System

Abstract

To provide a system that extracts useful information from text data and efficiently performs translation and information retrieval between multiple languages.SOLUTION: A system according to the embodiment comprises an analysis unit, an extraction unit, a translation unit, an information search unit, and a provision unit. The analysis unit extracts information from text data, and performs topic modeling and emotion analysis. The extraction unit summarizes the information extracted by the analysis unit, and extracts main points. The translation unit translates the text data extracted by the extraction unit between multiple languages. The information search unit searches for and acquires the text data translated by the translation unit in response to input from a user. The provision unit provides the information acquired by the information search 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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques have had the problem that it is difficult to efficiently extract useful information from text data and to perform translation and information search between multiple languages.

[0005] The system according to the embodiment aims to extract useful information from text data and efficiently perform translation and information search between multiple languages. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, an extraction unit, a translation unit, an information search unit, and a provision unit. The analysis unit extracts information from text data and performs topic modeling and sentiment analysis. The extraction unit summarizes the information extracted by the analysis unit and extracts key points. The translation unit translates the text data extracted by the extraction unit between multiple languages. The information search unit searches for and acquires the text data translated by the translation unit in response to a user input. The provision unit provides the information acquired by the information search unit. Effect of the Invention

[0007] The system according to the embodiment can extract useful information from text data and efficiently perform translation and information search between multiple languages. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A system according to an embodiment of the present invention is a system that extracts information from text data and performs topic modeling and sentiment analysis. The system summarizes long texts, extracts and presents key points. The system also translates text between multiple languages ​​to support international communication. The system also searches and acquires text data to provide optimal information for a user's question. For example, text data such as news articles and social media posts can be analyzed to identify key topics and sentiments. This allows a user to quickly grasp important information from a large amount of text data. The system then summarizes the long text, extracts and presents key points. For example, by summarizing long texts such as academic papers and reports and extracting key points, a user can obtain important information in a short time. It is also possible to perform summarization based on specific keywords specified by the user. This allows a user to obtain a summary tailored to his or her interests. The system also translates text between multiple languages ​​to support international communication. For example, translation between various languages, such as English to Japanese and Japanese to French, is possible. Translation can also be performed taking into account slang and dialects specific to the region, including the user's location. This provides a more natural and accurate translation. The system also searches and acquires text data to provide optimal information for a user's question. For example, if a user inputs "Tell me about the latest technology trends," it is possible to search for related text data and provide optimal information. Furthermore, it is also possible to improve the accuracy of search results based on the analysis results. It also has a control unit that integrates and manages these functions. The control unit integrates and manages each of the analysis unit, extraction unit, translation unit, information search unit, and provision unit. This allows each function to work efficiently in cooperation with each other. Thus, the present invention is a natural language processing development AI assistant that has the functions of text analysis, automatic summarization, language translation, and information search, and can provide users with quick and accurate information.

[0029] The development AI assistant for natural language processing according to the embodiment includes an analysis unit, an extraction unit, a translation unit, an information search unit, and a provision unit. The analysis unit extracts information from text data and performs topic modeling and sentiment analysis. For example, the analysis unit analyzes text data such as news articles and social media posts to identify major topics and sentiments. The analysis unit can extract topics of the text data using topic modeling techniques such as LDA (Latent Dirichlet Allocation) and NMF (Non-negative Matrix Factorization). The analysis unit can also analyze sentiment of the text data using dictionary-based techniques or machine learning-based techniques. For example, the analysis unit can calculate sentiment scores of the text data using a sentiment dictionary. The extraction unit summarizes the text data and extracts key points. For example, the extraction unit performs summarization based on the length of the sentence and the importance of the information to be summarized. The extraction unit can concisely summarize the text data using, for example, a text generation AI (e.g., LLM). The extraction unit can also perform summarization based on specific keywords specified by the user. For example, the extraction unit can prioritize and summarize information related to the keywords specified by the user. The translation unit translates text data between a plurality of languages. For example, the translation unit can translate between various languages, such as from English to Japanese and from Japanese to French. The translation unit can provide natural and accurate translations, for example, using neural machine translation (NMT) technology. The translation unit can also perform translations taking into account slang and dialects specific to a region, including the user's location. For example, the translation unit can appropriately translate expressions specific to a region by referring to a region database. The information search unit searches for and acquires text data according to a user's input. For example, when a user inputs "Tell me about the latest technology trends," the information search unit can search for related text data and provide optimal information. The information search unit can evaluate the relevance of the text data and rank search results, for example, using a search algorithm. The provision unit provides information according to the user's input. For example, the provision unit displays the search results to the user.The providing unit can provide information to the user through, for example, a web application or a mobile application, which allows the natural language processing development AI assistant according to the embodiment to efficiently analyze, summarize, translate, search, and provide text data.

[0030] The analysis unit extracts information from text data and performs topic modeling and sentiment analysis. For example, the analysis unit analyzes text data such as news articles and social media posts to identify major topics and sentiment. The analysis unit can extract topics from text data using topic modeling techniques such as LDA (Latent Dirichlet Allocation) and NMF (Non-negative Matrix Factorization). LDA is a technique that estimates the distribution of topics in a document set and probabilistically indicates which topics each document is related to. This allows the analysis unit to efficiently extract major topics from huge amounts of text data and visualize the relevance of each topic. In addition, NMF is a technique that reveals the topic structure of documents by factorizing non-negative matrices, and is particularly effective for large datasets. The analysis unit can combine these techniques to achieve more accurate topic modeling. In addition, the analysis unit can analyze the sentiment of text data using dictionary-based techniques and machine learning-based techniques. In dictionary-based techniques, a pre-defined sentiment dictionary is used to calculate sentiment scores for words and phrases in the text. For example, the sentiment of the entire text is evaluated by assigning a high score to positive words and a low score to negative words. On the other hand, machine learning-based methods train models using pre-labeled datasets to predict the sentiment of new text data. This allows the analyzer to analyze the sentiment of the text data with high accuracy and classify it into sentiment categories such as positive, negative, and neutral. By utilizing these techniques, the analyzer can comprehensively analyze the topics and sentiment of the text data and provide useful information to users.

[0031] The extraction unit summarizes the text data and extracts the main points. For example, the extraction unit performs summarization based on the length of the sentence and the importance of the information to be summarized. The extraction unit can, for example, use a text generation AI (for example, LLM) to concisely summarize the text data. Specifically, the LLM analyzes the input text data, extracts important information, and generates a short summary sentence. For example, when summarizing a news article, the LLM analyzes the entire article, extracts major events and important points, and generates a summary sentence of several lines. The extraction unit can also perform summarization based on specific keywords specified by the user. For example, if a user specifies that they want information related to "environmental issues" to be summarized, the extraction unit preferentially extracts information related to "environmental issues" in the text data and generates a summary sentence. This allows the user to efficiently obtain information on a specific topic that interests them. Furthermore, the extraction unit can combine multiple summarization methods to improve the accuracy of the summary. For example, the extraction unit combines statistical methods and machine learning methods to evaluate the importance of the text data and generate an optimal summary sentence. This allows the extraction unit to provide the user with a high-quality summary and help them understand the information.

[0032] The translation unit translates text data between multiple languages. For example, the translation unit can translate between various languages, such as from English to Japanese and from Japanese to French. The translation unit can provide natural and accurate translations, for example, using neural machine translation (NMT) technology. NMT utilizes deep learning technology to achieve high-quality translations that take context into account. Specifically, the NMT model goes through a process of encoding input text data and decoding the corresponding translation. This allows the translation unit to provide appropriate translations according to the context. The translation unit can also perform translations taking into account slang and dialects specific to the region, including the user's location. For example, the translation unit can refer to a regional database to appropriately translate expressions specific to the region. This allows the translation unit to provide natural translations that reflect the nuances of culture and language in each region. Furthermore, the translation unit can collect user feedback and continuously improve the accuracy of the translation model. For example, the model parameters are adjusted based on the evaluation of the translation results provided by the user, improving the translation accuracy. This allows the translation unit to always provide high-quality translations based on the latest information and meet the needs of users.

[0033] The information search unit searches and acquires text data according to the user's input. For example, when the user inputs "Tell me about the latest technology trends," the information search unit can search for related text data and provide optimal information. The information search unit can, for example, use a search algorithm to evaluate the relevance of the text data and rank search results. Specifically, the information search unit analyzes the user's query and extracts keywords and phrases included in the query. Next, the information search unit uses a search algorithm to search text data in a database and identify highly relevant documents. For example, the information search unit scores the relevance of documents using evaluation indices such as TF-IDF (Term Frequency-Inverse Document Frequency) and BM25, and displays the most relevant documents at the top. The information search unit can also provide personalized search results by taking into account the user's past search history and click history. This allows the user to efficiently acquire optimal information based on his or her interests and concerns. Furthermore, the information search unit can provide the latest information by including data updated in real time in the search target. For example, the information search unit periodically crawls frequently updated data sources, such as news articles and social media posts, to keep the database up to date. This allows the information search section to always provide the user with the latest information, thereby enabling rapid and accurate information searches.

[0034] The providing unit provides information according to the user's input. For example, the providing unit displays search results to the user. The providing unit can provide information to the user through, for example, a web application or a mobile application. Specifically, the providing unit displays search results for a query entered by the user in a visually easy-to-understand format. For example, the search results can be displayed in a list format, and a summary or related information can be added to each result, allowing the user to quickly find the information he or she needs. The providing unit also provides a filtering and sorting function for the search results, allowing the user to efficiently obtain information that meets his or her needs. For example, the search results can be sorted by date or relevance, or filtered by a specific category or tag. Furthermore, the providing unit can collect user feedback and continuously improve the quality of the information to be provided. For example, the user can leave ratings and comments on the provided information, allowing the providing unit to grasp the needs and satisfaction of the user and improve the accuracy and relevance of the information to be provided. The providing unit also supports multiple devices and platforms, allowing the user to access information anywhere. For example, a consistent user experience is provided on various devices, such as a desktop PC, a smartphone, and a tablet. This allows the providing unit to provide information to the user quickly and accurately, thereby improving the user's convenience.

[0035] The natural language processing development AI assistant includes a control unit that integrates and manages each of the analysis unit, extraction unit, translation unit, information search unit, and provision unit. The control unit integrates and manages each of the analysis unit, extraction unit, translation unit, information search unit, and provision unit. For example, the control unit adjusts the operation of each unit to achieve efficient information processing. For example, the control unit can design a system architecture and manage the data flow of each unit. For example, the control unit can monitor the operation status of each unit and adjust the operation as necessary. In this way, the natural language processing development AI assistant integrates the functions of each unit and efficiently manages them.

[0036] The extraction unit can perform summarization based on specific keywords specified by the user. For example, the extraction unit can prioritize and summarize information related to the keywords specified by the user. This provides a summary tailored to the user's interests. Some or all of the above-mentioned processing in the extraction unit can be performed using, for example, AI, or can be performed without using AI. For example, the extraction unit can input keywords specified by the user to a generation AI and cause the generation AI to perform a summary based on the keywords.

[0037] The translation unit can perform translation taking into account slang and dialects specific to the region, including the user's location. For example, the translation unit can refer to a region database to appropriately translate expressions specific to the region. This provides a natural translation that takes into account slang and dialects specific to the region. Some or all of the above-mentioned processing in the translation unit can be performed using, for example, AI, or can be performed without using AI. For example, the translation unit can input the region database into a generation AI and have the generation AI translate expressions specific to the region.

[0038] The extraction unit can apply different summarization algorithms to text data of different genres. For example, the extraction unit can apply a simple summarization algorithm to news articles and a detailed summarization algorithm to academic papers. This provides an optimal summary according to the genre. Some or all of the above-mentioned processing in the extraction unit can be performed, for example, using AI or without AI. For example, the extraction unit can input the genre of the text data to the generation AI and apply a summarization algorithm according to the genre to the generation AI.

[0039] The extraction unit can improve the accuracy of the summary based on the analysis result of the analysis unit. For example, the extraction unit can perform summarization based on important topics and emotions identified by the analysis unit. This provides a highly accurate summary based on the analysis result. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the analysis result of the analysis unit to the generation AI and cause the generation AI to execute a highly accurate summary.

[0040] The information search unit can improve the accuracy of the search results based on the analysis results of the analysis unit. For example, the information search unit can rank the search results based on important topics and emotions identified by the analysis unit. This provides highly accurate search results based on the analysis results. Some or all of the above-mentioned processing in the information search unit may be performed using, for example, AI, or may be performed without using AI. For example, the information search unit can input the analysis results of the analysis unit to a generation AI and cause the generation AI to execute highly accurate search results.

[0041] The extraction unit summarizes the text data acquired by the information search unit, and the provision unit can provide the main points extracted by the extraction unit to the user. The extraction unit, for example, summarizes the text data acquired by the information search unit and extracts the main points. For example, the extraction unit can pick up important information from the search results and perform a summary. The provision unit, for example, provides the main points extracted by the extraction unit to the user. For example, the provision unit can display the summarized information to the user. This provides a summary of the searched text data. A part or all of the above-mentioned processing in the extraction unit and the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the extraction unit can input the text data acquired by the information search unit to the generation AI and cause the generation AI to execute the summary. The provision unit can provide the user with the summary generated by the generation AI.

[0042] The providing unit can provide information on a specific topic preferentially based on the result of topic modeling by the analyzing unit. For example, the providing unit can provide information related to the user preferentially based on the result of the topic model. This allows information on a specific topic to be provided preferentially. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the topic modeling result of the analyzing unit to a generating AI and cause the generating AI to provide information on a specific topic.

[0043] The analysis unit can improve the accuracy of the analysis result by taking into account the context of the text data. For example, the analysis unit can analyze the context of the text data and improve the accuracy of the sentiment analysis based on the context. The analysis unit can also refine the topic modeling result by taking into account the context of the text data. This provides a highly accurate analysis result that takes the context into account. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input context information of the text data to the generation AI and cause the generation AI to perform analysis based on the context.

[0044] The analysis unit can evaluate the reliability of the analysis by referring to the source information of the text data. For example, if the source of the text data is reliable, the analysis unit can evaluate the reliability of the analysis result as high. Also, if the source of the text data is unclear, the analysis unit can evaluate the reliability of the analysis result as low. This provides a reliable analysis result based on the source information. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the source information of the text data to the generation AI and cause the generation AI to perform the evaluation of reliability.

[0045] The analysis unit can dynamically change the analysis algorithm according to the length of the text data. For example, the analysis unit can apply an algorithm that performs rapid analysis in the case of short text data. Also, the analysis unit can apply an algorithm that performs detailed analysis in the case of long text data. This provides an optimal analysis according to the length of the text data. 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 the length of the text data to the generation AI and cause the generation AI to select an analysis algorithm according to the length.

[0046] The analysis unit can optimize the analysis method according to the format of the text data. For example, in the case of text data in PDF format, the analysis unit can optimize the text extraction algorithm. In addition, in the case of text data in HTML format, the analysis unit can perform analysis taking into account tag information. This provides an optimal analysis according to the format of the text data. A part 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 format information of the text data to the generation AI and cause the generation AI to optimize the analysis method according to the format.

[0047] The extraction unit can determine the priority of summaries based on the importance of the text data. For example, the extraction unit can prioritize important text data for summarization. Also, the extraction unit can postpone summarization of text data with low importance. This provides a priority of summaries based on importance. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the importance of the text data to the generation AI and cause the generation AI to execute the priority of summaries based on importance.

[0048] The extraction unit can apply different summarization algorithms depending on the genre of the text data. For example, the extraction unit can apply a detailed summarization algorithm for academic papers. Also, the extraction unit can apply a concise summarization algorithm for news articles. This provides an optimal summary depending on the genre. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the genre of the text data to the generation AI and cause the generation AI to execute a summarization algorithm depending on the genre.

[0049] The extraction unit can determine the priority of summaries based on the submission time of the text data. For example, the extraction unit can prioritize summarizing the latest text data. Also, the extraction unit can postpone summarizing older text data. This provides a priority of summaries based on the submission time. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI or may be performed without using AI. For example, the extraction unit can input the submission time of the text data to the generation AI and cause the generation AI to perform the priority of summaries based on the submission time.

[0050] The extraction unit can adjust the order of summaries based on the relevance of the text data. For example, the extraction unit can prioritize summarizing highly relevant text data. Also, the extraction unit can postpone summarizing less relevant text data. This provides an order of summaries based on the relevance. A part or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI or may be performed without using AI. For example, the extraction unit can input the relevance of the text data to the generation AI and cause the generation AI to execute the order of summaries based on the relevance.

[0051] During translation, the translation unit can improve the accuracy of the translation by taking into account the cultural background of the text data. For example, the translation unit can select an appropriate expression by taking into account the cultural background of the text data. The translation unit can also adjust the nuance of the translation based on the cultural background. This provides a highly accurate translation that takes the cultural background into account. 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 cultural background information of the text data to the generation AI and cause the generation AI to perform a translation based on the cultural background.

[0052] The translation unit can refer to a dictionary for appropriately translating technical terms in text data during translation. For example, the translation unit can provide an appropriate translation by referring to a technical term dictionary. The translation unit can also dynamically update the dictionary to improve the translation accuracy of technical terms. This provides an appropriate translation of technical terms. Some or all of the above-mentioned processing in the translation unit can be performed, for example, using AI or can be performed without using AI. For example, the translation unit can input a technical term dictionary to a generation AI and cause the generation AI to translate technical terms.

[0053] The translation unit can optimize the translation method according to the format of the text data during translation. For example, the translation unit can apply a translation method that emphasizes technical terms in the case of technical documents. Also, the translation unit can apply a translation method that emphasizes style and nuance in the case of literary works. This provides an optimal translation method according to the format. 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 format information of the text data to the generation AI and cause the generation AI to optimize the translation method according to the format.

[0054] The translation unit can translate the text data while taking into consideration slang and dialects specific to the region. For example, the translation unit can appropriately translate expressions specific to the region by referring to a region database. This provides a natural translation that takes into consideration slang and dialects specific to the region. Some or all of the above-mentioned processing in the translation unit can be performed using, for example, AI, or can be performed without using AI. For example, the translation unit can input data on slang and dialects specific to the region to a generation AI and have the generation AI translate the expressions specific to the region.

[0055] The information search unit can evaluate the reliability of text data during a search to improve the accuracy of search results. For example, the information search unit can display highly reliable text data preferentially in the search results. The information search unit can also postpone less reliable text data. This provides highly accurate search results based on reliability. Some or all of the above-mentioned processing in the information search unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the information search unit can input the reliability of the text data to the generation AI and cause the generation AI to improve the accuracy of the search results based on reliability.

[0056] During a search, the information search unit can evaluate the relevance of the text data and determine the priority of search results. For example, the information search unit can give priority to highly relevant text data and display it in the search results. The information search unit can also postpone text data with low relevance. This provides a priority order of search results based on relevance. Some or all of the above-mentioned processing in the information search unit may be performed, for example, using AI or may be performed without using AI. For example, the information search unit can input the relevance of the text data to the generation AI and cause the generation AI to execute the priority order of search results based on relevance.

[0057] The information search unit can optimize the search method according to the format of the text data during the search. For example, in the case of a news article, the information search unit can prioritize searching the latest information. Also, in the case of an academic paper, the information search unit can prioritize searching for highly reliable information. This provides an optimal search method according to the format. Some or all of the above-mentioned processing in the information search unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the information search unit can input format information of the text data to the generation AI and cause the generation AI to optimize the search method according to the format.

[0058] During a search, the information search unit can determine the priority of search results based on the submission time of the text data. For example, the information search unit can give priority to the latest text data and display it in the search results. The information search unit can also postpone old text data. This provides a priority order of search results based on the submission time. Some or all of the above-mentioned processing in the information search unit may be performed, for example, using AI or may be performed without using AI. For example, the information search unit can input the submission time of the text data to the generation AI and cause the generation AI to execute the priority order of search results based on the submission time.

[0059] The providing unit can provide optimal information by referring to the user's past search history when providing information. For example, the providing unit can provide related information based on information previously searched by the user. The providing unit can also provide topics of interest to the user from the user's past search history with priority. This provides optimal information based on the past search history. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's past search history to the generating AI and cause the generating AI to provide optimal information.

[0060] The providing unit can determine the priority of information based on the user's current field of interest when providing information. For example, the providing unit can provide information by prioritizing topics in which the user is currently interested. The providing unit can also provide related information based on the user's field of interest. This provides the priority of information based on the current field of interest. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or may be performed without using AI. For example, the providing unit can input the user's current field of interest to the generating AI and cause the generating AI to execute the priority of information provision based on the field of interest.

[0061] The providing unit can select the optimal display method in consideration of the user's device information when providing information. For example, when the user is using a smartphone, the providing unit can provide a display method that matches the screen size. Also, when the user is using a tablet, the providing unit can provide a display method optimized for a large screen. This provides the optimal display method based on the device information. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's device information to the generating AI and cause the generating AI to select a display method based on the device information.

[0062] The providing unit can provide highly relevant information in consideration of the geographical location information of the user when providing information. For example, the providing unit can provide relevant information based on the user's current location. Furthermore, the providing unit can provide optimal information in consideration of the geographical location information of the user. This provides highly relevant information based on the geographical location information. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the geographical location information of the user to the generating AI and cause the generating AI to provide information based on the geographical location information.

[0063] The control unit can select an optimal control method by referring to the operation history of each unit. For example, the control unit can analyze the past operation history of each unit and select an optimal control method. The control unit can also improve the efficiency of the operation based on the operation history of each unit. This provides an optimal control method based on the operation history. A part or all of the above-mentioned processing in the control unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the control unit can input the operation history of each unit to the generation AI and cause the generation AI to select an optimal control method.

[0064] The control unit can monitor the operation status of each unit in real time and automatically correct it when an abnormality occurs. For example, the control unit can monitor the operation status of each unit in real time and automatically correct it when an abnormality is detected. The control unit can also monitor the operation status of each unit and issue an alert when an abnormality occurs. This improves the stability of the system through real-time monitoring and automatic correction. Some or all of the above-mentioned processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit can input the operation status of each unit to the generation AI and cause the generation AI to detect and correct an abnormality.

[0065] The control unit can periodically evaluate the operation status of each unit and update the optimal control method. For example, the control unit can periodically evaluate the operation status of each unit and update the optimal control method. The control unit can also evaluate the operation status of each unit and improve the efficiency of the operation. This improves the efficiency and accuracy of the system through periodic evaluation and updating. A part or all of the above-mentioned processing in the control unit may be performed, for example, using AI, or may be performed without using AI. For example, the control unit can input the operation status of each unit to the generation AI and cause the generation AI to execute the update of the optimal control method.

[0066] The control unit can analyze the operation history of each unit and predict future operations. For example, the control unit can analyze the operation history of each unit and predict future operations. The control unit can also improve the efficiency of operations based on the operation history of each unit. This provides future operation prediction based on the operation history. Some or all of the above-mentioned processing in the control unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the control unit can input the operation history of each unit to a generation AI and cause the generation AI to execute future operation prediction.

[0067] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0068] The analysis unit can evaluate the reliability of text data and prioritize analysis of reliable data. For example, the analysis unit can evaluate the source of a news article and prioritize analysis of data from a reliable source. The analysis unit can also evaluate the reliability of social media posts and filter out less reliable posts. Furthermore, the analysis unit can evaluate the number of citations of academic papers and prioritize analysis of papers with many citations. This provides analysis results based on reliable data.

[0069] The extraction unit can improve the accuracy of the summary by referring to the user's past search history. For example, the extraction unit can prioritize and summarize related information based on keywords searched for by the user in the past. The extraction unit can also identify topics of interest from the user's past search history and prioritize and summarize information related to the topics. Furthermore, the extraction unit can analyze the user's past search history and optimize the summarization algorithm. This provides a highly accurate summary based on the user's past search history.

[0070] The translation unit can improve the accuracy of the translation by taking into account the cultural background of the text data. For example, the translation unit can select an appropriate expression by taking into account the cultural background of the text data. The translation unit can also adjust the nuance of the translation based on the cultural background. Furthermore, the translation unit can appropriately translate region-specific expressions by referring to a database related to the cultural background. This provides a highly accurate translation that takes the cultural background into account.

[0071] The information search unit can determine the priority of search results based on the user's current field of interest. For example, the information search unit can prioritize topics in which the user is currently interested in the search results. The information search unit can also prioritize searching for related information based on the user's field of interest. Furthermore, the information search unit can refer to the user's past search history to identify the user's current field of interest and prioritize searching for information related to that field. This provides a priority of search results based on the user's current field of interest.

[0072] The providing unit can select the optimal display method in consideration of the device information of the user. For example, when the user is using a smartphone, the providing unit can provide a display method that matches the screen size. Also, when the user is using a tablet, the providing unit can provide a display method optimized for a large screen. Furthermore, the providing unit can select a font size and layout that are optimal for the device by referring to the device information of the user. In this way, the optimal display method based on the device information is provided.

[0073] The process flow of the first embodiment will be briefly described below.

[0074] Step 1: The analyzer extracts information from text data and performs topic modeling and sentiment analysis. For example, the analyzer analyzes text data such as news articles and social media posts to identify key topics and sentiment. The analyzer extracts topics using topic modeling techniques such as LDA (Latent Dirichlet Allocation) and NMF (Non-negative Matrix Factorization), and analyzes sentiment using dictionary-based and machine learning-based techniques. Step 2: The extraction unit summarizes the text data and extracts the main points. For example, it can summarize based on the length of the text or the importance of the information being summarized, and it can also summarize concisely using a text generation AI (e.g., LLM). It can also summarize based on specific keywords specified by the user. Step 3: The translation unit translates the text data between multiple languages. For example, translations can be made between various languages, such as English to Japanese, Japanese to French, etc. The translation unit uses Neural Machine Translation (NMT) technology to provide natural and accurate translations, and can also take into account regional slang and dialects. Step 4: The information search unit searches and retrieves text data according to the user's input. For example, if the user enters "Tell me about the latest technology trends," the unit searches for related text data and provides the most appropriate information. It uses a search algorithm to evaluate the relevance of the text data and ranks the search results. Step 5: The providing unit provides information according to the user's input. For example, the providing unit displays search results to the user. The information can be provided through a web application or a mobile application.

[0075] (Example 2) A system according to an embodiment of the present invention is a system that extracts information from text data and performs topic modeling and sentiment analysis. The system summarizes long texts, extracts and presents key points. The system also translates text between multiple languages ​​to support international communication. The system also searches and acquires text data to provide optimal information for a user's question. For example, text data such as news articles and social media posts can be analyzed to identify key topics and sentiments. This allows a user to quickly grasp important information from a large amount of text data. The system then summarizes the long text, extracts and presents key points. For example, by summarizing long texts such as academic papers and reports and extracting key points, a user can obtain important information in a short time. It is also possible to perform summarization based on specific keywords specified by the user. This allows a user to obtain a summary tailored to his or her interests. The system also translates text between multiple languages ​​to support international communication. For example, translation between various languages, such as English to Japanese and Japanese to French, is possible. Translation can also be performed taking into account slang and dialects specific to the region, including the user's location. This provides a more natural and accurate translation. The system also searches and acquires text data to provide optimal information for a user's question. For example, if a user inputs "Tell me about the latest technology trends," it is possible to search for related text data and provide optimal information. Furthermore, it is also possible to improve the accuracy of search results based on the analysis results. It also has a control unit that integrates and manages these functions. The control unit integrates and manages each of the analysis unit, extraction unit, translation unit, information search unit, and provision unit. This allows each function to work efficiently in cooperation with each other. Thus, the present invention is a natural language processing development AI assistant that has the functions of text analysis, automatic summarization, language translation, and information search, and can provide users with quick and accurate information.

[0076] The development AI assistant for natural language processing according to the embodiment includes an analysis unit, an extraction unit, a translation unit, an information search unit, and a provision unit. The analysis unit extracts information from text data and performs topic modeling and sentiment analysis. For example, the analysis unit analyzes text data such as news articles and social media posts to identify major topics and sentiments. The analysis unit can extract topics of the text data using topic modeling techniques such as LDA (Latent Dirichlet Allocation) and NMF (Non-negative Matrix Factorization). The analysis unit can also analyze sentiment of the text data using dictionary-based techniques or machine learning-based techniques. For example, the analysis unit can calculate sentiment scores of the text data using a sentiment dictionary. The extraction unit summarizes the text data and extracts key points. For example, the extraction unit performs summarization based on the length of the sentence and the importance of the information to be summarized. The extraction unit can concisely summarize the text data using, for example, a text generation AI (e.g., LLM). The extraction unit can also perform summarization based on specific keywords specified by the user. For example, the extraction unit can prioritize and summarize information related to the keywords specified by the user. The translation unit translates text data between a plurality of languages. For example, the translation unit can translate between various languages, such as from English to Japanese and from Japanese to French. The translation unit can provide natural and accurate translations, for example, using neural machine translation (NMT) technology. The translation unit can also perform translations taking into account slang and dialects specific to a region, including the user's location. For example, the translation unit can appropriately translate expressions specific to a region by referring to a region database. The information search unit searches for and acquires text data according to a user's input. For example, when a user inputs "Tell me about the latest technology trends," the information search unit can search for related text data and provide optimal information. The information search unit can evaluate the relevance of the text data and rank search results, for example, using a search algorithm. The provision unit provides information according to the user's input. For example, the provision unit displays the search results to the user.The providing unit can provide information to the user through, for example, a web application or a mobile application, which allows the natural language processing development AI assistant according to the embodiment to efficiently analyze, summarize, translate, search, and provide text data.

[0077] The analysis unit extracts information from text data and performs topic modeling and sentiment analysis. For example, the analysis unit analyzes text data such as news articles and social media posts to identify major topics and sentiment. The analysis unit can extract topics from text data using topic modeling techniques such as LDA (Latent Dirichlet Allocation) and NMF (Non-negative Matrix Factorization). LDA is a technique that estimates the distribution of topics in a document set and probabilistically indicates which topics each document is related to. This allows the analysis unit to efficiently extract major topics from huge amounts of text data and visualize the relevance of each topic. In addition, NMF is a technique that reveals the topic structure of documents by factorizing non-negative matrices, and is particularly effective for large datasets. The analysis unit can combine these techniques to achieve more accurate topic modeling. In addition, the analysis unit can analyze the sentiment of text data using dictionary-based techniques and machine learning-based techniques. In dictionary-based techniques, a pre-defined sentiment dictionary is used to calculate sentiment scores for words and phrases in the text. For example, the sentiment of the entire text is evaluated by assigning a high score to positive words and a low score to negative words. On the other hand, machine learning-based methods train models using pre-labeled datasets to predict the sentiment of new text data. This allows the analyzer to analyze the sentiment of the text data with high accuracy and classify it into sentiment categories such as positive, negative, and neutral. By utilizing these techniques, the analyzer can comprehensively analyze the topics and sentiment of the text data and provide useful information to users.

[0078] The extraction unit summarizes the text data and extracts the main points. For example, the extraction unit performs summarization based on the length of the sentence and the importance of the information to be summarized. The extraction unit can, for example, use a text generation AI (for example, LLM) to concisely summarize the text data. Specifically, the LLM analyzes the input text data, extracts important information, and generates a short summary sentence. For example, when summarizing a news article, the LLM analyzes the entire article, extracts major events and important points, and generates a summary sentence of several lines. The extraction unit can also perform summarization based on specific keywords specified by the user. For example, if a user specifies that they want information related to "environmental issues" to be summarized, the extraction unit preferentially extracts information related to "environmental issues" in the text data and generates a summary sentence. This allows the user to efficiently obtain information on a specific topic that interests them. Furthermore, the extraction unit can combine multiple summarization methods to improve the accuracy of the summary. For example, the extraction unit combines statistical methods and machine learning methods to evaluate the importance of the text data and generate an optimal summary sentence. This allows the extraction unit to provide the user with a high-quality summary and help them understand the information.

[0079] The translation unit translates text data between multiple languages. For example, the translation unit can translate between various languages, such as from English to Japanese and from Japanese to French. The translation unit can provide natural and accurate translations, for example, using neural machine translation (NMT) technology. NMT utilizes deep learning technology to achieve high-quality translations that take context into account. Specifically, the NMT model goes through a process of encoding input text data and decoding the corresponding translation. This allows the translation unit to provide appropriate translations according to the context. The translation unit can also perform translations taking into account slang and dialects specific to the region, including the user's location. For example, the translation unit can refer to a regional database to appropriately translate expressions specific to the region. This allows the translation unit to provide natural translations that reflect the nuances of culture and language in each region. Furthermore, the translation unit can collect user feedback and continuously improve the accuracy of the translation model. For example, the model parameters are adjusted based on the evaluation of the translation results provided by the user, improving the translation accuracy. This allows the translation unit to always provide high-quality translations based on the latest information and meet the needs of users.

[0080] The information search unit searches and acquires text data according to the user's input. For example, when the user inputs "Tell me about the latest technology trends," the information search unit can search for related text data and provide optimal information. The information search unit can, for example, use a search algorithm to evaluate the relevance of the text data and rank search results. Specifically, the information search unit analyzes the user's query and extracts keywords and phrases included in the query. Next, the information search unit uses a search algorithm to search text data in a database and identify highly relevant documents. For example, the information search unit scores the relevance of documents using evaluation indices such as TF-IDF (Term Frequency-Inverse Document Frequency) and BM25, and displays the most relevant documents at the top. The information search unit can also provide personalized search results by taking into account the user's past search history and click history. This allows the user to efficiently acquire optimal information based on his or her interests and concerns. Furthermore, the information search unit can provide the latest information by including data updated in real time in the search target. For example, the information search unit periodically crawls frequently updated data sources, such as news articles and social media posts, to keep the database up to date. This allows the information search section to always provide the user with the latest information, thereby enabling rapid and accurate information searches.

[0081] The providing unit provides information according to the user's input. For example, the providing unit displays search results to the user. The providing unit can provide information to the user through, for example, a web application or a mobile application. Specifically, the providing unit displays search results for a query entered by the user in a visually easy-to-understand format. For example, the search results can be displayed in a list format, and a summary or related information can be added to each result, allowing the user to quickly find the information he or she needs. The providing unit also provides a filtering and sorting function for the search results, allowing the user to efficiently obtain information that meets his or her needs. For example, the search results can be sorted by date or relevance, or filtered by a specific category or tag. Furthermore, the providing unit can collect user feedback and continuously improve the quality of the information to be provided. For example, the user can leave ratings and comments on the provided information, allowing the providing unit to grasp the needs and satisfaction of the user and improve the accuracy and relevance of the information to be provided. The providing unit also supports multiple devices and platforms, allowing the user to access information anywhere. For example, a consistent user experience is provided on various devices, such as a desktop PC, a smartphone, and a tablet. This allows the providing unit to provide information to the user quickly and accurately, thereby improving the user's convenience.

[0082] The natural language processing development AI assistant includes a control unit that integrates and manages each of the analysis unit, extraction unit, translation unit, information search unit, and provision unit. The control unit integrates and manages each of the analysis unit, extraction unit, translation unit, information search unit, and provision unit. For example, the control unit adjusts the operation of each unit to achieve efficient information processing. For example, the control unit can design a system architecture and manage the data flow of each unit. For example, the control unit can monitor the operation status of each unit and adjust the operation as necessary. In this way, the natural language processing development AI assistant integrates the functions of each unit and efficiently manages them.

[0083] The extraction unit can perform summarization based on specific keywords specified by the user. For example, the extraction unit can prioritize and summarize information related to the keywords specified by the user. This provides a summary tailored to the user's interests. Some or all of the above-mentioned processing in the extraction unit can be performed using, for example, AI, or can be performed without using AI. For example, the extraction unit can input keywords specified by the user to a generation AI and cause the generation AI to perform a summary based on the keywords.

[0084] The translation unit can perform translation taking into account slang and dialects specific to the region, including the user's location. For example, the translation unit can refer to a region database to appropriately translate expressions specific to the region. This provides a natural translation that takes into account slang and dialects specific to the region. Some or all of the above-mentioned processing in the translation unit can be performed using, for example, AI, or can be performed without using AI. For example, the translation unit can input the region database into a generation AI and have the generation AI translate expressions specific to the region.

[0085] The extraction unit can apply different summarization algorithms to text data of different genres. For example, the extraction unit can apply a simple summarization algorithm to news articles and a detailed summarization algorithm to academic papers. This provides an optimal summary according to the genre. Some or all of the above-mentioned processing in the extraction unit can be performed, for example, using AI or without AI. For example, the extraction unit can input the genre of the text data to the generation AI and apply a summarization algorithm according to the genre to the generation AI.

[0086] The extraction unit can improve the accuracy of the summary based on the analysis result of the analysis unit. For example, the extraction unit can perform summarization based on important topics and emotions identified by the analysis unit. This provides a highly accurate summary based on the analysis result. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the analysis result of the analysis unit to the generation AI and cause the generation AI to execute a highly accurate summary.

[0087] The information search unit can improve the accuracy of the search results based on the analysis results of the analysis unit. For example, the information search unit can rank the search results based on important topics and emotions identified by the analysis unit. This provides highly accurate search results based on the analysis results. Some or all of the above-mentioned processing in the information search unit may be performed using, for example, AI, or may be performed without using AI. For example, the information search unit can input the analysis results of the analysis unit to a generation AI and cause the generation AI to execute highly accurate search results.

[0088] The extraction unit summarizes the text data acquired by the information search unit, and the provision unit can provide the main points extracted by the extraction unit to the user. The extraction unit, for example, summarizes the text data acquired by the information search unit and extracts the main points. For example, the extraction unit can pick up important information from the search results and perform a summary. The provision unit, for example, provides the main points extracted by the extraction unit to the user. For example, the provision unit can display the summarized information to the user. This provides a summary of the searched text data. A part or all of the above-mentioned processing in the extraction unit and the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the extraction unit can input the text data acquired by the information search unit to the generation AI and cause the generation AI to execute the summary. The provision unit can provide the user with the summary generated by the generation AI.

[0089] The providing unit can provide information according to the user's emotion based on the emotion analysis result of the text data analyzed by the analyzing unit. For example, the providing unit can provide appropriate information to the user based on the emotion score. This allows information to be provided according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generating AI. The generating AI is a text generating AI (for example, LLM) or a multimodal generating AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the emotion analysis result of the analyzing unit to the generating AI and cause the generating AI to provide information according to the user's emotion.

[0090] The providing unit can provide information on a specific topic preferentially based on the result of topic modeling by the analyzing unit. For example, the providing unit can provide information related to the user preferentially based on the result of the topic model. This allows information on a specific topic to be provided preferentially. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the topic modeling result of the analyzing unit to a generating AI and cause the generating AI to provide information on a specific topic.

[0091] The analysis unit can estimate the user's emotion and adjust the priority of the analysis based on the estimated user's emotion. For example, when the user is feeling stressed, the analysis unit can prioritize emotion analysis and identify the cause of stress. Also, when the user is relaxed, the analysis unit can prioritize topic modeling and identify topics of interest. This adjusts the priority of the analysis according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to execute the priority of the analysis based on the emotion.

[0092] The analysis unit can improve the accuracy of the analysis result by taking into account the context of the text data. For example, the analysis unit can analyze the context of the text data and improve the accuracy of the sentiment analysis based on the context. The analysis unit can also refine the topic modeling result by taking into account the context of the text data. This provides a highly accurate analysis result that takes the context into account. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input context information of the text data to the generation AI and cause the generation AI to perform analysis based on the context.

[0093] The analysis unit can evaluate the reliability of the analysis by referring to the source information of the text data. For example, if the source of the text data is reliable, the analysis unit can evaluate the reliability of the analysis result as high. Also, if the source of the text data is unclear, the analysis unit can evaluate the reliability of the analysis result as low. This provides a reliable analysis result based on the source information. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the source information of the text data to the generation AI and cause the generation AI to perform the evaluation of reliability.

[0094] The analysis unit can estimate the user's emotion and adjust the display method of the analysis result based on the estimated user's emotion. For example, when the user is nervous, the analysis unit can provide a simple and highly visible display method. Also, when the user is relaxed, the analysis unit can provide a display method including detailed information. This provides a display method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display method based on the emotion.

[0095] The analysis unit can dynamically change the analysis algorithm according to the length of the text data. For example, the analysis unit can apply an algorithm that performs rapid analysis in the case of short text data. Also, the analysis unit can apply an algorithm that performs detailed analysis in the case of long text data. This provides an optimal analysis according to the length of the text data. 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 the length of the text data to the generation AI and cause the generation AI to select an analysis algorithm according to the length.

[0096] The analysis unit can optimize the analysis method according to the format of the text data. For example, in the case of text data in PDF format, the analysis unit can optimize the text extraction algorithm. In addition, in the case of text data in HTML format, the analysis unit can perform analysis taking into account tag information. This provides an optimal analysis according to the format of the text data. A part 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 format information of the text data to the generation AI and cause the generation AI to optimize the analysis method according to the format.

[0097] The extraction unit can estimate the user's emotion and adjust the level of detail of the summary based on the estimated user's emotion. For example, the extraction unit can provide a detailed summary when the user is relaxed. Also, the extraction unit can provide a concise summary when the user is in a hurry. This provides a detailed summary according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the extraction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the extraction unit can input the user's emotion data to the generation AI and cause the generation AI to execute the level of detail of the summary based on the emotion.

[0098] The extraction unit can determine the priority of summaries based on the importance of the text data. For example, the extraction unit can prioritize important text data for summarization. Also, the extraction unit can postpone summarization of text data with low importance. This provides a priority of summaries based on importance. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the importance of the text data to the generation AI and cause the generation AI to execute the priority of summaries based on importance.

[0099] The extraction unit can apply different summarization algorithms depending on the genre of the text data. For example, the extraction unit can apply a detailed summarization algorithm for academic papers. Also, the extraction unit can apply a concise summarization algorithm for news articles. This provides an optimal summary depending on the genre. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the genre of the text data to the generation AI and cause the generation AI to execute a summarization algorithm depending on the genre.

[0100] The extraction unit can estimate the user's emotion and adjust the expression method of the summary based on the estimated user's emotion. For example, the extraction unit can provide a simple and highly visible summary when the user is nervous. Also, the extraction unit can provide a summary including detailed information when the user is relaxed. This provides a summary expression method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the extraction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the extraction unit can input the user's emotion data to the generation AI and cause the generation AI to execute the emotion-based summary expression method.

[0101] The extraction unit can determine the priority of summaries based on the submission time of the text data. For example, the extraction unit can prioritize summarizing the latest text data. Also, the extraction unit can postpone summarizing older text data. This provides a priority of summaries based on the submission time. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI or may be performed without using AI. For example, the extraction unit can input the submission time of the text data to the generation AI and cause the generation AI to perform the priority of summaries based on the submission time.

[0102] The extraction unit can adjust the order of summaries based on the relevance of the text data. For example, the extraction unit can prioritize summarizing highly relevant text data. Also, the extraction unit can postpone summarizing less relevant text data. This provides an order of summaries based on the relevance. A part or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI or may be performed without using AI. For example, the extraction unit can input the relevance of the text data to the generation AI and cause the generation AI to execute the order of summaries based on the relevance.

[0103] The translation unit can estimate the user's emotion and adjust the translation expression method based on the estimated user's emotion. For example, the translation unit can provide a natural and fluent translation when the user is relaxed. Also, the translation unit can provide a concise and to the point translation when the user is in a hurry. This provides a translation expression method according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the translation unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the translation unit can input the user's emotion data to the generation AI and cause the generation AI to execute the emotion-based translation expression method.

[0104] During translation, the translation unit can improve the accuracy of the translation by taking into account the cultural background of the text data. For example, the translation unit can select an appropriate expression by taking into account the cultural background of the text data. The translation unit can also adjust the nuance of the translation based on the cultural background. This provides a highly accurate translation that takes the cultural background into account. 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 cultural background information of the text data to the generation AI and cause the generation AI to perform a translation based on the cultural background.

[0105] The translation unit can refer to a dictionary for appropriately translating technical terms in text data during translation. For example, the translation unit can provide an appropriate translation by referring to a technical term dictionary. The translation unit can also dynamically update the dictionary to improve the translation accuracy of technical terms. This provides an appropriate translation of technical terms. Some or all of the above-mentioned processing in the translation unit can be performed, for example, using AI or can be performed without using AI. For example, the translation unit can input a technical term dictionary to a generation AI and cause the generation AI to translate technical terms.

[0106] The translation unit can estimate the user's emotion and determine the priority of translation based on the estimated user's emotion. For example, the translation unit can perform a quick translation when the user is in a hurry. Also, the translation unit can provide a detailed translation when the user is relaxed. This provides a translation priority according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the translation unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the translation unit can input the user's emotion data to the generation AI and cause the generation AI to execute the translation priority based on the emotion.

[0107] The translation unit can optimize the translation method according to the format of the text data during translation. For example, the translation unit can apply a translation method that emphasizes technical terms in the case of technical documents. Also, the translation unit can apply a translation method that emphasizes style and nuance in the case of literary works. This provides an optimal translation method according to the format. 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 format information of the text data to the generation AI and cause the generation AI to optimize the translation method according to the format.

[0108] The translation unit can translate the text data while taking into consideration slang and dialects specific to the region. For example, the translation unit can appropriately translate expressions specific to the region by referring to a region database. This provides a natural translation that takes into consideration slang and dialects specific to the region. Some or all of the above-mentioned processing in the translation unit can be performed using, for example, AI, or can be performed without using AI. For example, the translation unit can input data on slang and dialects specific to the region to a generation AI and have the generation AI translate the expressions specific to the region.

[0109] The information search unit can estimate the user's emotion and adjust the display method of the search results based on the estimated user's emotion. For example, when the user is nervous, the information search unit can provide a simple and highly visible display method. Also, when the user is relaxed, the information search unit can provide a display method including detailed information. This provides a display method of the search results according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the information search unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the information search unit can input the user's emotion data to the generation AI and cause the generation AI to execute a display method of the search results based on the emotion.

[0110] The information search unit can evaluate the reliability of text data during a search to improve the accuracy of search results. For example, the information search unit can display highly reliable text data preferentially in the search results. The information search unit can also postpone less reliable text data. This provides highly accurate search results based on reliability. Some or all of the above-mentioned processing in the information search unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the information search unit can input the reliability of the text data to the generation AI and cause the generation AI to improve the accuracy of the search results based on reliability.

[0111] During a search, the information search unit can evaluate the relevance of the text data and determine the priority of search results. For example, the information search unit can give priority to highly relevant text data and display it in the search results. The information search unit can also postpone text data with low relevance. This provides a priority order of search results based on relevance. Some or all of the above-mentioned processing in the information search unit may be performed, for example, using AI or may be performed without using AI. For example, the information search unit can input the relevance of the text data to the generation AI and cause the generation AI to execute the priority order of search results based on relevance.

[0112] The information search unit can estimate the user's emotion and determine the priority of search results based on the estimated user's emotion. For example, the information search unit can quickly display search results when the user is in a hurry. Also, the information search unit can provide detailed search results when the user is relaxed. This provides the priority of search results according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the information search unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the information search unit can input the user's emotion data to the generation AI and cause the generation AI to execute the priority of search results based on the emotion.

[0113] The information search unit can optimize the search method according to the format of the text data during the search. For example, in the case of a news article, the information search unit can prioritize searching the latest information. Also, in the case of an academic paper, the information search unit can prioritize searching for highly reliable information. This provides an optimal search method according to the format. Some or all of the above-mentioned processing in the information search unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the information search unit can input format information of the text data to the generation AI and cause the generation AI to optimize the search method according to the format.

[0114] During a search, the information search unit can determine the priority of search results based on the submission time of the text data. For example, the information search unit can give priority to the latest text data and display it in the search results. The information search unit can also postpone old text data. This provides a priority order of search results based on the submission time. Some or all of the above-mentioned processing in the information search unit may be performed, for example, using AI or may be performed without using AI. For example, the information search unit can input the submission time of the text data to the generation AI and cause the generation AI to execute the priority order of search results based on the submission time.

[0115] The providing unit can estimate the user's emotion and adjust the expression method of information provision based on the estimated user's emotion. For example, when the user is nervous, the providing unit can provide simple and highly visible information. Also, when the user is relaxed, the providing unit can perform a method of providing information including detailed information. This provides an expression method of information provision according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotion data to the generation AI and cause the generation AI to execute an expression method of information provision based on emotion.

[0116] The providing unit can provide optimal information by referring to the user's past search history when providing information. For example, the providing unit can provide related information based on information previously searched by the user. The providing unit can also provide topics of interest to the user from the user's past search history with priority. This provides optimal information based on the past search history. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's past search history to the generating AI and cause the generating AI to provide optimal information.

[0117] The providing unit can determine the priority of information based on the user's current field of interest when providing information. For example, the providing unit can provide information by prioritizing topics in which the user is currently interested. The providing unit can also provide related information based on the user's field of interest. This provides the priority of information based on the current field of interest. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or may be performed without using AI. For example, the providing unit can input the user's current field of interest to the generating AI and cause the generating AI to execute the priority of information provision based on the field of interest.

[0118] The providing unit can estimate the user's emotion and determine the priority of information provision based on the estimated user's emotion. For example, the providing unit can provide information quickly when the user is in a hurry. Also, the providing unit can provide detailed information when the user is relaxed. This provides the priority of information provision according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotion data to the generation AI and cause the generation AI to execute the priority of information provision based on the emotion.

[0119] The providing unit can select the optimal display method in consideration of the user's device information when providing information. For example, when the user is using a smartphone, the providing unit can provide a display method that matches the screen size. Also, when the user is using a tablet, the providing unit can provide a display method optimized for a large screen. This provides the optimal display method based on the device information. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's device information to the generating AI and cause the generating AI to select a display method based on the device information.

[0120] The providing unit can provide highly relevant information in consideration of the geographical location information of the user when providing information. For example, the providing unit can provide relevant information based on the user's current location. Furthermore, the providing unit can provide optimal information in consideration of the geographical location information of the user. This provides highly relevant information based on the geographical location information. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the geographical location information of the user to the generating AI and cause the generating AI to provide information based on the geographical location information.

[0121] The control unit can estimate the user's emotion and adjust the operation of each part based on the estimated user's emotion. For example, when the user is nervous, the control unit can adjust the operation of each part to be simple. Also, when the user is relaxed, the control unit can adjust to perform detailed operations. This adjusts the operation of each part according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the control unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the control unit can input the user's emotion data to the generation AI and cause the generation AI to execute the operation adjustment of each part based on the emotion.

[0122] The control unit can select an optimal control method by referring to the operation history of each unit. For example, the control unit can analyze the past operation history of each unit and select an optimal control method. The control unit can also improve the efficiency of the operation based on the operation history of each unit. This provides an optimal control method based on the operation history. A part or all of the above-mentioned processing in the control unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the control unit can input the operation history of each unit to the generation AI and cause the generation AI to select an optimal control method.

[0123] The control unit can monitor the operation status of each unit in real time and automatically correct it when an abnormality occurs. For example, the control unit can monitor the operation status of each unit in real time and automatically correct it when an abnormality is detected. The control unit can also monitor the operation status of each unit and issue an alert when an abnormality occurs. This improves the stability of the system through real-time monitoring and automatic correction. Some or all of the above-mentioned processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit can input the operation status of each unit to the generation AI and cause the generation AI to detect and correct an abnormality.

[0124] The control unit can estimate the user's emotion and determine the operation priority of each unit based on the estimated user's emotion. For example, the control unit can prioritize quick actions when the user is in a hurry. Also, the control unit can prioritize detailed actions when the user is relaxed. This provides an operation priority according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the control unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the control unit can input the user's emotion data to the generation AI and cause the generation AI to execute an operation priority based on the emotion.

[0125] The control unit can periodically evaluate the operation status of each unit and update the optimal control method. For example, the control unit can periodically evaluate the operation status of each unit and update the optimal control method. The control unit can also evaluate the operation status of each unit and improve the efficiency of the operation. This improves the efficiency and accuracy of the system through periodic evaluation and updating. A part or all of the above-mentioned processing in the control unit may be performed, for example, using AI, or may be performed without using AI. For example, the control unit can input the operation status of each unit to the generation AI and cause the generation AI to execute the update of the optimal control method.

[0126] The control unit can analyze the operation history of each unit and predict future operations. For example, the control unit can analyze the operation history of each unit and predict future operations. The control unit can also improve the efficiency of operations based on the operation history of each unit. This provides future operation prediction based on the operation history. Some or all of the above-mentioned processing in the control unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the control unit can input the operation history of each unit to a generation AI and cause the generation AI to execute future operation prediction.

[0127] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0128] The analysis unit can evaluate the reliability of text data and prioritize analysis of reliable data. For example, the analysis unit can evaluate the source of a news article and prioritize analysis of data from a reliable source. The analysis unit can also evaluate the reliability of social media posts and filter out less reliable posts. Furthermore, the analysis unit can evaluate the number of citations of academic papers and prioritize analysis of papers with many citations. This provides analysis results based on reliable data.

[0129] The extraction unit can improve the accuracy of the summary by referring to the user's past search history. For example, the extraction unit can prioritize and summarize related information based on keywords searched for by the user in the past. The extraction unit can also identify topics of interest from the user's past search history and prioritize and summarize information related to the topics. Furthermore, the extraction unit can analyze the user's past search history and optimize the summarization algorithm. This provides a highly accurate summary based on the user's past search history.

[0130] The translation unit can improve the accuracy of the translation by taking into account the cultural background of the text data. For example, the translation unit can select an appropriate expression by taking into account the cultural background of the text data. The translation unit can also adjust the nuance of the translation based on the cultural background. Furthermore, the translation unit can appropriately translate region-specific expressions by referring to a database related to the cultural background. This provides a highly accurate translation that takes the cultural background into account.

[0131] The information search unit can determine the priority of search results based on the user's current field of interest. For example, the information search unit can prioritize topics in which the user is currently interested in the search results. The information search unit can also prioritize searching for related information based on the user's field of interest. Furthermore, the information search unit can refer to the user's past search history to identify the user's current field of interest and prioritize searching for information related to that field. This provides a priority of search results based on the user's current field of interest.

[0132] The providing unit can select the optimal display method in consideration of the device information of the user. For example, when the user is using a smartphone, the providing unit can provide a display method that matches the screen size. Also, when the user is using a tablet, the providing unit can provide a display method optimized for a large screen. Furthermore, the providing unit can select a font size and layout that are optimal for the device by referring to the device information of the user. In this way, the optimal display method based on the device information is provided.

[0133] The analysis unit can estimate the user's emotion and adjust the priority of the analysis based on the estimated user's emotion. For example, when the user is feeling stressed, the analysis unit can prioritize execution of emotion analysis to identify the cause of the stress. Also, when the user is relaxed, the analysis unit can prioritize execution of topic modeling to identify topics of interest. Furthermore, the analysis unit can adjust the level of detail of the analysis based on the user's emotion. This adjusts the priority of the analysis according to the user's emotion.

[0134] The extraction unit can estimate the user's emotion and adjust the level of detail of the summary based on the estimated user's emotion. For example, the extraction unit can provide a detailed summary when the user is relaxed. Also, the extraction unit can provide a concise summary when the user is in a hurry. Furthermore, the extraction unit can adjust the manner of expression of the summary based on the user's emotion. In this way, a detailed summary according to the user's emotion is provided.

[0135] The translation unit can estimate the user's emotion and adjust the translation expression method based on the estimated user's emotion. For example, the translation unit can provide a natural and fluent translation when the user is relaxed. Also, the translation unit can provide a concise and to the point translation when the user is in a hurry. Furthermore, the translation unit can adjust the nuance of the translation based on the user's emotion. This provides a translation expression method according to the user's emotion.

[0136] The information search unit can estimate the user's emotion and adjust the display method of the search results based on the estimated user's emotion. For example, when the user is nervous, the information search unit can provide a display method that is simple and highly visible. When the user is relaxed, the information search unit can provide a display method that includes detailed information. Furthermore, the information search unit can adjust the layout of the search results based on the user's emotion. This provides a display method of the search results according to the user's emotion.

[0137] The providing unit can estimate the user's emotion and adjust the method of expressing information provision based on the estimated user's emotion. For example, when the user is nervous, the providing unit can provide information that is simple and highly visible. When the user is relaxed, the providing unit can provide information that includes detailed information. Furthermore, the providing unit can adjust the priority of information provision based on the user's emotion. This provides a method of expressing information provision according to the user's emotion.

[0138] The process flow of the second embodiment will be briefly described below.

[0139] Step 1: The analyzer extracts information from text data and performs topic modeling and sentiment analysis. For example, the analyzer analyzes text data such as news articles and social media posts to identify key topics and sentiment. The analyzer extracts topics using topic modeling techniques such as LDA (Latent Dirichlet Allocation) and NMF (Non-negative Matrix Factorization), and analyzes sentiment using dictionary-based and machine learning-based techniques. Step 2: The extraction unit summarizes the text data and extracts the main points. For example, it can summarize based on the length of the text or the importance of the information being summarized, and it can also summarize concisely using a text generation AI (e.g., LLM). It can also summarize based on specific keywords specified by the user. Step 3: The translation unit translates the text data between multiple languages. For example, translations can be made between various languages, such as English to Japanese, Japanese to French, etc. The translation unit uses Neural Machine Translation (NMT) technology to provide natural and accurate translations, and can also take into account regional slang and dialects. Step 4: The information search unit searches and retrieves text data according to the user's input. For example, if the user enters "Tell me about the latest technology trends," the unit searches for related text data and provides the most appropriate information. It uses a search algorithm to evaluate the relevance of the text data and ranks the search results. Step 5: The providing unit provides information according to the user's input. For example, the providing unit displays search results to the user. The information can be provided through a web application or a mobile application.

[0140] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0141] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0142] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0143] For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the extraction unit is realized by the control unit 46A of the smart device 14. For example, the translation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the information search unit is realized by the control unit 46A of the smart device 14. For example, the provision unit is realized by the specific processing unit 290 of the data processing device 12. For example, the control unit is realized by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0144] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0145] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0146] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0147] 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.

[0148] 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 the voice according to instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0150] 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 performed in a secure state.

[0151] Fig. 4 shows an example of 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.

[0152] 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.

[0153] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0154] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0155] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0156] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0157] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0158] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0159] For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the extraction unit is realized by the control unit 46A of the smart glasses 214. For example, the translation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the information search unit is realized by the control unit 46A of the smart glasses 214. For example, the provision unit is realized by the specific processing unit 290 of the data processing device 12. For example, the control unit is realized by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0160] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0161] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0162] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0163] 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.

[0164] 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 the voice according to instructions from the processor 46.

[0165] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0166] 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 performed in a secure state.

[0167] 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.

[0168] 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.

[0169] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0170] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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.

[0171] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0172] 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 voice indicating a user input for 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.

[0173] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0174] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0175] For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the extraction unit is realized by the control unit 46A of the headset type terminal 314. For example, the translation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the information search unit is realized by the control unit 46A of the headset type terminal 314. For example, the provision unit is realized by the specific processing unit 290 of the data processing device 12. For example, the control unit is realized by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0176] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0177] 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.

[0178] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0179] 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.

[0180] 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 the voice according to instructions from the processor 46.

[0181] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0182] 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 performed in a secure state.

[0183] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0184] 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.

[0185] 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.

[0186] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0187] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0188] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0189] 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 a voice indicating a user input for 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.

[0190] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0191] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0192] For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the extraction unit is realized by the control unit 46A of the robot 414. For example, the translation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the information search unit is realized by the control unit 46A of the robot 414. For example, the provision unit is realized by the specific processing unit 290 of the data processing device 12. For example, the control unit is realized by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0193] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0194] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0195] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0196] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0197] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0198] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0199] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0200] 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.

[0201] 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 Universal Serial Bus (USB) 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.

[0202] In addition, 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 upon request from the data processing device 12.

[0203] 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.

[0204] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0205] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0206] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0207] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0208] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0209] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0210] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0211] (Appendix 1) an analyzer that extracts information from the text data and performs topic modeling and sentiment analysis; an extraction unit that summarizes the information extracted by the analysis unit and extracts key points; a translation unit that translates the text data extracted by the extraction unit between a plurality of languages; an information retrieval unit that retrieves the text data translated by the translation unit in response to a user's input; a providing unit that provides the information acquired by the information search unit. A system characterized by: (Appendix 2) A control unit that integrally manages the analysis unit, the extraction unit, the translation unit, the information search unit, and the provision unit. 2. The system of claim 1, (Appendix 3) The extraction unit is Summarize based on specific keywords specified by the user 2. The system of claim 1, (Appendix 4) The translation unit is Translations take into account regional slang and dialects, including the user's location 2. The system of claim 1, (Appendix 5) The extraction unit is Applying different summarization algorithms to text data of different genres 2. The system of claim 1, (Appendix 6) The extraction unit is Improve the accuracy of summaries based on the analysis results of the analysis part 2. The system of claim 1, (Appendix 7) The information search unit is Improve the accuracy of search results based on the analysis results of the analysis section 2. The system of claim 1, (Appendix 8) The extraction unit is Summarizing the text data retrieved by the information retrieval unit and extracting key points; The providing unit is Providing the main points extracted by the extracting unit to a user 2. The system of claim 1, (Appendix 9) The providing unit is Based on the emotion analysis results of the text data analyzed by the analysis unit, information is provided according to the user's emotions. 2. The system of claim 1, (Appendix 10) The providing unit is Based on the results of topic modeling by the analysis section, information on specific topics is provided preferentially. 2. The system of claim 1, (Appendix 11) The analysis unit is Infer user sentiment and adjust analysis priorities based on the inferred user sentiment 2. The system of claim 1, (Appendix 12) The analysis unit is Improve the accuracy of analysis results by considering the context of text data 2. The system of claim 1, (Appendix 13) The analysis unit is Evaluate the reliability of the analysis by referring to the source information of the text data 2. The system of claim 1, (Appendix 14) The analysis unit is Infer user emotions and adjust the way analysis results are displayed based on the inferred user emotions 2. The system of claim 1, (Appendix 15) The analysis unit is Dynamically change the parsing algorithm depending on the length of the text data 2. The system of claim 1, (Appendix 16) The analysis unit is Optimize analysis methods according to the format of text data 2. The system of claim 1, (Appendix 17) The extraction unit is Estimating user emotions and adjusting the level of detail of summaries based on the estimated user emotions 2. The system of claim 1, (Appendix 18) The extraction unit is Prioritize summaries based on the importance of text data 2. The system of claim 1, (Appendix 19) The extraction unit is Apply different summarization algorithms depending on the genre of text data 2. The system of claim 1, (Appendix 20) The extraction unit is Estimate the user's emotions and adjust the way summaries are presented based on the estimated user emotions. 2. The system of claim 1, (Appendix 21) The extraction unit is Prioritize summaries based on when text data was submitted 2. The system of claim 1, (Appendix 22) The extraction unit is Adjusting the order of summaries based on the relevance of text data 2. The system of claim 1, (Appendix 23) The translation unit is Estimate the user's emotions and adjust the translation expression based on the estimated user emotions. 2. The system of claim 1, (Appendix 24) The translation unit is Improve translation accuracy by taking into account the cultural background of text data during translation. 2. The system of claim 1, (Appendix 25) The translation unit is When translating, refer to dictionaries to properly translate technical terms in text data 2. The system of claim 1, (Appendix 26) The translation unit is Estimate user sentiment and prioritize translations based on the estimated user sentiment 2. The system of claim 1, (Appendix 27) The translation unit is Optimize the translation method according to the format of the text data during translation. 2. The system of claim 1, (Appendix 28) The translation unit is When translating, the text data is translated taking into account slang and dialects specific to the region. 2. The system of claim 1, (Appendix 29) The information search unit is Infer user sentiment and adjust how search results are displayed based on the inferred user sentiment 2. The system of claim 1, (Appendix 30) The information search unit is When searching, the reliability of text data is evaluated to improve the accuracy of search results 2. The system of claim 1, (Appendix 31) The information search unit is At search time, we evaluate the relevance of text data to prioritize search results 2. The system of claim 1, (Appendix 32) The information search unit is Infer user sentiment and prioritize search results based on the inferred user sentiment 2. The system of claim 1, (Appendix 33) The information search unit is Optimize search methods according to the format of text data when searching 2. The system of claim 1, (Appendix 34) The information search unit is When searching, search results are prioritized based on when text data was submitted 2. The system of claim 1, (Appendix 35) The providing unit is Estimate the user's emotions and adjust the way information is presented based on the estimated user's emotions. 2. The system of claim 1, (Appendix 36) The providing unit is When providing information, provide the most appropriate information by referring to the user's past search history 2. The system of claim 1, (Appendix 37) The providing unit is Prioritize information as it is presented based on the user's current areas of interest 2. The system of claim 1, (Appendix 38) The providing unit is Estimate the user's emotions and determine the priority of information provision based on the estimated user's emotions. 2. The system of claim 1, (Appendix 39) The providing unit is When providing information, the optimal display method is selected taking into account the user's device information. 2. The system of claim 1, (Appendix 40) The providing unit is When providing information, the service takes into account the user's geographic location to provide more relevant information. 2. The system of claim 1, (Appendix 41) The control unit is Estimate the user's emotions and adjust the operation of each part based on the estimated user's emotions 3. The system of claim 2, (Appendix 42) The control unit is Refer to the operation history of each part to select the optimal control method 3. The system of claim 2, (Appendix 43) The control unit is Monitors the operating status of each part in real time and automatically corrects any abnormalities that occur 3. The system of claim 2, (Appendix 44) The control unit is Estimate the user's emotions and determine the operation priority of each part based on the estimated user's emotions. 3. The system of claim 2, (Appendix 45) The control unit is Periodically evaluate the operating status of each part and update the optimal control method 3. The system of claim 2, (Appendix 46) The control unit is Analyze the operation history of each part and predict future operation 3. The system of claim 2, [Explanation of symbols]

[0212] 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. an analyzer that extracts information from the text data and performs topic modeling and sentiment analysis; an extraction unit that summarizes the information extracted by the analysis unit and extracts key points; a translation unit that translates the text data extracted by the extraction unit between a plurality of languages; an information retrieval unit that retrieves the text data translated by the translation unit in response to a user's input; a providing unit that provides the information acquired by the information search unit. A system characterized by:

2. A control unit that integrally manages the analysis unit, the extraction unit, the translation unit, the information search unit, and the provision unit.

2. The system of claim 1 .

3. The extraction unit is Summarize based on specific keywords specified by the user 2. The system of claim 1 .

4. The translation unit is Translations take into account regional slang and dialects, including the user's location 2. The system of claim 1 .

5. The extraction unit is Applying different summarization algorithms to text data of different genres 2. The system of claim 1 .

6. The extraction unit is The accuracy of the summary is improved based on the analysis result of the analysis unit.

2. The system of claim 1 .

7. The information search unit is Improve the accuracy of the search results based on the analysis results of the analysis unit 2. The system of claim 1 .

8. The extraction unit is Summarizing the text data acquired by the information retrieval unit and extracting key points; The providing unit is Providing the main points extracted by the extracting unit to a user 2. The system of claim 1 .

9. The providing unit is Based on the emotion analysis result of the text data analyzed by the analysis unit, information is provided according to the emotion of the user.

2. The system of claim 1 .

10. The providing unit is Based on the results of topic modeling by the analysis unit, information on a specific topic is preferentially provided.

2. The system of claim 1 .

Images