System

Abstract

To provide a system that specifies a bias or false information in a news article to allow a reader to calmly determine information.SOLUTION: A system according to an embodiment comprises a receiving unit, a detection unit, an evaluation unit, an analysis unit, and a visualization unit. The receiving unit inputs a text of a news article. The detection unit analyzes the text input by the receiving unit and detects a bias language. The evaluation unit evaluates the reliability of a source on the basis of the bias language detected by the detection unit. The analysis unit performs emotion analysis on the basis of a result of the evaluation performed by the evaluation unit. The visualization unit visualizes a result of the emotion analysis performed by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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 technology has the disadvantage that it is difficult to efficiently identify bias and misinformation in news articles and enable readers to make rational judgments about the information.

[0005] The system of the embodiment aims to identify bias and misinformation in news articles and enable readers to calmly judge the information. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a detection unit, an evaluation unit, an analysis unit, and a visualization unit. The reception unit inputs text of a news article. The detection unit analyzes the text input by the reception unit and detects biased language. The evaluation unit evaluates the reliability of a source based on the biased language detected by the detection unit. The analysis unit performs sentiment analysis based on the result of the evaluation by the evaluation unit. The visualization unit visualizes the result of the analysis by the analysis unit. Effect of the Invention

[0007] The system according to the embodiment can identify bias and misinformation in news articles, allowing readers to make rational judgments about the information. [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 news article analysis system according to an embodiment of the present invention is a system that analyzes news articles using AI tools to identify bias and misinformation. In this news article analysis system, the text of a news article is input to an AI, and the AI ​​performs text analysis to identify bias and misinformation in the article using functions such as detection of biased language, source verification, sentiment analysis, and data visualization. Based on this result, an index for evaluating the reliability of information is provided to readers. This can promote media literacy and promote accurate news / media. For example, the text of a news article is input to an AI. For example, an article is copied from an online news site and input into the AI. At this time, detailed data such as the title, text, and author information of the article are input. Next, the AI ​​analyzes the input text. The AI ​​uses natural language processing technology to understand the content of the article and detect biased language. For example, it can detect words that indicate a specific political position and emotional expressions. Furthermore, the AI ​​verifies the source. It evaluates whether the source of the article and the cited information source are reliable. For example, it checks whether the cited statistical data is official and whether the source is a reliable institution. Next, the AI ​​performs sentiment analysis. It evaluates what emotions the content of the article evokes. For example, it determines whether the article contains content that is likely to cause fear or anger in the reader. Finally, AI visualizes the data. It visually displays the results of identifying bias and misinformation in the article in graphs and charts. This allows readers to intuitively understand the reliability of the information. This mechanism allows readers to calmly judge the bias and misinformation in news articles. For example, it can identify articles that have a specific political stance or articles that contain a lot of emotional expressions and evaluate the reliability of the information. This improves media literacy and promotes accurate news / media. This allows the news article analysis system to help readers calmly judge bias and misinformation in news articles.

[0029] The news article analysis system according to the embodiment includes a reception unit, a detection unit, an evaluation unit, an analysis unit, and a visualization unit. The reception unit inputs the text of a news article. The text of the news article includes, for example, the title, text, and author information of the article copied from an online news site, but is not limited to such an example. The reception unit, for example, copies the news article and inputs it to the AI. The reception unit can also automatically collect the text of the news article. For example, the reception unit has a function of periodically collecting articles from a specific news site. The detection unit analyzes the text input by the reception unit and detects biased language. The biased language includes, for example, words indicating a specific political position and emotional expressions, but is not limited to such an example. The detection unit understands the content of the article and detects biased language, for example, using natural language processing technology. For example, it can detect words indicating a specific political position and emotional expressions. The evaluation unit evaluates the reliability of the source based on the biased language detected by the detection unit. The reliability of the source includes, for example, whether the cited statistical data is official and whether the source is a reliable institution, but is not limited to such an example. The evaluation unit, for example, evaluates whether the cited information source is reliable. For example, it checks whether the cited statistical data is official and whether the source is a reliable institution. The analysis unit performs sentiment analysis based on the results evaluated by the evaluation unit. Sentiment analysis includes, for example, what emotions the content of the article causes, but is not limited to such examples. The analysis unit determines, for example, whether the content of the article causes fear or anger in the reader. For example, it evaluates whether the content of the article causes fear or anger in the reader. The visualization unit visualizes the results analyzed by the analysis unit. Visualization includes, for example, visually displaying the results of identifying bias and misinformation in the article in a graph or chart, but is not limited to such examples. The visualization unit, for example, visually displays the results of identifying bias and misinformation in the article in a graph or chart. For example, it visually displays the results of identifying bias and misinformation in the article in a graph or chart.As a result, the news article analysis system can assist readers in calmly judging bias and misinformation in news articles. Some or all of the above-mentioned processes in the reception unit, detection unit, evaluation unit, analysis unit, and visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can automatically collect the text of the news article using AI when inputting the text of the news article. The detection unit can detect bias language using AI when analyzing the text of the news article. The evaluation unit can evaluate the reliability of the source using AI when evaluating the reliability of the source based on the bias language. The analysis unit can evaluate what emotions the content of the article evokes using AI when performing sentiment analysis. The visualization unit can visually display the identified results of bias and misinformation in the article in graphs and charts using AI when visualizing the analysis results.

[0030] The reception unit inputs the text of the news article. The text of the news article includes, for example, the title, text, author information, etc. of the article copied from an online news site, but is not limited to such examples. For example, the reception unit copies the news article and inputs it to the AI. The reception unit can also automatically collect the text of the news article. For example, the reception unit has a function of periodically collecting articles from a specific news site. Specifically, the reception unit can use web scraping technology to periodically collect articles from a specific news site. Web scraping technology is a technology that analyzes the HTML structure of a webpage and extracts necessary information. This allows the reception unit to obtain update information of the news site in real time and automatically collect the latest news articles. The reception unit can also collect news articles using an RSS feed. An RSS feed is a format for distributing update information of a website, and the latest articles can be automatically obtained by subscribing to an RSS feed provided by a news site. Furthermore, the reception unit can also collect news articles using an API. By using the API provided by the news site, articles can be searched and obtained based on specific keywords and categories. This allows the reception unit to collect news articles in a variety of ways and input them into the system.

[0031] The detection unit analyzes the text input by the reception unit and detects biased language. Biased language includes, but is not limited to, words that indicate a particular political position and emotional expressions. The detection unit understands the content of the article and detects biased language, for example, using natural language processing technology. Specifically, the detection unit performs morphological analysis, divides the text into words, and analyzes the part of speech and meaning of each word. Next, a sentiment analysis algorithm is used to evaluate the emotional nuance of each word or phrase and classify it as positive, negative, or neutral. Furthermore, the detection unit checks against a predefined biased language list to detect words or phrases that include a particular political position or emotional expression. For example, an article that includes biased language such as "biased reporting" or "emotional expression" can be identified. Based on these analysis results, the detection unit can score the bias degree of the entire article and quantitatively evaluate the degree of bias.

[0032] The evaluation unit evaluates the reliability of the source based on the bias language detected by the detection unit. The reliability of the source includes, for example, whether the cited statistical data is official and whether the source is a reliable institution, but is not limited to such examples. The evaluation unit evaluates, for example, whether the cited information source is reliable. Specifically, the evaluation unit checks the source of the cited statistical data and evaluates whether the source is a reliable institution such as a government agency or an academic institution. In addition, the evaluation unit refers to the past reliability evaluation of the cited information source and checks whether it has provided false information in the past. Furthermore, the evaluation unit evaluates the expertise and authority of the cited information source and checks whether the information was provided by an expert or authority in the field. In this way, the evaluation unit can comprehensively evaluate the reliability of the news article and distinguish between highly reliable articles and low reliable articles.

[0033] The analysis unit performs sentiment analysis based on the results of the evaluation by the evaluation unit. Sentiment analysis includes, for example, what emotions the content of the article causes, but is not limited to such examples. The analysis unit determines, for example, whether the content of the article causes fear or anger in the reader. Specifically, the analysis unit uses natural language processing technology to analyze the text of the article and identify words and phrases that cause emotional expressions and emotions. Next, using a sentiment analysis algorithm, calculates a sentiment score for the entire article and classifies it as positive, negative, or neutral. Furthermore, the analysis unit can evaluate the impact on the reader based on the sentiment score of the article and identify articles that are likely to cause a specific emotion. For example, if the content of the article causes fear or anger in the reader, the article can be marked as a warning to alert the reader. In this way, the analysis unit can evaluate the emotional impact of the news article and minimize the risk to the reader.

[0034] The visualization unit visualizes the results of the analysis by the analysis unit. Visualization includes, for example, visually displaying the results of identifying bias and misinformation in an article in a graph or chart, but is not limited to such examples. The visualization unit visually displays, for example, the results of identifying bias and misinformation in an article in a graph or chart. Specifically, the visualization unit displays the bias degree and emotion score of an article in a bar graph or pie chart, so that a reader can understand the bias and emotional impact of an article at a glance. In addition, the visualization unit displays the reliability evaluation result of an article in a heat map or scorecard, so that a reliable article can be visually distinguished from a low reliable article. Furthermore, the visualization unit displays the fluctuation of the emotion score of an article in a time series graph, so that an emotional trend in a specific period can be grasped. In this way, the visualization unit can visually display the analysis result of a news article, and can assist a reader in calmly determining the bias and emotional impact of an article.

[0035] The detection unit can detect words or emotional expressions that indicate a particular political position. The detection unit can, for example, detect words that indicate a particular political position. For example, it can detect words related to a particular political party name or policy. The detection unit can also detect emotional expressions. For example, it can detect adjectives and adverbs that indicate strong emotions. This makes it possible to clarify the bias of an article by detecting a particular political position or emotional expression. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using AI, or may be performed without using AI. For example, the detection unit can input the text of a news article into AI, and the AI ​​can detect words or emotional expressions that indicate a particular political position.

[0036] The evaluation unit can evaluate whether the cited source is official or not. The evaluation unit, for example, evaluates whether the cited source is official or not. For example, it can confirm whether the cited statistical data is official or whether the source is a reliable institution. This can improve the reliability of the article by evaluating the reliability of the cited source. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input the text of a news article into an AI, which can evaluate the reliability of the cited source.

[0037] The analysis unit can evaluate whether the content of the article evokes any emotion. The analysis unit, for example, evaluates what emotion the content of the article evokes. For example, it can determine whether the content of the article evokes fear or anger in the reader. This makes it possible to provide information based on the reader's emotions by evaluating the emotional impact of the article. Some 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 text of a news article into AI, which can evaluate what emotion the content of the article evokes.

[0038] The visualization unit can display the results of identifying bias or misinformation in an article in a graph or chart. The visualization unit, for example, visually displays the results of identifying bias or misinformation in an article in a graph or chart. For example, the results of identifying bias or misinformation in an article can be displayed in a bar graph, pie chart, line graph, or the like. This allows the reader to intuitively understand the reliability of the information through visual display. Some or all of the above-mentioned processing in the visualization unit may be performed, for example, using AI, or may be performed without using AI. For example, the visualization unit can input the text of a news article into AI, and the AI ​​can visually display the results of identifying bias or misinformation in an article in a graph or chart.

[0039] The reception unit can acquire and input articles from an online news site. The reception unit, for example, copies and inputs articles from an online news site. For example, articles can be acquired from a specific news portal or blog. This enables efficient data collection by inputting articles directly from online news sites. Some or all of the above-mentioned processing in the reception unit can be performed, for example, using AI or can be performed without using AI. For example, when acquiring articles from an online news site, the reception unit can automatically collect articles using AI.

[0040] The reception unit can analyze the user's past news article browsing history and select an appropriate input method. The reception unit, for example, analyzes the user's past news article browsing history and selects the optimal input method. For example, articles from news sites that the user frequently browsed in the past can be preferentially input. Also, based on the genre of articles that the user liked to read in the past, related articles can be input. Also, by referring to the format of an article that the user browsed for a long time in the past, articles of a similar format can be input. As a result, the optimal input method is selected based on the past browsing history, improving the convenience of the user. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's past news article browsing history to the generation AI, which can select the optimal input method.

[0041] The reception unit can perform filtering based on the user's current field of interest when inputting a news article. The reception unit, for example, performs filtering based on the user's current field of interest when inputting a news article. For example, articles related to topics in which the user is currently interested can be preferentially input. Also, related news articles can be input based on keywords recently searched by the user. Also, articles related to topics that the user follows on social media can be input. In this way, by filtering based on the user's field of interest, highly relevant news articles can be provided. Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's field of interest data to the generation AI, and the generation AI can filter the news articles.

[0042] The reception unit can preferentially input highly relevant articles in consideration of the geographical location information of the user when inputting a news article. For example, the reception unit preferentially inputs highly relevant articles in consideration of the geographical location information of the user when inputting a news article. For example, local news related to the user's current location can be preferentially input. International news related to the user's country or region can also be preferentially input. Articles related to nearby events and occurrences can also be input based on the user's location information. In this way, by taking the geographical location information into consideration, news articles that are highly relevant to the user can be provided. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the geographical location information of the user to the generation AI, and the generation AI can determine the priority order of the news articles.

[0043] The reception unit can analyze the social media activity of the user when a news article is input, and input related articles. The reception unit can, for example, analyze the social media activity of the user when a news article is input, and input related articles. For example, news related to an article shared by the user on social media can be input. Articles can also be input based on the content posted by an account the user follows on social media. News related to a group or community in which the user participates on social media can also be input. In this way, by analyzing social media activity, news articles related to the user can be provided. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the social media activity data of the user to the generation AI, and the generation AI can select a related news article.

[0044] The detection unit can improve the accuracy of detection by taking into account the context of the article when detecting biased language. The detection unit, for example, analyzes the context before and after the article to improve the accuracy of detecting biased language. For example, the detection of biased language can be performed by taking into account the theme of each paragraph of the article. The detection unit can also analyze the tone of the entire article and adjust the detection criteria for biased language. This improves the accuracy of detecting biased language by taking into account the context of the article. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the text of a news article to a generation AI, which can detect biased language by taking into account the context of the article.

[0045] When detecting biased language, the detection unit can perform the detection taking into consideration the attribute information of the author of the article. The detection unit detects biased language, for example, taking into consideration the political stance of the author of the article. For example, biased language can be detected by referring to the past writing history of the author of the article. The detection unit can also detect biased language taking into consideration the specialty field of the author of the article. As a result, the accuracy of detecting biased language is improved by taking into consideration the attribute information of the author. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI, or may be performed without using AI. For example, the detection unit can input the text of a news article to a generation AI, and the generation AI can detect biased language by taking into consideration the attribute information of the author of the article.

[0046] The detection unit can detect biased language taking into consideration the geographical distribution of the article when detecting biased language. The detection unit detects biased language taking into consideration the region from which the article originates, for example. For example, biased language related to the target region of the article can be detected. The detection unit can also detect biased language taking into consideration the geographical background of the article. This improves the accuracy of detecting biased language by taking the geographical distribution into consideration. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the text of a news article to a generation AI, which can detect biased language taking into consideration the geographical distribution of the article.

[0047] The detection unit can improve the accuracy of detection when detecting biased language by referring to related literature of the article. The detection unit detects biased language by, for example, referring to cited literature of the article. For example, biased language can be detected by referring to research papers related to the article. The detection unit can also improve the accuracy of detecting biased language based on the reference literature of the article. As a result, the accuracy of detecting biased language is improved by referring to related literature. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or may be performed without using AI. For example, the detection unit can input the text of a news article to a generation AI, and the generation AI can detect biased language by referring to related literature of the article.

[0048] The evaluation unit can optimize the evaluation algorithm by referring to past evaluation data when evaluating the reliability of a source. The evaluation unit can optimize the evaluation algorithm based on, for example, past reliability evaluation data. For example, the reliability evaluation criteria can be adjusted by referring to past evaluation results. The evaluation unit can also analyze past evaluation data and improve the accuracy of the reliability evaluation. As a result, the accuracy of the reliability evaluation is improved by referring to the past evaluation data. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input past evaluation data to a generation AI, which can optimize the evaluation algorithm.

[0049] The evaluation unit can evaluate the reliability of a source by taking into account the attribute information of the cited information source. The evaluation unit, for example, evaluates the reliability by taking into account the origin of the cited information source. For example, the evaluation can be performed by referring to past reliability evaluations of the cited information source. The evaluation unit can also evaluate the reliability by taking into account the specialty field of the cited information source. This improves the accuracy of the reliability evaluation by taking into account the attribute information of the cited information source. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input the text of a news article into the generation AI, and the generation AI can evaluate the reliability by taking into account the attribute information of the cited information source.

[0050] The evaluation unit can evaluate the reliability of a source by taking into account the geographical distribution of the information source. The evaluation unit evaluates the reliability by taking into account, for example, the region from which the information source originates. For example, the reliability evaluation can be performed in relation to the target region of the information source. The evaluation unit can also evaluate the reliability by taking into account the geographical background of the information source. This improves the accuracy of the reliability evaluation by taking into account the geographical distribution. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input the text of a news article into a generation AI, which can evaluate the reliability by taking into account the geographical distribution of the information source.

[0051] The evaluation unit can improve the accuracy of the evaluation when evaluating the reliability of a source by referring to related literature of the information source. The evaluation unit, for example, evaluates the reliability by referring to cited literature of the information source. For example, the reliability can be evaluated by referring to related research papers of the information source. The evaluation unit can also improve the accuracy of the reliability evaluation based on reference literature of the information source. As a result, the accuracy of the reliability evaluation is improved by referring to related literature. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input the text of a news article to a generation AI, and the generation AI can evaluate the reliability by referring to related literature of the information source.

[0052] The analysis unit can improve the accuracy of the analysis by considering the context of the article during the sentiment analysis. The analysis unit, for example, analyzes the context before and after the article to improve the accuracy of the sentiment analysis. For example, the sentiment analysis can be performed by considering the theme of each paragraph of the article. The analysis unit can also analyze the tone of the entire article and adjust the criteria for the sentiment analysis. This improves the accuracy of the sentiment analysis by considering the context of the article. 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 text of a news article to a generation AI, which can perform sentiment analysis by considering the context of the article.

[0053] The analysis unit can perform sentiment analysis while taking into account the attribute information of the article's author. The analysis unit performs sentiment analysis while taking into account, for example, the political stance of the article's author. For example, sentiment analysis can be performed by referring to the past writing history of the article's author. The analysis unit can also perform sentiment analysis while taking into account the specialty of the article's author. This improves the accuracy of sentiment analysis by taking into account the attribute information of the author. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the text of a news article into a generation AI, which can perform sentiment analysis while taking into account the attribute information of the article's author.

[0054] The analysis unit can perform sentiment analysis while taking into account the geographical distribution of the article. The analysis unit performs sentiment analysis while taking into account, for example, the region from which the article originates. For example, sentiment analysis related to the target region of the article can be performed. The analysis unit can also perform sentiment analysis while taking into account the geographical background of the article. This improves the accuracy of the sentiment analysis by taking into account the geographical distribution. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or without using AI. For example, the analysis unit can input the text of a news article to a generation AI, which can perform sentiment analysis while taking into account the geographical distribution of the article.

[0055] The analysis unit can improve the accuracy of the analysis during sentiment analysis by referring to related literature of the article. The analysis unit, for example, performs sentiment analysis by referring to cited literature of the article. For example, sentiment analysis can be performed by referring to research papers related to the article. The analysis unit can also improve the accuracy of the sentiment analysis based on the reference literature of the article. As a result, the accuracy of the sentiment analysis is improved by referring to related literature. 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 text of a news article to a generation AI, which can perform sentiment analysis by referring to related literature of the article.

[0056] The visualization unit can optimize the display algorithm by referring to past visualization data at the time of visualization. The visualization unit optimizes the display algorithm based on, for example, past visualization data. For example, the visualization standard can be adjusted by referring to past display results. The visualization unit can also analyze past visualization data and improve the accuracy of the display. As a result, the accuracy of the display is improved by referring to the past visualization data. A part or all of the above-mentioned processing in the visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the visualization unit inputs past visualization data to a generation AI, which can optimize the display algorithm.

[0057] The visualization unit can display the article while considering the attribute information of the article. The visualization unit, for example, selects and displays an appropriate graph or chart according to the genre of the article. For example, the amount of information to be displayed can be adjusted according to the length of the article. The visualization unit can also adjust the display style according to the source of the article. This improves the accuracy of the display by considering the attribute information of the article. Some or all of the above-mentioned processing in the visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the visualization unit inputs the text of a news article to a generation AI, and the generation AI can display the article while considering the attribute information of the article.

[0058] The visualization unit can perform display taking into consideration the geographical distribution of the article when visualizing. The visualization unit performs visualization taking into consideration, for example, the region from which the article originates. For example, visualization related to the target region of the article can be performed. The visualization unit can also perform visualization taking into consideration the geographical background of the article. This improves the accuracy of the display by taking the geographical distribution into consideration. A part or all of the above-mentioned processing in the visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the visualization unit can input the text of a news article to a generation AI, and the generation AI can perform visualization taking into consideration the geographical distribution of the article.

[0059] The visualization unit can improve the accuracy of the display by referring to the related literature of the article during visualization. The visualization unit performs visualization by referring to, for example, cited literature of the article. For example, visualization can be performed by referring to research papers related to the article. The visualization unit can also improve the accuracy of visualization based on the reference literature of the article. As a result, the accuracy of display is improved by referring to related literature. A part or all of the above-mentioned processing in the visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the visualization unit inputs the text of a news article to a generation AI, and the generation AI can perform visualization by referring to related literature of the article.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The news article analysis system may further include a feedback unit that collects user feedback. The feedback unit collects how the user felt about the article analysis result. For example, it may evaluate whether the user is satisfied or dissatisfied with the analysis result. The feedback unit may also improve the analysis algorithm of the system based on the feedback provided by the user. For example, if the user is dissatisfied with a particular bias detection result, the detection algorithm may be adjusted based on the feedback. Furthermore, the feedback unit may also include a function for sharing the user's feedback with other users. This allows the user's feedback to be collected and used to improve the system.

[0062] The detection unit can take into account the reliability of the article's source when detecting biased language in an article. For example, stricter bias detection criteria can be applied to articles from less reliable sources. The detection unit can also improve the accuracy of bias detection based on the past reliability evaluation of the source. For example, more detailed bias detection can be performed on a source that has published many less reliable articles in the past. In this way, the accuracy of bias detection can be improved by taking into account the reliability of the source.

[0063] The evaluation unit can take into account the update frequency of the source when evaluating the reliability of the source. For example, a source that is frequently updated can be evaluated as having high reliability. The evaluation unit can also adjust the reliability evaluation criteria based on the update history of the source. For example, a low reliability evaluation can be set for a source that was frequently updated in the past but has been updated less recently. Furthermore, the evaluation unit can analyze the update contents of the source and reflect them in the reliability evaluation. In this way, the accuracy of the reliability evaluation can be improved by taking into account the update frequency of the source.

[0064] The analysis unit can take into account the readership of the article when performing sentiment analysis of the article. For example, it can evaluate what emotions an article evokes in a particular age group or gender. The analysis unit can also adjust the criteria for sentiment analysis based on attribute information of the readership. For example, it can emphasize emotional expressions for younger generations and calm expressions for older generations. Furthermore, the analysis unit can collect feedback from the readership and improve the accuracy of the sentiment analysis. This allows for more appropriate sentiment analysis by taking the readership into account.

[0065] The visualization unit can take into account the visual preferences of the user when displaying the results of identifying bias or misinformation in an article. For example, the visualization unit can display graphs and charts using colors and fonts preferred by the user. The visualization unit can also adjust the display style based on the user's visual preferences. For example, if the user prefers simple designs, simple graphs and charts can be displayed. Furthermore, the visualization unit can collect user feedback and improve the accuracy of the display. This makes it possible to provide more intuitive information by taking into account the user's visual preferences.

[0066] The process flow of the first embodiment will be briefly described below.

[0067] Step 1: The reception unit inputs the text of a news article. The text of a news article includes, for example, the title, text, and author information of the article copied from an online news site. The reception unit can copy the news article and input it into the AI, or collect it automatically. For example, it has a function of periodically collecting articles from a specific news site. Step 2: The detection unit analyzes the text entered by the reception unit and detects biased language. Biased language includes words that indicate a specific political stance and emotional expressions. The detection unit uses natural language processing technology to understand the content of the article and detect biased language. Step 3: The evaluation unit evaluates the reliability of the source based on the bias language detected by the detection unit. The reliability of the source includes whether the cited statistical data is official and whether the source is a trustworthy institution. The evaluation unit evaluates whether the cited source is trustworthy. Step 4: The analysis unit performs sentiment analysis based on the results of the evaluation by the evaluation unit. Sentiment analysis includes determining what emotions the content of the article evokes. The analysis unit determines whether the content of the article evokes fear or anger in the reader. Step 5: The visualization section visualizes the results of the analysis by the analysis section. Visualization includes visually displaying the identified bias and misinformation in articles using graphs and charts. This helps readers calmly judge the bias and misinformation in news articles.

[0068] (Example 2) A news article analysis system according to an embodiment of the present invention is a system that analyzes news articles using AI tools to identify bias and misinformation. In this news article analysis system, the text of a news article is input to an AI, and the AI ​​performs text analysis to identify bias and misinformation in the article using functions such as detection of biased language, source verification, sentiment analysis, and data visualization. Based on this result, an index for evaluating the reliability of information is provided to readers. This can promote media literacy and promote accurate news / media. For example, the text of a news article is input to an AI. For example, an article is copied from an online news site and input into the AI. At this time, detailed data such as the title, text, and author information of the article are input. Next, the AI ​​analyzes the input text. The AI ​​uses natural language processing technology to understand the content of the article and detect biased language. For example, it can detect words that indicate a specific political position and emotional expressions. Furthermore, the AI ​​verifies the source. It evaluates whether the source of the article and the cited information source are reliable. For example, it checks whether the cited statistical data is official and whether the source is a reliable institution. Next, the AI ​​performs sentiment analysis. It evaluates what emotions the content of the article evokes. For example, it determines whether the article contains content that is likely to cause fear or anger in the reader. Finally, AI visualizes the data. It visually displays the results of identifying bias and misinformation in the article in graphs and charts. This allows readers to intuitively understand the reliability of the information. This mechanism allows readers to calmly judge the bias and misinformation in news articles. For example, it can identify articles that have a specific political stance or articles that contain a lot of emotional expressions and evaluate the reliability of the information. This improves media literacy and promotes accurate news / media. This allows the news article analysis system to help readers calmly judge bias and misinformation in news articles.

[0069] The news article analysis system according to the embodiment includes a reception unit, a detection unit, an evaluation unit, an analysis unit, and a visualization unit. The reception unit inputs the text of a news article. The text of the news article includes, for example, the title, text, and author information of the article copied from an online news site, but is not limited to such an example. The reception unit, for example, copies the news article and inputs it to the AI. The reception unit can also automatically collect the text of the news article. For example, the reception unit has a function of periodically collecting articles from a specific news site. The detection unit analyzes the text input by the reception unit and detects biased language. The biased language includes, for example, words indicating a specific political position and emotional expressions, but is not limited to such an example. The detection unit understands the content of the article and detects biased language, for example, using natural language processing technology. For example, it can detect words indicating a specific political position and emotional expressions. The evaluation unit evaluates the reliability of the source based on the biased language detected by the detection unit. The reliability of the source includes, for example, whether the cited statistical data is official and whether the source is a reliable institution, but is not limited to such an example. The evaluation unit, for example, evaluates whether the cited information source is reliable. For example, it checks whether the cited statistical data is official and whether the source is a reliable institution. The analysis unit performs sentiment analysis based on the results evaluated by the evaluation unit. Sentiment analysis includes, for example, what emotions the content of the article causes, but is not limited to such examples. The analysis unit determines, for example, whether the content of the article causes fear or anger in the reader. For example, it evaluates whether the content of the article causes fear or anger in the reader. The visualization unit visualizes the results analyzed by the analysis unit. Visualization includes, for example, visually displaying the results of identifying bias and misinformation in the article in a graph or chart, but is not limited to such examples. The visualization unit, for example, visually displays the results of identifying bias and misinformation in the article in a graph or chart. For example, it visually displays the results of identifying bias and misinformation in the article in a graph or chart.As a result, the news article analysis system can assist readers in calmly judging bias and misinformation in news articles. Some or all of the above-mentioned processes in the reception unit, detection unit, evaluation unit, analysis unit, and visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can automatically collect the text of the news article using AI when inputting the text of the news article. The detection unit can detect bias language using AI when analyzing the text of the news article. The evaluation unit can evaluate the reliability of the source using AI when evaluating the reliability of the source based on the bias language. The analysis unit can evaluate what emotions the content of the article evokes using AI when performing sentiment analysis. The visualization unit can visually display the identified results of bias and misinformation in the article in graphs and charts using AI when visualizing the analysis results.

[0070] The reception unit inputs the text of the news article. The text of the news article includes, for example, the title, text, author information, etc. of the article copied from an online news site, but is not limited to such examples. For example, the reception unit copies the news article and inputs it to the AI. The reception unit can also automatically collect the text of the news article. For example, the reception unit has a function of periodically collecting articles from a specific news site. Specifically, the reception unit can use web scraping technology to periodically collect articles from a specific news site. Web scraping technology is a technology that analyzes the HTML structure of a webpage and extracts necessary information. This allows the reception unit to obtain update information of the news site in real time and automatically collect the latest news articles. The reception unit can also collect news articles using an RSS feed. An RSS feed is a format for distributing update information of a website, and the latest articles can be automatically obtained by subscribing to an RSS feed provided by a news site. Furthermore, the reception unit can also collect news articles using an API. By using the API provided by the news site, articles can be searched and obtained based on specific keywords and categories. This allows the reception unit to collect news articles in a variety of ways and input them into the system.

[0071] The detection unit analyzes the text input by the reception unit and detects biased language. Biased language includes, but is not limited to, words that indicate a particular political position and emotional expressions. The detection unit understands the content of the article and detects biased language, for example, using natural language processing technology. Specifically, the detection unit performs morphological analysis, divides the text into words, and analyzes the part of speech and meaning of each word. Next, a sentiment analysis algorithm is used to evaluate the emotional nuance of each word or phrase and classify it as positive, negative, or neutral. Furthermore, the detection unit checks against a predefined biased language list to detect words or phrases that include a particular political position or emotional expression. For example, an article that includes biased language such as "biased reporting" or "emotional expression" can be identified. Based on these analysis results, the detection unit can score the bias degree of the entire article and quantitatively evaluate the degree of bias.

[0072] The evaluation unit evaluates the reliability of the source based on the bias language detected by the detection unit. The reliability of the source includes, for example, whether the cited statistical data is official and whether the source is a reliable institution, but is not limited to such examples. The evaluation unit evaluates, for example, whether the cited information source is reliable. Specifically, the evaluation unit checks the source of the cited statistical data and evaluates whether the source is a reliable institution such as a government agency or an academic institution. In addition, the evaluation unit refers to the past reliability evaluation of the cited information source and checks whether it has provided false information in the past. Furthermore, the evaluation unit evaluates the expertise and authority of the cited information source and checks whether the information was provided by an expert or authority in the field. In this way, the evaluation unit can comprehensively evaluate the reliability of the news article and distinguish between highly reliable articles and low reliable articles.

[0073] The analysis unit performs sentiment analysis based on the results of the evaluation by the evaluation unit. Sentiment analysis includes, for example, what emotions the content of the article causes, but is not limited to such examples. The analysis unit determines, for example, whether the content of the article causes fear or anger in the reader. Specifically, the analysis unit uses natural language processing technology to analyze the text of the article and identify words and phrases that cause emotional expressions and emotions. Next, using a sentiment analysis algorithm, calculates a sentiment score for the entire article and classifies it as positive, negative, or neutral. Furthermore, the analysis unit can evaluate the impact on the reader based on the sentiment score of the article and identify articles that are likely to cause a specific emotion. For example, if the content of the article causes fear or anger in the reader, the article can be marked as a warning to alert the reader. In this way, the analysis unit can evaluate the emotional impact of the news article and minimize the risk to the reader.

[0074] The visualization unit visualizes the results of the analysis by the analysis unit. Visualization includes, for example, visually displaying the results of identifying bias and misinformation in an article in a graph or chart, but is not limited to such examples. The visualization unit visually displays, for example, the results of identifying bias and misinformation in an article in a graph or chart. Specifically, the visualization unit displays the bias degree and emotion score of an article in a bar graph or pie chart, so that a reader can understand the bias and emotional impact of an article at a glance. In addition, the visualization unit displays the reliability evaluation result of an article in a heat map or scorecard, so that a reliable article can be visually distinguished from a low reliable article. Furthermore, the visualization unit displays the fluctuation of the emotion score of an article in a time series graph, so that an emotional trend in a specific period can be grasped. In this way, the visualization unit can visually display the analysis result of a news article, and can assist a reader in calmly determining the bias and emotional impact of an article.

[0075] The detection unit can detect words or emotional expressions that indicate a particular political position. The detection unit can, for example, detect words that indicate a particular political position. For example, it can detect words related to a particular political party name or policy. The detection unit can also detect emotional expressions. For example, it can detect adjectives and adverbs that indicate strong emotions. This makes it possible to clarify the bias of an article by detecting a particular political position or emotional expression. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using AI, or may be performed without using AI. For example, the detection unit can input the text of a news article into AI, and the AI ​​can detect words or emotional expressions that indicate a particular political position.

[0076] The evaluation unit can evaluate whether the cited source is official or not. The evaluation unit, for example, evaluates whether the cited source is official or not. For example, it can confirm whether the cited statistical data is official or whether the source is a reliable institution. This can improve the reliability of the article by evaluating the reliability of the cited source. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input the text of a news article into an AI, which can evaluate the reliability of the cited source.

[0077] The analysis unit can evaluate whether the content of the article evokes any emotion. The analysis unit, for example, evaluates what emotion the content of the article evokes. For example, it can determine whether the content of the article evokes fear or anger in the reader. This makes it possible to provide information based on the reader's emotions by evaluating the emotional impact of the article. Some 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 text of a news article into AI, which can evaluate what emotion the content of the article evokes.

[0078] The visualization unit can display the results of identifying bias or misinformation in an article in a graph or chart. The visualization unit, for example, visually displays the results of identifying bias or misinformation in an article in a graph or chart. For example, the results of identifying bias or misinformation in an article can be displayed in a bar graph, pie chart, line graph, or the like. This allows the reader to intuitively understand the reliability of the information through visual display. Some or all of the above-mentioned processing in the visualization unit may be performed, for example, using AI, or may be performed without using AI. For example, the visualization unit can input the text of a news article into AI, and the AI ​​can visually display the results of identifying bias or misinformation in an article in a graph or chart.

[0079] The reception unit can acquire and input articles from an online news site. The reception unit, for example, copies and inputs articles from an online news site. For example, articles can be acquired from a specific news portal or blog. This enables efficient data collection by inputting articles directly from online news sites. Some or all of the above-mentioned processing in the reception unit can be performed, for example, using AI or can be performed without using AI. For example, when acquiring articles from an online news site, the reception unit can automatically collect articles using AI.

[0080] The reception unit can estimate the user's emotion and optimize the input timing of the news article based on the estimated user's emotion. The reception unit, for example, estimates the user's emotion and adjusts the input timing of the news article based on the estimated user's emotion. For example, if the user is stressed, the reception unit can prompt the user to input a news article during a time when the user can relax. Also, if the user is concentrating, the reception unit can prompt the user to input a news article immediately. Also, if the user is tired, the reception unit can prompt the user to input a news article after a break. In this way, the input timing can be adjusted according to the user's emotion, so that the news article can be input at a more appropriate timing. 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 reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI, which can estimate the user's emotion, and adjust the input timing of the news article based on the result.

[0081] The reception unit can analyze the user's past news article browsing history and select an appropriate input method. The reception unit, for example, analyzes the user's past news article browsing history and selects the optimal input method. For example, articles from news sites that the user frequently browsed in the past can be preferentially input. Also, based on the genre of articles that the user liked to read in the past, related articles can be input. Also, by referring to the format of an article that the user browsed for a long time in the past, articles of a similar format can be input. As a result, the optimal input method is selected based on the past browsing history, improving the convenience of the user. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's past news article browsing history to the generation AI, which can select the optimal input method.

[0082] The reception unit can perform filtering based on the user's current field of interest when inputting a news article. The reception unit, for example, performs filtering based on the user's current field of interest when inputting a news article. For example, articles related to topics in which the user is currently interested can be preferentially input. Also, related news articles can be input based on keywords recently searched by the user. Also, articles related to topics that the user follows on social media can be input. In this way, by filtering based on the user's field of interest, highly relevant news articles can be provided. Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's field of interest data to the generation AI, and the generation AI can filter the news articles.

[0083] The reception unit can estimate the user's emotion and set the priority of the news articles to be input based on the estimated user's emotion. The reception unit, for example, estimates the user's emotion and determines the priority of the news articles based on the estimated user's emotion. For example, when the user is relaxed, an article with light content can be preferentially input. Also, when the user is excited, an important news article can be preferentially input. Also, when the user is sad, an article with positive content can be preferentially input. This enables more appropriate information provision by determining the priority of the news articles 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 reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI, and the generation AI can determine the priority of the news articles.

[0084] The reception unit can preferentially input highly relevant articles in consideration of the geographical location information of the user when inputting a news article. For example, the reception unit preferentially inputs highly relevant articles in consideration of the geographical location information of the user when inputting a news article. For example, local news related to the user's current location can be preferentially input. International news related to the user's country or region can also be preferentially input. Articles related to nearby events and occurrences can also be input based on the user's location information. In this way, by taking the geographical location information into consideration, news articles that are highly relevant to the user can be provided. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the geographical location information of the user to the generation AI, and the generation AI can determine the priority order of the news articles.

[0085] The reception unit can analyze the social media activity of the user when a news article is input, and input related articles. The reception unit can, for example, analyze the social media activity of the user when a news article is input, and input related articles. For example, news related to an article shared by the user on social media can be input. Articles can also be input based on the content posted by an account the user follows on social media. News related to a group or community in which the user participates on social media can also be input. In this way, by analyzing social media activity, news articles related to the user can be provided. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the social media activity data of the user to the generation AI, and the generation AI can select a related news article.

[0086] The detection unit can estimate the user's emotion and adjust the biased language detection criteria based on the estimated user's emotion. The detection unit, for example, estimates the user's emotion and adjusts the biased language detection criteria based on the estimated user's emotion. For example, when the user is relaxed, a broad range of biased language detection criteria can be set. Also, when the user is nervous, a strict biased language detection criteria can be set. Also, when the user is excited, a criterion that focuses on detecting emotional expressions can be set. This enables more appropriate bias detection by adjusting the biased language detection criteria 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 detection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detection unit inputs the user's emotion data to the generation AI, and the generation AI adjusts the biased language detection criteria.

[0087] The detection unit can improve the accuracy of detection by taking into account the context of the article when detecting biased language. The detection unit, for example, analyzes the context before and after the article to improve the accuracy of detecting biased language. For example, the detection of biased language can be performed by taking into account the theme of each paragraph of the article. The detection unit can also analyze the tone of the entire article and adjust the detection criteria for biased language. This improves the accuracy of detecting biased language by taking into account the context of the article. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the text of a news article to a generation AI, which can detect biased language by taking into account the context of the article.

[0088] When detecting biased language, the detection unit can perform the detection taking into consideration the attribute information of the author of the article. The detection unit detects biased language, for example, taking into consideration the political stance of the author of the article. For example, biased language can be detected by referring to the past writing history of the author of the article. The detection unit can also detect biased language taking into consideration the specialty field of the author of the article. As a result, the accuracy of detecting biased language is improved by taking into consideration the attribute information of the author. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI, or may be performed without using AI. For example, the detection unit can input the text of a news article to a generation AI, and the generation AI can detect biased language by taking into consideration the attribute information of the author of the article.

[0089] The detection unit can estimate the user's emotion and adjust the display order of the detection results based on the estimated user's emotion. The detection unit, for example, estimates the user's emotion and adjusts the display order of the detection results based on the estimated user's emotion. For example, when the user is relaxed, detailed detection results can be preferentially displayed. Also, when the user is nervous, important detection results can be preferentially displayed. Also, when the user is excited, detection results including emotional expressions can be preferentially displayed. This makes it possible to provide more appropriate information by adjusting the display order of the detection 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, 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 detection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detection unit inputs the user's emotion data to the generation AI, and the generation AI adjusts the display order of the detection results.

[0090] The detection unit can detect biased language taking into consideration the geographical distribution of the article when detecting biased language. The detection unit detects biased language taking into consideration the region from which the article originates, for example. For example, biased language related to the target region of the article can be detected. The detection unit can also detect biased language taking into consideration the geographical background of the article. This improves the accuracy of detecting biased language by taking the geographical distribution into consideration. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the text of a news article to a generation AI, which can detect biased language taking into consideration the geographical distribution of the article.

[0091] The detection unit can improve the accuracy of detection when detecting biased language by referring to related literature of the article. The detection unit detects biased language by, for example, referring to cited literature of the article. For example, biased language can be detected by referring to research papers related to the article. The detection unit can also improve the accuracy of detecting biased language based on the reference literature of the article. As a result, the accuracy of detecting biased language is improved by referring to related literature. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or may be performed without using AI. For example, the detection unit can input the text of a news article to a generation AI, and the generation AI can detect biased language by referring to related literature of the article.

[0092] The evaluation unit can estimate the user's emotion and adjust the reliability evaluation criteria of the source based on the estimated user's emotion. The evaluation unit, for example, estimates the user's emotion and adjusts the reliability evaluation criteria of the source based on the estimated user's emotion. For example, when the user is relaxed, a broad reliability evaluation criterion can be set. Also, when the user is nervous, a strict reliability evaluation criterion can be set. Also, when the user is excited, a reliability evaluation criterion including an emotional expression can be set. This enables a more appropriate reliability evaluation by adjusting the reliability evaluation criterion according to the user's emotion. The estimation of the 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 evaluation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the evaluation unit can input the user's emotion data to the generation AI, and the generation AI can adjust the reliability evaluation criteria of the source.

[0093] The evaluation unit can optimize the evaluation algorithm by referring to past evaluation data when evaluating the reliability of a source. The evaluation unit can optimize the evaluation algorithm based on, for example, past reliability evaluation data. For example, the reliability evaluation criteria can be adjusted by referring to past evaluation results. The evaluation unit can also analyze past evaluation data and improve the accuracy of the reliability evaluation. As a result, the accuracy of the reliability evaluation is improved by referring to the past evaluation data. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input past evaluation data to a generation AI, which can optimize the evaluation algorithm.

[0094] The evaluation unit can evaluate the reliability of a source by taking into account the attribute information of the cited information source. The evaluation unit, for example, evaluates the reliability by taking into account the origin of the cited information source. For example, the evaluation can be performed by referring to past reliability evaluations of the cited information source. The evaluation unit can also evaluate the reliability by taking into account the specialty field of the cited information source. This improves the accuracy of the reliability evaluation by taking into account the attribute information of the cited information source. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input the text of a news article into the generation AI, and the generation AI can evaluate the reliability by taking into account the attribute information of the cited information source.

[0095] The evaluation unit can estimate the user's emotion and adjust the display method of the evaluation result based on the estimated user's emotion. The evaluation unit, for example, estimates the user's emotion and adjusts the display method of the evaluation result based on the estimated user's emotion. For example, when the user is relaxed, detailed evaluation results can be displayed. Also, when the user is nervous, important evaluation results can be preferentially displayed. Also, when the user is excited, evaluation results including emotional expressions can be displayed. This makes it possible to provide more appropriate information by adjusting the display method of the evaluation result 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 evaluation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the evaluation unit inputs the user's emotion data into the generation AI, and the generation AI adjusts the display method of the evaluation result.

[0096] The evaluation unit can evaluate the reliability of a source by taking into account the geographical distribution of the information source. The evaluation unit evaluates the reliability by taking into account, for example, the region from which the information source originates. For example, the reliability evaluation can be performed in relation to the target region of the information source. The evaluation unit can also evaluate the reliability by taking into account the geographical background of the information source. This improves the accuracy of the reliability evaluation by taking into account the geographical distribution. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input the text of a news article into a generation AI, which can evaluate the reliability by taking into account the geographical distribution of the information source.

[0097] The evaluation unit can improve the accuracy of the evaluation when evaluating the reliability of a source by referring to related literature of the information source. The evaluation unit, for example, evaluates the reliability by referring to cited literature of the information source. For example, the reliability can be evaluated by referring to related research papers of the information source. The evaluation unit can also improve the accuracy of the reliability evaluation based on reference literature of the information source. As a result, the accuracy of the reliability evaluation is improved by referring to related literature. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input the text of a news article to a generation AI, and the generation AI can evaluate the reliability by referring to related literature of the information source.

[0098] The analysis unit can estimate the user's emotion and adjust the criteria for emotion analysis based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the criteria for emotion analysis based on the estimated user's emotion. For example, when the user is relaxed, broad emotion analysis criteria can be set. Also, when the user is nervous, strict emotion analysis criteria can be set. Also, when the user is excited, criteria that focus on analyzing emotional expressions can be set. This enables more appropriate emotion analysis by adjusting the criteria for emotion 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, 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 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 the generation AI can adjust the criteria for emotion analysis.

[0099] The analysis unit can improve the accuracy of the analysis by considering the context of the article during the sentiment analysis. The analysis unit, for example, analyzes the context before and after the article to improve the accuracy of the sentiment analysis. For example, the sentiment analysis can be performed by considering the theme of each paragraph of the article. The analysis unit can also analyze the tone of the entire article and adjust the criteria for the sentiment analysis. This improves the accuracy of the sentiment analysis by considering the context of the article. 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 text of a news article to a generation AI, which can perform sentiment analysis by considering the context of the article.

[0100] The analysis unit can perform sentiment analysis while taking into account the attribute information of the article's author. The analysis unit performs sentiment analysis while taking into account, for example, the political stance of the article's author. For example, sentiment analysis can be performed by referring to the past writing history of the article's author. The analysis unit can also perform sentiment analysis while taking into account the specialty of the article's author. This improves the accuracy of sentiment analysis by taking into account the attribute information of the author. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the text of a news article into a generation AI, which can perform sentiment analysis while taking into account the attribute information of the article's author.

[0101] The analysis unit can estimate the user's emotion and adjust the display order of the analysis results based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the display order of the analysis results based on the estimated user's emotion. For example, when the user is relaxed, detailed analysis results can be preferentially displayed. Also, when the user is nervous, important analysis results can be preferentially displayed. Also, when the user is excited, analysis results including emotional expressions can be preferentially displayed. This makes it possible to provide more appropriate information by adjusting the display order of the analysis 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, 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 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 the generation AI can adjust the display order of the analysis results.

[0102] The analysis unit can perform sentiment analysis while taking into account the geographical distribution of the article. The analysis unit performs sentiment analysis while taking into account, for example, the region from which the article originates. For example, sentiment analysis related to the target region of the article can be performed. The analysis unit can also perform sentiment analysis while taking into account the geographical background of the article. This improves the accuracy of the sentiment analysis by taking into account the geographical distribution. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or without using AI. For example, the analysis unit can input the text of a news article to a generation AI, which can perform sentiment analysis while taking into account the geographical distribution of the article.

[0103] The analysis unit can improve the accuracy of the analysis during sentiment analysis by referring to related literature of the article. The analysis unit, for example, performs sentiment analysis by referring to cited literature of the article. For example, sentiment analysis can be performed by referring to research papers related to the article. The analysis unit can also improve the accuracy of the sentiment analysis based on the reference literature of the article. As a result, the accuracy of the sentiment analysis is improved by referring to related literature. 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 text of a news article to a generation AI, which can perform sentiment analysis by referring to related literature of the article.

[0104] The visualization unit can estimate the user's emotion and adjust the display method of the visualization based on the estimated user's emotion. The visualization unit, for example, estimates the user's emotion and adjusts the display method of the visualization based on the estimated user's emotion. For example, when the user is relaxed, detailed graphs and charts can be displayed. Also, when the user is nervous, simple and highly visible graphs and charts can be displayed. Also, when the user is excited, graphs and charts including emotional expressions can be displayed. This makes it possible to provide more appropriate information by adjusting the display method of the visualization according to the user's emotion. The estimation of the 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 visualization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the visualization unit can input the user's emotion data to the generation AI, and the generation AI can adjust the display method of the visualization.

[0105] The visualization unit can optimize the display algorithm by referring to past visualization data at the time of visualization. The visualization unit optimizes the display algorithm based on, for example, past visualization data. For example, the visualization standard can be adjusted by referring to past display results. The visualization unit can also analyze past visualization data and improve the accuracy of the display. As a result, the accuracy of the display is improved by referring to the past visualization data. A part or all of the above-mentioned processing in the visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the visualization unit inputs past visualization data to a generation AI, which can optimize the display algorithm.

[0106] The visualization unit can display the article while considering the attribute information of the article. The visualization unit, for example, selects and displays an appropriate graph or chart according to the genre of the article. For example, the amount of information to be displayed can be adjusted according to the length of the article. The visualization unit can also adjust the display style according to the source of the article. This improves the accuracy of the display by considering the attribute information of the article. Some or all of the above-mentioned processing in the visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the visualization unit inputs the text of a news article to a generation AI, and the generation AI can display the article while considering the attribute information of the article.

[0107] The visualization unit can estimate the user's emotion and determine the priority of visualization based on the estimated user's emotion. The visualization unit, for example, estimates the user's emotion and determines the priority of visualization based on the estimated user's emotion. For example, when the user is relaxed, detailed visualization results can be preferentially displayed. Also, when the user is nervous, important visualization results can be preferentially displayed. Also, when the user is excited, visualization results including emotional expressions can be preferentially displayed. This enables more appropriate information provision by determining the priority of visualization 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 visualization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the visualization unit inputs the user's emotion data to the generation AI, and the generation AI can determine the priority of visualization.

[0108] The visualization unit can perform display taking into consideration the geographical distribution of the article when visualizing. The visualization unit performs visualization taking into consideration, for example, the region from which the article originates. For example, visualization related to the target region of the article can be performed. The visualization unit can also perform visualization taking into consideration the geographical background of the article. This improves the accuracy of the display by taking the geographical distribution into consideration. A part or all of the above-mentioned processing in the visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the visualization unit can input the text of a news article to a generation AI, and the generation AI can perform visualization taking into consideration the geographical distribution of the article.

[0109] The visualization unit can improve the accuracy of the display by referring to the related literature of the article during visualization. The visualization unit performs visualization by referring to, for example, cited literature of the article. For example, visualization can be performed by referring to research papers related to the article. The visualization unit can also improve the accuracy of visualization based on the reference literature of the article. As a result, the accuracy of display is improved by referring to related literature. A part or all of the above-mentioned processing in the visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the visualization unit inputs the text of a news article to a generation AI, and the generation AI can perform visualization by referring to related literature of the article.

[0110] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0111] The news article analysis system may further include a feedback unit that collects user feedback. The feedback unit collects how the user felt about the article analysis result. For example, it may evaluate whether the user is satisfied or dissatisfied with the analysis result. The feedback unit may also improve the analysis algorithm of the system based on the feedback provided by the user. For example, if the user is dissatisfied with a particular bias detection result, the detection algorithm may be adjusted based on the feedback. Furthermore, the feedback unit may also include a function for sharing the user's feedback with other users. This allows the user's feedback to be collected and used to improve the system.

[0112] The detection unit can take into account the reliability of the article's source when detecting biased language in an article. For example, stricter bias detection criteria can be applied to articles from less reliable sources. The detection unit can also improve the accuracy of bias detection based on the past reliability evaluation of the source. For example, more detailed bias detection can be performed on a source that has published many less reliable articles in the past. In this way, the accuracy of bias detection can be improved by taking into account the reliability of the source.

[0113] The evaluation unit can take into account the update frequency of the source when evaluating the reliability of the source. For example, a source that is frequently updated can be evaluated as having high reliability. The evaluation unit can also adjust the reliability evaluation criteria based on the update history of the source. For example, a low reliability evaluation can be set for a source that was frequently updated in the past but has been updated less recently. Furthermore, the evaluation unit can analyze the update contents of the source and reflect them in the reliability evaluation. In this way, the accuracy of the reliability evaluation can be improved by taking into account the update frequency of the source.

[0114] The analysis unit can take into account the readership of the article when performing sentiment analysis of the article. For example, it can evaluate what emotions an article evokes in a particular age group or gender. The analysis unit can also adjust the criteria for sentiment analysis based on attribute information of the readership. For example, it can emphasize emotional expressions for younger generations and calm expressions for older generations. Furthermore, the analysis unit can collect feedback from the readership and improve the accuracy of the sentiment analysis. This allows for more appropriate sentiment analysis by taking the readership into account.

[0115] The visualization unit can take into account the visual preferences of the user when displaying the results of identifying bias or misinformation in an article. For example, the visualization unit can display graphs and charts using colors and fonts preferred by the user. The visualization unit can also adjust the display style based on the user's visual preferences. For example, if the user prefers simple designs, simple graphs and charts can be displayed. Furthermore, the visualization unit can collect user feedback and improve the accuracy of the display. This makes it possible to provide more intuitive information by taking into account the user's visual preferences.

[0116] The reception unit can estimate the user's emotions and adjust the input method of a news article based on the estimated user's emotions. For example, if the user is feeling stressed, the input of a news article can be prompted while playing relaxing music. Also, if the user is concentrating, the input of a news article can be prompted with minimal notifications. Furthermore, if the user is tired, a message encouraging the user to take a break can be displayed and the user can be prompted to input a news article after that. In this way, a more comfortable input environment can be provided by adjusting the input method according to the user's emotions.

[0117] The detection unit can estimate the user's emotions and customize the biased language detection results based on the estimated user's emotions. For example, when the user is relaxed, detailed biased language detection results can be displayed. Also, when the user is nervous, important biased language detection results can be preferentially displayed. Furthermore, when the user is excited, biased language detection results including emotional expressions can be highlighted and displayed. This makes it possible to provide more appropriate information by customizing biased language detection results according to the user's emotions.

[0118] The evaluation unit can estimate the user's emotions and customize the reliability evaluation results of the source based on the estimated user's emotions. For example, when the user is relaxed, detailed reliability evaluation results can be displayed. Also, when the user is nervous, important reliability evaluation results can be preferentially displayed. Furthermore, when the user is excited, reliability evaluation results including emotional expressions can be highlighted and displayed. In this way, by customizing the reliability evaluation results according to the user's emotions, more appropriate information can be provided.

[0119] The analysis unit can estimate the user's emotions and customize the emotion analysis results based on the estimated user's emotions. For example, if the user is relaxed, detailed emotion analysis results can be displayed. Also, if the user is nervous, important emotion analysis results can be displayed with priority. Furthermore, if the user is excited, emotion analysis results including emotional expressions can be displayed with emphasis. In this way, more appropriate information can be provided by customizing the emotion analysis results according to the user's emotions.

[0120] The visualization unit can estimate the user's emotions and customize the visualization results based on the estimated user's emotions. For example, when the user is relaxed, detailed graphs and charts can be displayed. When the user is nervous, simple graphs and charts with high visibility can be displayed. Furthermore, when the user is excited, graphs and charts including emotional expressions can be displayed in an emphasized manner. This makes it possible to provide more appropriate information by customizing the visualization results according to the user's emotions.

[0121] The process flow of the second embodiment will be briefly described below.

[0122] Step 1: The reception unit inputs the text of a news article. The text of a news article includes, for example, the title, text, and author information of the article copied from an online news site. The reception unit can copy the news article and input it into the AI, or collect it automatically. For example, it has a function of periodically collecting articles from a specific news site. Step 2: The detection unit analyzes the text entered by the reception unit and detects biased language. Biased language includes words that indicate a specific political stance and emotional expressions. The detection unit uses natural language processing technology to understand the content of the article and detect biased language. Step 3: The evaluation unit evaluates the reliability of the source based on the bias language detected by the detection unit. The reliability of the source includes whether the cited statistical data is official and whether the source is a trustworthy institution. The evaluation unit evaluates whether the cited source is trustworthy. Step 4: The analysis unit performs sentiment analysis based on the results of the evaluation by the evaluation unit. Sentiment analysis includes determining what emotions the content of the article evokes. The analysis unit determines whether the content of the article evokes fear or anger in the reader. Step 5: The visualization section visualizes the results of the analysis by the analysis section. Visualization includes visually displaying the identified bias and misinformation in articles using graphs and charts. This helps readers calmly judge the bias and misinformation in news articles.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] Each of the multiple elements including the above-mentioned reception unit, detection unit, evaluation unit, analysis unit, and visualization unit is realized, for example, in at least one of the smart device 14 and the data processing device 12. For example, the reception unit can input the text of a news article by the control unit 46A of the smart device 14. The detection unit can detect biased language by, for example, the specific processing unit 290 of the data processing device 12. The evaluation unit can evaluate the reliability of a source by, for example, the specific processing unit 290 of the data processing device 12. The analysis unit can perform sentiment analysis by, for example, the specific processing unit 290 of the data processing device 12. The visualization unit can visually display the analysis result in a graph or chart by, for example, the control unit 46A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0127] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements including the above-mentioned reception unit, detection unit, evaluation unit, analysis unit, and visualization unit is realized, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit can input the text of a news article by the control unit 46A of the smart glasses 214. The detection unit can detect biased language by, for example, the specific processing unit 290 of the data processing device 12. The evaluation unit can evaluate the reliability of a source by, for example, the specific processing unit 290 of the data processing device 12. The analysis unit can perform sentiment analysis by, for example, the specific processing unit 290 of the data processing device 12. The visualization unit can visually display the analysis result in a graph or chart by, for example, the control unit 46A of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0143] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] Each of the multiple elements including the above-mentioned reception unit, detection unit, evaluation unit, analysis unit, and visualization unit is realized, for example, in at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit can input the text of a news article by the control unit 46A of the headset type terminal 314. The detection unit can detect biased language by the specific processing unit 290 of the data processing device 12, for example. The evaluation unit can evaluate the reliability of a source by the specific processing unit 290 of the data processing device 12, for example. The analysis unit can perform sentiment analysis by the specific processing unit 290 of the data processing device 12, for example. The visualization unit can visually display the analysis result in a graph or chart by the control unit 46A of the headset type terminal 314, for example. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0159] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[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 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.

[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 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.

[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 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.

[0175] Each of the multiple elements including the above-mentioned reception unit, detection unit, evaluation unit, analysis unit, and visualization unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit can input the text of a news article by the control unit 46A of the robot 414. The detection unit can detect biased language by the specific processing unit 290 of the data processing device 12, for example. The evaluation unit can evaluate the reliability of a source by the specific processing unit 290 of the data processing device 12, for example. The analysis unit can perform sentiment analysis by the specific processing unit 290 of the data processing device 12, for example. The visualization unit can visually display the analysis result in a graph or chart by the control unit 46A of the robot 414, for example. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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).

[0180] 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.

[0181] 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."

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] (Appendix 1) a reception section for inputting the text of a news article; A detection unit that analyzes the text input by the reception unit and detects biased language; an evaluation unit that evaluates the reliability of a source based on the bias language detected by the detection unit; an analysis unit that performs sentiment analysis based on the results of the evaluation by the evaluation unit; A visualization unit that visualizes the results of the analysis by the analysis unit. A system characterized by: (Appendix 2) The detection unit is Detecting political or emotional statements 2. The system of claim 1, (Appendix 3) The evaluation unit is Evaluate whether the cited sources are authoritative 2. The system of claim 1, (Appendix 4) The analysis unit includes: Evaluate what emotions the article evokes or dislikes 2. The system of claim 1, (Appendix 5) The visualization unit is Displaying graphs or charts showing the results of identifying bias or misinformation in an article 2. The system of claim 1, (Appendix 6) The reception unit is Enter articles from online news sites 2. The system of claim 1, (Appendix 7) The reception unit is Estimate user emotions and optimize the timing of news article input based on the estimated user emotions 2. The system of claim 1, (Appendix 8) The reception unit is Analyze the user's past news article browsing history and select the appropriate input method 2. The system of claim 1, (Appendix 9) The reception unit is Filtering news articles as they are entered based on the user's current interests 2. The system of claim 1, (Appendix 10) The reception unit is Infer user sentiment and prioritize incoming news articles based on the estimated user sentiment 2. The system of claim 1, (Appendix 11) The reception unit is When entering news articles, the system takes into account the user's geographic location information to prioritize relevant articles. 2. The system of claim 1, (Appendix 12) The reception unit is When a news article is entered, the system analyzes the user's social media activity and enters related articles. 2. The system of claim 1, (Appendix 13) The detection unit is Estimate user sentiment and adjust biased language detection criteria based on the estimated user sentiment. 2. The system of claim 1, (Appendix 14) The detection unit is When detecting biased language, the accuracy of the detection is improved by taking into account the context of the article. 2. The system of claim 1, (Appendix 15) The detection unit is When detecting biased language, the detection is performed taking into account the attribute information of the article's author. 2. The system of claim 1, (Appendix 16) The detection unit is Estimate the user's emotions and adjust the display order of the detection results based on the estimated user emotions. 2. The system of claim 1, (Appendix 17) The detection unit is When detecting biased language, the geographical distribution of articles is taken into account. 2. The system of claim 1, (Appendix 18) The detection unit is When detecting biased language, improve the accuracy of the detection by referring to related literature of the article 2. The system of claim 1, (Appendix 19) The evaluation unit is Inferring a user's sentiment and adjusting a source credibility metric based on the inferred user's sentiment 2. The system of claim 1, (Appendix 20) The evaluation unit is When assessing the reliability of a source, we refer to past evaluation data to optimize our evaluation algorithms. 2. The system of claim 1, (Appendix 21) The evaluation unit is When assessing the reliability of a source, consider the attributes of the source cited. 2. The system of claim 1, (Appendix 22) The evaluation unit is Inferring user emotion and adjusting the way rating results are displayed based on the estimated user emotion 2. The system of claim 1, (Appendix 23) The evaluation unit is When assessing the reliability of sources, take into account their geographical distribution 2. The system of claim 1, (Appendix 24) The evaluation unit is When assessing the reliability of a source, refer to the relevant literature of the source to improve the accuracy of the assessment. 2. The system of claim 1, (Appendix 25) The analysis unit includes: Inferring a user's sentiment and adjusting sentiment analysis criteria based on the inferred user's sentiment 2. The system of claim 1, (Appendix 26) The analysis unit includes: When analyzing sentiment, take article context into account to improve analysis accuracy 2. The system of claim 1, (Appendix 27) The analysis unit includes: When analyzing sentiment, the author's attributes are taken into account. 2. The system of claim 1, (Appendix 28) The analysis unit includes: Infer user sentiment and adjust the display order of analysis results based on the inferred user sentiment 2. The system of claim 1, (Appendix 29) The analysis unit includes: When analyzing sentiment, the geographical distribution of articles is taken into account. 2. The system of claim 1, (Appendix 30) The analysis unit includes: When analyzing sentiment, refer to related literature of the article to improve the accuracy of the analysis. 2. The system of claim 1, (Appendix 31) The visualization unit is Infer user emotions and adjust visualizations based on the inferred emotions 2. The system of claim 1, (Appendix 32) The visualization unit is When visualizing, the display algorithm is optimized by referring to past visualization data. 2. The system of claim 1, (Appendix 33) The visualization unit is When visualizing, the article's attribute information is taken into consideration. 2. The system of claim 1, (Appendix 34) The visualization unit is Infer user sentiment and prioritize visualizations based on the inferred sentiment 2. The system of claim 1, (Appendix 35) The visualization unit is When visualizing, the geographical distribution of articles is taken into account. 2. The system of claim 1, (Appendix 36) The visualization unit is During visualization, the accuracy of the display is improved by referencing related literature of articles. 2. The system of claim 1, [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception section for inputting the text of a news article; A detection unit that analyzes the text input by the reception unit and detects biased language; an evaluation unit that evaluates the reliability of a source based on the bias language detected by the detection unit; an analysis unit that performs a sentiment analysis based on the result of the evaluation by the evaluation unit; A visualization unit that visualizes the results of the analysis by the analysis unit. A system characterized by:

2. The detection unit is Detecting political or emotional statements 2. The system of claim 1 .

3. The evaluation unit is Evaluate whether the cited sources are authoritative 2. The system of claim 1 .

4. The analysis unit includes: Evaluate what emotions the article evokes or dislikes 2. The system of claim 1 .

5. The visualization unit is Displaying graphs or charts showing the results of identifying bias or misinformation in an article 2. The system of claim 1 .

6. The reception unit is Enter articles from online news sites 2. The system of claim 1 .

7. The reception unit is Estimate user emotions and optimize the timing of news article input based on the estimated user emotions 2. The system of claim 1 .

8. The reception unit is Analyze the user's past news article browsing history and select the appropriate input method 2. The system of claim 1 .

Images