System

Abstract

An object of a system according to an embodiment is to make it possible to easily check the content of a link destination without jumping to the link destination.SOLUTION: A system includes a link destination content analysis unit, a summary generation unit, and a display unit. The link destination content analysis unit analyzes the content of the link destination. The summary generation unit generates a summary based on the content analyzed by the link destination content analysis unit. The display unit displays the summary generated by the summary generation unit in a balloon format.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology requires users to click on each link one by one to check the content of the linked page, which is time-consuming.

[0005] The system according to the embodiment aims to enable a user to easily check the content of a link destination without having to jump to the link destination. [Means for solving the problem]

[0006] A system according to an embodiment includes a link destination content analysis unit, a summary generation unit, and a display unit. The link destination content analysis unit analyzes the content of the link destination. The summary generation unit generates a summary based on the content analyzed by the link destination content analysis unit. The display unit displays the summary generated by the summary generation unit in a speech bubble format. [Effects of the Invention]

[0007] The system according to the embodiment can make it possible to easily check the content of a link destination without having to jump to the link destination. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The browser system according to the embodiment of the present invention is a system in which the content of the linked page is displayed in a speech bubble when the cursor is placed on the link (or when a long press is performed). This allows the user to check the overview of the linked page without having to jump to the linked page, thereby saving time.

[0029] A browser system according to an embodiment includes a link destination content analysis unit, a summary generation unit, and a display unit. The link destination content analysis unit analyzes the content of the link destination. For example, it analyzes the HTML structure of the link destination and extracts important information based on heading tags and paragraph tags. It can also extract a page summary and keywords by utilizing metadata of the link destination. It can also analyze the style sheets and scripts used in the linked page to accurately determine the content to be displayed. The summary generation unit generates a summary based on the content analyzed by the link destination content analysis unit. For example, the generation AI uses a text generation AI (e.g., LLM) to concisely summarize the content of the link destination. The generation AI can also summarize the content of the link destination using a multimodal generation AI. The generation AI can also extract and summarize important parts of a sentence. The display unit displays the summary generated by the summary generation unit in a speech bubble format. For example, the shape, color, and display position of the speech bubble can be customized. The display unit can automatically display the summary when the user places the cursor over (or touches and holds) a link. As a result, the browser system according to the embodiment allows the user to check the overview without jumping to the linked page, thereby saving time.

[0030] The link content analysis unit can generate summaries based on the linked page structure and metadata. For example, the link content analysis unit uses a generation AI to analyze the HTML structure of the linked page and extract important information based on heading and paragraph tags. For example, it prioritizes including the content of h1 and h2 tags in the summary. It also utilizes the linked page's metadata to extract a page summary and keywords, which are reflected in the summary. For example, it analyzes the content of the meta tag's description and keywords. It also analyzes the style sheets and scripts used on the linked page to accurately determine the content to be displayed. For example, it generates summaries taking into account the influence of CSS and JavaScript. This allows for the generation of more accurate summaries by taking the linked page structure and metadata into account.

[0031] The summary generation unit can generate a customized summary based on the user's past browsing history or interests. The summary generation unit, for example, analyzes the user's past browsing history and extracts related keywords and topics to reflect in the summary. For example, it prioritizes displaying information from frequently viewed categories. It also customizes the content of the summary based on the user's interests. For example, it highlights information related to topics that interest the user. It also references the user's past search history and includes related search keywords in the summary. For example, it displays in detail the content of links that contain keywords searched for in the past. In this way, by generating a customized summary based on the user's past browsing history and interests, it is possible to provide the user with more useful information.

[0032] The summary generation unit can analyze the linked video or audio content and generate a summary of the video or a transcript of the audio. For example, the summary generation unit uses a generation AI to analyze the linked video content and extract important scenes and segments to generate a summary. For example, the summary generation unit displays a summary along with a thumbnail of the video. It also uses speech recognition technology to convert the linked audio content into a transcript and display it as a summary. For example, it summarizes the contents of a podcast in text. It also analyzes the metadata of the video or audio content, extracts important information, and reflects it in the summary. For example, it generates a summary based on the video title or description. By analyzing the linked video or audio content and generating a summary or transcript, users can efficiently understand the content.

[0033] The summary generation unit can also display a summary of the content of the link destination in an email client or messaging app. The summary generation unit, for example, integrates a summary display function into an email client, and displays a summary of the content of the link destination when the cursor is placed on a link in an email. For example, the summary generation unit analyzes links in the email body and displays a summary. Also, a summary display function is added to a messaging app, and a summary of the content of the link destination is displayed when a link in a message is touched and held. For example, a link in a chat is analyzed and displayed as a summary. Also, the content of an email or message is analyzed, and a summary of the link destination is automatically generated. For example, the content of the link destination is summarized based on the subject and body of the email. In this way, a summary of the content of the link destination can be displayed in an email client or messaging app, allowing the user to efficiently grasp information.

[0034] The generative AI model can be specialized for local government websites and can handle the terminology or format specific to the bidding project or the minutes. For example, a generative AI model specialized for local government websites can be developed and trained to learn the terminology specific to bidding projects and minutes. For example, it can analyze terminology and formats specific to the local government. The format of the bidding project or minutes can also be analyzed, and the generative AI can generate a summary that corresponds to that format. For example, it can generate a summary for each item in the minutes. The generative AI can also be trained using a dataset specialized for local government websites to generate highly accurate summaries. For example, past bidding projects and minutes can be used as learning data. In this way, by developing a generative AI model specialized for local government websites, it is possible to generate summaries that correspond to the terminology and format specific to bidding projects and minutes.

[0035] The linked content analysis unit can generate a more comprehensive summary by referencing related laws and regulations when analyzing the linked content of the local government's website. For example, when analyzing the linked content of a local government's website, the linked content analysis unit automatically references related laws and regulations and reflects them in the summary. For example, laws and regulations related to bidding projects are included in the summary. A database of laws and regulations is also integrated into the generation AI and referenced when analyzing the linked content. For example, a summary is generated based on the local government's rules and ordinances. A comprehensive summary is also generated by cross-referencing the linked content of the local government's website with related laws and regulations. For example, the contents of the minutes of a meeting and related laws and regulations are displayed simultaneously. This allows a more comprehensive summary to be generated by also referencing related laws and regulations.

[0036] The summary generation unit can integrate the summary display function of the local government's homepage into the smart city's information provision system, allowing citizens to quickly obtain the information they need. The summary generation unit, for example, integrates the summary display function into the smart city's information provision system, allowing citizens to quickly check the content of linked destinations. For example, it displays a summary of information on public services. The summary display function of the local government's homepage can also be incorporated into a smart city app, allowing citizens to efficiently obtain the information they need. For example, it displays summaries of traffic information and event information. A generative AI model specialized for the smart city's information provision system can be developed to analyze the content of linked destinations on the local government's homepage and generate summaries. For example, summaries can be generated based on the smart city's database. In this way, by integrating the summary display function into the smart city's information provision system, citizens can quickly obtain the information they need.

[0037] The major browser app can be equipped with an algorithm that learns the user's browsing patterns and displays summaries at the optimal timing. The major browser app, for example, analyzes the user's browsing patterns and develops an algorithm that displays summaries at the optimal timing. For example, the major browser app may display summaries the moment the user places the cursor on a link. The major browser app may also customize the timing of summary display based on the user's browsing history. For example, summaries may be displayed immediately for links to frequently visited sites. The major browser app may also monitor browser usage in real time and adjust the timing of summary display according to the user's behavioral patterns. For example, the major browser app may learn the time the user places the cursor on a link and display summaries at the optimal timing. This allows the major browser app to learn the user's browsing patterns and display summaries at the optimal timing, thereby providing the user with the most appropriate information.

[0038] The browser extension can simultaneously display related news and articles when the user hovers the cursor over the link containing a specific keyword. The browser extension is developed with a function that displays related news and articles when the user hovers the cursor over a link containing a specific keyword. For example, when the cursor is hovers over a link to a news site, related articles are displayed. Furthermore, a user can set keywords of interest, and when the cursor is hovers over a link containing that keyword, related information is displayed. For example, news is displayed based on the keywords set by the user. Furthermore, a system is constructed that simultaneously displays linked content and related news and articles through the browser extension. For example, the content of the linked content is analyzed and related information is automatically displayed. As a result, when the cursor is hovers over a link containing a specific keyword, related news and articles are also displayed simultaneously, allowing the user to efficiently obtain related information.

[0039] The summary display function can extend the summary display function of the major browser app to the desktop application or the mobile application. For example, the summary display function of the major browser app is integrated into a desktop application to display a summary of the contents of a link destination. For example, the summary display function is added to a desktop email client or a document management app. Furthermore, the summary display function is introduced into a mobile application to display a summary of the contents of a link destination. For example, the summary display function is added to a mobile news app or a mobile social networking app. Furthermore, the summary display function is extended to both desktop and mobile applications, allowing users to efficiently check the contents of a link destination on any device. For example, a cross-platform summary display function is provided. By extending the summary display function to desktop applications and mobile applications, users can efficiently check information on any device.

[0040] The summary display function of the browser can be provided with a function that works in conjunction with the voice assistant and reads the summary aloud. For example, the summary display function of the browser can be developed to work in conjunction with a voice assistant and read the contents of the linked destination aloud. For example, a function that works in conjunction with Google Assistant or Amazon Alexa to read the summary aloud can be developed. Also, a system can be built in which the voice assistant automatically reads the summary aloud when the user places the cursor over a link. For example, the summary is played aloud as soon as the user touches the link. Also, an option to enable the summary reading function can be provided from the settings menu of the voice assistant. For example, the user can customize the settings of the voice assistant to enable summary reading. In this way, by working in conjunction with the voice assistant and reading the summary aloud, the user can efficiently obtain information even in situations where they cannot visually confirm the information.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The browser system can also analyze the user's browsing history and customize the linked summary based on the content of previously visited pages. For example, for links to news sites frequently visited by the user, the system can prioritize displaying information related to a specific category on that site. It can also filter the linked content based on keywords previously searched by the user, and include more relevant information in the summary. Furthermore, the system can learn the user's browsing patterns and adjust the summary display content according to specific times of day or days of the week. This allows the system to utilize the user's past behavioral data to provide more personalized summaries.

[0043] The link destination content analyzer can also analyze the content of linked images and videos to generate summaries that include visual elements. For example, it can analyze linked images to extract key objects and scenes and incorporate them into the summary. It can also analyze the content of videos to extract important scenes and segments to generate summaries. It can also analyze linked interactive elements (e.g., forms and buttons) to include their functions and purposes in the summary. This makes it possible to provide comprehensive summaries that take into account the visual and interactive elements of linked content.

[0044] The summary generator can also customize the content of the linked page based on the user's current geographic location. For example, if the user is in a particular area, the summary can prioritize information related to that area. It can also incorporate local events and news into the summary based on the user's location. Furthermore, the summary generator can utilize the user's location to generate a summary that shows how the linked page relates to the user's current situation. This allows the user to receive more relevant information based on their current geographic location.

[0045] The summary generation unit can analyze the linked video or audio content and generate a summary of the video or a transcript of the audio. For example, the generation AI analyzes the linked video content and extracts important scenes and segments to generate a summary. For example, the summary is displayed along with a thumbnail of the video. Alternatively, speech recognition technology can be used to convert the linked audio content into a transcript and display it as a summary. For example, the content of a podcast can be summarized in text. Alternatively, metadata of the video or audio content can be analyzed to extract important information and reflect it in the summary. For example, a summary can be generated based on the video title or description. This allows users to efficiently understand the content by analyzing the linked video or audio content and generating summaries or transcripts.

[0046] The summary generator can also integrate with the user's social media accounts to prioritize the inclusion of links shared by the user's followers and friends in the summary. For example, it can display summaries of news articles and blog posts shared by the user's friends. It can also generate summaries of links related to topics of interest based on the user's social media activity history. Furthermore, it can analyze the user's social media reactions (e.g., likes and comments) and customize the summary content based on those reactions. This allows the user to receive more relevant information based on their social media activity.

[0047] Generative AI models can also be developed to be specialized for specific industries or fields, and to handle the terminology and formats of those fields. For example, a generative AI model specialized for the medical field can be developed and trained to handle medical terminology and medical record formats. A generative AI model specialized for the legal field can also be developed to handle legal terminology and case law formats. Furthermore, a generative AI model specialized for the education field can be developed to analyze educational terminology and the formats of teaching materials. By developing a generative AI model specialized for a specific industry or field, it is possible to generate summaries with higher accuracy.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The link destination content analyzer analyzes the content of the linked page. For example, it analyzes the HTML structure of the linked page and extracts important information based on heading tags and paragraph tags. It can also use the linked page's metadata to extract a page summary and keywords. It can also analyze the style sheets and scripts used on the linked page to accurately determine the content that will be displayed. Step 2: The summary generator generates a summary based on the content analyzed by the link destination content analyzer. For example, the generation AI may use a text generation AI (e.g., LLM) to concisely summarize the content of the link destination. The generation AI may also use a multimodal generation AI to summarize the content of the link destination. The generation AI may also extract and summarize important parts of the text. Step 3: The display unit displays the summary generated by the summary generator in a balloon format. For example, the shape, color, and display position of the balloon can be customized. The display unit can also automatically display the summary when the user places the cursor on a link (or touches and holds it).

[0050] (Example 2) The browser system according to the embodiment of the present invention is a system in which the content of the linked page is displayed in a speech bubble when the cursor is placed on the link (or when a long press is performed). This allows the user to check the overview of the linked page without having to jump to the linked page, thereby saving time.

[0051] A browser system according to an embodiment includes a link destination content analysis unit, a summary generation unit, and a display unit. The link destination content analysis unit analyzes the content of the link destination. For example, it analyzes the HTML structure of the link destination and extracts important information based on heading tags and paragraph tags. It can also extract a page summary and keywords by utilizing metadata of the link destination. It can also analyze the style sheets and scripts used in the linked page to accurately determine the content to be displayed. The summary generation unit generates a summary based on the content analyzed by the link destination content analysis unit. For example, the generation AI uses a text generation AI (e.g., LLM) to concisely summarize the content of the link destination. The generation AI can also summarize the content of the link destination using a multimodal generation AI. The generation AI can also extract and summarize important parts of a sentence. The display unit displays the summary generated by the summary generation unit in a speech bubble format. For example, the shape, color, and display position of the speech bubble can be customized. The display unit can automatically display the summary when the user places the cursor over (or touches and holds) a link. As a result, the browser system according to the embodiment allows the user to check the overview without jumping to the linked page, thereby saving time.

[0052] The link content analysis unit can generate summaries based on the linked page structure and metadata. For example, the link content analysis unit uses a generation AI to analyze the HTML structure of the linked page and extract important information based on heading and paragraph tags. For example, it prioritizes including the content of h1 and h2 tags in the summary. It also utilizes the linked page's metadata to extract a page summary and keywords, which are reflected in the summary. For example, it analyzes the content of the meta tag's description and keywords. It also analyzes the style sheets and scripts used on the linked page to accurately determine the content to be displayed. For example, it generates summaries taking into account the influence of CSS and JavaScript. This allows for the generation of more accurate summaries by taking the linked page structure and metadata into account.

[0053] The summary generation unit can generate a customized summary based on the user's past browsing history or interests. The summary generation unit, for example, analyzes the user's past browsing history and extracts related keywords and topics to reflect in the summary. For example, it prioritizes displaying information from frequently viewed categories. It also customizes the content of the summary based on the user's interests. For example, it highlights information related to topics that interest the user. It also references the user's past search history and includes related search keywords in the summary. For example, it displays in detail the content of links that contain keywords searched for in the past. In this way, by generating a customized summary based on the user's past browsing history and interests, it is possible to provide the user with more useful information.

[0054] The summary generation unit uses the emotion estimation function to evaluate the emotional impact that the linked content has on the user and can prioritize displaying positive content. For example, the summary generation unit uses a generation AI to analyze the text of the linked page and perform emotion analysis. For example, it extracts words and phrases that indicate positive emotions and reflects them in the summary. It also uses the emotion estimation function to evaluate the emotional impact that the linked content has on the user and prioritize displaying positive content. For example, it highlights positive news and articles that users like. Furthermore, if the linked content evokes negative emotions, it omits that part and generates a summary centered on positive elements. For example, it avoids negative news and prioritizes displaying positive information. In this way, the emotion estimation function can prioritize displaying content that has a positive impact on the user.

[0055] The summary generation unit can analyze the linked video or audio content and generate a summary of the video or a transcript of the audio. For example, the summary generation unit uses a generation AI to analyze the linked video content and extract important scenes and segments to generate a summary. For example, the summary generation unit displays a summary along with a thumbnail of the video. It also uses speech recognition technology to convert the linked audio content into a transcript and display it as a summary. For example, it summarizes the contents of a podcast in text. It also analyzes the metadata of the video or audio content, extracts important information, and reflects it in the summary. For example, it generates a summary based on the video title or description. By analyzing the linked video or audio content and generating a summary or transcript, users can efficiently understand the content.

[0056] The summary generation unit can also display a summary of the content of the link destination in an email client or messaging app. The summary generation unit, for example, integrates a summary display function into an email client, and displays a summary of the content of the link destination when the cursor is placed on a link in an email. For example, the summary generation unit analyzes links in the email body and displays a summary. Also, a summary display function is added to a messaging app, and a summary of the content of the link destination is displayed when a link in a message is touched and held. For example, a link in a chat is analyzed and displayed as a summary. Also, the content of an email or message is analyzed, and a summary of the link destination is automatically generated. For example, the content of the link destination is summarized based on the subject and body of the email. In this way, a summary of the content of the link destination can be displayed in an email client or messaging app, allowing the user to efficiently grasp information.

[0057] The summary generation unit uses an emotion estimation function to estimate the emotion of the user when the user places the cursor on a link in real time, and can display a summary according to the user's emotion. For example, the summary generation unit uses the emotion estimation function to analyze the emotion in real time when the user places the cursor on a link. For example, the summary generation unit calculates an emotion score by analyzing the user's facial expression and voice. Furthermore, the summary generation unit displays a summary according to the user's emotion based on the emotion estimation data. For example, if the user is expressing positive emotion, positive content is emphasized. Furthermore, the summary generation unit monitors the user's emotional response in real time and dynamically adjusts the summary display according to the emotion. For example, if the user is expressing negative emotion, positive information is displayed preferentially. In this way, by displaying a summary according to the user's emotion, more appropriate information can be provided to the user.

[0058] The generative AI model can be specialized for local government websites and can handle the terminology or format specific to the bidding project or the minutes. For example, a generative AI model specialized for local government websites can be developed and trained to learn the terminology specific to bidding projects and minutes. For example, it can analyze terminology and formats specific to the local government. The format of the bidding project or minutes can also be analyzed, and the generative AI can generate a summary that corresponds to that format. For example, it can generate a summary for each item in the minutes. The generative AI can also be trained using a dataset specialized for local government websites to generate highly accurate summaries. For example, past bidding projects and minutes can be used as learning data. In this way, by developing a generative AI model specialized for local government websites, it is possible to generate summaries that correspond to the terminology and format specific to bidding projects and minutes.

[0059] The linked content analysis unit can generate a more comprehensive summary by referencing related laws and regulations when analyzing the linked content of the local government's website. For example, when analyzing the linked content of a local government's website, the linked content analysis unit automatically references related laws and regulations and reflects them in the summary. For example, laws and regulations related to bidding projects are included in the summary. A database of laws and regulations is also integrated into the generation AI and referenced when analyzing the linked content. For example, a summary is generated based on the local government's rules and ordinances. A comprehensive summary is also generated by cross-referencing the linked content of the local government's website with related laws and regulations. For example, the contents of the minutes of a meeting and related laws and regulations are displayed simultaneously. This allows a more comprehensive summary to be generated by also referencing related laws and regulations.

[0060] The summary generation unit can evaluate the emotional impact that the content of the local government's homepage has on citizens and prioritize displaying positive information. The summary generation unit, for example, analyzes the content of the local government's homepage and evaluates the emotional impact on citizens using an emotion estimation function. For example, it prioritizes displaying positive news and information. Furthermore, it customizes the content of the local government's homepage based on the emotion estimation data and emphasizes positive information. For example, it displays positive topics that interest citizens. Furthermore, it analyzes the content of links on the local government's homepage and prioritizes including positive information in the summary using the emotion estimation function. For example, it emphasizes news that evokes positive emotions. In this way, it is possible to provide useful information to citizens by evaluating the emotional impact that the content of the local government's homepage has on citizens and prioritize displaying positive information.

[0061] The summary generation unit can integrate the summary display function of the local government's homepage into the smart city's information provision system, allowing citizens to quickly obtain the information they need. The summary generation unit, for example, integrates the summary display function into the smart city's information provision system, allowing citizens to quickly check the content of linked destinations. For example, it displays a summary of information on public services. The summary display function of the local government's homepage can also be incorporated into a smart city app, allowing citizens to efficiently obtain the information they need. For example, it displays summaries of traffic information and event information. A generative AI model specialized for the smart city's information provision system can be developed to analyze the content of linked destinations on the local government's homepage and generate summaries. For example, summaries can be generated based on the smart city's database. In this way, by integrating the summary display function into the smart city's information provision system, citizens can quickly obtain the information they need.

[0062] The summary generation unit can collect citizens' emotional reactions to the content of the links on the local government's homepage and use this as a reference for the policy decision-making. The summary generation unit, for example, collects citizens' emotional reactions to the content of the links on the local government's homepage and uses this data as a reference for policy decision-making. For example, it prioritizes the implementation of policies that receive a lot of positive reactions. It also uses an emotion estimation function to collect citizens' emotional reactions in real time and improve the content of the local government's homepage. For example, it corrects information that receives a lot of negative reactions. It also builds a system that improves the local government's policy-making process based on citizens' emotional reaction data. For example, it determines policy priorities based on emotion scores. In this way, by collecting citizens' emotional reactions and using them as a reference for policy decision-making, it is possible to realize policies that are more in line with citizens.

[0063] The major browser app can be equipped with an algorithm that learns the user's browsing patterns and displays summaries at the optimal timing. The major browser app, for example, analyzes the user's browsing patterns and develops an algorithm that displays summaries at the optimal timing. For example, the major browser app may display summaries the moment the user places the cursor on a link. The major browser app may also customize the timing of summary display based on the user's browsing history. For example, summaries may be displayed immediately for links to frequently visited sites. The major browser app may also monitor browser usage in real time and adjust the timing of summary display according to the user's behavioral patterns. For example, the major browser app may learn the time the user places the cursor on a link and display summaries at the optimal timing. This allows the major browser app to learn the user's browsing patterns and display summaries at the optimal timing, thereby providing the user with the most appropriate information.

[0064] The browser extension can simultaneously display related news and articles when the user hovers the cursor over the link containing a specific keyword. The browser extension is developed with a function that displays related news and articles when the user hovers the cursor over a link containing a specific keyword. For example, when the cursor is hovers over a link to a news site, related articles are displayed. Furthermore, a user can set keywords of interest, and when the cursor is hovers over a link containing that keyword, related information is displayed. For example, news is displayed based on the keywords set by the user. Furthermore, a system is constructed that simultaneously displays linked content and related news and articles through the browser extension. For example, the content of the linked content is analyzed and related information is automatically displayed. As a result, when the cursor is hovers over a link containing a specific keyword, related news and articles are also displayed simultaneously, allowing the user to efficiently obtain related information.

[0065] The emotion estimation function estimates the emotion of the user when the user places the cursor over the link in real time, and can customize the browser interface according to the user's emotion. For example, the emotion estimation function analyzes the emotion of the user when the user places the cursor over a link in real time and customizes the browser interface. For example, if the user is expressing positive emotion, the theme is changed to a bright one. We also develop a system that dynamically adjusts the browser interface based on the user's emotional response. For example, if the user is expressing negative emotion, the interface is changed to a relaxing one. We also collect emotion estimation data in real time and customize the browser according to the user's emotion. For example, the font size and color are adjusted according to the user's emotion. This makes it possible to customize the browser interface according to the user's emotion, thereby providing the user with a comfortable browsing experience.

[0066] The summary display function can extend the summary display function of the major browser app to the desktop application or the mobile application. For example, the summary display function of the major browser app is integrated into a desktop application to display a summary of the contents of a link destination. For example, the summary display function is added to a desktop email client or a document management app. Furthermore, the summary display function is introduced into a mobile application to display a summary of the contents of a link destination. For example, the summary display function is added to a mobile news app or a mobile social networking app. Furthermore, the summary display function is extended to both desktop and mobile applications, allowing users to efficiently check the contents of a link destination on any device. For example, a cross-platform summary display function is provided. By extending the summary display function to desktop applications and mobile applications, users can efficiently check information on any device.

[0067] The summary display function of the browser can be provided with a function that works in conjunction with the voice assistant and reads the summary aloud. For example, the summary display function of the browser can be developed to work in conjunction with a voice assistant and read the contents of the linked destination aloud. For example, a function that works in conjunction with Google Assistant or Amazon Alexa to read the summary aloud can be developed. Also, a system can be built in which the voice assistant automatically reads the summary aloud when the user places the cursor over a link. For example, the summary is played aloud as soon as the user touches the link. Also, an option to enable the summary reading function can be provided from the settings menu of the voice assistant. For example, the user can customize the settings of the voice assistant to enable summary reading. In this way, by working in conjunction with the voice assistant and reading the summary aloud, the user can efficiently obtain information even in situations where they cannot visually confirm the information.

[0068] The emotion estimation function can monitor the emotion of the user when the cursor hovers over the link in real time, and display the advertisement or content according to the user's emotion. For example, the emotion estimation function develops a system that analyzes the emotion of the user when the cursor hovers over a link in real time, and displays advertisements according to the emotion. For example, if the user shows positive emotion, relevant advertisements are displayed. Also, a system is constructed that dynamically adjusts content in the browser based on the user's emotional response. For example, if the user shows negative emotion, relaxing content is displayed. Also, a system is developed that collects emotion estimation data in real time, and displays advertisements and content according to the user's emotion. For example, the content of advertisements is customized to match the user's emotion. As a result, more appropriate information can be provided to the user by displaying advertisements and content according to the user's emotion.

[0069] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0070] The browser system can also analyze the user's browsing history and customize the linked summary based on the content of previously visited pages. For example, for links to news sites frequently visited by the user, the system can prioritize displaying information related to a specific category on that site. It can also filter the linked content based on keywords previously searched by the user, and include more relevant information in the summary. Furthermore, the system can learn the user's browsing patterns and adjust the summary display content according to specific times of day or days of the week. This allows the system to utilize the user's past behavioral data to provide more personalized summaries.

[0071] The link destination content analyzer can also analyze the content of linked images and videos to generate summaries that include visual elements. For example, it can analyze linked images to extract key objects and scenes and incorporate them into the summary. It can also analyze the content of videos to extract important scenes and segments to generate summaries. It can also analyze linked interactive elements (e.g., forms and buttons) to include their functions and purposes in the summary. This makes it possible to provide comprehensive summaries that take into account the visual and interactive elements of linked content.

[0072] The summary generator can also customize the content of the linked page based on the user's current geographic location. For example, if the user is in a particular area, the summary can prioritize information related to that area. It can also incorporate local events and news into the summary based on the user's location. Furthermore, the summary generator can utilize the user's location to generate a summary that shows how the linked page relates to the user's current situation. This allows the user to receive more relevant information based on their current geographic location.

[0073] The summary generator can also use its emotion estimation function to evaluate the emotional impact of the linked content on the user and generate a summary that matches the user's current emotional state. For example, if the user is feeling stressed, it will prioritize displaying relaxing content. If the user is excited, it will emphasize positive information that will maintain that excitement. Furthermore, it is possible to omit part of the linked content depending on the user's emotional state and provide the most useful information for the user. This makes it possible to provide a summary that is customized according to the user's emotional state.

[0074] The summary generation unit can analyze the linked video or audio content and generate a summary of the video or a transcript of the audio. For example, the generation AI analyzes the linked video content and extracts important scenes and segments to generate a summary. For example, the summary is displayed along with a thumbnail of the video. Alternatively, speech recognition technology can be used to convert the linked audio content into a transcript and display it as a summary. For example, the content of a podcast can be summarized in text. Alternatively, metadata of the video or audio content can be analyzed to extract important information and reflect it in the summary. For example, a summary can be generated based on the video title or description. This allows users to efficiently understand the content by analyzing the linked video or audio content and generating summaries or transcripts.

[0075] The summary generator can also integrate with the user's social media accounts to prioritize the inclusion of links shared by the user's followers and friends in the summary. For example, it can display summaries of news articles and blog posts shared by the user's friends. It can also generate summaries of links related to topics of interest based on the user's social media activity history. Furthermore, it can analyze the user's social media reactions (e.g., likes and comments) and customize the summary content based on those reactions. This allows the user to receive more relevant information based on their social media activity.

[0076] The summary generation unit can use an emotion estimation function to estimate the emotion of the user when the user places the cursor on a link in real time, and display a summary according to the user's emotion. For example, when the user places the cursor on a link, the emotion estimation function is used to analyze the emotion in real time. For example, the emotion score is calculated by analyzing the user's facial expression and voice. Furthermore, the summary generation unit displays a summary according to the user's emotion based on the emotion estimation data. For example, if the user is expressing positive emotion, positive content is emphasized. Furthermore, the emotional response of the user is monitored in real time, and the summary display according to the emotion is dynamically adjusted. For example, if the user is expressing negative emotion, positive information is displayed preferentially. In this way, by displaying a summary according to the user's emotion, more appropriate information can be provided to the user.

[0077] Generative AI models can also be developed to be specialized for specific industries or fields, and to handle the terminology and formats of those fields. For example, a generative AI model specialized for the medical field can be developed and trained to handle medical terminology and medical record formats. A generative AI model specialized for the legal field can also be developed to handle legal terminology and case law formats. Furthermore, a generative AI model specialized for the education field can be developed to analyze educational terminology and the formats of teaching materials. By developing a generative AI model specialized for a specific industry or field, it is possible to generate summaries with higher accuracy.

[0078] The link destination content analysis unit can also evaluate the impact of the linked content on the user's health condition and prioritize health-related information in the summary. For example, if the linked content contains health advice or information, that part can be highlighted and reflected in the summary. Also, if the linked content may have a negative impact on health, that part can be omitted and information more useful to the user can be provided. Furthermore, based on data on the user's health condition, a summary can be generated that shows how the linked content is relevant to the user. This makes it possible to provide a summary that takes the user's health condition into consideration.

[0079] The summary generation unit can use the emotion estimation function to evaluate the emotional impact that the content of the local government's homepage has on citizens and prioritize displaying positive information. For example, the content of the local government's homepage can be analyzed and the emotion estimation function can be used to evaluate the emotional impact on citizens. For example, positive news and information can be prioritized and displayed. The content of the local government's homepage can be customized based on the emotion estimation data to emphasize positive information. For example, positive topics that interest citizens can be displayed. The content of links on the local government's homepage can be analyzed and positive information can be prioritized and included in the summary using the emotion estimation function. For example, news that evokes positive emotions can be emphasized. In this way, the emotional impact that the content of the local government's homepage has on citizens can be evaluated and positive information can be prioritized and displayed, thereby providing useful information to citizens.

[0080] The processing flow of the second embodiment will be briefly explained below.

[0081] Step 1: The link destination content analyzer analyzes the content of the linked page. For example, it analyzes the HTML structure of the linked page and extracts important information based on heading tags and paragraph tags. It can also use the linked page's metadata to extract a page summary and keywords. It can also analyze the style sheets and scripts used on the linked page to accurately determine the content that will be displayed. Step 2: The summary generator generates a summary based on the content analyzed by the link destination content analyzer. For example, the generation AI may use a text generation AI (e.g., LLM) to concisely summarize the content of the link destination. The generation AI may also use a multimodal generation AI to summarize the content of the link destination. The generation AI may also extract and summarize important parts of the text. Step 3: The display unit displays the summary generated by the summary generator in a balloon format. For example, the shape, color, and display position of the balloon can be customized. The display unit can also automatically display the summary when the user places the cursor on a link (or touches and holds it).

[0082] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0083] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0084] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0085] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0086] 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.

[0087] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0088] 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.

[0089] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0090] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0091] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0092] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0093] 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.

[0094] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0095] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0096] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0097] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0098] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0099] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0100] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0101] 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.

[0102] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0103] 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.

[0104] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0105] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0106] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0107] 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.

[0108] 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.

[0109] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0110] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0111] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0112] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0113] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0114] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0115] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0116] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0117] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0118] 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.

[0119] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0121] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0122] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0123] 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.

[0124] 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.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0126] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0127] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0128] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0130] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0131] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0132] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0133] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0134] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0135] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0136] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0137] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0138] 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.

[0139] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0140] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0141] 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.

[0142] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0143] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0144] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0145] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0146] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0147] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0148] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0149] 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 system comprising: a link destination content analysis unit that analyzes the content of a link destination; a summary generation unit that generates a summary based on the content analyzed by the link destination content analysis unit; and a display unit that displays the summary generated by the summary generation unit in speech bubble format.

2. 2. The system according to claim 1, wherein the link destination content analysis unit generates a summary based on the page structure and metadata of the linked page.

3. The system of claim 1 , wherein the summary generator analyzes the linked video or audio content and generates a summary of the video or a transcript of the audio.

4. The system of claim 1, wherein the generative AI model is specialized for local government homepages and corresponds to the specific terminology or format of bidding proposals or meeting minutes.

5. The system of claim 1 , wherein the major browser app includes an algorithm that learns a user's browsing patterns and displays summaries at optimal times.

6. 2. The system according to claim 1, wherein the summary generator evaluates the emotional impact that the content of the linked page has on the user, and displays positive content with priority.

7. 2. The system according to claim 1, wherein the summary generation unit evaluates the emotional impact that the content of the local government's homepage has on citizens and displays positive information preferentially.

8. The system according to claim 1, wherein the emotion estimation function estimates the emotion of the user when the user places the cursor over a link in real time and customizes the browser interface according to the user's emotion.

Images