System

Abstract

An object of a system according to an embodiment is to realize quick and accurate information sharing at the time of a disaster, prevent diffusion of erroneous information, and enable multilingual support.SOLUTION: A system includes a reception part, an analysis part, an identification part, a warning part, a translation part, an acquisition part, a grasping part, and a distribution part. The reception unit receives a post from a user. The analysis unit analyzes and summarizes the posting received by the reception unit. The identification unit identifies the posted content analyzed by the analysis unit. The warning unit warns of the error information identified by the identification unit. The translation unit translates the posts in different languages. The acquisition unit acquires position information. The grasping unit grasps the safety information for each area based on the position information acquired by the acquisition unit. The distribution unit distributes the support needs based on the information grasped by the grasping unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, information sharing during disasters was not carried out quickly and accurately, and issues included the spread of misinformation and a lack of multilingual support.

[0005] The system according to the embodiment aims to realize rapid and accurate information sharing in the event of a disaster, prevent the spread of false information, and enable multilingual support. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, an identification unit, a warning unit, a translation unit, an acquisition unit, a comprehension unit, and a distribution unit. The reception unit receives posts from users. The analysis unit analyzes and summarizes the posts received by the reception unit. The identification unit identifies the content of the posts analyzed by the analysis unit. The warning unit issues a warning about false information identified by the identification unit. The translation unit translates posts in different languages. The acquisition unit acquires location information. The comprehension unit comprehends safety information for each region based on the location information acquired by the acquisition unit. The distribution unit distributes support needs based on the information comprehended by the comprehension unit. [Effects of the Invention]

[0007] The system according to the embodiment can realize rapid and accurate information sharing in the event of a disaster, prevent the spread of false information, and enable multilingual support. [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 disaster information sharing platform according to an embodiment of the present invention is a system that automatically accepts user posts, analyzes and summarizes them using a generation AI, identifies misinformation, displays warnings, translates posts in different languages, acquires location information, identifies safety information for each region, and distributes information on support needs. The disaster information sharing platform analyzes and summarizes user posts in real time, enabling rapid and accurate information sharing. For example, if a user posts something like "My family is safe" during a disaster, the generation AI analyzes and summarizes the content and displays it as "Family Safety Confirmation." The generation AI then analyzes the content of the post and identifies misinformation. For example, if incorrect information is posted, the generation AI identifies the information and displays a warning to the user. It also supports multiple languages, translating posts in different languages ​​in real time, enabling access to a wide community. Under normal circumstances, it functions as a forum for sharing information to prepare for disasters and strengthen local communities. For example, information on local disaster prevention drills and disaster preparedness is shared. This raises disaster prevention awareness throughout the community and facilitates disaster response. During disasters, safety information and requests for support can be posted and viewed smoothly. For example, if a disaster victim posts a request for assistance, such as "Water is in short supply," the AI ​​analyzes the information and identifies the assistance needs of each region. This enables efficient delivery of assistance. Furthermore, location information can be used to grasp the safety information of each region. For example, if many safety information posts are made in a specific region, the situation in that region can be quickly grasped. This supports rapid information sharing and safe communication during disasters. This allows the disaster information sharing platform to support rapid information sharing and safe communication during disasters, setting a new standard for disaster response. For example, by quickly and accurately analyzing user posts, identifying misinformation, and displaying warnings, accurate information sharing is possible. Furthermore, real-time translation of posts in different languages ​​enables access to a wide community. Furthermore, location information can be used to grasp the safety information of each region and efficiently deliver assistance needs.

[0029] A disaster information sharing platform according to an embodiment includes a reception unit, an analysis unit, an identification unit, a warning unit, a translation unit, an acquisition unit, a comprehension unit, and a distribution unit. The reception unit receives posts from users. The posts from users include, but are not limited to, text, images, and videos. The reception unit can receive posts from, for example, a smartphone or a PC. The reception unit can also support various input methods, such as voice input and image input. The analysis unit uses a generation AI to analyze and summarize the posts received by the reception unit. The analysis is performed using, for example, natural language processing technology, but is not limited to, for example. For example, the generation AI analyzes and summarizes the posts using a text generation AI (e.g., LLM). The analysis unit can also analyze and summarize the content of the posts using a multimodal generation AI. The analysis unit can also extract and summarize important parts of the text using the generation AI. The identification unit uses the generation AI to identify the content of the posts analyzed by the analysis unit. The identification is performed using, for example, a misinformation detection algorithm, but is not limited to, such an example. For example, the identification unit uses a generation AI to evaluate the reliability of the posted content and identify the misinformation. The warning unit warns of the misinformation identified by the identification unit. The warning is performed by, for example, a pop-up notification or an email notification, but is not limited to, such an example. For example, the warning unit displays a warning to the user when misinformation is identified. The translation unit uses a generation AI to translate posts in different languages. The translation is performed by, for example, a real-time translation or a batch translation, but is not limited to, such an example. For example, the translation unit translates posts in different languages ​​in real time using the generation AI. The acquisition unit acquires location information. The location information is acquired by, for example, a GPS data or an IP address, but is not limited to, such an example. For example, the acquisition unit acquires location information from the user's smartphone or PC. The understanding unit understands safety information for each region based on the location information acquired by the acquisition unit. The understanding is performed by, for example, a method of checking the user's safety and understanding the damage situation, but is not limited to, such an example. For example, the ascertaining unit ascertains safety information for each region based on the acquired location information.The distribution unit distributes support needs based on the information grasped by the grasping unit. The distribution may be, for example, a request for supplies or medical assistance, but is not limited to such examples. For example, the distribution unit distributes support needs based on the grasped information. As a result, the disaster information sharing platform according to the embodiment can analyze and summarize posts from users in real time, enabling rapid and accurate information sharing. For example, accurate information sharing is possible by quickly and accurately analyzing posts written by users, identifying misinformation, and displaying warnings. Furthermore, real-time translation of posts written in different languages ​​enables access to a wide community. Furthermore, location information can be used to grasp safety information for each region and efficiently distribute support needs.

[0030] The reception unit can accept posts from a smartphone or a PC. The reception unit accepts posts from, for example, a smartphone or a PC. Examples of smartphones or PCs include, but are not limited to, operating systems such as iOS, Android, and Windows. For example, the reception unit can accept posts through a smartphone app. The reception unit can also accept posts through a PC web browser. This improves user convenience by accepting posts from smartphones and PCs. Some or all of the above-described processing in the reception unit may be performed using, or without, AI. For example, the reception unit can input posts from a smartphone or PC into a generation AI and have the generation AI analyze the content of the posts.

[0031] The analysis unit can analyze and summarize posts using natural language processing technology. The analysis unit can analyze and summarize posts using, for example, natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, semantic analysis, etc., but is not limited to these examples. For example, the analysis unit can analyze and summarize words in posts using morphological analysis. The analysis unit can also analyze and summarize the sentence structure of posts using grammatical analysis. The analysis unit can also analyze and summarize the meaning of posts using semantic analysis. This improves the accuracy of post analysis and summarization by using natural language processing technology. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input the content of the post into a generation AI and have the generation AI analyze and summarize the content of the post.

[0032] The identification unit can identify misinformation. The identification unit, for example, identifies misinformation. Misinformation includes, for example, false information and misleading information, but is not limited to these examples. For example, the identification unit identifies misinformation using a misinformation detection algorithm. The identification unit can also evaluate the reliability of the posted content and identify misinformation. The identification unit can also identify misinformation by taking into account the interrelationships between posts. This enables accurate information sharing by identifying misinformation. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the identification unit can input the posted content into the generation AI and have the generation AI identify the misinformation.

[0033] The warning unit can display a warning to the user when false information is identified. The warning unit displays a warning to the user when false information is identified, for example. Methods of displaying the warning include, but are not limited to, pop-up notifications, email notifications, etc. For example, the warning unit displays a pop-up notification when false information is identified. The warning unit can also send an email notification when false information is identified. The warning unit can also display an in-app notification when false information is identified. In this way, accurate information is provided to the user by displaying a warning when false information is identified. Some or all of the above-described processing in the warning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the warning unit can input the result of identifying false information to the generation AI and cause the generation AI to display the warning.

[0034] The translation unit can instantly translate posts in different languages. For example, the translation unit instantly translates posts in different languages. Translation methods include, but are not limited to, real-time translation, batch translation, and the like. For example, the translation unit instantly translates posts in different languages ​​using real-time translation. The translation unit can also translate posts in different languages ​​using batch translation. The translation unit can also translate posts in different languages ​​using a generation AI. This enables access to a wider community by translating posts in different languages ​​in real time. Some or all of the above-described processing in the translation unit may be performed using, or without, the generation AI. For example, the translation unit can input posts in different languages ​​into the generation AI and have the generation AI perform the translation.

[0035] The acquisition unit can acquire location information. The acquisition unit acquires, for example, location information. Methods for acquiring location information include, but are not limited to, GPS data, IP addresses, etc. For example, the acquisition unit acquires GPS data from the user's smartphone. The acquisition unit can also acquire an IP address from the user's PC. The acquisition unit can also acquire the user's location information in real time. By acquiring the location information, it becomes possible to grasp safety information for each region. Some or all of the above-mentioned processing in the acquisition unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the acquisition unit can input the user's location information to the generation AI and have the generation AI analyze the location information.

[0036] The grasping unit can grasp the safety information for each region based on the acquired location information. The grasping unit grasps the safety information for each region based on, for example, the acquired location information. Methods of grasping the safety information include, for example, checking the safety of users and grasping the damage situation, but are not limited to these examples. For example, the grasping unit grasps the safety information for each region based on the acquired location information. The grasping unit can also grasp the safety information by analyzing the content posted by users. The grasping unit can also grasp the safety information for each region in real time. This enables rapid information sharing by grasping the safety information for each region. Some or all of the above-mentioned processing in the grasping unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the grasping unit can input the acquired location information to the generation AI and cause the generation AI to grasp the safety information.

[0037] The distribution unit can distribute support needs based on the grasped information. The distribution unit distributes support needs based on, for example, the grasped information. Methods of distributing support needs include, for example, the need for supplies, a request for medical support, etc., but are not limited to these examples. For example, the distribution unit distributes the need for supplies based on the grasped information. The distribution unit can also distribute a request for medical support. The distribution unit can also distribute support needs for each region in real time. This enables efficient distribution of support by distributing the support needs. Some or all of the above-mentioned processing in the distribution unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the distribution unit can input the grasped information into a generation AI and cause the generation AI to distribute the support needs.

[0038] The reception unit can analyze the user's past posting history and select an appropriate reception method when receiving a post. For example, the reception unit analyzes the user's past posting history and selects an appropriate reception method when receiving a post. Analysis of the past posting history includes, but is not limited to, methods such as text mining and frequency analysis. For example, the reception unit prioritizes suggesting a posting method that the user has frequently used in the past. The reception unit can also analyze the content of the user's past posts and provide related templates. The reception unit can also suggest the optimal reception method for a specific time period based on the user's past posting history. This allows the optimal reception method to be selected by analyzing the user's past posting history. Some or all of the above-described processing by the reception unit may be performed using, or without, a generation AI. For example, the reception unit can input the user's past posting history into the generation AI and have the generation AI select a reception method.

[0039] The reception unit may filter posts based on the user's current situation or areas of interest when receiving the posts. For example, the reception unit may filter posts based on the user's current situation or areas of interest when receiving the posts. Filtering methods include, but are not limited to, survey results and behavioral history. For example, the reception unit may prioritize disaster information for the user's current location. The reception unit may also prioritize posts related to the user's areas of interest. The reception unit may also determine the priority of posts based on the user's current situation (e.g., whether the user is evacuating). By filtering based on the user's current situation and areas of interest, highly relevant posts can be prioritized. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit may input the user's current situation and areas of interest into the generation AI and have the generation AI perform filtering.

[0040] The reception unit can select an appropriate reception means depending on the user's input method when receiving a post. For example, the reception unit selects an appropriate reception means depending on the user's input method when receiving a post. Input methods include, but are not limited to, voice input, text input, and image input. For example, if the user selects voice input, the reception unit can use voice recognition technology to receive the post. Furthermore, if the user selects text input, the reception unit can also use text analysis technology to receive the post. Furthermore, if the user posts an image, the reception unit can analyze the content of the post using image analysis technology and receive it. This allows for smooth reception of posts by selecting the optimal reception means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the user's input data into the generation AI and have the generation AI select the reception means.

[0041] The reception unit may, when receiving posts, prioritize posts that are highly relevant based on the user's geographical location information. For example, when receiving posts, the reception unit may, when receiving posts, prioritize posts that are highly relevant based on the user's geographical location information. Methods for acquiring geographical location information include, but are not limited to, GPS data, IP addresses, etc. For example, the reception unit may prioritize disaster information for the user's current location. The reception unit may also prioritize related assistance requests based on the user's geographical location information. The reception unit may also prioritize safety information for each region based on the user's geographical location information. This allows highly relevant posts to be prioritized by taking the user's geographical location information into consideration. Some or all of the above-described processing by the reception unit may be performed using, or without, a generation AI. For example, the reception unit may input the user's geographical location information into the generation AI and cause the generation AI to receive highly relevant posts.

[0042] The reception unit can analyze the user's social media activity when receiving a post and receive relevant posts. For example, the reception unit can analyze the user's social media activity when receiving a post and receive relevant posts. Analysis of social media activity includes, but is not limited to, posting frequency and engagement. For example, the reception unit can receive relevant posts based on information shared by the user on social media. The reception unit can also analyze the user's social media activity history and preferentially receive relevant posts. The reception unit can also receive related posts based on posts made by the user's friends on social media. In this way, by analyzing the user's social media activity, relevant posts can be preferentially received. Some or all of the above-described processing by the reception unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the reception unit can input the user's social media activity data into the generation AI and cause the generation AI to receive relevant posts.

[0043] The reception unit can adjust the reception method by reflecting the user's past feedback when receiving a post. For example, the reception unit adjusts the reception method by reflecting the user's past feedback when receiving a post. Analysis of past feedback includes, but is not limited to, user ratings and comments. For example, the reception unit proposes an optimal reception method based on feedback previously provided by the user. The reception unit can also customize the reception interface by reflecting the user's past feedback. The reception unit can also optimize the reception procedure based on the user's past feedback. In this way, the optimal reception method can be provided by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can input the user's past feedback data into the generation AI and cause the generation AI to adjust the reception method.

[0044] The analysis unit can set the level of detail of the analysis based on the importance of the post during analysis. For example, the analysis unit sets the level of detail of the analysis based on the importance of the post during analysis. Evaluation of the importance of a post includes, but is not limited to, for example, impact and urgency. For example, the analysis unit performs a detailed analysis on posts with high importance. The analysis unit can also perform a simplified analysis on posts with low importance. The analysis unit can also determine the priority of the analysis according to the importance. In this way, by adjusting the level of detail of the analysis based on the importance of the post, detailed analysis can be performed on important posts. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input post importance data to the generation AI and cause the generation AI to set the level of detail of the analysis.

[0045] The analysis unit can apply an appropriate analysis algorithm depending on the category of the post during analysis. For example, the analysis unit applies an appropriate analysis algorithm depending on the category of the post during analysis. Post categories include, but are not limited to, news, entertainment, and technology. For example, the analysis unit applies a specific analysis algorithm to posts about safety information. The analysis unit can also apply a different analysis algorithm to posts requesting assistance. The analysis unit can also apply an even different analysis algorithm to posts about disaster information. In this way, by applying different analysis algorithms depending on the category of the post, more appropriate analysis results can be provided. Some or all of the above-described processing by the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input post category data into the generation AI and cause the generation AI to apply the analysis algorithm.

[0046] The analysis unit can improve the accuracy of the analysis based on the user's past analysis results during analysis. For example, the analysis unit can improve the accuracy of the analysis based on the user's past analysis results during analysis. Examples of analysis of past analysis results include, but are not limited to, text mining and frequency analysis. For example, the analysis unit can improve the accuracy of the current analysis based on the user's past analysis results. The analysis unit can also refer to the user's past analysis results to perform optimal analysis of similar posts. The analysis unit can also analyze the user's past analysis results and optimize the analysis algorithm. This allows the accuracy of the current analysis to be improved by referring to the user's past analysis results. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the user's past analysis result data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0047] The analysis unit can set analysis priorities based on the submission time of posts during analysis. For example, the analysis unit sets analysis priorities based on the submission time of posts during analysis. Evaluation of submission time includes, but is not limited to, the submission date and time and the submission frequency. For example, the analysis unit prioritizes analysis of the most recent posts. The analysis unit can also set a lower analysis priority for posts submitted earlier. The analysis unit can also adjust the analysis schedule according to the submission time. By determining the analysis priority based on the submission time of posts, the most recent posts can be prioritized for analysis. Some or all of the above-described processing by the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input post submission time data into the generation AI and cause the generation AI to set the analysis priorities.

[0048] The analysis unit can set the analysis order based on the relevance of posts during analysis. The analysis unit, for example, sets the analysis order based on the relevance of posts during analysis. The relevance evaluation includes, for example, a co-occurrence network or a similarity score, but is not limited to these examples. For example, the analysis unit prioritizes analysis of highly relevant posts. The analysis unit can also postpone the analysis order of less relevant posts. The analysis unit can also adjust the analysis schedule according to the relevance of posts. By adjusting the analysis order based on the relevance of posts, highly relevant posts can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input relevance data of posts into the generation AI and cause the generation AI to set the analysis order.

[0049] The analysis unit can set the use of technical terms in the analysis according to the user's level of expertise during analysis. For example, the analysis unit can set the use of technical terms in the analysis according to the user's level of expertise during analysis. Evaluation of the level of expertise includes, but is not limited to, e.g., qualification information and past posting content. For example, the analysis unit can provide analysis results that use a lot of technical terms to users with high levels of expertise. The analysis unit can also provide analysis results in simpler terms to users with low levels of expertise. The analysis unit can also adjust the way the analysis results are presented according to the user's level of expertise. By adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input the user's level of expertise data into the generation AI and have the generation AI execute the use of technical terms.

[0050] The identification unit can improve the accuracy of identification based on the interrelationships between posts during identification. For example, the identification unit improves the accuracy of identification based on the interrelationships between posts during identification. Evaluation of the interrelationships between posts includes, but is not limited to, a co-occurrence network or a similarity score. For example, the identification unit analyzes the interrelationships between multiple posts to improve the accuracy of identifying misinformation. The identification unit can also identify related information by taking the interrelationships between posts into consideration. The identification unit can also optimize the identification algorithm based on the interrelationships between posts. In this way, the accuracy of identification can be improved by taking the interrelationships between posts into consideration. Some or all of the above-described processing in the identification unit may be performed using, or without, a generation AI. For example, the identification unit can input post interrelationship data into the generation AI and cause the generation AI to improve the accuracy of identification.

[0051] The identification unit can perform identification based on attribute information of the submitter of the post. For example, the identification unit performs identification based on attribute information of the submitter of the post. Evaluation of the submitter's attribute information includes, but is not limited to, age, gender, and occupation. For example, the identification unit improves the accuracy of identifying false information by taking into account the submitter's reliability. The identification unit can also identify related information based on the submitter's attribute information. The identification unit can also improve the accuracy of identification by referring to the submitter's past posting history. In this way, the accuracy of identification can be improved by taking into account the attribute information of the submitter of the post. Some or all of the above-described processing in the identification unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the identification unit can input the submitter's attribute information data into the generation AI and have the generation AI perform the identification.

[0052] The identification unit can set an identification weight based on the submission frequency of posts during identification. The identification unit, for example, sets an identification weight based on the submission frequency of posts during identification. Evaluation of the submission frequency includes, but is not limited to, for example, the number of submissions and the submission interval. For example, the identification unit can set a high identification weight for posts submitted frequently. The identification unit can also set a low identification weight for posts submitted infrequently. The identification unit can also determine an identification priority according to the submission frequency. In this way, by assigning an identification weight based on the submission frequency of posts, it is possible to determine an identification priority. Some or all of the above-described processing in the identification unit may be performed using, or without, a generation AI. For example, the identification unit can input submission frequency data to the generation AI and cause the generation AI to perform the identification weighting.

[0053] The identification unit may perform identification based on the geographic distribution of posts during identification. For example, the identification unit may perform identification based on the geographic distribution of posts during identification. Evaluation of the geographic distribution may include, but is not limited to, the number of posts by region and the geographical extent of influence. For example, if there are many posts in a specific region, the identification unit may preferentially identify information about that region. The identification unit may also identify related information based on the geographic distribution. The identification unit may also optimize the identification algorithm taking the geographic distribution into account. This allows related information to be preferentially identified by taking the geographic distribution of posts into account. Some or all of the above-described processing in the identification unit may be performed using, or without, a generation AI. For example, the identification unit may input geographic distribution data of posts into the generation AI and have the generation AI perform the identification.

[0054] The identification unit can improve the accuracy of identification by referring to related literature of the post during identification. For example, the identification unit can improve the accuracy of identification by referring to related literature of the post during identification. References to related literature include, but are not limited to, academic papers and technical reports. For example, the identification unit can improve the accuracy of identification by referring to literature related to the content of the post. The identification unit can also improve the accuracy of identifying misinformation based on the related literature. The identification unit can also analyze related literature of the post and optimize the identification algorithm. By referring to related literature of the post, the accuracy of identification can be improved. Some or all of the above-described processing in the identification unit can be performed using, or without, a generation AI. For example, the identification unit can input related literature data of the post into the generation AI and have the generation AI perform the identification.

[0055] The identification unit can perform identification based on the market value of the post during identification. For example, the identification unit performs identification based on the market value of the post during identification. Market value evaluations include, but are not limited to, sales forecasts and market shares. For example, the identification unit can assign a high identification weight to information with high market value. The identification unit can also assign a low identification weight to information with low market value. The identification unit can also determine the priority of identification according to the market value. This makes it possible to adjust the identification weight by taking the market value of the post into consideration. Some or all of the above-described processing in the identification unit may be performed using, or without, the generation AI. For example, the identification unit can input market value data to the generation AI and have the generation AI perform the identification.

[0056] The warning unit can set the level of detail of the warning based on the importance of the misinformation when issuing a warning. For example, the warning unit sets the level of detail of the warning based on the importance of the misinformation when issuing a warning. Evaluation of the importance of the misinformation includes, but is not limited to, impact and urgency. For example, the warning unit displays a detailed warning for misinformation with a high level of importance. The warning unit can also display a simplified warning for misinformation with a low level of importance. The warning unit can also determine the priority of the warning based on the importance. This allows a detailed warning to be issued for important misinformation by adjusting the level of detail of the warning based on the importance of the misinformation. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input importance data of the misinformation into the generation AI and have the generation AI set the level of detail of the warning.

[0057] The warning unit can apply an appropriate warning algorithm depending on the category of misinformation when issuing a warning. For example, the warning unit applies an appropriate warning algorithm depending on the category of misinformation when issuing a warning. Examples of categories of misinformation include, but are not limited to, news, entertainment, and technology. For example, the warning unit applies a specific warning algorithm to misinformation about safety information. The warning unit can also apply a different warning algorithm to misinformation about assistance requests. The warning unit can also apply an even different warning algorithm to misinformation about disaster information. In this way, by applying different warning algorithms depending on the category of misinformation, more appropriate warnings can be provided. Some or all of the above-mentioned processing in the warning unit may be performed using, or without using, a generation AI. For example, the warning unit can input category data of the misinformation into the generation AI and cause the generation AI to apply the warning algorithm.

[0058] The warning unit can improve the accuracy of the warning based on the user's past warning results when issuing a warning. For example, the warning unit can improve the accuracy of the warning based on the user's past warning results when issuing a warning. Analysis of past warning results includes, but is not limited to, the effectiveness of the warning and the user's reaction. For example, the warning unit can improve the accuracy of the current warning based on the user's past warning results. The warning unit can also refer to the user's past warning results to provide an optimal warning for similar misinformation. The warning unit can also analyze the user's past warning results and optimize the warning algorithm. This allows the accuracy of the current warning to be improved by referring to the user's past warning results. Some or all of the above-described processing in the warning unit can be performed using, or without, a generation AI. For example, the warning unit can input the user's past warning result data into the generation AI and cause the generation AI to improve the accuracy of the warning.

[0059] The warning unit can set a priority of the warning based on the time of submission of the misinformation when issuing a warning. For example, the warning unit can set a priority of the warning based on the time of submission of the misinformation when issuing a warning. Evaluation of the submission time includes, but is not limited to, the submission date and time and the frequency of submission. For example, the warning unit can prioritize issuing a warning for the most recent misinformation. The warning unit can also set a lower priority of the warning for misinformation that was submitted earlier. The warning unit can also adjust the warning schedule according to the time of submission. By determining the priority of the warning based on the time of submission of the misinformation, it is possible to prioritize issuing a warning for the most recent misinformation. Some or all of the above-described processing in the warning unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the warning unit can input data on the time of submission of the misinformation into the generation AI and cause the generation AI to set the priority of the warning.

[0060] The warning unit can set the order of warnings based on the relevance of the misinformation when issuing a warning. For example, the warning unit sets the order of warnings based on the relevance of the misinformation when issuing a warning. Examples of the evaluation of relevance include, but are not limited to, a co-occurrence network and a similarity score. For example, the warning unit prioritizes issuing a warning for highly relevant misinformation. The warning unit can also postpone issuing a warning for less relevant misinformation. The warning unit can also adjust the warning schedule according to the relevance of the misinformation. In this way, by adjusting the order of warnings based on the relevance of the misinformation, it is possible to prioritize issuing a warning for highly relevant misinformation. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input relevance data of the misinformation into the generation AI and cause the generation AI to set the order of warnings.

[0061] The warning unit may set the use of technical terms in the warning according to the user's level of expertise when issuing a warning. For example, the warning unit may set the use of technical terms in the warning according to the user's level of expertise when issuing a warning. Evaluation of the level of expertise may include, but is not limited to, e.g., qualifications and past postings. For example, the warning unit may display a warning that uses a lot of technical terms for users with high levels of expertise. The warning unit may also display a warning in simpler language for users with low levels of expertise. The warning unit may also adjust the way the warning is expressed according to the user's level of expertise. This allows for providing a more understandable warning by adjusting the use of technical terms in the warning according to the user's level of expertise. Some or all of the above-described processing in the warning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the warning unit may input the user's level of expertise data into the generation AI and cause the generation AI to use technical terms.

[0062] The translation unit can set the level of translation detail based on the importance of the post during translation. For example, the translation unit sets the level of translation detail based on the importance of the post during translation. Evaluation of the importance of a post includes, but is not limited to, for example, impact and urgency. For example, the translation unit provides a detailed translation for a post with high importance. The translation unit can also provide a simplified translation for a post with low importance. The translation unit can also determine the priority of the translation according to the importance. In this way, by adjusting the level of translation detail based on the importance of the post, detailed translation can be provided for important posts. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the translation unit can input post importance data into the generation AI and cause the generation AI to set the level of translation detail.

[0063] The translation unit can apply an appropriate translation algorithm depending on the category of the post during translation. For example, the translation unit applies an appropriate translation algorithm depending on the category of the post during translation. Post categories include, but are not limited to, news, entertainment, and technology. For example, the translation unit applies a specific translation algorithm to posts about safety information. The translation unit can also apply a different translation algorithm to posts requesting assistance. The translation unit can also apply an even different translation algorithm to posts about disaster information. In this way, by applying different translation algorithms depending on the category of the post, more appropriate translation results can be provided. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can input post category data into the generation AI and cause the generation AI to apply the translation algorithm.

[0064] The translation unit can improve the accuracy of translation based on the user's past translation results during translation. For example, the translation unit can improve the accuracy of translation based on the user's past translation results during translation. Analysis of past translation results includes, but is not limited to, the accuracy of the translation and user feedback. For example, the translation unit can improve the accuracy of the current translation based on the user's past translation results. The translation unit can also refer to the user's past translation results to perform optimal translations for similar posts. The translation unit can also analyze the user's past translation results and optimize the translation algorithm. This allows the current translation accuracy to be improved by referring to the user's past translation results. Some or all of the above-described processing in the translation unit can be performed using, or without, a generation AI. For example, the translation unit can input the user's past translation result data into the generation AI and have the generation AI improve the translation accuracy.

[0065] The translation unit can set translation priorities based on the submission time of the post during translation. The translation unit, for example, sets translation priorities based on the submission time of the post during translation. Evaluation of submission time includes, but is not limited to, for example, the submission date and time and the submission frequency. For example, the translation unit prioritizes translation of the most recent post. The translation unit can also set a lower translation priority for posts submitted earlier. The translation unit can also adjust the translation schedule according to the submission time. In this way, by determining translation priorities based on the submission time of the post, it is possible to prioritize translation of the most recent post. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the translation unit can input post submission time data into the generation AI and have the generation AI set the translation priorities.

[0066] The translation unit can set the order of translation based on the relevance of posts during translation. The translation unit, for example, sets the order of translation based on the relevance of posts during translation. The evaluation of relevance includes, but is not limited to, for example, a co-occurrence network or a similarity score. For example, the translation unit prioritizes translation for highly relevant posts. The translation unit can also postpone the order of translation for less relevant posts. The translation unit can also adjust the translation schedule according to the relevance of posts. In this way, by adjusting the order of translation based on the relevance of posts, highly relevant posts can be prioritized for translation. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can input post relevance data into the generation AI and cause the generation AI to set the order of translation.

[0067] The translation unit can set the use of technical terms in the translation according to the user's level of expertise during translation. For example, the translation unit can set the use of technical terms in the translation according to the user's level of expertise during translation. Evaluation of the level of expertise includes, but is not limited to, e.g., qualification information and past postings. For example, the translation unit can provide a translation that uses a lot of technical terms for a user with high level of expertise. The translation unit can also provide a translation in simpler language for a user with low level of expertise. The translation unit can also adjust the way the translation result is expressed according to the user's level of expertise. This allows for the provision of a translation result that is easier to understand by adjusting the use of technical terms in the translation according to the user's level of expertise. Some or all of the above-described processing in the translation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the translation unit can input the user's level of expertise data into the generation AI and have the generation AI execute the use of technical terms.

[0068] The acquisition unit can analyze the user's past location information history and select an appropriate acquisition method when acquiring location information. For example, the acquisition unit can analyze the user's past location information history and select an appropriate acquisition method when acquiring location information. The analysis of the past location information history includes, but is not limited to, past location data and movement patterns. For example, the acquisition unit can select an optimal acquisition method based on places the user has frequently visited in the past. The acquisition unit can also analyze the user's past location information history and suggest an efficient acquisition method. The acquisition unit can also optimize the timing of acquiring location information by referring to the user's past location information history. This allows the optimal acquisition method to be selected by analyzing the user's past location information history. Some or all of the above-described processing in the acquisition unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the acquisition unit can input the user's past location information history data into the generation AI and have the generation AI select an acquisition method.

[0069] The acquisition unit may perform filtering based on the user's current situation or areas of interest when acquiring location information. For example, the acquisition unit may perform filtering based on the user's current situation or areas of interest when acquiring location information. Filtering methods include, but are not limited to, survey results and behavioral history. For example, the acquisition unit may preferentially acquire location information for the area where the user is currently located. The acquisition unit may also preferentially acquire location information related to the user's areas of interest. The acquisition unit may also filter location information based on the user's current situation (e.g., whether the user is evacuating). By performing filtering based on the user's current situation and areas of interest, highly relevant location information can be preferentially acquired. Some or all of the above-described processing in the acquisition unit may be performed using, or without, a generation AI. For example, the acquisition unit may input the user's current situation and area of ​​interest data into the generation AI and cause the generation AI to perform filtering.

[0070] The acquisition unit can select an appropriate acquisition means according to the user's input method when acquiring location information. For example, the acquisition unit selects an appropriate acquisition means according to the user's input method when acquiring location information. Input methods include, but are not limited to, voice input, text input, and image input. For example, if the user selects voice input, the acquisition unit can acquire location information using voice recognition technology. Also, if the user selects text input, the acquisition unit can acquire location information using text analysis technology. Also, if the user posts an image, the acquisition unit can acquire location information using image analysis technology. This allows for smooth acquisition of location information by selecting the optimal acquisition means according to the user's input method. Some or all of the above-described processing in the acquisition unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the acquisition unit can input the user's input data to the generation AI and cause the generation AI to select the acquisition means.

[0071] The acquisition unit can prioritize acquisition of highly relevant location information based on the user's geographical location information when acquiring location information. For example, the acquisition unit prioritizes acquisition of highly relevant location information based on the user's geographical location information when acquiring location information. Methods for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. For example, the acquisition unit prioritizes acquisition of location information of a region where the user is currently located. The acquisition unit can also prioritize acquisition of related location information based on the user's geographical location information. The acquisition unit can also prioritize acquisition of location information for each region based on the user's geographical location information. This makes it possible to prioritize acquisition of highly relevant location information by taking the user's geographical location information into consideration. Some or all of the above-described processing in the acquisition unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the acquisition unit can input the user's geographical location information data to the generation AI and cause the generation AI to acquire highly relevant location information.

[0072] The acquisition unit may analyze the user's social media activity when acquiring the location information and acquire relevant location information. For example, the acquisition unit may analyze the user's social media activity when acquiring the location information and acquire relevant location information. Analysis of social media activity may include, but is not limited to, posting frequency and engagement. For example, the acquisition unit may acquire relevant location information based on location information shared by the user on social media. The acquisition unit may also analyze the user's social media activity history and prioritize acquisition of relevant location information. The acquisition unit may also acquire relevant location information by referring to the location information of the user's friends on social media. This allows for analysis of the user's social media activity to prioritize acquisition of relevant location information. Some or all of the above-described processing by the acquisition unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the acquisition unit may input the user's social media activity data into the generation AI and cause the generation AI to acquire relevant location information.

[0073] The acquisition unit can adjust the acquisition method by reflecting the user's past feedback when acquiring location information. For example, the acquisition unit adjusts the acquisition method by reflecting the user's past feedback when acquiring location information. Analysis of past feedback includes, but is not limited to, user ratings and comments. For example, the acquisition unit can propose an optimal acquisition method based on feedback provided by the user in the past. The acquisition unit can also customize the location information acquisition interface by reflecting the user's past feedback. The acquisition unit can also optimize the location information acquisition procedure based on the user's past feedback. This makes it possible to provide an optimal acquisition method by reflecting the user's past feedback. Some or all of the above-described processing in the acquisition unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the acquisition unit can input the user's past feedback data into the generation AI and cause the generation AI to adjust the acquisition method.

[0074] The ascertaining unit, when ascertaining safety information, can predict current safety information based on past safety information data. For example, when ascertaining safety information, the ascertaining unit predicts current safety information based on past safety information data. Analysis of past safety information data includes, for example, past disaster data and damage situations, but is not limited to these examples. For example, the ascertaining unit predicts current safety information based on past safety information data. The ascertaining unit can also refer to past safety information data to ascertain optimal safety information for similar situations. The ascertaining unit can also analyze past safety information data and optimize a safety information ascertaining algorithm. In this way, current safety information can be predicted by referring to past safety information data. Some or all of the above-described processing in the ascertaining unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the ascertaining unit can input past safety information data to the generation AI and cause the generation AI to predict safety information.

[0075] The ascertaining unit can apply an appropriate ascertaining method for each category of post when ascertaining safety information. For example, the ascertaining unit applies an appropriate ascertaining method for each category of post when ascertaining safety information. Post categories include, but are not limited to, news, entertainment, and technology. For example, the ascertaining unit applies a specific ascertaining method to posts of safety information. The ascertaining unit can also apply a different ascertaining method to posts requesting assistance. The ascertaining unit can also apply an even different ascertaining method to posts of disaster information. In this way, by applying different ascertaining methods to each category of post, more appropriate safety information can be provided. Some or all of the above-described processing by the ascertaining unit may be performed using, or without using, a generation AI. For example, the ascertaining unit can input post category data into the generation AI and cause the generation AI to apply the ascertaining method.

[0076] The ascertaining unit can analyze the safety information based on the poster's attribute information when ascertaining the safety information. For example, when ascertaining the safety information, the ascertaining unit analyzes the safety information based on the poster's attribute information. Evaluation of the poster's attribute information includes, but is not limited to, age, gender, and occupation. For example, the ascertaining unit analyzes the safety information taking into account the poster's reliability. The ascertaining unit can also ascertain related safety information based on the poster's attribute information. The ascertaining unit can also improve the accuracy of the analysis of the safety information by referring to the poster's past posting history. In this way, the accuracy of the analysis of the safety information can be improved by taking the poster's attribute information into consideration. Some or all of the above-described processing in the ascertaining unit may be performed using, or without using, the generation AI. For example, the ascertaining unit can input the poster's attribute information data into the generation AI and cause the generation AI to analyze the safety information.

[0077] The ascertaining unit, when ascertaining the safety information, can evaluate changes in the safety information based on the submission time of the post. For example, when ascertaining the safety information, the ascertaining unit evaluates changes in the safety information based on the submission time of the post. Evaluation of the submission time includes, but is not limited to, for example, the submission date and time and the submission frequency. For example, the ascertaining unit prioritizes analysis of recently submitted safety information. The ascertaining unit can also set a lower analysis priority for older submitted safety information. The ascertaining unit can also analyze changes in the safety information according to the submission time. In this way, by analyzing changes in the safety information based on the submission time of the post, more appropriate safety information can be provided. Some or all of the above-described processing by the ascertaining unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the ascertaining unit can input submission time data into the generation AI and cause the generation AI to evaluate changes in the safety information.

[0078] The ascertaining unit can analyze the safety information based on related market data when ascertaining the safety information. For example, the ascertaining unit analyzes the safety information based on related market data when ascertaining the safety information. Reference to related market data includes, but is not limited to, market research reports and sales data. For example, the ascertaining unit analyzes the safety information based on the related market data. The ascertaining unit can also refer to market data to improve the reliability of the safety information. The ascertaining unit can also analyze market data and optimize the algorithm for ascertaining the safety information. In this way, the reliability of the safety information can be improved by referring to the related market data. Some or all of the above-mentioned processing in the ascertaining unit may be performed using, or without using, the generation AI. For example, the ascertaining unit can input related market data to the generation AI and cause the generation AI to analyze the safety information.

[0079] The ascertaining unit can analyze the safety information based on the technological maturity when ascertaining the safety information. For example, the ascertaining unit analyzes the safety information based on the technological maturity when ascertaining the safety information. Evaluation of the technological maturity includes, but is not limited to, for example, the prevalence of technology and the evolutionary stage of technology. For example, the ascertaining unit sets a high reliability for information with a high level of technological maturity. The ascertaining unit can also set a low reliability for information with a low level of technological maturity. The ascertaining unit can also adjust the analysis accuracy of the safety information according to the technological maturity. In this way, the analysis accuracy of the safety information can be adjusted by taking the technological maturity into consideration. Some or all of the above-mentioned processing in the ascertaining unit may be performed using, or without using, the generation AI. For example, the ascertaining unit can input technical maturity data to the generation AI and cause the generation AI to analyze the safety information.

[0080] The distribution unit can predict current support needs based on past support data when distributing support needs. For example, the distribution unit predicts current support needs based on past support data when distributing support needs. Analysis of past support data includes, but is not limited to, past support activities and support effects. For example, the distribution unit predicts current support needs based on past support data. The distribution unit can also refer to past support data to distribute optimal support needs for similar situations. The distribution unit can also analyze past support data and optimize a support need distribution algorithm. This makes it possible to predict current support needs by referring to past support data. Some or all of the above-described processing in the distribution unit may be performed using, or without using, a generation AI. For example, the distribution unit can input past support data into the generation AI and cause the generation AI to predict support needs.

[0081] The distribution unit can apply an appropriate distribution method for each post category when distributing the support needs. For example, the distribution unit applies an appropriate distribution method for each post category when distributing the support needs. Post categories include, but are not limited to, news, entertainment, and technology. For example, the distribution unit applies a specific distribution method to support needs related to safety information. The distribution unit can also apply a different distribution method to support needs related to assistance requests. The distribution unit can also apply an even different distribution method to support needs related to disaster information. In this way, by applying different distribution methods to each post category, more appropriate support needs can be provided. Some or all of the above-described processing in the distribution unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the distribution unit can input post category data into the generation AI and cause the generation AI to apply the distribution method.

[0082] The distribution unit can analyze the support needs based on the poster's attribute information when distributing the support needs. For example, the distribution unit analyzes the support needs based on the poster's attribute information when distributing the support needs. Evaluation of the poster's attribute information includes, but is not limited to, age, gender, and occupation. For example, the distribution unit analyzes the support needs taking into account the poster's reliability. The distribution unit can also identify related support needs based on the poster's attribute information. The distribution unit can also improve the accuracy of the analysis of support needs by referring to the poster's past posting history. In this way, the accuracy of the analysis of support needs can be improved by taking the poster's attribute information into consideration. Some or all of the above-described processing in the distribution unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the distribution unit can input the poster's attribute information data into the generation AI and cause the generation AI to analyze the support needs.

[0083] The distribution unit can evaluate changes in support needs based on the submission time of the post when distributing the support needs. For example, the distribution unit evaluates changes in support needs based on the submission time of the post when distributing the support needs. Evaluation of the submission time includes, but is not limited to, for example, the submission date and time and the submission frequency. For example, the distribution unit prioritizes analysis of support needs that have been submitted recently. The distribution unit can also set a lower analysis priority for support needs that have been submitted older. The distribution unit can also analyze changes in support needs based on the submission time. This makes it possible to provide more appropriate support needs by analyzing changes in support needs based on the submission time of the post. Some or all of the above-described processing in the distribution unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the distribution unit can input submission time data into the generation AI and cause the generation AI to evaluate changes in support needs.

[0084] The distribution unit can analyze the support needs based on related market data when distributing the support needs. For example, the distribution unit analyzes the support needs based on related market data when distributing the support needs. Reference to related market data includes, but is not limited to, market research reports and sales data. For example, the distribution unit analyzes the support needs based on the related market data. The distribution unit can also refer to market data to improve the reliability of the support needs. The distribution unit can also analyze market data and optimize the distribution algorithm for the support needs. In this way, the reliability of the support needs can be improved by referring to the related market data. Some or all of the above-mentioned processing in the distribution unit may be performed using, or without using, the generation AI. For example, the distribution unit can input related market data into the generation AI and cause the generation AI to analyze the support needs.

[0085] The distribution unit can analyze the support needs based on the technological maturity when distributing the support needs. For example, the distribution unit analyzes the support needs based on the technological maturity when distributing the support needs. Evaluation of the technological maturity includes, but is not limited to, for example, the prevalence of technology and the evolutionary stage of technology. For example, the distribution unit sets a high reliability for information with a high level of technological maturity. The distribution unit can also set a low reliability for information with a low level of technological maturity. The distribution unit can also adjust the analysis accuracy of the support needs according to the technological maturity. In this way, the analysis accuracy of the support needs can be adjusted by taking the technological maturity into consideration. Some or all of the above-mentioned processing in the distribution unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the distribution unit can input the technological maturity data into the generation AI and cause the generation AI to analyze the support needs.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The reception unit can analyze the user's past posting history and understand trends in the content of posts. For example, it can provide related templates based on the content that the user frequently posted in the past. It can also analyze the time periods when the user posted in the past and suggest the optimal timing for posting. It can also analyze the user's reactions to past posts and suggest areas for improving the content of posts. This makes it possible to post more effectively by utilizing the user's past posting history.

[0088] The identification unit can take into account the poster's past posting history when evaluating the reliability of posted content. For example, it can prioritize information from posters who have provided reliable information in the past. It can also be wary of information from posters who have provided false information in the past. Furthermore, it can analyze the poster's past posted content and evaluate their expertise in a specific field. This allows for more accurate evaluation of the reliability of posted content.

[0089] The translation unit can analyze a user's past translation history to improve translation accuracy. For example, it can learn from past translation corrections made by the user and avoid similar mistakes. It can also analyze a user's translation style and provide individually optimized translations. Furthermore, it can customize translations of specific terms and phrases based on the user's past translation history. This provides a more natural translation result for the user.

[0090] The grasping unit can analyze the user's past safety information and evaluate the reliability of the current safety information. For example, it can prioritize information from users who have provided accurate safety information in the past. It can also be wary of information from users who have provided incorrect safety information in the past. Furthermore, it can grasp trends in safety information in specific regions or situations based on past safety information. This allows for more accurate evaluation of the reliability of safety information.

[0091] The distribution unit can analyze the results of distribution of past support needs and optimize the method of distribution of current support needs. For example, it can reuse distribution methods that were effective in the past. It can also improve distribution methods that had problems in the past. Furthermore, it can propose the optimal distribution method for a specific situation based on the results of distribution of past support needs. This makes it possible to distribute support needs more effectively.

[0092] The processing flow of the first embodiment will be briefly explained below.

[0093] Step 1: The reception unit accepts posts from users. Posts from users include text, images, videos, etc. The reception unit can accept posts from smartphones and PCs, and supports various input methods such as voice input and image input. Step 2: The analysis unit uses a generation AI to analyze and summarize the posts received by the reception unit. The analysis is performed using natural language processing technology and multimodal generation AI. For example, a text generation AI (LLM) is used to analyze and summarize the posts. Step 3: The identification unit uses the generation AI to identify the posted content analyzed by the analysis unit. Identification is performed using a misinformation detection algorithm to evaluate the reliability of the posted content and identify misinformation. Step 4: The warning unit warns the user of the misinformation identified by the identification unit. The warning is given by a pop-up notification, an email notification, or the like, and displays a warning to the user when misinformation is identified. Step 5: The translation department uses generative AI to translate posts in different languages. The translation is done through methods such as real-time translation and batch translation, and posts in different languages ​​are translated in real time. Step 6: The acquisition unit acquires location information. The location information is acquired by methods such as GPS data or IP address, and is acquired from the user's smartphone or PC. Step 7: The ascertaining unit ascertains safety information for each region based on the location information acquired by the acquiring unit. The ascertaining is performed by methods such as confirming the safety of users and ascertaining the damage situation. Step 8: The distribution unit distributes support needs based on the information obtained by the identification unit. The distribution is carried out in the form of a request for supplies or medical support.

[0094] (Example 2) A disaster information sharing platform according to an embodiment of the present invention is a system that automatically accepts user posts, analyzes and summarizes them using a generation AI, identifies misinformation, displays warnings, translates posts in different languages, acquires location information, identifies safety information for each region, and distributes information on support needs. The disaster information sharing platform analyzes and summarizes user posts in real time, enabling rapid and accurate information sharing. For example, if a user posts something like "My family is safe" during a disaster, the generation AI analyzes and summarizes the content and displays it as "Family Safety Confirmation." The generation AI then analyzes the content of the post and identifies misinformation. For example, if incorrect information is posted, the generation AI identifies the information and displays a warning to the user. It also supports multiple languages, translating posts in different languages ​​in real time, enabling access to a wide community. Under normal circumstances, it functions as a forum for sharing information to prepare for disasters and strengthen local communities. For example, information on local disaster prevention drills and disaster preparedness is shared. This raises disaster prevention awareness throughout the community and facilitates disaster response. During disasters, safety information and requests for support can be posted and viewed smoothly. For example, if a disaster victim posts a request for assistance, such as "Water is in short supply," the AI ​​analyzes the information and identifies the assistance needs of each region. This enables efficient delivery of assistance. Furthermore, location information can be used to grasp the safety information of each region. For example, if many safety information posts are made in a specific region, the situation in that region can be quickly grasped. This supports rapid information sharing and safe communication during disasters. This allows the disaster information sharing platform to support rapid information sharing and safe communication during disasters, setting a new standard for disaster response. For example, by quickly and accurately analyzing user posts, identifying misinformation, and displaying warnings, accurate information sharing is possible. Furthermore, real-time translation of posts in different languages ​​enables access to a wide community. Furthermore, location information can be used to grasp the safety information of each region and efficiently deliver assistance needs.

[0095] A disaster information sharing platform according to an embodiment includes a reception unit, an analysis unit, an identification unit, a warning unit, a translation unit, an acquisition unit, a comprehension unit, and a distribution unit. The reception unit receives posts from users. The posts from users include, but are not limited to, text, images, and videos. The reception unit can receive posts from, for example, a smartphone or a PC. The reception unit can also support various input methods, such as voice input and image input. The analysis unit uses a generation AI to analyze and summarize the posts received by the reception unit. The analysis is performed using, for example, natural language processing technology, but is not limited to, for example. For example, the generation AI analyzes and summarizes the posts using a text generation AI (e.g., LLM). The analysis unit can also analyze and summarize the content of the posts using a multimodal generation AI. The analysis unit can also extract and summarize important parts of the text using the generation AI. The identification unit uses the generation AI to identify the content of the posts analyzed by the analysis unit. The identification is performed using, for example, a misinformation detection algorithm, but is not limited to, such an example. For example, the identification unit uses a generation AI to evaluate the reliability of the posted content and identify the misinformation. The warning unit warns of the misinformation identified by the identification unit. The warning is performed by, for example, a pop-up notification or an email notification, but is not limited to, such an example. For example, the warning unit displays a warning to the user when misinformation is identified. The translation unit uses a generation AI to translate posts in different languages. The translation is performed by, for example, a real-time translation or a batch translation, but is not limited to, such an example. For example, the translation unit translates posts in different languages ​​in real time using the generation AI. The acquisition unit acquires location information. The location information is acquired by, for example, a GPS data or an IP address, but is not limited to, such an example. For example, the acquisition unit acquires location information from the user's smartphone or PC. The understanding unit understands safety information for each region based on the location information acquired by the acquisition unit. The understanding is performed by, for example, a method of checking the user's safety and understanding the damage situation, but is not limited to, such an example. For example, the ascertaining unit ascertains safety information for each region based on the acquired location information.The distribution unit distributes support needs based on the information grasped by the grasping unit. The distribution may be, for example, a request for supplies or medical assistance, but is not limited to such examples. For example, the distribution unit distributes support needs based on the grasped information. As a result, the disaster information sharing platform according to the embodiment can analyze and summarize posts from users in real time, enabling rapid and accurate information sharing. For example, accurate information sharing is possible by quickly and accurately analyzing posts written by users, identifying misinformation, and displaying warnings. Furthermore, real-time translation of posts written in different languages ​​enables access to a wide community. Furthermore, location information can be used to grasp safety information for each region and efficiently distribute support needs.

[0096] The reception unit can accept posts from a smartphone or a PC. The reception unit accepts posts from, for example, a smartphone or a PC. Examples of smartphones or PCs include, but are not limited to, operating systems such as iOS, Android, and Windows. For example, the reception unit can accept posts through a smartphone app. The reception unit can also accept posts through a PC web browser. This improves user convenience by accepting posts from smartphones and PCs. Some or all of the above-described processing in the reception unit may be performed using, or without, AI. For example, the reception unit can input posts from a smartphone or PC into a generation AI and have the generation AI analyze the content of the posts.

[0097] The analysis unit can analyze and summarize posts using natural language processing technology. The analysis unit can analyze and summarize posts using, for example, natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, semantic analysis, etc., but is not limited to these examples. For example, the analysis unit can analyze and summarize words in posts using morphological analysis. The analysis unit can also analyze and summarize the sentence structure of posts using grammatical analysis. The analysis unit can also analyze and summarize the meaning of posts using semantic analysis. This improves the accuracy of post analysis and summarization by using natural language processing technology. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input the content of the post into a generation AI and have the generation AI analyze and summarize the content of the post.

[0098] The identification unit can identify misinformation. The identification unit, for example, identifies misinformation. Misinformation includes, for example, false information and misleading information, but is not limited to these examples. For example, the identification unit identifies misinformation using a misinformation detection algorithm. The identification unit can also evaluate the reliability of the posted content and identify misinformation. The identification unit can also identify misinformation by taking into account the interrelationships between posts. This enables accurate information sharing by identifying misinformation. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the identification unit can input the posted content into the generation AI and have the generation AI identify the misinformation.

[0099] The warning unit can display a warning to the user when false information is identified. The warning unit displays a warning to the user when false information is identified, for example. Methods of displaying the warning include, but are not limited to, pop-up notifications, email notifications, etc. For example, the warning unit displays a pop-up notification when false information is identified. The warning unit can also send an email notification when false information is identified. The warning unit can also display an in-app notification when false information is identified. In this way, accurate information is provided to the user by displaying a warning when false information is identified. Some or all of the above-described processing in the warning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the warning unit can input the result of identifying false information to the generation AI and cause the generation AI to display the warning.

[0100] The translation unit can instantly translate posts in different languages. For example, the translation unit instantly translates posts in different languages. Translation methods include, but are not limited to, real-time translation, batch translation, and the like. For example, the translation unit instantly translates posts in different languages ​​using real-time translation. The translation unit can also translate posts in different languages ​​using batch translation. The translation unit can also translate posts in different languages ​​using a generation AI. This enables access to a wider community by translating posts in different languages ​​in real time. Some or all of the above-described processing in the translation unit may be performed using, or without, the generation AI. For example, the translation unit can input posts in different languages ​​into the generation AI and have the generation AI perform the translation.

[0101] The acquisition unit can acquire location information. The acquisition unit acquires, for example, location information. Methods for acquiring location information include, but are not limited to, GPS data, IP addresses, etc. For example, the acquisition unit acquires GPS data from the user's smartphone. The acquisition unit can also acquire an IP address from the user's PC. The acquisition unit can also acquire the user's location information in real time. By acquiring the location information, it becomes possible to grasp safety information for each region. Some or all of the above-mentioned processing in the acquisition unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the acquisition unit can input the user's location information to the generation AI and have the generation AI analyze the location information.

[0102] The grasping unit can grasp the safety information for each region based on the acquired location information. The grasping unit grasps the safety information for each region based on, for example, the acquired location information. Methods of grasping the safety information include, for example, checking the safety of users and grasping the damage situation, but are not limited to these examples. For example, the grasping unit grasps the safety information for each region based on the acquired location information. The grasping unit can also grasp the safety information by analyzing the content posted by users. The grasping unit can also grasp the safety information for each region in real time. This enables rapid information sharing by grasping the safety information for each region. Some or all of the above-mentioned processing in the grasping unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the grasping unit can input the acquired location information to the generation AI and cause the generation AI to grasp the safety information.

[0103] The distribution unit can distribute support needs based on the grasped information. The distribution unit distributes support needs based on, for example, the grasped information. Methods of distributing support needs include, for example, the need for supplies, a request for medical support, etc., but are not limited to these examples. For example, the distribution unit distributes the need for supplies based on the grasped information. The distribution unit can also distribute a request for medical support. The distribution unit can also distribute support needs for each region in real time. This enables efficient distribution of support by distributing the support needs. Some or all of the above-mentioned processing in the distribution unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the distribution unit can input the grasped information into a generation AI and cause the generation AI to distribute the support needs.

[0104] The reception unit can estimate a user's emotion and set the timing for accepting posts based on the estimated user emotion. The reception unit, for example, estimates a user's emotion and sets the timing for accepting posts based on the estimated user emotion. The emotion estimation uses, for example, an emotion analysis algorithm, but is not limited to this example. For example, the reception unit analyzes a user's facial expression to estimate the emotion. The reception unit can also analyze a user's voice to estimate the emotion. The reception unit can also analyze a user's biometric data to estimate the emotion. This allows the timing for accepting posts to be adjusted according to the user's emotion, thereby allowing posts to be accepted at a more appropriate time. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the reception unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0105] The reception unit can analyze the user's past posting history and select an appropriate reception method when receiving a post. For example, the reception unit analyzes the user's past posting history and selects an appropriate reception method when receiving a post. Analysis of the past posting history includes, but is not limited to, methods such as text mining and frequency analysis. For example, the reception unit prioritizes suggesting a posting method that the user has frequently used in the past. The reception unit can also analyze the content of the user's past posts and provide related templates. The reception unit can also suggest the optimal reception method for a specific time period based on the user's past posting history. This allows the optimal reception method to be selected by analyzing the user's past posting history. Some or all of the above-described processing by the reception unit may be performed using, or without, a generation AI. For example, the reception unit can input the user's past posting history into the generation AI and have the generation AI select a reception method.

[0106] The reception unit may filter posts based on the user's current situation or areas of interest when receiving the posts. For example, the reception unit may filter posts based on the user's current situation or areas of interest when receiving the posts. Filtering methods include, but are not limited to, survey results and behavioral history. For example, the reception unit may prioritize disaster information for the user's current location. The reception unit may also prioritize posts related to the user's areas of interest. The reception unit may also determine the priority of posts based on the user's current situation (e.g., whether the user is evacuating). By filtering based on the user's current situation and areas of interest, highly relevant posts can be prioritized. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit may input the user's current situation and areas of interest into the generation AI and have the generation AI perform filtering.

[0107] The reception unit can select an appropriate reception means depending on the user's input method when receiving a post. For example, the reception unit selects an appropriate reception means depending on the user's input method when receiving a post. Input methods include, but are not limited to, voice input, text input, and image input. For example, if the user selects voice input, the reception unit can use voice recognition technology to receive the post. Furthermore, if the user selects text input, the reception unit can also use text analysis technology to receive the post. Furthermore, if the user posts an image, the reception unit can analyze the content of the post using image analysis technology and receive it. This allows for smooth reception of posts by selecting the optimal reception means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the user's input data into the generation AI and have the generation AI select the reception means.

[0108] The reception unit can estimate the user's emotions and determine the priority of posts to be received based on the estimated user emotions. The reception unit, for example, estimates the user's emotions and determines the priority of posts to be received based on the estimated user emotions. The emotion estimation can be performed using, for example, an emotion analysis algorithm, but is not limited to this example. For example, the reception unit can analyze the user's facial expression to estimate the emotion. The reception unit can also analyze the user's voice to estimate the emotion. The reception unit can also analyze the user's biometric data to estimate the emotion. This allows for the priority of posts to be determined based on the user's emotions, thereby enabling important posts to be addressed quickly. The emotion estimation can be achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to this example. Some or all of the above-described processing in the reception unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the reception unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0109] The reception unit may prioritize receiving posts that are highly relevant based on the user's geographical location information when receiving posts. For example, the reception unit may prioritize receiving posts that are highly relevant based on the user's geographical location information when receiving posts. Methods for acquiring geographical location information include, but are not limited to, GPS data, IP addresses, and the like. For example, the reception unit may prioritize receiving disaster information for the user's current area. The reception unit may also prioritize receiving related assistance requests based on the user's geographical location information. The reception unit may also prioritize receiving safety information for each area based on the user's geographical location information. This allows highly relevant posts to be prioritized by taking the user's geographical location information into consideration. Some or all of the above-described processing by the reception unit may be performed using, or without, a generation AI. For example, the reception unit may input the user's geographical location information into the generation AI and cause the generation AI to receive highly relevant posts.

[0110] The reception unit can analyze the user's social media activity when receiving a post and receive relevant posts. For example, the reception unit can analyze the user's social media activity when receiving a post and receive relevant posts. Analysis of social media activity includes, but is not limited to, posting frequency and engagement. For example, the reception unit can receive relevant posts based on information shared by the user on social media. The reception unit can also analyze the user's social media activity history and preferentially receive relevant posts. The reception unit can also receive related posts based on posts made by the user's friends on social media. In this way, by analyzing the user's social media activity, relevant posts can be preferentially received. Some or all of the above-described processing by the reception unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the reception unit can input the user's social media activity data into the generation AI and cause the generation AI to receive relevant posts.

[0111] The reception unit can adjust the reception method by reflecting the user's past feedback when receiving a post. For example, the reception unit adjusts the reception method by reflecting the user's past feedback when receiving a post. Analysis of past feedback includes, but is not limited to, user ratings and comments. For example, the reception unit proposes an optimal reception method based on feedback previously provided by the user. The reception unit can also customize the reception interface by reflecting the user's past feedback. The reception unit can also optimize the reception procedure based on the user's past feedback. In this way, the optimal reception method can be provided by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can input the user's past feedback data into the generation AI and cause the generation AI to adjust the reception method.

[0112] The analysis unit can estimate the user's emotion and set the analysis expression method based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and sets the analysis expression method based on the estimated user's emotion. The emotion estimation can be performed using, for example, an emotion analysis algorithm, but is not limited to this example. For example, the analysis unit can analyze the user's facial expression to estimate the emotion. The analysis unit can also analyze the user's voice to estimate the emotion. The analysis unit can also analyze the user's biometric data to estimate the emotion. This allows for adjusting the analysis expression method according to the user's emotion, thereby providing more appropriate analysis results. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0113] The analysis unit can set the level of detail of the analysis based on the importance of the post during analysis. For example, the analysis unit sets the level of detail of the analysis based on the importance of the post during analysis. Evaluation of the importance of a post includes, but is not limited to, for example, impact and urgency. For example, the analysis unit performs a detailed analysis on posts with high importance. The analysis unit can also perform a simplified analysis on posts with low importance. The analysis unit can also determine the priority of the analysis according to the importance. In this way, by adjusting the level of detail of the analysis based on the importance of the post, detailed analysis can be performed on important posts. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input post importance data to the generation AI and cause the generation AI to set the level of detail of the analysis.

[0114] The analysis unit can apply an appropriate analysis algorithm depending on the category of the post during analysis. For example, the analysis unit applies an appropriate analysis algorithm depending on the category of the post during analysis. Post categories include, but are not limited to, news, entertainment, and technology. For example, the analysis unit applies a specific analysis algorithm to posts about safety information. The analysis unit can also apply a different analysis algorithm to posts requesting assistance. The analysis unit can also apply an even different analysis algorithm to posts about disaster information. In this way, by applying different analysis algorithms depending on the category of the post, more appropriate analysis results can be provided. Some or all of the above-described processing by the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input post category data into the generation AI and cause the generation AI to apply the analysis algorithm.

[0115] The analysis unit can improve the accuracy of the analysis based on the user's past analysis results during analysis. For example, the analysis unit can improve the accuracy of the analysis based on the user's past analysis results during analysis. Examples of analysis of past analysis results include, but are not limited to, text mining and frequency analysis. For example, the analysis unit can improve the accuracy of the current analysis based on the user's past analysis results. The analysis unit can also refer to the user's past analysis results to perform optimal analysis of similar posts. The analysis unit can also analyze the user's past analysis results and optimize the analysis algorithm. This allows the accuracy of the current analysis to be improved by referring to the user's past analysis results. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the user's past analysis result data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0116] The analysis unit can estimate the user's emotion and set the length of the analysis based on the estimated user's emotion. The analysis unit can estimate the user's emotion and set the length of the analysis based on the estimated user's emotion. The emotion estimation can be performed using, for example, an emotion analysis algorithm, but is not limited to, this example. For example, the analysis unit can analyze the user's facial expression to estimate the emotion. The analysis unit can also analyze the user's voice to estimate the emotion. The analysis unit can also analyze the user's biometric data to estimate the emotion. This allows for adjusting the length of the analysis based on the user's emotion, thereby providing more appropriate analysis results. The emotion estimation can be achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, the generation AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0117] The analysis unit can set analysis priorities based on the submission time of posts during analysis. For example, the analysis unit sets analysis priorities based on the submission time of posts during analysis. Evaluation of submission time includes, but is not limited to, the submission date and time and the submission frequency. For example, the analysis unit prioritizes analysis of the most recent posts. The analysis unit can also set a lower analysis priority for posts submitted earlier. The analysis unit can also adjust the analysis schedule according to the submission time. By determining the analysis priority based on the submission time of posts, the most recent posts can be prioritized for analysis. Some or all of the above-described processing by the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input post submission time data into the generation AI and cause the generation AI to set the analysis priorities.

[0118] The analysis unit can set the analysis order based on the relevance of posts during analysis. The analysis unit, for example, sets the analysis order based on the relevance of posts during analysis. The relevance evaluation includes, for example, a co-occurrence network or a similarity score, but is not limited to these examples. For example, the analysis unit prioritizes analysis of highly relevant posts. The analysis unit can also postpone the analysis order of less relevant posts. The analysis unit can also adjust the analysis schedule according to the relevance of posts. By adjusting the analysis order based on the relevance of posts, highly relevant posts can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input relevance data of posts into the generation AI and cause the generation AI to set the analysis order.

[0119] The analysis unit can set the use of technical terms in the analysis according to the user's level of expertise during analysis. For example, the analysis unit can set the use of technical terms in the analysis according to the user's level of expertise during analysis. Evaluation of the level of expertise includes, but is not limited to, e.g., qualification information and past posting content. For example, the analysis unit can provide analysis results that use a lot of technical terms to users with high levels of expertise. The analysis unit can also provide analysis results in simpler terms to users with low levels of expertise. The analysis unit can also adjust the way the analysis results are presented according to the user's level of expertise. By adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input the user's level of expertise data into the generation AI and have the generation AI execute the use of technical terms.

[0120] The identification unit can estimate the user's emotion and set the identification criteria based on the estimated user's emotion. For example, the identification unit can estimate the user's emotion and set the identification criteria based on the estimated user's emotion. The emotion estimation can be performed using, for example, an emotion analysis algorithm, but is not limited to this example. For example, the identification unit can analyze the user's facial expression to estimate the emotion. The identification unit can also analyze the user's voice to estimate the emotion. The identification unit can also analyze the user's biometric data to estimate the emotion. This allows for adjusting the identification criteria according to the user's emotion, thereby providing more appropriate identification results. The emotion estimation can be achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the identification unit can be performed using, for example, the generation AI. For example, the identification unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0121] The identification unit can improve the accuracy of identification based on the interrelationships between posts during identification. For example, the identification unit improves the accuracy of identification based on the interrelationships between posts during identification. Evaluation of the interrelationships between posts includes, but is not limited to, a co-occurrence network or a similarity score. For example, the identification unit analyzes the interrelationships between multiple posts to improve the accuracy of identifying misinformation. The identification unit can also identify related information by taking the interrelationships between posts into consideration. The identification unit can also optimize the identification algorithm based on the interrelationships between posts. In this way, the accuracy of identification can be improved by taking the interrelationships between posts into consideration. Some or all of the above-described processing in the identification unit may be performed using, or without, a generation AI. For example, the identification unit can input post interrelationship data into the generation AI and cause the generation AI to improve the accuracy of identification.

[0122] The identification unit can perform identification based on attribute information of the submitter of the post. For example, the identification unit performs identification based on attribute information of the submitter of the post. Evaluation of the submitter's attribute information includes, but is not limited to, age, gender, and occupation. For example, the identification unit improves the accuracy of identifying false information by taking into account the submitter's reliability. The identification unit can also identify related information based on the submitter's attribute information. The identification unit can also improve the accuracy of identification by referring to the submitter's past posting history. In this way, the accuracy of identification can be improved by taking into account the attribute information of the submitter of the post. Some or all of the above-described processing in the identification unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the identification unit can input the submitter's attribute information data into the generation AI and have the generation AI perform the identification.

[0123] The identification unit can set an identification weight based on the submission frequency of posts during identification. The identification unit, for example, sets an identification weight based on the submission frequency of posts during identification. Evaluation of the submission frequency includes, but is not limited to, for example, the number of submissions and the submission interval. For example, the identification unit can set a high identification weight for posts submitted frequently. The identification unit can also set a low identification weight for posts submitted infrequently. The identification unit can also determine an identification priority according to the submission frequency. In this way, by assigning an identification weight based on the submission frequency of posts, it is possible to determine an identification priority. Some or all of the above-described processing in the identification unit may be performed using, or without, a generation AI. For example, the identification unit can input submission frequency data to the generation AI and cause the generation AI to perform the identification weighting.

[0124] The identification unit can estimate the user's emotion and set the order in which the identification results are displayed based on the estimated user's emotion. The identification unit can, for example, estimate the user's emotion and set the order in which the identification results are displayed based on the estimated user's emotion. The emotion estimation can be performed using, for example, an emotion analysis algorithm, but is not limited to, this example. For example, the identification unit can analyze the user's facial expression to estimate the emotion. The identification unit can also analyze the user's voice to estimate the emotion. The identification unit can also analyze the user's biometric data to estimate the emotion. This allows important identification results to be displayed preferentially by adjusting the order in which the identification results are displayed based on the user's emotion. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the identification unit can be performed using, for example, the generation AI, or without the generation AI. For example, the identification unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0125] The identification unit may perform identification based on the geographic distribution of posts during identification. For example, the identification unit may perform identification based on the geographic distribution of posts during identification. Evaluation of the geographic distribution may include, but is not limited to, the number of posts by region and the geographical extent of influence. For example, if there are many posts in a specific region, the identification unit may preferentially identify information about that region. The identification unit may also identify related information based on the geographic distribution. The identification unit may also optimize the identification algorithm taking the geographic distribution into account. This allows related information to be preferentially identified by taking the geographic distribution of posts into account. Some or all of the above-described processing in the identification unit may be performed using, or without, a generation AI. For example, the identification unit may input geographic distribution data of posts into the generation AI and have the generation AI perform the identification.

[0126] The identification unit can improve the accuracy of identification by referring to related literature of the post during identification. For example, the identification unit can improve the accuracy of identification by referring to related literature of the post during identification. References to related literature include, but are not limited to, academic papers and technical reports. For example, the identification unit can improve the accuracy of identification by referring to literature related to the content of the post. The identification unit can also improve the accuracy of identifying misinformation based on the related literature. The identification unit can also analyze related literature of the post and optimize the identification algorithm. By referring to related literature of the post, the accuracy of identification can be improved. Some or all of the above-described processing in the identification unit can be performed using, or without, a generation AI. For example, the identification unit can input related literature data of the post into the generation AI and have the generation AI perform the identification.

[0127] The identification unit can perform identification based on the market value of the post during identification. For example, the identification unit performs identification based on the market value of the post during identification. Market value evaluations include, but are not limited to, sales forecasts and market shares. For example, the identification unit can assign a high identification weight to information with high market value. The identification unit can also assign a low identification weight to information with low market value. The identification unit can also determine the priority of identification according to the market value. This makes it possible to adjust the identification weight by taking the market value of the post into consideration. Some or all of the above-described processing in the identification unit may be performed using, or without, the generation AI. For example, the identification unit can input market value data to the generation AI and have the generation AI perform the identification.

[0128] The warning unit can estimate the user's emotion and set a warning display method based on the estimated user's emotion. The warning unit can estimate the user's emotion and set a warning display method based on the estimated user's emotion. The emotion estimation can be performed using, for example, an emotion analysis algorithm, but is not limited to this example. For example, the warning unit can analyze the user's facial expression to estimate the emotion. The warning unit can also analyze the user's voice to estimate the emotion. The warning unit can also analyze the user's biometric data to estimate the emotion. This allows for adjusting the warning display method according to the user's emotion, thereby providing a more appropriate warning. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the warning unit can be performed using, for example, the generation AI. For example, the warning unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0129] The warning unit can set the level of detail of the warning based on the importance of the misinformation when issuing a warning. For example, the warning unit sets the level of detail of the warning based on the importance of the misinformation when issuing a warning. Evaluation of the importance of the misinformation includes, but is not limited to, impact and urgency. For example, the warning unit displays a detailed warning for misinformation with a high level of importance. The warning unit can also display a simplified warning for misinformation with a low level of importance. The warning unit can also determine the priority of the warning based on the importance. This allows a detailed warning to be issued for important misinformation by adjusting the level of detail of the warning based on the importance of the misinformation. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input importance data of the misinformation into the generation AI and have the generation AI set the level of detail of the warning.

[0130] The warning unit can apply an appropriate warning algorithm depending on the category of misinformation when issuing a warning. For example, the warning unit applies an appropriate warning algorithm depending on the category of misinformation when issuing a warning. Examples of categories of misinformation include, but are not limited to, news, entertainment, and technology. For example, the warning unit applies a specific warning algorithm to misinformation about safety information. The warning unit can also apply a different warning algorithm to misinformation about assistance requests. The warning unit can also apply an even different warning algorithm to misinformation about disaster information. In this way, by applying different warning algorithms depending on the category of misinformation, more appropriate warnings can be provided. Some or all of the above-mentioned processing in the warning unit may be performed using, or without using, a generation AI. For example, the warning unit can input category data of the misinformation into the generation AI and cause the generation AI to apply the warning algorithm.

[0131] The warning unit can improve the accuracy of the warning based on the user's past warning results when issuing a warning. For example, the warning unit can improve the accuracy of the warning based on the user's past warning results when issuing a warning. Analysis of past warning results includes, but is not limited to, the effectiveness of the warning and the user's reaction. For example, the warning unit can improve the accuracy of the current warning based on the user's past warning results. The warning unit can also refer to the user's past warning results to provide an optimal warning for similar misinformation. The warning unit can also analyze the user's past warning results and optimize the warning algorithm. This allows the accuracy of the current warning to be improved by referring to the user's past warning results. Some or all of the above-described processing in the warning unit can be performed using, or without, a generation AI. For example, the warning unit can input the user's past warning result data into the generation AI and cause the generation AI to improve the accuracy of the warning.

[0132] The warning unit can estimate the user's emotion and set the length of the warning based on the estimated user's emotion. The warning unit can estimate the user's emotion and set the length of the warning based on the estimated user's emotion, for example. The emotion estimation can be performed using, but is not limited to, an emotion analysis algorithm. For example, the warning unit can analyze the user's facial expression to estimate the emotion. The warning unit can also analyze the user's voice to estimate the emotion. The warning unit can also analyze the user's biometric data to estimate the emotion. This allows for adjusting the length of the warning based on the user's emotion, thereby providing a more appropriate warning. The emotion estimation can be achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the warning unit can be performed using, for example, the generation AI. For example, the warning unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0133] The warning unit can set a priority of the warning based on the time of submission of the misinformation when issuing a warning. For example, the warning unit can set a priority of the warning based on the time of submission of the misinformation when issuing a warning. Evaluation of the submission time includes, but is not limited to, the submission date and time and the frequency of submission. For example, the warning unit can prioritize issuing a warning for the most recent misinformation. The warning unit can also set a lower priority of the warning for misinformation that was submitted earlier. The warning unit can also adjust the warning schedule according to the time of submission. By determining the priority of the warning based on the time of submission of the misinformation, it is possible to prioritize issuing a warning for the most recent misinformation. Some or all of the above-described processing in the warning unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the warning unit can input data on the time of submission of the misinformation into the generation AI and cause the generation AI to set the priority of the warning.

[0134] The warning unit can set the order of warnings based on the relevance of the misinformation when issuing a warning. For example, the warning unit sets the order of warnings based on the relevance of the misinformation when issuing a warning. Examples of the evaluation of relevance include, but are not limited to, a co-occurrence network and a similarity score. For example, the warning unit prioritizes issuing a warning for highly relevant misinformation. The warning unit can also postpone issuing a warning for less relevant misinformation. The warning unit can also adjust the warning schedule according to the relevance of the misinformation. In this way, by adjusting the order of warnings based on the relevance of the misinformation, it is possible to prioritize issuing a warning for highly relevant misinformation. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input relevance data of the misinformation into the generation AI and cause the generation AI to set the order of warnings.

[0135] The warning unit may set the use of technical terms in the warning according to the user's level of expertise when issuing a warning. For example, the warning unit may set the use of technical terms in the warning according to the user's level of expertise when issuing a warning. Evaluation of the level of expertise may include, but is not limited to, e.g., qualifications and past postings. For example, the warning unit may display a warning that uses a lot of technical terms for users with high levels of expertise. The warning unit may also display a warning in simpler language for users with low levels of expertise. The warning unit may also adjust the way the warning is expressed according to the user's level of expertise. This allows for providing a more understandable warning by adjusting the use of technical terms in the warning according to the user's level of expertise. Some or all of the above-described processing in the warning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the warning unit may input the user's level of expertise data into the generation AI and cause the generation AI to use technical terms.

[0136] The translation unit can estimate the user's emotion and set the translation expression method based on the estimated user's emotion. The translation unit can estimate the user's emotion and set the translation expression method based on the estimated user's emotion, for example. The emotion estimation can be performed using, but is not limited to, an emotion analysis algorithm. For example, the translation unit can analyze the user's facial expression to estimate the emotion. The translation unit can also analyze the user's voice to estimate the emotion. The translation unit can also analyze the user's biometric data to estimate the emotion. This allows the translation expression method to be adjusted according to the user's emotion, thereby providing a more appropriate translation result. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the translation unit can be performed using, for example, the generation AI, or without the generation AI. For example, the translation unit can input the user's emotional data into the generation AI and have the generation AI perform emotion estimation.

[0137] The translation unit can set the level of translation detail based on the importance of the post during translation. For example, the translation unit sets the level of translation detail based on the importance of the post during translation. Evaluation of the importance of a post includes, but is not limited to, for example, impact and urgency. For example, the translation unit provides a detailed translation for a post with high importance. The translation unit can also provide a simplified translation for a post with low importance. The translation unit can also determine the priority of the translation according to the importance. In this way, by adjusting the level of translation detail based on the importance of the post, detailed translation can be provided for important posts. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the translation unit can input post importance data into the generation AI and cause the generation AI to set the level of translation detail.

[0138] The translation unit can apply an appropriate translation algorithm depending on the category of the post during translation. For example, the translation unit applies an appropriate translation algorithm depending on the category of the post during translation. Post categories include, but are not limited to, news, entertainment, and technology. For example, the translation unit applies a specific translation algorithm to posts about safety information. The translation unit can also apply a different translation algorithm to posts requesting assistance. The translation unit can also apply an even different translation algorithm to posts about disaster information. In this way, by applying different translation algorithms depending on the category of the post, more appropriate translation results can be provided. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can input post category data into the generation AI and cause the generation AI to apply the translation algorithm.

[0139] The translation unit can improve the accuracy of translation based on the user's past translation results during translation. For example, the translation unit can improve the accuracy of translation based on the user's past translation results during translation. Analysis of past translation results includes, but is not limited to, the accuracy of the translation and user feedback. For example, the translation unit can improve the accuracy of the current translation based on the user's past translation results. The translation unit can also refer to the user's past translation results to perform optimal translations for similar posts. The translation unit can also analyze the user's past translation results and optimize the translation algorithm. This allows the current translation accuracy to be improved by referring to the user's past translation results. Some or all of the above-described processing in the translation unit can be performed using, or without, a generation AI. For example, the translation unit can input the user's past translation result data into the generation AI and have the generation AI improve the translation accuracy.

[0140] The translation unit can estimate the user's emotion and set the translation length based on the estimated user's emotion. The translation unit can estimate the user's emotion and set the translation length based on the estimated user's emotion, for example. The emotion estimation can be performed using, but is not limited to, an emotion analysis algorithm. For example, the translation unit can analyze the user's facial expression to estimate the emotion. The translation unit can also analyze the user's voice to estimate the emotion. The translation unit can also analyze the user's biometric data to estimate the emotion. This allows for adjusting the translation length according to the user's emotion, thereby providing a more appropriate translation result. The emotion estimation can be achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the translation unit can be performed using, for example, the generation AI. For example, the translation unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0141] The translation unit can set translation priorities based on the submission time of the post during translation. The translation unit, for example, sets translation priorities based on the submission time of the post during translation. Evaluation of submission time includes, but is not limited to, for example, the submission date and time and the submission frequency. For example, the translation unit prioritizes translation of the most recent post. The translation unit can also set a lower translation priority for posts submitted earlier. The translation unit can also adjust the translation schedule according to the submission time. In this way, by determining translation priorities based on the submission time of the post, it is possible to prioritize translation of the most recent post. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the translation unit can input post submission time data into the generation AI and have the generation AI set the translation priorities.

[0142] The translation unit can set the order of translation based on the relevance of posts during translation. The translation unit, for example, sets the order of translation based on the relevance of posts during translation. The evaluation of relevance includes, but is not limited to, for example, a co-occurrence network or a similarity score. For example, the translation unit prioritizes translation for highly relevant posts. The translation unit can also postpone the order of translation for less relevant posts. The translation unit can also adjust the translation schedule according to the relevance of posts. In this way, by adjusting the order of translation based on the relevance of posts, highly relevant posts can be prioritized for translation. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can input post relevance data into the generation AI and cause the generation AI to set the order of translation.

[0143] The translation unit can set the use of technical terms in the translation according to the user's level of expertise during translation. For example, the translation unit can set the use of technical terms in the translation according to the user's level of expertise during translation. Evaluation of the level of expertise includes, but is not limited to, e.g., qualification information and past postings. For example, the translation unit can provide a translation that uses a lot of technical terms for a user with high level of expertise. The translation unit can also provide a translation in simpler language for a user with low level of expertise. The translation unit can also adjust the way the translation result is expressed according to the user's level of expertise. This allows for the provision of a translation result that is easier to understand by adjusting the use of technical terms in the translation according to the user's level of expertise. Some or all of the above-described processing in the translation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the translation unit can input the user's level of expertise data into the generation AI and have the generation AI execute the use of technical terms.

[0144] The acquisition unit can estimate the user's emotion and set the timing for acquiring location information based on the estimated user's emotion. For example, the acquisition unit can estimate the user's emotion and set the timing for acquiring location information based on the estimated user's emotion. The emotion estimation can be performed using, for example, an emotion analysis algorithm, but is not limited to this example. For example, the acquisition unit can analyze the user's facial expression to estimate the emotion. The acquisition unit can also analyze the user's voice to estimate the emotion. The acquisition unit can also analyze the user's biometric data to estimate the emotion. This allows the acquisition of location information at a more appropriate timing by adjusting the timing for acquiring location information according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the acquisition unit can be performed using, for example, the generation AI, or without the generation AI. For example, the acquisition unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0145] The acquisition unit can analyze the user's past location information history and select an appropriate acquisition method when acquiring location information. For example, the acquisition unit can analyze the user's past location information history and select an appropriate acquisition method when acquiring location information. The analysis of the past location information history includes, but is not limited to, past location data and movement patterns. For example, the acquisition unit can select an optimal acquisition method based on places the user has frequently visited in the past. The acquisition unit can also analyze the user's past location information history and suggest an efficient acquisition method. The acquisition unit can also optimize the timing of acquiring location information by referring to the user's past location information history. This allows the optimal acquisition method to be selected by analyzing the user's past location information history. Some or all of the above-described processing in the acquisition unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the acquisition unit can input the user's past location information history data into the generation AI and have the generation AI select an acquisition method.

[0146] The acquisition unit may perform filtering based on the user's current situation or areas of interest when acquiring location information. For example, the acquisition unit may perform filtering based on the user's current situation or areas of interest when acquiring location information. Filtering methods include, but are not limited to, survey results and behavioral history. For example, the acquisition unit may preferentially acquire location information for the area where the user is currently located. The acquisition unit may also preferentially acquire location information related to the user's areas of interest. The acquisition unit may also filter location information based on the user's current situation (e.g., whether the user is evacuating). By performing filtering based on the user's current situation and areas of interest, highly relevant location information can be preferentially acquired. Some or all of the above-described processing in the acquisition unit may be performed using, or without, a generation AI. For example, the acquisition unit may input the user's current situation and area of ​​interest data into the generation AI and cause the generation AI to perform filtering.

[0147] The acquisition unit can select an appropriate acquisition means according to the user's input method when acquiring location information. For example, the acquisition unit selects an appropriate acquisition means according to the user's input method when acquiring location information. Input methods include, but are not limited to, voice input, text input, and image input. For example, if the user selects voice input, the acquisition unit can acquire location information using voice recognition technology. Also, if the user selects text input, the acquisition unit can acquire location information using text analysis technology. Also, if the user posts an image, the acquisition unit can acquire location information using image analysis technology. This allows for smooth acquisition of location information by selecting the optimal acquisition means according to the user's input method. Some or all of the above-described processing in the acquisition unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the acquisition unit can input the user's input data to the generation AI and cause the generation AI to select the acquisition means.

[0148] The acquisition unit can estimate the user's emotion and set a priority order for the location information to be acquired based on the estimated user's emotion. The acquisition unit can, for example, estimate the user's emotion and set a priority order for the location information to be acquired based on the estimated user's emotion. The emotion estimation can be performed using, for example, an emotion analysis algorithm, but is not limited to, this example. For example, the acquisition unit can analyze the user's facial expression to estimate the emotion. The acquisition unit can also analyze the user's voice to estimate the emotion. The acquisition unit can also analyze the user's biometric data to estimate the emotion. This allows important location information to be quickly acquired by determining the priority order for the location information according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the acquisition unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the acquisition unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0149] The acquisition unit can prioritize acquisition of highly relevant location information based on the user's geographical location information when acquiring location information. For example, the acquisition unit prioritizes acquisition of highly relevant location information based on the user's geographical location information when acquiring location information. Methods for acquiring geographical location information include, but are not limited to, GPS data and IP addresses. For example, the acquisition unit prioritizes acquisition of location information of a region where the user is currently located. The acquisition unit can also prioritize acquisition of related location information based on the user's geographical location information. The acquisition unit can also prioritize acquisition of location information for each region based on the user's geographical location information. This makes it possible to prioritize acquisition of highly relevant location information by taking the user's geographical location information into consideration. Some or all of the above-described processing in the acquisition unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the acquisition unit can input the user's geographical location information data to the generation AI and cause the generation AI to acquire highly relevant location information.

[0150] The acquisition unit may analyze the user's social media activity when acquiring the location information and acquire relevant location information. For example, the acquisition unit may analyze the user's social media activity when acquiring the location information and acquire relevant location information. Analysis of social media activity may include, but is not limited to, posting frequency and engagement. For example, the acquisition unit may acquire relevant location information based on location information shared by the user on social media. The acquisition unit may also analyze the user's social media activity history and prioritize acquisition of relevant location information. The acquisition unit may also acquire relevant location information by referring to the location information of the user's friends on social media. This allows for analysis of the user's social media activity to prioritize acquisition of relevant location information. Some or all of the above-described processing by the acquisition unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the acquisition unit may input the user's social media activity data into the generation AI and cause the generation AI to acquire relevant location information.

[0151] The acquisition unit can adjust the acquisition method by reflecting the user's past feedback when acquiring location information. For example, the acquisition unit adjusts the acquisition method by reflecting the user's past feedback when acquiring location information. Analysis of past feedback includes, but is not limited to, user ratings and comments. For example, the acquisition unit can propose an optimal acquisition method based on feedback provided by the user in the past. The acquisition unit can also customize the location information acquisition interface by reflecting the user's past feedback. The acquisition unit can also optimize the location information acquisition procedure based on the user's past feedback. This makes it possible to provide an optimal acquisition method by reflecting the user's past feedback. Some or all of the above-described processing in the acquisition unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the acquisition unit can input the user's past feedback data into the generation AI and cause the generation AI to adjust the acquisition method.

[0152] The grasping unit can estimate the user's emotion and set a method for grasping the safety information based on the estimated user's emotion. The grasping unit, for example, estimates the user's emotion and sets a method for grasping the safety information based on the estimated user's emotion. The emotion estimation uses, for example, an emotion analysis algorithm, but is not limited to such an example. For example, the grasping unit analyzes the user's facial expression to estimate the emotion. The grasping unit can also analyze the user's voice to estimate the emotion. The grasping unit can also analyze the user's biometric data to estimate the emotion. This allows for adjusting the method for grasping the safety information according to the user's emotion, thereby providing more appropriate safety information. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such an example. Some or all of the above-described processing in the grasping unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comprehension unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0153] The ascertaining unit, when ascertaining safety information, can predict current safety information based on past safety information data. For example, when ascertaining safety information, the ascertaining unit predicts current safety information based on past safety information data. Analysis of past safety information data includes, for example, past disaster data and damage situations, but is not limited to these examples. For example, the ascertaining unit predicts current safety information based on past safety information data. The ascertaining unit can also refer to past safety information data to ascertain optimal safety information for similar situations. The ascertaining unit can also analyze past safety information data and optimize a safety information ascertaining algorithm. In this way, current safety information can be predicted by referring to past safety information data. Some or all of the above-described processing in the ascertaining unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the ascertaining unit can input past safety information data to the generation AI and cause the generation AI to predict safety information.

[0154] The ascertaining unit can apply an appropriate ascertaining method for each category of post when ascertaining safety information. For example, the ascertaining unit applies an appropriate ascertaining method for each category of post when ascertaining safety information. Post categories include, but are not limited to, news, entertainment, and technology. For example, the ascertaining unit applies a specific ascertaining method to posts of safety information. The ascertaining unit can also apply a different ascertaining method to posts requesting assistance. The ascertaining unit can also apply an even different ascertaining method to posts of disaster information. In this way, by applying different ascertaining methods to each category of post, more appropriate safety information can be provided. Some or all of the above-described processing by the ascertaining unit may be performed using, or without using, a generation AI. For example, the ascertaining unit can input post category data into the generation AI and cause the generation AI to apply the ascertaining method.

[0155] The ascertaining unit can analyze the safety information based on the poster's attribute information when ascertaining the safety information. For example, when ascertaining the safety information, the ascertaining unit analyzes the safety information based on the poster's attribute information. Evaluation of the poster's attribute information includes, but is not limited to, age, gender, and occupation. For example, the ascertaining unit analyzes the safety information taking into account the poster's reliability. The ascertaining unit can also ascertain related safety information based on the poster's attribute information. The ascertaining unit can also improve the accuracy of the analysis of the safety information by referring to the poster's past posting history. In this way, the accuracy of the analysis of the safety information can be improved by taking the poster's attribute information into consideration. Some or all of the above-described processing in the ascertaining unit may be performed using, or without using, the generation AI. For example, the ascertaining unit can input the poster's attribute information data into the generation AI and cause the generation AI to analyze the safety information.

[0156] The grasping unit can estimate the user's emotion and set the importance of the safety information based on the estimated user's emotion. The grasping unit can, for example, estimate the user's emotion and set the importance of the safety information based on the estimated user's emotion. The emotion estimation can be performed using, for example, an emotion analysis algorithm, but is not limited to, this example. For example, the grasping unit can analyze the user's facial expression to estimate the emotion. The grasping unit can also analyze the user's voice to estimate the emotion. The grasping unit can also analyze the user's biometric data to estimate the emotion. This allows the importance of the safety information to be adjusted according to the user's emotion, thereby providing more appropriate safety information. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the grasping unit can be performed using, for example, the generation AI, or without the generation AI. For example, the comprehension unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0157] The ascertaining unit, when ascertaining the safety information, can evaluate changes in the safety information based on the submission time of the post. For example, when ascertaining the safety information, the ascertaining unit evaluates changes in the safety information based on the submission time of the post. Evaluation of the submission time includes, but is not limited to, for example, the submission date and time and the submission frequency. For example, the ascertaining unit prioritizes analysis of recently submitted safety information. The ascertaining unit can also set a lower analysis priority for older submitted safety information. The ascertaining unit can also analyze changes in the safety information according to the submission time. In this way, by analyzing changes in the safety information based on the submission time of the post, more appropriate safety information can be provided. Some or all of the above-described processing by the ascertaining unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the ascertaining unit can input submission time data into the generation AI and cause the generation AI to evaluate changes in the safety information.

[0158] The ascertaining unit can analyze the safety information based on related market data when ascertaining the safety information. For example, the ascertaining unit analyzes the safety information based on related market data when ascertaining the safety information. Reference to related market data includes, but is not limited to, market research reports and sales data. For example, the ascertaining unit analyzes the safety information based on the related market data. The ascertaining unit can also refer to market data to improve the reliability of the safety information. The ascertaining unit can also analyze market data and optimize the algorithm for ascertaining the safety information. In this way, the reliability of the safety information can be improved by referring to the related market data. Some or all of the above-mentioned processing in the ascertaining unit may be performed using, or without using, the generation AI. For example, the ascertaining unit can input related market data to the generation AI and cause the generation AI to analyze the safety information.

[0159] The ascertaining unit can analyze the safety information based on the technological maturity when ascertaining the safety information. For example, the ascertaining unit analyzes the safety information based on the technological maturity when ascertaining the safety information. Evaluation of the technological maturity includes, but is not limited to, for example, the prevalence of technology and the evolutionary stage of technology. For example, the ascertaining unit sets a high reliability for information with a high level of technological maturity. The ascertaining unit can also set a low reliability for information with a low level of technological maturity. The ascertaining unit can also adjust the analysis accuracy of the safety information according to the technological maturity. In this way, the analysis accuracy of the safety information can be adjusted by taking the technological maturity into consideration. Some or all of the above-mentioned processing in the ascertaining unit may be performed using, or without using, the generation AI. For example, the ascertaining unit can input technical maturity data to the generation AI and cause the generation AI to analyze the safety information.

[0160] The distribution unit can estimate the user's emotion and set a method for distributing the assistance needs based on the estimated user's emotion. The distribution unit, for example, estimates the user's emotion and sets a method for distributing the assistance needs based on the estimated user's emotion. The emotion estimation uses, for example, an emotion analysis algorithm, but is not limited to this example. For example, the distribution unit analyzes the user's facial expression to estimate the emotion. The distribution unit can also analyze the user's voice to estimate the emotion. The distribution unit can also analyze the user's biometric data to estimate the emotion. This allows for adjusting the method for distributing the assistance needs according to the user's emotion, thereby providing more appropriate assistance needs. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the distribution unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the distribution unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0161] The distribution unit can predict current support needs based on past support data when distributing support needs. For example, the distribution unit predicts current support needs based on past support data when distributing support needs. Analysis of past support data includes, but is not limited to, past support activities and support effects. For example, the distribution unit predicts current support needs based on past support data. The distribution unit can also refer to past support data to distribute optimal support needs for similar situations. The distribution unit can also analyze past support data and optimize a support need distribution algorithm. This makes it possible to predict current support needs by referring to past support data. Some or all of the above-described processing in the distribution unit may be performed using, or without using, a generation AI. For example, the distribution unit can input past support data into the generation AI and cause the generation AI to predict support needs.

[0162] The distribution unit can apply an appropriate distribution method for each post category when distributing the support needs. For example, the distribution unit applies an appropriate distribution method for each post category when distributing the support needs. Post categories include, but are not limited to, news, entertainment, and technology. For example, the distribution unit applies a specific distribution method to support needs related to safety information. The distribution unit can also apply a different distribution method to support needs related to assistance requests. The distribution unit can also apply an even different distribution method to support needs related to disaster information. In this way, by applying different distribution methods to each post category, more appropriate support needs can be provided. Some or all of the above-described processing in the distribution unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the distribution unit can input post category data into the generation AI and cause the generation AI to apply the distribution method.

[0163] The distribution unit can analyze the support needs based on the poster's attribute information when distributing the support needs. For example, the distribution unit analyzes the support needs based on the poster's attribute information when distributing the support needs. Evaluation of the poster's attribute information includes, but is not limited to, age, gender, and occupation. For example, the distribution unit analyzes the support needs taking into account the poster's reliability. The distribution unit can also identify related support needs based on the poster's attribute information. The distribution unit can also improve the accuracy of the analysis of support needs by referring to the poster's past posting history. In this way, the accuracy of the analysis of support needs can be improved by taking the poster's attribute information into consideration. Some or all of the above-described processing in the distribution unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the distribution unit can input the poster's attribute information data into the generation AI and cause the generation AI to analyze the support needs.

[0164] The distribution unit can estimate the user's emotion and set the importance of the support needs based on the estimated user's emotion. The distribution unit can, for example, estimate the user's emotion and set the importance of the support needs based on the estimated user's emotion. The emotion estimation can be performed using, for example, an emotion analysis algorithm, but is not limited to this example. For example, the distribution unit can analyze the user's facial expression to estimate the emotion. The distribution unit can also analyze the user's voice to estimate the emotion. The distribution unit can also analyze the user's biometric data to estimate the emotion. This allows the importance of the support needs to be adjusted according to the user's emotion, thereby providing more appropriate support needs. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the distribution unit can be performed using, for example, the generation AI, or without the generation AI. For example, the distribution unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0165] The distribution unit can evaluate changes in support needs based on the submission time of the post when distributing the support needs. For example, the distribution unit evaluates changes in support needs based on the submission time of the post when distributing the support needs. Evaluation of the submission time includes, but is not limited to, for example, the submission date and time and the submission frequency. For example, the distribution unit prioritizes analysis of support needs that have been submitted recently. The distribution unit can also set a lower analysis priority for support needs that have been submitted older. The distribution unit can also analyze changes in support needs based on the submission time. This makes it possible to provide more appropriate support needs by analyzing changes in support needs based on the submission time of the post. Some or all of the above-described processing in the distribution unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the distribution unit can input submission time data into the generation AI and cause the generation AI to evaluate changes in support needs.

[0166] The distribution unit can analyze the support needs based on related market data when distributing the support needs. For example, the distribution unit analyzes the support needs based on related market data when distributing the support needs. Reference to related market data includes, but is not limited to, market research reports and sales data. For example, the distribution unit analyzes the support needs based on the related market data. The distribution unit can also refer to market data to improve the reliability of the support needs. The distribution unit can also analyze market data and optimize the distribution algorithm for the support needs. In this way, the reliability of the support needs can be improved by referring to the related market data. Some or all of the above-mentioned processing in the distribution unit may be performed using, or without using, the generation AI. For example, the distribution unit can input related market data into the generation AI and cause the generation AI to analyze the support needs.

[0167] The distribution unit can analyze the support needs based on the technological maturity when distributing the support needs. For example, the distribution unit analyzes the support needs based on the technological maturity when distributing the support needs. Evaluation of the technological maturity includes, but is not limited to, for example, the prevalence of technology and the evolutionary stage of technology. For example, the distribution unit sets a high reliability for information with a high level of technological maturity. The distribution unit can also set a low reliability for information with a low level of technological maturity. The distribution unit can also adjust the analysis accuracy of the support needs according to the technological maturity. In this way, the analysis accuracy of the support needs can be adjusted by taking the technological maturity into consideration. Some or all of the above-mentioned processing in the distribution unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the distribution unit can input the technological maturity data into the generation AI and cause the generation AI to analyze the support needs. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, identification unit, warning unit, translation unit, acquisition unit, understanding unit, and distribution unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives posts from users. The analysis unit is realized by the identification processing unit 290 of the data processing device 12 and analyzes and summarizes the posts using a generation AI. The identification unit is realized by the identification processing unit 290 of the data processing device 12 and identifies false information. The warning unit is realized by the control unit 46A of the smart device 14 and displays a warning to the user when false information is identified. The translation unit is realized by the identification processing unit 290 of the data processing device 12 and translates posts in different languages. The acquisition unit is realized by the control unit 46A of the smart device 14 and acquires location information. The understanding unit is realized by the identification processing unit 290 of the data processing device 12 and understands safety information for each region. The distribution unit is realized by the specific processing unit 290 of the data processing device 12, and distributes the support needs. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, identification unit, warning unit, translation unit, acquisition unit, understanding unit, and distribution unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives posts from users. The analysis unit is realized by the identification processing unit 290 of the data processing device 12 and analyzes and summarizes posts using a generation AI. The identification unit is realized by the identification processing unit 290 of the data processing device 12 and identifies false information. The warning unit is realized by the control unit 46A of the smart glasses 214 and displays a warning to the user when false information is identified. The translation unit is realized by the identification processing unit 290 of the data processing device 12 and translates posts in different languages. The acquisition unit is realized by the control unit 46A of the smart glasses 214 and acquires location information. The understanding unit is realized by the identification processing unit 290 of the data processing device 12 and understands safety information by region. The distribution unit is realized by the specific processing unit 290 of the data processing device 12, and distributes the support needs. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, identification unit, warning unit, translation unit, acquisition unit, understanding unit, and distribution unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset-type terminal 314 and receives posts from users. The analysis unit is realized by the identification processing unit 290 of the data processing device 12 and analyzes and summarizes the posts using a generation AI. The identification unit is realized by the identification processing unit 290 of the data processing device 12 and identifies false information. The warning unit is realized by the control unit 46A of the headset-type terminal 314 and displays a warning to the user when false information is identified. The translation unit is realized by the identification processing unit 290 of the data processing device 12 and translates posts in different languages. The acquisition unit is realized by the control unit 46A of the headset-type terminal 314 and acquires location information. The understanding unit is realized by the identification processing unit 290 of the data processing device 12 and understands safety information for each region. The distribution unit is realized by the specific processing unit 290 of the data processing device 12, and distributes the support needs. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, identification unit, warning unit, translation unit, acquisition unit, understanding unit, and distribution unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives posts from users. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes and summarizes the posts using a generation AI. The identification unit is realized by the specific processing unit 290 of the data processing device 12 and identifies false information. The warning unit is realized by the control unit 46A of the robot 414 and displays a warning to the user when false information is identified. The translation unit is realized by the specific processing unit 290 of the data processing device 12 and translates posts in different languages. The acquisition unit is realized by the control unit 46A of the robot 414 and acquires location information. The understanding unit is realized by the specific processing unit 290 of the data processing device 12 and understands safety information for each region. The distribution unit is realized by the specific processing unit 290 of the data processing device 12, and distributes the support needs.

[0168] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0169] The reception unit can analyze the user's past posting history and understand trends in the content of posts. For example, it can provide related templates based on the content that the user frequently posted in the past. It can also analyze the time periods when the user posted in the past and suggest the optimal timing for posting. It can also analyze the user's reactions to past posts and suggest areas for improving the content of posts. This makes it possible to post more effectively by utilizing the user's past posting history.

[0170] The analysis unit can estimate the user's emotions and adjust the way the analysis results are presented based on the estimated emotions. For example, if the user is feeling anxious, the analysis results can be explained more carefully. Alternatively, if the user is excited, the analysis results can be summarized more succinctly. Furthermore, the display format of the analysis results can be changed depending on the user's emotions. This makes it possible to provide analysis results that correspond to the user's emotions.

[0171] The identification unit can take into account the poster's past posting history when evaluating the reliability of posted content. For example, it can prioritize information from posters who have provided reliable information in the past. It can also be wary of information from posters who have provided false information in the past. Furthermore, it can analyze the poster's past posted content and evaluate their expertise in a specific field. This allows for more accurate evaluation of the reliability of posted content.

[0172] The warning unit can estimate the user's emotions and adjust the way the warning is displayed based on the estimated emotions. For example, if the user is feeling stressed, the warning can be displayed gently. Alternatively, if the user is calm, the warning can be displayed directly. Furthermore, the timing of displaying the warning can be adjusted according to the user's emotions. In this way, an appropriate warning can be provided according to the user's emotions.

[0173] The translation unit can analyze a user's past translation history to improve translation accuracy. For example, it can learn from past translation corrections made by the user and avoid similar mistakes. It can also analyze a user's translation style and provide individually optimized translations. Furthermore, it can customize translations of specific terms and phrases based on the user's past translation history. This provides a more natural translation result for the user.

[0174] The acquisition unit can estimate the user's emotions and adjust the frequency of acquiring location information based on the estimated emotions. For example, if the user feels anxious, location information can be acquired frequently to provide a sense of security. Alternatively, if the user feels relaxed, the frequency of acquiring location information can be reduced. Furthermore, the method of acquiring location information can be changed depending on the user's emotions. This enables flexible acquisition of location information according to the user's emotions.

[0175] The grasping unit can analyze the user's past safety information and evaluate the reliability of the current safety information. For example, it can prioritize information from users who have provided accurate safety information in the past. It can also be wary of information from users who have provided incorrect safety information in the past. Furthermore, it can grasp trends in safety information in specific regions or situations based on past safety information. This allows for more accurate evaluation of the reliability of safety information.

[0176] The delivery unit can estimate the user's emotions and adjust the delivery content of the support needs based on the estimated emotions. For example, if the user is feeling anxious, the delivery unit can explain the support needs in detail. Alternatively, if the user is calm, the delivery unit can summarize the support needs concisely. Furthermore, the delivery timing of the support needs can be adjusted according to the user's emotions. In this way, appropriate support needs according to the user's emotions are provided.

[0177] The distribution unit can analyze the results of distribution of past support needs and optimize the method of distribution of current support needs. For example, it can reuse distribution methods that were effective in the past. It can also improve distribution methods that had problems in the past. Furthermore, it can propose the optimal distribution method for a specific situation based on the results of distribution of past support needs. This makes it possible to distribute support needs more effectively.

[0178] The reception unit can estimate the user's emotions and filter the posted content based on the estimated emotions. For example, if the user is feeling stressed, it can prioritize the display of posts with positive content. Alternatively, if the user is calm, it can display all the posted content. Furthermore, it can adjust the display order of the posted content according to the user's emotions. This makes it possible to filter the posted content appropriately according to the user's emotions.

[0179] The processing flow of the second embodiment will be briefly explained below.

[0180] Step 1: The reception unit accepts posts from users. Posts from users include text, images, videos, etc. The reception unit can accept posts from smartphones and PCs, and supports various input methods such as voice input and image input. Step 2: The analysis unit uses a generation AI to analyze and summarize the posts received by the reception unit. The analysis is performed using natural language processing technology and multimodal generation AI. For example, a text generation AI (LLM) is used to analyze and summarize the posts. Step 3: The identification unit uses the generation AI to identify the posted content analyzed by the analysis unit. Identification is performed using a misinformation detection algorithm to evaluate the reliability of the posted content and identify misinformation. Step 4: The warning unit warns the user of the misinformation identified by the identification unit. The warning is given by a pop-up notification, an email notification, or the like, and displays a warning to the user when misinformation is identified. Step 5: The translation department uses generative AI to translate posts in different languages. The translation is done through methods such as real-time translation and batch translation, and posts in different languages ​​are translated in real time. Step 6: The acquisition unit acquires location information. The location information is acquired by methods such as GPS data or IP address, and is acquired from the user's smartphone or PC. Step 7: The ascertaining unit ascertains safety information for each region based on the location information acquired by the acquiring unit. The ascertaining is performed by methods such as confirming the safety of users and ascertaining the damage situation. Step 8: The distribution unit distributes support needs based on the information obtained by the identification unit. The distribution is carried out in the form of a request for supplies or medical support.

[0181] 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.

[0182] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0183] 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.

[0184] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0185] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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).

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0199] 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.

[0200] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0201] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0215] 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.

[0216] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0217] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0232] 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.

[0233] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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).

[0238] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0239] 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."

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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.

[0251] 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.

[0252] [Explanation of symbols]

[0253] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives posts from users; an analysis unit that analyzes and summarizes the posts received by the reception unit; an identification unit that identifies the posted content analyzed by the analysis unit; a warning unit that warns of erroneous information identified by the identification unit; A translation department that translates posts in different languages; an acquisition unit that acquires location information; a determination unit that determines safety information for each region based on the location information obtained by the obtaining unit; a distribution unit that distributes support needs based on the information grasped by the grasping unit; Equipped with A system characterized by:

2. The reception unit Accept submissions from smartphones or PCs The system of claim 1 .

3. The analysis unit Analyze and summarize posts using natural language processing techniques The system of claim 1 .

4. The identification unit Identifying misinformation The system of claim 1 .

5. The warning unit Warn users when misinformation is identified The system of claim 1 .

6. The translation unit Instantly translate posts in different languages The system of claim 1 .

7. The acquisition unit Get location information The system of claim 1 .

8. The grasping unit Gain information on the safety of each region based on the acquired location information The system of claim 1 .

Images