processing device 12 and determines its meaning. The translation unit performs appropriate translation based on the context determined by the specific processing unit 290 of the data processing device 12. Some or all of the collection unit, analysis unit, and translation unit may also be realized by the control unit 46A of the headset type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, and translation unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit can collect news articles and social media posts by the control unit 46A of the robot 414. The analysis unit analyzes the context of the collected data using a generation AI by the specific processing unit 290 of the data processing device 12 and determines its meaning. The translation unit performs appropriate translation based on the context determined by the specific processing unit 290 of the data processing device 12. Some or all of the collection unit, analysis unit, and translation unit may also be realized by the control unit 46A of the robot 414.

[0115] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0116] The translation system may further include a speech analysis unit that analyzes the user's speech input. The speech analysis unit converts the user's speech into text and sends the text to the analysis unit. For example, if the user verbally requests, "Please translate this sentence," the speech analysis unit converts the speech into text and sends it to the analysis unit. The speech analysis unit can also analyze the user's speech rate and tone to estimate the user's emotions. For example, if a user is in a hurry, their speech rate often increases. Therefore, the speech analysis unit analyzes the speech rate and estimates that the user is in a hurry. Furthermore, the speech analysis unit can suggest an appropriate translation method based on the user's speech content. For example, if a user utters, "Please translate a technical document," the speech analysis unit analyzes the content and suggests a translation method appropriate for the technical document. This improves user convenience by using speech input.

[0117] The translation system may further include a history reference unit that references the user's past translation history. The history reference unit stores the user's past translation results in a database and references them when creating a new translation. For example, if a user reuses a term from a technical document that they have previously translated, the history reference unit searches for that term and provides an appropriate translation. The history reference unit may also adjust algorithms to improve translation accuracy based on past translation results. For example, it may analyze past translation results and find common patterns to improve translation accuracy. Furthermore, the history reference unit may determine translation priorities based on the user's translation history. For example, it may prioritize translations of documents in fields that the user frequently translates. This improves translation accuracy and efficiency by utilizing past translation history.

[0118] The translation system can further include an expertise evaluation unit that evaluates the user's level of expertise. The expertise evaluation unit evaluates the user's level of expertise based on information provided by the user and past usage history. For example, if a user frequently translates technical documents, the expertise evaluation unit evaluates the user as an expert. The expertise evaluation unit can also adjust the level of detail of the translation depending on the user's level of expertise. For example, it can provide a detailed translation for experts and a concise translation for general users. Furthermore, the expertise evaluation unit can select an appropriate translation algorithm based on the user's level of expertise. For example, it can use a translation algorithm that uses a lot of technical terminology for experts and a concise translation algorithm for general users. This makes it possible to provide an appropriate translation according to the user's level of expertise.

[0119] The translation system may further include a location information analysis unit that takes into account the user's geographical location information. The location information analysis unit identifies the user's current location and prioritizes collecting data related to that location. For example, if the user is in Japan, news articles and social media posts related to Japan are prioritized. The location information analysis unit can also collect local event information and store information based on the user's location information. For example, if the user is in Tokyo, event information and store information for Tokyo are collected. The location information analysis unit can also determine translation priorities based on the user's location information. For example, if the user is in a hurry, nearby information is prioritized for translation. This allows the system to collect highly relevant data and provide appropriate translations by taking the user's geographical location information into account.

[0120] The translation system may further include a social media analysis unit that analyzes a user's social media activity. The social media analysis unit analyzes the accounts the user follows and the content of their posts to collect relevant data. For example, if a user follows technology accounts, technology-related posts will be collected preferentially. The social media analysis unit may also analyze the content of the user's posts and collect data based on the user's interests. For example, if a user frequently posts about entertainment, entertainment-related data will be collected preferentially. The social media analysis unit may also collect relevant data based on the activities of the user's friends. For example, it may collect posts shared by the user's friends. In this way, by analyzing the user's social media activity, highly relevant data can be collected and appropriate translations can be provided.

[0121] The translation system can also estimate the user's emotions and adjust the tone of the translation based on the estimated emotions. For example, if the user is relaxed, the translation can be performed in a softer tone. For example, the user's facial expressions can be captured with a camera and their emotions can be estimated using an emotion estimation algorithm. Alternatively, if the user is in a hurry, the translation can be performed in a concise and direct tone. For example, the user's voice can be recorded and their emotions can be estimated using voice analysis technology. Furthermore, if the user is excited, the translation can be performed in a tone that emphasizes emotional expressions. For example, the user's biometric data (heart rate and electrodermal activity) can be collected with a sensor and their emotions can be estimated using an emotion estimation algorithm. This allows the tone of the translation to be adjusted according to the user's emotions, resulting in a more appropriate translation.

[0122] The translation system can also estimate the user's emotions and adjust the length of the translation based on the estimated emotions. For example, if the user is in a hurry, a short, concise translation can be provided. For example, the user's facial expressions can be captured with a camera and their emotions can be estimated using an emotion estimation algorithm. Alternatively, if the user is relaxed, a longer translation with more detailed explanations can be provided. For example, the user's voice can be recorded and their emotions can be estimated using voice analysis technology. Furthermore, if the user is excited, a translation that emphasizes emotional expressions can be provided. For example, the user's biometric data (heart rate and electrodermal activity) can be collected with a sensor and their emotions can be estimated using an emotion estimation algorithm. This allows the length of the translation to be adjusted according to the user's emotions, resulting in a more appropriate translation.

[0123] The translation system can also estimate the user's emotions and adjust the translation style based on the estimated emotions. For example, if the user is relaxed, the translation can be done using softer expressions. For example, the user's facial expressions can be captured with a camera and their emotions can be estimated using an emotion estimation algorithm. Alternatively, if the user is in a hurry, the translation can be done using concise and direct expressions. For example, the user's voice can be recorded and their emotions can be estimated using voice analysis technology. Furthermore, if the user is excited, emotional expressions can be emphasized in the translation. For example, the user's biometric data (heart rate and electrodermal activity) can be collected with a sensor and their emotions can be estimated using an emotion estimation algorithm. This allows the translation style to be adjusted according to the user's emotions, resulting in a more appropriate translation.

[0124] The translation system can also estimate the user's emotions and prioritize translations based on the estimated emotions. For example, if the user is feeling stressed, it can prioritize translations that require urgent attention. For example, it can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. Also, if the user is relaxed, it can prioritize detailed translations. For example, it can record the user's voice and estimate their emotions using voice analysis technology. Furthermore, if the user is in a hurry, it can prioritize concise translations. For example, it can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate their emotions using an emotion estimation algorithm. This allows it to prioritize translations based on the user's emotions, resulting in more appropriate translations.

[0125] The translation system can also estimate the user's emotions and adjust the accuracy of the translation based on the estimated emotions. For example, if the user is relaxed, an algorithm that performs detailed context analysis can be used. For example, the user's facial expressions can be captured with a camera and their emotions can be estimated using an emotion estimation algorithm. Alternatively, if the user is in a hurry, an algorithm that performs simplified context analysis can be used. For example, the user's voice can be recorded and their emotions can be estimated using voice analysis technology. Furthermore, if the user is excited, an algorithm that performs context analysis that emphasizes emotional elements can be used. For example, the user's biometric data (heart rate and electrodermal activity) can be collected with a sensor and their emotions can be estimated using an emotion estimation algorithm. This allows the accuracy of the translation to be adjusted according to the user's emotions, resulting in a more appropriate translation.

[0126] The processing flow of the second embodiment will be briefly explained below.

[0127] Step 1: The collection unit collects data. The data includes news articles, social media posts, blogs, forum posts, etc. The collection unit collects data from specific news sites and social media platforms, and periodically scans blog and forum posts to collect relevant data. Step 2: The analysis unit analyzes the data collected by the collection unit and determines the Japanese context. The analysis is performed using generative AI, natural language processing technology, machine learning algorithms, morphological analysis, grammatical analysis, semantic analysis, etc. For example, morphological analysis is used to analyze the meaning of words and determine the context. Grammatical analysis analyzes the structure of sentences, and semantic analysis analyzes the meaning of words to determine the context. Step 3: The translation unit performs translation based on the context determined by the analysis unit. Translation is performed using translation memory, neural machine translation technology, encoder-decoder models, etc. For example, a translation memory can be used to refer to past translation results and perform an appropriate translation. Neural machine translation technology uses a neural network to perform translation based on the context, and an encoder-decoder model encodes and decodes the input sentence to perform the translation.

[0128] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0131] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0132] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0133] 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.

[0134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0135] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0139] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0140] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0142] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0143] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0144] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0146] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0147] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0148] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0149] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0150] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0151] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0152] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0154] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0155] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0156] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0157] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0158] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0159] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0160] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0162] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0164] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0165] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0166] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0167] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0168] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0169] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0170] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0171] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0172] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0173] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0174] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0175] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0176] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0177] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0178] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0179] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0180] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0181] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0182] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0183] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0184] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0185] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0186] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0187] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0188] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0189] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0190] 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.

[0191] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0192] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0193] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0194] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0195] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0196] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0197] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0198] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0199] [Explanation of symbols]

[0200] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects data; an analysis unit that analyzes the data collected by the collection unit and determines the context of the Japanese language; a translation unit that performs translation based on the context determined by the analysis unit; Equipped with A system characterized by:

2. The collecting unit Collect data including news articles and social media posts 2. The system of claim 1.

3. The analysis unit Analyzing Japanese context using natural language processing techniques and machine learning algorithms 2. The system of claim 1.

4. The translation unit Translations are performed using translation memory and neural machine translation technology 2. The system of claim 1.

5. Equipped with a reception unit that accepts feedback, Incorporating user feedback 2. The system of claim 1.

6. We have an administrative department that manages technical terms. Use a technical dictionary to translate proper nouns and technical terms 2. The system of claim 1.

7. The collecting unit Inferring user emotions and adjusting the timing of data collection based on the estimated user emotions 2. The system of claim 1.

8. The collecting unit In addition to news articles and social media posts, the collection also includes blog and forum posts.

2. The system of claim 1.

9. The collecting unit As you collect data, filter it based on specific keywords or topics.

2. The system of claim 1.

Images