system

Abstract

The system according to the embodiment aims to impose appropriate restrictions and filters on information on the Internet. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, a filter unit, and a management unit. The collection unit collects information on the Internet. The analysis unit analyzes the information collected by the collection unit. The filter unit applies restrictions and filters based on the information analyzed by the analysis unit. The management unit provides the user with the information restricted by the filter unit.

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 technologies make it difficult to impose appropriate restrictions and filters on information on the internet, leading to risks such as misinformation and copyright issues.

[0005] The system according to the embodiment aims to impose appropriate restrictions and filters on information on the Internet. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a filter unit, and a management unit. The collection unit collects information on the Internet. The analysis unit analyzes the information collected by the collection unit. The filter unit applies restrictions and filters based on the information analyzed by the analysis unit. The management unit provides the user with the information restricted by the filter unit. [Effects of the Invention]

[0007] The system according to the embodiment can impose appropriate restrictions and filters on information on the Internet. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A censorship system according to an embodiment of the present invention integrates online information with multiple AIs to address issues such as the learning and output of false information, copyright and portrait rights issues, and the fact that the creator is an AI. This censorship system provides an environment in which users can use AI with peace of mind. Specifically, it includes a collection unit that collects online information, an analysis unit that analyzes the collected information, a filter unit that applies restrictions and filters based on the analyzed information, and a management unit that provides users with information restricted by the filter unit. For example, the collection unit collects information from news sites, blogs, social media, etc. The analysis unit analyzes the collected information and identifies false information and issues related to copyright and portrait rights. The filter unit prevents the display of articles containing false information and blocks images and videos with copyright issues. The management unit ensures that the information searched by users is reliable. In this way, a censorship system using multiple AIs integrates online information with multiple AIs to address issues such as the learning and output of false information, copyright and portrait rights issues, and the fact that the creator is an AI, thereby providing an environment in which users can use AI with peace of mind. This censorship system provides an environment in which users can use AI with peace of mind.

[0029] The censorship system according to this embodiment comprises a collection unit, an analysis unit, a filter unit, and a management unit. The collection unit collects information from the internet. The collection unit collects information from sources such as news sites, blogs, and social networking services (SNS). The collection unit can obtain data using crawling technology or APIs. For example, the collection unit periodically checks the RSS feeds of news sites and collects new articles. The collection unit can also obtain the latest posts using blog APIs. Furthermore, the collection unit can collect user posts using SNS APIs. The analysis unit analyzes the collected information. For example, the analysis unit uses text analysis technology to analyze the content of news articles and identify misinformation and issues related to copyright and portrait rights. The analysis unit can also use image analysis technology to verify the copyright of images and videos. For example, the analysis unit uses fact-checking algorithms to determine whether the content of news articles is factual. The analysis unit can also use image recognition technology to verify the copyright of images and videos. The filter unit applies restrictions and filters based on the analyzed information. For example, the filter unit prevents the display of articles containing misinformation. The filtering unit can identify articles containing false information using keyword filtering technology and restrict their display. The filtering unit can also block images and videos that infringe on copyright. For example, it can use image recognition technology to identify and block images and videos that infringe on copyright. The management unit provides users with information restricted by the filtering unit. For example, the management unit ensures that the information searched by the user is reliable. The management unit can display reliable information through the user interface. For example, it can display reliable news articles and blog posts based on keywords searched by the user. The management unit can also manage the user's browsing history and prioritize the display of reliable information. Thus, the censorship system according to this embodiment can provide users with an environment in which they can use AI with peace of mind.

[0030] The data collection unit can collect information from news sites, blogs, or social media. For example, the data collection unit can periodically check the RSS feeds of news sites and collect new articles. The data collection unit can also use blog APIs to retrieve the latest posts. For example, the data collection unit can use the API of a specific blog platform to collect the latest posts. The data collection unit can also use social media APIs to collect user posts. For example, the data collection unit can use the API of a specific social media platform to collect user posts. This allows for broad coverage of information by collecting information from diverse sources. Some or all of the above processes in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input the RSS feeds of news sites into an AI and have the AI ​​collect new articles.

[0031] The analysis unit can analyze the collected information and identify misinformation or copyright / portrait rights issues. For example, the analysis unit can use text analysis technology to analyze the content of news articles and identify misinformation or copyright / portrait rights issues. For example, the analysis unit can use fact-checking algorithms to determine whether the content of news articles is factual. The analysis unit can also use image analysis technology to verify the copyright of images and videos. For example, the analysis unit can use image recognition technology to verify the copyright of images and videos. Furthermore, the analysis unit can use machine learning algorithms to evaluate the reliability of the collected information. For example, the analysis unit can calculate a reliability score for the collected information and identify unreliable information. This allows for the provision of reliable information by identifying misinformation and copyright issues. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the collected information into AI and have the AI ​​perform the identification of misinformation and copyright issues.

[0032] The filter unit can prevent the display of articles containing false information. For example, the filter unit can identify and restrict the display of articles containing false information using keyword filtering technology. For instance, the filter unit can filter articles containing specific keywords and restrict their display. The filter unit can also identify and restrict the display of articles that are likely to contain false information using a scoring system. For example, the filter unit can calculate a reliability score for articles and prevent the display of articles with low scores. Furthermore, the filter unit can use machine learning algorithms to identify and restrict the display of false information. For example, the filter unit can use machine learning models to identify and restrict the display of articles that are likely to contain false information. This eliminates false information, thereby providing users with reliable information. Some or all of the above processing in the filter unit may be performed using AI, or not. For example, the filter unit can input collected articles into an AI and have the AI ​​identify and restrict the display of false information.

[0033] The filter unit can block images or videos with copyright issues. For example, the filter unit can use image recognition technology to identify images or videos with copyright issues and block their display. For example, the filter unit can use a specific image recognition algorithm to identify images or videos with copyright issues and block their display. The filter unit can also identify images or videos with copyright issues based on legal standards and block their display. For example, the filter unit can identify images or videos with copyright issues based on copyright law and block their display. The filter unit can also use a machine learning algorithm to identify images or videos with copyright issues and block their display. For example, the filter unit can use a machine learning model to identify images or videos with copyright issues and block their display. This can avoid copyright issues and reduce legal risks. Some or all of the above-mentioned processing in the filter unit can be performed using, for example, AI, or without AI. For example, the filter unit can input collected images and videos into AI and have the AI ​​identify copyright issues and block their display.

[0034] The management unit can ensure that the information searched by the user is reliable. For example, the management unit displays reliable news articles and blog posts based on keywords searched by the user. For example, the management unit prioritizes displaying information from information sources with a specific reliability score. The management unit can also manage the history of information viewed by the user and prioritize displaying reliable information. For example, the management unit displays reliable information based on the user's browsing history. Furthermore, the management unit can display reliable information through a user interface. For example, the management unit displays reliable news articles and blog posts based on keywords searched by the user. This provides an environment in which the user can use information with peace of mind. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input keywords searched by the user into AI and cause the AI ​​to display reliable information.

[0035] The collection unit can evaluate the reliability of information at the time of collection and prioritize collection from reliable sources. The collection unit, for example, evaluates the reliability of a news site and prioritizes collection of information from reliable sites. The collection unit can evaluate the reliability of the information source based on the reliability score. For example, the collection unit calculates the reliability score of a news site and collects information from reliable sites. The collection unit can also evaluate the reliability of blogs and prioritize collection of information from blogs written by experts. For example, the collection unit collects information from blogs written by experts based on the reliability score of the blog. The collection unit can also evaluate the reliability of social media and prioritize collection of information from official accounts. For example, the collection unit collects information based on the reliability score of official social media accounts. This prioritizes collection of reliable information, thereby improving the quality of information. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the reliability evaluation of the information source into AI and cause the AI ​​to collect information from reliable sources.

[0036] The collection unit can apply different collection algorithms depending on the type of information when collecting. For example, in the case of news articles, the collection unit applies an algorithm that prioritizes collecting the latest information. The collection unit can select an optimal collection algorithm depending on the type of information. For example, in collecting news articles, the collection unit applies an algorithm that prioritizes collecting the latest information. In addition, in the case of blog articles, the collection unit can apply an algorithm that collects information based on popularity and number of views. For example, in collecting blog articles, the collection unit applies an algorithm that collects information based on popularity and number of views. In addition, in the case of social media posts, the collection unit can apply an algorithm that collects information based on engagement rate. For example, in collecting social media posts, the collection unit applies an algorithm that collects information based on engagement rate. This enables optimal collection depending on the category of information. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input a collection algorithm depending on the type of information into AI and cause the AI ​​to perform optimal collection.

[0037] The collection unit can prioritize collecting highly relevant information by taking into account the user's geographical location information. For example, if the user is in a specific area, the collection unit prioritizes collecting news related to that area. The collection unit can evaluate the relevance of information based on the geographical location information and prioritize collecting highly relevant information. For example, the collection unit collects news related to the area based on the user's GPS data. Furthermore, if the user is traveling, the collection unit can prioritize collecting tourist information about the travel destination. For example, the collection unit collects tourist information about the travel destination based on the user's geographical location information. Furthermore, if the user is at an event venue, the collection unit can prioritize collecting information related to the event. For example, the collection unit collects information related to the event based on the user's geographical location information. This makes it possible to provide highly relevant information based on the user's geographical location information. Some or all of the above-described processing by the collection unit may be performed using, or without, AI. For example, the collection unit may input the user's geographical location information into AI and cause the AI ​​to collect highly relevant information.

[0038] The collection unit can analyze the user's social media activities and collect related information during collection. For example, if the user frequently uses a specific hashtag, the collection unit can collect information related to the hashtag. The collection unit can evaluate the relevance of information based on the social media activities and collect related information. For example, the collection unit can analyze the user's social media posts and collect information related to a specific hashtag. Furthermore, if the user follows a specific account, the collection unit can preferentially collect information from that account. For example, the collection unit can collect posts from the accounts the user follows. Furthermore, if the user posts frequently about a specific topic, the collection unit can collect information related to that topic. For example, the collection unit can analyze the content of the user's posts and collect information related to a specific topic. This makes it possible to provide related information based on the user's social media activities. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the user's social media activity data into AI and have the AI ​​collect related information.

[0039] The analysis unit can evaluate the reliability of information during analysis and exclude unreliable information. For example, the analysis unit can evaluate the reliability of news articles and exclude unreliable articles. The analysis unit can evaluate the reliability of information based on the reliability score and exclude unreliable information. For example, the analysis unit can calculate the reliability score of news articles and exclude unreliable articles. The analysis unit can also evaluate the reliability of blog articles and exclude unreliable blogs. For example, the analysis unit can exclude unreliable blogs based on the reliability score of the blog. The analysis unit can also evaluate the reliability of social media posts and exclude unreliable posts. For example, the analysis unit can exclude unreliable posts based on the reliability score of the social media posts. This eliminates unreliable information, thereby improving the reliability of the analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the collected information into AI and have the AI ​​exclude unreliable information.

[0040] The analysis unit can apply different analysis algorithms depending on the type of information during analysis. For example, in the case of a news article, the analysis unit applies an algorithm for fact-checking. The analysis unit can select the optimal analysis algorithm depending on the type of information. For example, the analysis unit applies an algorithm for fact-checking when analyzing a news article. The analysis unit can also apply an algorithm for evaluating the reliability of the content in the case of a blog article. For example, the analysis unit applies an algorithm for evaluating the reliability of the content in the case of a blog article. Furthermore, the analysis unit can also apply an algorithm for evaluating reliability based on the engagement rate in the case of a social media post. For example, the analysis unit applies an algorithm for evaluating reliability based on the engagement rate in the analysis of a social media post. This enables optimal analysis depending on the category of information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input an analysis algorithm depending on the type of information into AI and cause the AI ​​to perform the optimal analysis.

[0041] During analysis, the analysis unit can determine the priority of analysis based on the time of submission of information. The analysis unit, for example, prioritizes analysis of the latest news article. The analysis unit can determine the priority of information based on the time of submission and prioritize analysis of the latest information. For example, the analysis unit prioritizes analysis of the latest news article based on the time of submission of the news article. The analysis unit can also postpone information that was submitted earlier. For example, the analysis unit postpones analysis of information that was submitted earlier. Furthermore, the analysis unit can also prioritize analysis of information with high urgency. For example, the analysis unit prioritizes analysis of information with high urgency. This makes it possible to determine the priority based on the time of submission. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the time of submission of information to AI and have the AI ​​determine the priority.

[0042] The analysis unit can adjust the order of analysis based on the relevance of the information during analysis. For example, the analysis unit can prioritize the analysis of information related to topics of high interest to the user. The analysis unit can adjust the order of analysis based on the relevance of the information, prioritizing the analysis of highly relevant information. For example, the analysis unit can prioritize the analysis of information related to topics of high interest to the user. The analysis unit can also prioritize the analysis of highly relevant information based on the user's past search history. For example, the analysis unit can prioritize the analysis of highly relevant information based on the user's past search history. Furthermore, the analysis unit can also prioritize the analysis of information related to the user's current activities. For example, the analysis unit can prioritize the analysis of information related to the user's current activities. This makes it possible to adjust the order of analysis based on relevance. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the relevance of the information into the AI ​​and have the AI ​​perform the adjustment of the order of analysis.

[0043] The filtering unit can evaluate the reliability of information during filtering and exclude unreliable information. For example, the filtering unit can evaluate the reliability of news articles and exclude unreliable articles. The filtering unit can evaluate the reliability of information based on reliability scores and exclude unreliable information. For example, the filtering unit can calculate reliability scores for news articles and exclude unreliable articles. The filtering unit can also evaluate the reliability of blog posts and exclude unreliable blogs. For example, the filtering unit can exclude unreliable blogs based on their reliability scores. Furthermore, the filtering unit can evaluate the reliability of social media posts and exclude unreliable posts. For example, the filtering unit can exclude unreliable posts based on their reliability scores. This improves the reliability of the filtered results by excluding unreliable information. Some or all of the above processing in the filtering unit may be performed using AI, for example, or without AI. For example, the filtering unit can input the collected information into AI and have the AI ​​perform the exclusion of unreliable information.

[0044] The filter unit can apply different filter algorithms depending on the type of information during filtering. For example, in the case of news articles, the filter unit applies a filter algorithm for fact-checking. The filter unit can select the optimal filter algorithm depending on the type of information. For example, in filtering news articles, the filter unit applies a filter algorithm for fact-checking. The filter unit can also apply a filter algorithm that evaluates the reliability of the content in the case of blog posts. For example, in filtering blog posts, the filter unit applies a filter algorithm that evaluates the reliability of the content. Furthermore, in the case of social media posts, the filter unit can apply a filter algorithm that evaluates reliability based on the engagement rate. For example, in filtering social media posts, the filter unit applies a filter algorithm that evaluates reliability based on the engagement rate. This enables optimal filtering according to the category of information. Some or all of the above processing in the filter unit may be performed using AI, for example, or without AI. For example, the filter unit can input a filter algorithm according to the type of information into the AI ​​and have the AI ​​execute the optimal filter.

[0045] During filtering, the filter unit can determine the priority of the filter based on the time of submission of the information. For example, the filter unit prioritizes filtering the latest news articles. The filter unit can determine the priority of information based on the time of submission and prioritize filtering the latest information. For example, the filter unit prioritizes filtering the latest news articles based on the time of submission of the news articles. The filter unit can also postpone filtering information that was submitted earlier. For example, the filter unit filters information that was submitted earlier later. The filter unit can also prioritize filtering information that is highly urgent. For example, the filter unit prioritizes filtering information that is highly urgent. This makes it possible to determine the priority based on the time of submission. Some or all of the above-described processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can input the time of submission of information into AI and have the AI ​​determine the priority.

[0046] The filter unit can adjust the filter order based on the relevance of the information when filtering. For example, the filter unit prioritizes filtering information related to topics that the user is highly interested in. The filter unit can adjust the filter order based on the relevance of the information to prioritize filtering highly relevant information. For example, the filter unit prioritizes filtering information related to topics that the user is highly interested in. The filter unit can also prioritize filtering highly relevant information based on the user's past search history. For example, the filter unit prioritizes filtering highly relevant information based on the user's past search history. The filter unit can also prioritize filtering information related to the user's current activity. For example, the filter unit prioritizes filtering information related to the user's current activity. This enables adjustment of the filter order based on relevance. Some or all of the above-described processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can input the relevance of the information into AI and have the AI ​​adjust the filter order.

[0047] The management unit can evaluate the reliability of information during management and exclude low-reliability information. For example, the management unit evaluates the reliability of news articles and excludes low-reliability articles. The management unit can evaluate the reliability of information based on the reliability score and exclude low-reliability information. For example, the management unit calculates the reliability score of news articles and excludes low-reliability articles. The management unit can also evaluate the reliability of blog articles and exclude low-reliability blogs. For example, the management unit excludes low-reliability blogs based on the reliability score of the blog. Furthermore, the management unit can evaluate the reliability of social media posts and exclude low-reliability posts. For example, the management unit excludes low-reliability posts based on the reliability score of the social media posts. This eliminates low-reliability information, thereby improving the reliability of the management results. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input collected information into AI and have the AI ​​exclude low-reliability information.

[0048] The management unit can apply different management algorithms depending on the type of information during management. For example, in the case of news articles, the management unit applies a management algorithm for fact-checking. The management unit can select the optimal management algorithm depending on the type of information. For example, the management unit applies a management algorithm for fact-checking when managing news articles. The management unit can also apply a management algorithm for evaluating the reliability of content in the case of blog articles. For example, the management unit applies a management algorithm for evaluating the reliability of content in the case of blog articles. Furthermore, the management unit can also apply a management algorithm for evaluating reliability based on engagement rate in the case of social media posts. For example, the management unit applies a management algorithm for evaluating reliability based on engagement rate in the case of social media posts. This enables optimal management depending on the category of information. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input a management algorithm depending on the type of information into AI and have the AI ​​perform optimal management.

[0049] During management, the management unit can determine management priorities based on the time of submission of information. The management unit, for example, prioritizes managing the latest news articles. The management unit can determine the priority of information based on the time of submission and prioritize managing the latest information. For example, the management unit prioritizes managing the latest news articles based on the time of submission of the news articles. The management unit can also postpone information that was submitted earlier. For example, the management unit manages information that was submitted earlier later. Furthermore, the management unit can also prioritize managing information that is highly urgent. For example, the management unit prioritizes managing information that is highly urgent. This makes it possible to determine priorities based on the time of submission. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the time of submission of information into AI and have the AI ​​determine the priorities.

[0050] During management, the management unit can adjust the management order based on the relevance of the information. For example, the management unit prioritizes managing information related to topics that the user is highly interested in. The management unit can adjust the management order based on the relevance of the information and prioritize managing highly relevant information. For example, the management unit prioritizes managing information related to topics that the user is highly interested in. The management unit can also prioritize managing highly relevant information based on the user's past search history. For example, the management unit prioritizes managing highly relevant information based on the user's past search history. Furthermore, the management unit can also prioritize managing information related to the user's current activity. For example, the management unit prioritizes managing information related to the user's current activity. This makes it possible to adjust the management order based on the relevance. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the relevance of the information into AI and have the AI ​​adjust the management order.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The analysis unit can refer to the information source's past reliability history to evaluate the reliability of the collected information. For example, the analysis unit can prioritize news sites and blogs that have provided reliable information in the past. The analysis unit can also filter information from specific information sources based on the information source's reliability history. Furthermore, the analysis unit can calculate a reliability score for the information based on the information source's reliability history and exclude information with low reliability. This allows the analysis unit to utilize the past reliability history to perform a more accurate reliability evaluation.

[0053] The collection unit can customize information based on the user's interests. For example, the collection unit analyzes the user's past search history and browsing history to prioritize collection of information related to topics of interest to the user. The collection unit can also collect related information based on the social media accounts and blogs the user follows. Furthermore, the collection unit can collect the latest information on specific topics based on keyword alerts set by the user. This allows the collection unit to provide information tailored to the user's interests.

[0054] When evaluating the reliability of information, the analysis unit can evaluate not only the source of the information but also the content of the information itself. For example, the analysis unit can check whether the content of the information is consistent with other reliable information sources. The analysis unit can also check whether the content of the information is consistent with past facts. Furthermore, the analysis unit can evaluate whether the content of the information is consistent with expert opinions or research results. This allows the analysis unit to perform a more accurate reliability evaluation by evaluating the content of the information itself.

[0055] The filter unit can adjust the filter criteria based on user feedback. For example, if a user trusts a particular information source, the filter unit can preferentially display information from that information source. Also, if a user is interested in a particular topic, the filter unit can preferentially display information related to that topic. Furthermore, if a user determines that certain information is inappropriate, the filter unit can filter that information. This allows the filter unit to utilize user feedback to provide more appropriate information.

[0056] The management unit can analyze the user's behavioral patterns and optimize the method of providing information. For example, the management unit can analyze what time of day the user often views information and provide information tailored to that time of day. The management unit can also analyze which device the user often uses to view information and provide information in a format optimized for that device. Furthermore, the management unit can analyze which format of information the user prefers (text, image, video, etc.) and provide information in that format. This allows the management unit to provide information more effectively based on the user's behavioral patterns.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The collection unit collects information on the Internet. For example, the collection unit collects information from news sites, blogs, social networking sites, etc. The collection unit can obtain data using crawling technology or APIs. For example, the collection unit can periodically check the RSS feed of a news site to collect new articles. The collection unit can also obtain the latest posts using a blog's API. Furthermore, the collection unit can collect user posts using a social networking site's API. Step 2: The analysis unit analyzes the collected information. For example, the analysis unit uses text analysis technology to analyze the content of news articles and identify misinformation and issues related to copyright and portrait rights. The analysis unit can also use image analysis technology to check the copyright of images and videos. For example, the analysis unit uses fact-checking algorithms to determine whether the content of news articles is factual. The analysis unit can also use image recognition technology to check the copyright of images and videos. Step 3: The filter unit applies restrictions and filters based on the analyzed information. For example, the filter unit prevents articles containing false information from being displayed. The filter unit can identify articles containing false information using keyword filtering technology and restrict their display. The filter unit can also block images and videos with copyright issues. For example, the filter unit can identify images and videos with copyright issues using image recognition technology and block their display. Step 4: The management unit provides the user with information restricted by the filter unit. For example, the management unit ensures that the information searched by the user is reliable. The management unit can display reliable information through a user interface. For example, the management unit can display reliable news articles or blog posts based on keywords searched by the user. The management unit can also manage the history of information viewed by the user and prioritize displaying reliable information.

[0059] (Example 2) A censorship system according to an embodiment of the present invention integrates online information with multiple AIs to address issues such as the learning and output of false information, copyright and portrait rights issues, and the fact that the creator is an AI. This censorship system provides an environment in which users can use AI with peace of mind. Specifically, it includes a collection unit that collects online information, an analysis unit that analyzes the collected information, a filter unit that applies restrictions and filters based on the analyzed information, and a management unit that provides users with information restricted by the filter unit. For example, the collection unit collects information from news sites, blogs, social media, etc. The analysis unit analyzes the collected information and identifies false information and issues related to copyright and portrait rights. The filter unit prevents the display of articles containing false information and blocks images and videos with copyright issues. The management unit ensures that the information searched by users is reliable. In this way, a censorship system using multiple AIs integrates online information with multiple AIs to address issues such as the learning and output of false information, copyright and portrait rights issues, and the fact that the creator is an AI, thereby providing an environment in which users can use AI with peace of mind. This censorship system provides an environment in which users can use AI with peace of mind.

[0060] A censorship system according to an embodiment includes a collection unit, an analysis unit, a filter unit, and a management unit. The collection unit collects information from the Internet. For example, the collection unit collects information from news sites, blogs, social networking sites, and the like. The collection unit can acquire data using crawling technology or an API. For example, the collection unit periodically checks the RSS feed of a news site to collect new articles. The collection unit can also obtain the latest posts using a blog's API. The collection unit can also collect user posts using a social networking site's API. The analysis unit analyzes the collected information. For example, the analysis unit can analyze the content of news articles using text analysis technology to identify false information and issues related to copyright and portrait rights. The analysis unit can also check the copyright of images and videos using image analysis technology. For example, the analysis unit can use a fact-checking algorithm to determine whether the content of a news article is factual. The analysis unit can also check the copyright of images and videos using image recognition technology. The filter unit imposes restrictions and filters based on the analyzed information. For example, the filter unit can prevent articles containing false information from being displayed. The filter unit can identify articles containing false information using keyword filtering technology and restrict their display. The filter unit can also block images and videos with copyright issues. For example, the filter unit can use image recognition technology to identify images and videos with copyright issues and block their display. The management unit provides the user with information restricted by the filter unit. The management unit, for example, ensures that the information searched by the user is reliable. The management unit can display reliable information through a user interface. For example, the management unit can display reliable news articles and blog posts based on keywords searched by the user. The management unit can also manage the history of information viewed by the user and prioritize the display of reliable information. As a result, the censorship system according to the embodiment can provide an environment in which users can use AI with peace of mind.

[0061] The data collection unit can collect information from news sites, blogs, or social media. For example, the data collection unit can periodically check the RSS feeds of news sites and collect new articles. The data collection unit can also use blog APIs to retrieve the latest posts. For example, the data collection unit can use the API of a specific blog platform to collect the latest posts. The data collection unit can also use social media APIs to collect user posts. For example, the data collection unit can use the API of a specific social media platform to collect user posts. This allows for broad coverage of information by collecting information from diverse sources. Some or all of the above processes in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input the RSS feeds of news sites into an AI and have the AI ​​collect new articles.

[0062] The analysis unit can analyze the collected information and identify misinformation or copyright / portrait rights issues. For example, the analysis unit can use text analysis technology to analyze the content of news articles and identify misinformation or copyright / portrait rights issues. For example, the analysis unit can use fact-checking algorithms to determine whether the content of news articles is factual. The analysis unit can also use image analysis technology to verify the copyright of images and videos. For example, the analysis unit can use image recognition technology to verify the copyright of images and videos. Furthermore, the analysis unit can use machine learning algorithms to evaluate the reliability of the collected information. For example, the analysis unit can calculate a reliability score for the collected information and identify unreliable information. This allows for the provision of reliable information by identifying misinformation and copyright issues. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the collected information into AI and have the AI ​​perform the identification of misinformation and copyright issues.

[0063] The filter unit can prevent articles containing false information from being displayed. For example, the filter unit can use keyword filtering technology to identify articles containing false information and restrict their display. For example, the filter unit can filter articles containing specific keywords and restrict their display. The filter unit can also use a scoring system to identify articles that are likely to be false information and restrict their display. For example, the filter unit can calculate a credibility score for each article and prevent articles with a low score from being displayed. The filter unit can also use a machine learning algorithm to identify false information and restrict its display. For example, the filter unit can use a machine learning model to identify articles that are likely to be false information and restrict their display. This eliminates false information, thereby providing users with reliable information. Some or all of the above-described processing in the filter unit can be performed using, for example, AI, or without AI. For example, the filter unit can input collected articles into AI and have the AI ​​identify false information and restrict its display.

[0064] The filter unit can block images or videos with copyright issues. For example, the filter unit can use image recognition technology to identify images or videos with copyright issues and block their display. For example, the filter unit can use a specific image recognition algorithm to identify images or videos with copyright issues and block their display. The filter unit can also identify images or videos with copyright issues based on legal standards and block their display. For example, the filter unit can identify images or videos with copyright issues based on copyright law and block their display. The filter unit can also use a machine learning algorithm to identify images or videos with copyright issues and block their display. For example, the filter unit can use a machine learning model to identify images or videos with copyright issues and block their display. This can avoid copyright issues and reduce legal risks. Some or all of the above-mentioned processing in the filter unit can be performed using, for example, AI, or without AI. For example, the filter unit can input collected images and videos into AI and have the AI ​​identify copyright issues and block their display.

[0065] The management unit can ensure that the information searched by the user is reliable. For example, the management unit displays reliable news articles and blog posts based on keywords searched by the user. For example, the management unit prioritizes displaying information from information sources with a specific reliability score. The management unit can also manage the history of information viewed by the user and prioritize displaying reliable information. For example, the management unit displays reliable information based on the user's browsing history. Furthermore, the management unit can display reliable information through a user interface. For example, the management unit displays reliable news articles and blog posts based on keywords searched by the user. This provides an environment in which the user can use information with peace of mind. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input keywords searched by the user into AI and cause the AI ​​to display reliable information.

[0066] The censorship system further includes a collection unit that estimates a user's emotions and prioritizes information sources to be collected based on the estimated user emotions. For example, if the user is feeling anxious, the collection unit prioritizes collecting information from reliable news sites. The collection unit can estimate the user's emotions using a sentiment analysis algorithm and prioritize information sources based on the estimated emotions. For example, the collection unit estimates the user's emotions based on user feedback and collects information from reliable sources. Furthermore, if the user is relaxed, the collection unit can also collect information from blogs and social media in a balanced manner. For example, the collection unit collects information from blogs and social media according to the user's emotions. Furthermore, if the user is excited, the collection unit can prioritize collecting the latest trend information. For example, the collection unit collects the latest news and trend information based on the user's emotions. This enables information collection according to the user's emotions. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit may input the user's emotional data into AI and have the AI ​​determine the priority of information sources.

[0067] The collection unit can evaluate the reliability of information at the time of collection and prioritize collection from reliable sources. The collection unit, for example, evaluates the reliability of a news site and prioritizes collection of information from reliable sites. The collection unit can evaluate the reliability of the information source based on the reliability score. For example, the collection unit calculates the reliability score of a news site and collects information from reliable sites. The collection unit can also evaluate the reliability of blogs and prioritize collection of information from blogs written by experts. For example, the collection unit collects information from blogs written by experts based on the reliability score of the blog. The collection unit can also evaluate the reliability of social media and prioritize collection of information from official accounts. For example, the collection unit collects information based on the reliability score of official social media accounts. This prioritizes collection of reliable information, thereby improving the quality of information. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the reliability evaluation of the information source into AI and cause the AI ​​to collect information from reliable sources.

[0068] The data collection unit can apply different collection algorithms depending on the type of information during collection. For example, in the case of news articles, the data collection unit can apply an algorithm that prioritizes the collection of the latest information. The data collection unit can select the optimal collection algorithm depending on the type of information. For example, when collecting news articles, the data collection unit can apply an algorithm that prioritizes the collection of the latest information. In addition, in the case of blog posts, the data collection unit can apply an algorithm that collects information based on popularity or the number of views. For example, when collecting blog posts, the data collection unit can apply an algorithm that collects information based on popularity or the number of views. Furthermore, in the case of social media posts, the data collection unit can apply an algorithm that collects information based on the engagement rate. For example, when collecting social media posts, the data collection unit can apply an algorithm that collects information based on the engagement rate. This enables optimal collection according to the category of information. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input a collection algorithm according to the type of information into the AI ​​and have the AI ​​perform the optimal collection.

[0069] The collection unit can estimate the user's emotions and adjust the type of information to be collected based on the estimated user emotions. For example, if the user is feeling anxious, the collection unit can prioritize collecting information that provides a sense of security. The collection unit can estimate the user's emotions using an emotion analysis algorithm and adjust the type of information based on the estimated emotions. For example, the collection unit can estimate the user's emotions based on user feedback and collect information that provides a sense of security. Furthermore, if the user is relaxed, the collection unit can collect more entertainment information. For example, the collection unit can collect entertainment information according to the user's emotions. Furthermore, if the user is excited, the collection unit can prioritize collecting the latest news and trend information. For example, the collection unit can collect the latest news and trend information based on the user's emotions. This allows the type of information to be adjusted according to the user's emotions, thereby providing more appropriate information. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the user's emotion data into AI and have the AI ​​adjust the type of information.

[0070] The collection unit can prioritize collecting highly relevant information by taking into account the user's geographical location information. For example, if the user is in a specific area, the collection unit prioritizes collecting news related to that area. The collection unit can evaluate the relevance of information based on the geographical location information and prioritize collecting highly relevant information. For example, the collection unit collects news related to the area based on the user's GPS data. Furthermore, if the user is traveling, the collection unit can prioritize collecting tourist information about the travel destination. For example, the collection unit collects tourist information about the travel destination based on the user's geographical location information. Furthermore, if the user is at an event venue, the collection unit can prioritize collecting information related to the event. For example, the collection unit collects information related to the event based on the user's geographical location information. This makes it possible to provide highly relevant information based on the user's geographical location information. Some or all of the above-described processing by the collection unit may be performed using, or without, AI. For example, the collection unit may input the user's geographical location information into AI and cause the AI ​​to collect highly relevant information.

[0071] The collection unit can analyze the user's social media activities and collect related information during collection. For example, if the user frequently uses a specific hashtag, the collection unit can collect information related to the hashtag. The collection unit can evaluate the relevance of information based on the social media activities and collect related information. For example, the collection unit can analyze the user's social media posts and collect information related to a specific hashtag. Furthermore, if the user follows a specific account, the collection unit can preferentially collect information from that account. For example, the collection unit can collect posts from the accounts the user follows. Furthermore, if the user posts frequently about a specific topic, the collection unit can collect information related to that topic. For example, the collection unit can analyze the content of the user's posts and collect information related to a specific topic. This makes it possible to provide related information based on the user's social media activities. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the user's social media activity data into AI and have the AI ​​collect related information.

[0072] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions. For example, when the user is feeling anxious, the analysis unit increases the accuracy of the analysis to provide more reliable information. The analysis unit can estimate the user's emotions using an emotion analysis algorithm and adjust the accuracy of the analysis based on the estimated emotions. For example, the analysis unit can estimate the emotions based on user feedback and increase the accuracy of the analysis. Furthermore, when the user is relaxed, the analysis unit can maintain the accuracy of the analysis at normal levels and provide balanced information. For example, the analysis unit can adjust the accuracy of the analysis based on the user's emotions. Furthermore, when the user is excited, the analysis unit can increase the accuracy of the analysis to provide more up-to-date information. For example, the analysis unit can adjust the accuracy of the analysis based on the user's emotions. This enables the analysis accuracy to be adjusted according to the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's emotion data into AI and have the AI ​​adjust the accuracy of the analysis.

[0073] The analysis unit can evaluate the reliability of information during analysis and exclude unreliable information. For example, the analysis unit can evaluate the reliability of news articles and exclude unreliable articles. The analysis unit can evaluate the reliability of information based on the reliability score and exclude unreliable information. For example, the analysis unit can calculate the reliability score of news articles and exclude unreliable articles. The analysis unit can also evaluate the reliability of blog articles and exclude unreliable blogs. For example, the analysis unit can exclude unreliable blogs based on the reliability score of the blog. The analysis unit can also evaluate the reliability of social media posts and exclude unreliable posts. For example, the analysis unit can exclude unreliable posts based on the reliability score of the social media posts. This eliminates unreliable information, thereby improving the reliability of the analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input collected information into AI and have the AI ​​exclude unreliable information.

[0074] The analysis unit can apply different analysis algorithms depending on the type of information during analysis. For example, in the case of a news article, the analysis unit applies an algorithm for fact-checking. The analysis unit can select the optimal analysis algorithm depending on the type of information. For example, the analysis unit applies an algorithm for fact-checking when analyzing a news article. The analysis unit can also apply an algorithm for evaluating the reliability of the content in the case of a blog article. For example, the analysis unit applies an algorithm for evaluating the reliability of the content in the case of a blog article. Furthermore, the analysis unit can also apply an algorithm for evaluating reliability based on the engagement rate in the case of a social media post. For example, the analysis unit applies an algorithm for evaluating reliability based on the engagement rate in the analysis of a social media post. This enables optimal analysis depending on the category of information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input an analysis algorithm depending on the type of information into AI and cause the AI ​​to perform the optimal analysis.

[0075] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is feeling anxious, the analysis unit provides a simple, highly visible display method. The analysis unit can estimate the user's emotions using an emotion analysis algorithm and adjust the display method of the analysis results based on the estimated emotions. For example, the analysis unit can estimate the emotions based on user feedback and provide a simple, highly visible display method. The analysis unit can also provide a display method including detailed information if the user is relaxed. For example, the analysis unit can provide a display method including detailed information depending on the user's emotions. Furthermore, the analysis unit can also provide a visually stimulating display method if the user is excited. For example, the analysis unit can provide a visually stimulating display method based on the user's emotions. This makes it possible to adjust the display method according to the user's emotions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's emotion data into AI and have the AI ​​adjust the display method.

[0076] During analysis, the analysis unit can determine the priority of analysis based on the time of submission of information. The analysis unit, for example, prioritizes analysis of the latest news article. The analysis unit can determine the priority of information based on the time of submission and prioritize analysis of the latest information. For example, the analysis unit prioritizes analysis of the latest news article based on the time of submission of the news article. The analysis unit can also postpone information that was submitted earlier. For example, the analysis unit postpones analysis of information that was submitted earlier. Furthermore, the analysis unit can also prioritize analysis of information with high urgency. For example, the analysis unit prioritizes analysis of information with high urgency. This makes it possible to determine the priority based on the time of submission. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the time of submission of information to AI and have the AI ​​determine the priority.

[0077] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the information. For example, the analysis unit prioritizes analyzing information related to topics that the user is highly interested in. The analysis unit can adjust the order of analysis based on the relevance of the information and prioritize analyzing highly relevant information. For example, the analysis unit prioritizes analyzing information related to topics that the user is highly interested in. The analysis unit can also prioritize analyzing highly relevant information based on the user's past search history. For example, the analysis unit prioritizes analyzing highly relevant information based on the user's past search history. Furthermore, the analysis unit can also prioritize analyzing information related to the user's current activity. For example, the analysis unit prioritizes analyzing information related to the user's current activity. This makes it possible to adjust the order of analysis based on relevance. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance of the information into AI and have the AI ​​adjust the order of analysis.

[0078] The filter unit can estimate the user's emotions and adjust the filter criteria based on the estimated user emotions. For example, the filter unit applies strict filter criteria when the user is feeling anxious. The filter unit can estimate the user's emotions using an emotion analysis algorithm and adjust the filter criteria based on the estimated emotions. For example, the filter unit estimates the emotions based on user feedback and applies strict filter criteria. The filter unit can also apply normal filter criteria when the user is relaxed. For example, the filter unit applies normal filter criteria according to the user's emotions. Furthermore, the filter unit can also apply lenient filter criteria when the user is excited. For example, the filter unit applies lenient filter criteria based on the user's emotions. This makes it possible to adjust the filter criteria according to the user's emotions. Some or all of the above-described processing in the filter unit can be performed using, for example, AI, or without AI. For example, the filter unit can input the user's emotion data into AI and have the AI ​​adjust the filter criteria.

[0079] The filter unit can evaluate the reliability of information and exclude low-reliability information during filtering. For example, the filter unit can evaluate the reliability of news articles and exclude low-reliability articles. The filter unit can evaluate the reliability of information based on the reliability score and exclude low-reliability information. For example, the filter unit calculates the reliability score of news articles and excludes low-reliability articles. The filter unit can also evaluate the reliability of blog articles and exclude low-reliability blogs. For example, the filter unit can exclude low-reliability blogs based on the reliability score of the blog. The filter unit can also evaluate the reliability of social media posts and exclude low-reliability posts. For example, the filter unit excludes low-reliability posts based on the reliability score of the social media posts. This eliminates low-reliability information, thereby improving the reliability of the filter results. Some or all of the above-described processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can input collected information into AI and have the AI ​​exclude low-reliability information.

[0080] The filter unit can apply different filter algorithms depending on the type of information when filtering. For example, in the case of news articles, the filter unit applies a filter algorithm for fact-checking. The filter unit can select the optimal filter algorithm depending on the type of information. For example, the filter unit applies a filter algorithm for fact-checking when filtering news articles. The filter unit can also apply a filter algorithm that evaluates the reliability of content when filtering blog articles. For example, the filter unit applies a filter algorithm that evaluates the reliability of content when filtering blog articles. The filter unit can also apply a filter algorithm that evaluates reliability based on engagement rate when filtering social media posts. For example, the filter unit applies a filter algorithm that evaluates reliability based on engagement rate when filtering social media posts. This enables optimal filtering depending on the category of information. Some or all of the above-described processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can input a filter algorithm depending on the type of information into AI and have the AI ​​execute the optimal filter.

[0081] The filter unit can estimate the user's emotions and adjust the display method of the filter results based on the estimated user emotions. For example, if the user is feeling anxious, the filter unit provides a simple, highly visible display method. The filter unit can estimate the user's emotions using an emotion analysis algorithm and adjust the display method of the filter results based on the estimated emotions. For example, the filter unit estimates the emotions based on user feedback and provides a simple, highly visible display method. The filter unit can also provide a display method including detailed information if the user is relaxed. For example, the filter unit provides a display method including detailed information according to the user's emotions. Furthermore, the filter unit can also provide a visually stimulating display method if the user is excited. For example, the filter unit provides a visually stimulating display method based on the user's emotions. This makes it possible to adjust the display method according to the user's emotions. Some or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without AI. For example, the filter unit can input the user's emotion data into AI and have the AI ​​adjust the display method.

[0082] During filtering, the filter unit can determine the priority of the filter based on the time of submission of the information. For example, the filter unit prioritizes filtering the latest news articles. The filter unit can determine the priority of information based on the time of submission and prioritize filtering the latest information. For example, the filter unit prioritizes filtering the latest news articles based on the time of submission of the news articles. The filter unit can also postpone filtering information that was submitted earlier. For example, the filter unit filters information that was submitted earlier later. The filter unit can also prioritize filtering information that is highly urgent. For example, the filter unit prioritizes filtering information that is highly urgent. This makes it possible to determine the priority based on the time of submission. Some or all of the above-described processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can input the time of submission of information into AI and have the AI ​​determine the priority.

[0083] The filter unit can adjust the filter order based on the relevance of the information when filtering. For example, the filter unit prioritizes filtering information related to topics that the user is highly interested in. The filter unit can adjust the filter order based on the relevance of the information to prioritize filtering highly relevant information. For example, the filter unit prioritizes filtering information related to topics that the user is highly interested in. The filter unit can also prioritize filtering highly relevant information based on the user's past search history. For example, the filter unit prioritizes filtering highly relevant information based on the user's past search history. The filter unit can also prioritize filtering information related to the user's current activity. For example, the filter unit prioritizes filtering information related to the user's current activity. This enables adjustment of the filter order based on relevance. Some or all of the above-described processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can input the relevance of the information into AI and have the AI ​​adjust the filter order.

[0084] The management unit can estimate the user's emotions and adjust the management method based on the estimated user emotions. For example, the management unit applies a strict management method when the user is feeling anxious. The management unit can estimate the user's emotions using an emotion analysis algorithm and adjust the management method based on the estimated emotions. For example, the management unit estimates the emotions based on user feedback and applies a strict management method. The management unit can also apply a normal management method when the user is relaxed. For example, the management unit applies the normal management method according to the user's emotions. Furthermore, the management unit can also apply a lenient management method when the user is excited. For example, the management unit applies a lenient management method based on the user's emotions. This makes it possible to adjust the management method according to the user's emotions. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the user's emotion data into AI and have the AI ​​adjust the management method.

[0085] The management unit can evaluate the reliability of information during management and exclude low-reliability information. For example, the management unit evaluates the reliability of news articles and excludes low-reliability articles. The management unit can evaluate the reliability of information based on the reliability score and exclude low-reliability information. For example, the management unit calculates the reliability score of news articles and excludes low-reliability articles. The management unit can also evaluate the reliability of blog articles and exclude low-reliability blogs. For example, the management unit excludes low-reliability blogs based on the reliability score of the blog. Furthermore, the management unit can evaluate the reliability of social media posts and exclude low-reliability posts. For example, the management unit excludes low-reliability posts based on the reliability score of the social media posts. This eliminates low-reliability information, thereby improving the reliability of the management results. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input collected information into AI and have the AI ​​exclude low-reliability information.

[0086] The management department can apply different management algorithms depending on the type of information during management. For example, in the case of news articles, the management department can apply a management algorithm for fact-checking. The management department can select the optimal management algorithm depending on the type of information. For example, in the management of news articles, the management department can apply a management algorithm for fact-checking. In addition, in the case of blog posts, the management department can apply a management algorithm that evaluates the reliability of the content. For example, in the management of blog posts, the management department can apply a management algorithm that evaluates the reliability of the content. Furthermore, in the case of social media posts, the management department can apply a management algorithm that evaluates the reliability based on the engagement rate. For example, in the management of social media posts, the management department can apply a management algorithm that evaluates the reliability based on the engagement rate. This enables optimal management according to the category of information. Some or all of the above processes in the management department may be performed using AI, for example, or without AI. For example, the management department can input management algorithms according to the type of information into AI and have the AI ​​perform the optimal management.

[0087] The management unit can estimate the user's emotions and adjust the display method of the management results based on the estimated user emotions. For example, if the user is feeling anxious, the management unit provides a simple, highly visible display method. The management unit can estimate the user's emotions using an emotion analysis algorithm and adjust the display method of the management results based on the estimated emotions. For example, the management unit can estimate the emotions based on user feedback and provide a simple, highly visible display method. The management unit can also provide a display method including detailed information if the user is relaxed. For example, the management unit provides a display method including detailed information according to the user's emotions. Furthermore, the management unit can also provide a visually stimulating display method if the user is excited. For example, the management unit provides a visually stimulating display method based on the user's emotions. This makes it possible to adjust the display method according to the user's emotions. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without AI. For example, the management unit can input the user's emotion data into AI and have the AI ​​adjust the display method.

[0088] During management, the management unit can determine management priorities based on the time of submission of information. The management unit, for example, prioritizes managing the latest news articles. The management unit can determine the priority of information based on the time of submission and prioritize managing the latest information. For example, the management unit prioritizes managing the latest news articles based on the time of submission of the news articles. The management unit can also postpone information that was submitted earlier. For example, the management unit manages information that was submitted earlier later. Furthermore, the management unit can also prioritize managing information that is highly urgent. For example, the management unit prioritizes managing information that is highly urgent. This makes it possible to determine priorities based on the time of submission. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the time of submission of information into AI and have the AI ​​determine the priorities.

[0089] During management, the management unit can adjust the management order based on the relevance of the information. For example, the management unit prioritizes managing information related to topics that the user is highly interested in. The management unit can adjust the management order based on the relevance of the information and prioritize managing highly relevant information. For example, the management unit prioritizes managing information related to topics that the user is highly interested in. The management unit can also prioritize managing highly relevant information based on the user's past search history. For example, the management unit prioritizes managing highly relevant information based on the user's past search history. Furthermore, the management unit can also prioritize managing information related to the user's current activity. For example, the management unit prioritizes managing information related to the user's current activity. This makes it possible to adjust the management order based on the relevance. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the relevance of the information into AI and have the AI ​​adjust the management order. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, filter unit, and management unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit is implemented by the computer 36 of the smart device 14 and the specific processing unit 290 of the data processing device 12 and collects information from news sites, blogs, social networking sites, etc. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected information to identify false information and issues related to copyright and portrait rights. The filter unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and prevents the display of articles containing false information and blocks images and videos with copyright issues. The management unit is implemented, for example, by the control unit 46A of the smart device 14 and the specific processing unit 290 of the data processing device 12 and ensures that the information searched by the user is reliable. Furthermore, the collection unit has the function of estimating the user's emotions and determining the priority of information sources to be collected based on the estimated user emotions, and is realized, for example, by the computer 36 of the smart device 14 and the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, filter unit, and management unit, described above, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is implemented by the computer 36 of the smart glasses 214 and the specific processing unit 290 of the data processing device 12, and collects information from news sites, blogs, social networking sites, etc. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected information to identify false information and issues related to copyright and portrait rights. The filter unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and prevents the display of articles containing false information and blocks images and videos with copyright issues. The management unit is implemented, for example, by the control unit 46A of the smart glasses 214 and the specific processing unit 290 of the data processing device 12, and ensures that the information searched by the user is reliable. Furthermore, the collection unit has a function of estimating the user's emotions and determining the priority of information sources to be collected based on the estimated user emotions, and is realized, for example, by the computer 36 of the smart glasses 214 and the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements described above, including the collection unit, analysis unit, filter unit, and management unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the computer 36 of the headset terminal 314 and the specific processing unit 290 of the data processing unit 12, and collects information from news sites, blogs, social networking services, etc. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, and analyzes the collected information to identify misinformation and issues related to copyright and portrait rights. The filter unit is implemented by the specific processing unit 290 of the data processing unit 12, and prevents the display of articles containing misinformation and blocks images and videos that have copyright issues. The management unit is implemented by the control unit 46A of the headset terminal 314 and the specific processing unit 290 of the data processing unit 12, and ensures that the information searched by the user is reliable. Furthermore, the collection unit has a function of estimating the user's emotions and determining the priority of information sources to be collected based on the estimated user emotions, and is realized, for example, by the computer 36 of the headset-type terminal 314 and the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, filter unit, and management unit, described above, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit is implemented by the computer 36 of the robot 414 and the specific processing unit 290 of the data processing device 12 and collects information from news sites, blogs, social networking sites, etc. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected information to identify false information and issues related to copyright and portrait rights. The filter unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and prevents the display of articles containing false information and blocks images and videos with copyright issues. The management unit is implemented, for example, by the control unit 46A of the robot 414 and the specific processing unit 290 of the data processing device 12 and ensures that the information searched by the user is reliable. Furthermore, the collection unit has a function of estimating the user's emotions and determining the priority of information sources to be collected based on the estimated user emotions, and is realized, for example, by the computer 36 of the robot 414 and the specific processing unit 290 of the data processing device 12.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The analysis unit can refer to the information source's past reliability history to evaluate the reliability of the collected information. For example, the analysis unit can prioritize news sites and blogs that have provided reliable information in the past. The analysis unit can also filter information from specific information sources based on the information source's reliability history. Furthermore, the analysis unit can calculate a reliability score for the information based on the information source's reliability history and exclude information with low reliability. This allows the analysis unit to utilize the past reliability history to perform a more accurate reliability evaluation.

[0092] The data collection unit can customize information based on the user's interests. For example, it analyzes the user's past search and browsing history and prioritizes collecting information related to topics the user is interested in. It can also collect relevant information based on the social media accounts and blogs the user follows. Furthermore, it can collect the latest information on specific topics based on keyword alerts set by the user. This allows the data collection unit to provide information tailored to the user's interests.

[0093] The analysis unit can evaluate not only the source of the information but also the content of the information itself when assessing its reliability. For example, the analysis unit can verify whether the content of the information is consistent with other reliable sources. It can also check whether the content of the information is consistent with past facts. Furthermore, the analysis unit can evaluate whether the content of the information is consistent with expert opinions and research results. As a result, the analysis unit can perform a more accurate reliability assessment by evaluating the content of the information itself.

[0094] The filter can adjust its filtering criteria based on user feedback. For example, if a user trusts a particular information source, the filter will prioritize displaying information from that source. It can also prioritize displaying information related to a specific topic if the user is interested in that topic. Furthermore, if a user deems certain information inappropriate, the filter can filter that information. This allows the filter to leverage user feedback to provide more relevant information.

[0095] The management unit can analyze the user's behavioral patterns and optimize the method of providing information. For example, the management unit can analyze what time of day the user often views information and provide information tailored to that time of day. The management unit can also analyze which device the user often uses to view information and provide information in a format optimized for that device. Furthermore, the management unit can analyze which format of information the user prefers (text, image, video, etc.) and provide information in that format. This allows the management unit to provide information more effectively based on the user's behavioral patterns.

[0096] The collection unit can estimate the user's emotions and adjust the frequency of information collection based on the estimated emotions. For example, if the user feels anxious, the collection unit can frequently collect information from reliable information sources. If the user feels relaxed, the collection unit can also collect entertainment information at an appropriate frequency. Furthermore, if the user feels excited, the collection unit can quickly collect the latest news and trend information. This allows the collection unit to adjust the frequency of information collection according to the user's emotions.

[0097] The analysis unit can estimate the user's emotions and adjust the importance of the analysis results based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit can emphasize and display highly reliable information. If the user is relaxed, the analysis unit can also provide balanced information. Furthermore, if the user is excited, the analysis unit can prioritize displaying the latest news and trend information. This allows the analysis unit to adjust the importance of the analysis results according to the user's emotions.

[0098] The filter unit can estimate the user's emotions and adjust the strictness of the filter based on the estimated emotions. For example, if the user is feeling anxious, the filter unit applies strict filter criteria to eliminate unreliable information. If the user is relaxed, the filter unit can also apply normal filter criteria. Furthermore, if the user is excited, the filter unit can apply lenient filter criteria to provide a variety of information. This allows the filter unit to adjust the filter criteria according to the user's emotions.

[0099] The management unit can estimate the user's emotions and adjust the display order of information based on the estimated emotions. For example, if the user is feeling anxious, the management unit can display highly reliable information first. If the user is feeling relaxed, the management unit can also display entertainment information in a balanced manner. Furthermore, if the user is excited, the management unit can prioritize displaying the latest news and trend information. This allows the management unit to adjust the display order of information according to the user's emotions.

[0100] The management unit can estimate the user's emotions and adjust the display format of information based on the estimated emotions. For example, if the user is feeling anxious, the management unit can provide a simple, highly visible display format. If the user is feeling relaxed, the management unit can also provide a display format including detailed information. Furthermore, if the user is excited, the management unit can provide a visually stimulating display format. This enables the management unit to adjust the information display format according to the user's emotions.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The data collection unit collects information from the internet. The data collection unit collects information from sources such as news sites, blogs, and social media. The data collection unit can obtain data using crawling techniques or APIs. For example, the data collection unit can periodically check the RSS feeds of news sites and collect new articles. The data collection unit can also use blog APIs to retrieve the latest posts. Furthermore, the data collection unit can use social media APIs to collect user posts. Step 2: The analysis unit analyzes the collected information. For example, the analysis unit uses text analysis technology to analyze the content of news articles and identify misinformation and issues related to copyright and portrait rights. The analysis unit can also use image analysis technology to verify the copyright of images and videos. For example, the analysis unit uses fact-checking algorithms to determine whether the content of news articles is factual. The analysis unit can also use image recognition technology to verify the copyright of images and videos. Step 3: The filter unit applies restrictions and filters based on the analyzed information. For example, the filter unit prevents the display of articles containing false information. The filter unit can identify articles containing false information using keyword filtering technology and restrict their display. The filter unit can also block images and videos that infringe on copyright. For example, the filter unit can identify images and videos that infringe on copyright using image recognition technology and block their display. Step 4: The administration unit provides users with information restricted by the filtering unit. The administration unit ensures, for example, that the information the user searches for is reliable. The administration unit can display reliable information through the user interface. For example, the administration unit can display reliable news articles or blog posts based on the keywords the user searches for. The administration unit can also manage the user's browsing history and prioritize the display of reliable information.

[0103] 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.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0105] 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.

[0106] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0118] 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.

[0119] 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.

[0120] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0121] 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.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0131] 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.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0134] 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.

[0135] 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.

[0136] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0137] 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.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0150] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0151] 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.

[0152] 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.

[0153] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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."

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] [Explanation of symbols]

[0175] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects information on the Internet; an analysis unit that analyzes the information collected by the collection unit; a filter unit that applies restrictions and filters based on the information analyzed by the analysis unit; a management unit that provides the user with information restricted by the filter unit. A system characterized by:

2. The collecting unit Gather information from news sites, blogs, or social media The system of claim 1 .

3. The analysis unit Analyze the collected information to identify misinformation or copyright or image rights issues The system of claim 1 .

4. The filter section is Prevent articles containing false information from appearing The system of claim 1 .

5. The filter section is Block images or videos with copyright issues The system of claim 1 .

6. The management unit Ensuring that the information users search for is trustworthy The system of claim 1 .

7. The collecting unit Estimate the user's emotions and prioritize the information sources to be collected based on the estimated user emotions. The system of claim 1 .

8. The collecting unit When collecting information, assess its reliability and prioritize collection from reliable sources. The system of claim 1 .

Images