system

Abstract

The system according to this embodiment aims to predict the risk of social media posts going viral and to take prompt countermeasures. [Solution] The system according to the embodiment comprises an analysis unit, a modification unit, a resimulation unit, and a fire suppression unit. The analysis unit analyzes the text of the SNS post entered by the user. The modification unit modifies the post based on the simulation results obtained by the analysis unit. The resimulation unit resimulates the post modified by the modification unit. If the post goes viral, the fire suppression unit automatically switches the system to fire suppression mode and executes a series of processes to suppress the virality.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to predict the risk of an SNS post going viral and take prompt countermeasures.

[0005] The system according to the embodiment aims to predict the risk of an SNS post going viral and take prompt countermeasures.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a modification unit, a resimulation unit, and a fire suppression unit. The analysis unit analyzes the text of the SNS post entered by the user. The modification unit modifies the post based on the simulation results obtained by the analysis unit. The resimulation unit resimulates the post modified by the modification unit. If the post goes viral, the fire suppression unit automatically switches the system to fire suppression mode and executes a series of processes to suppress the viral spread. [Effects of the Invention]

[0007] The system according to this embodiment can predict the risk of a social media post going viral and take swift countermeasures. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of 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), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The online crisis risk management system according to an embodiment of the present invention is a system that supports corporate brand protection and rapid response by predicting and taking measures against online crises in social media posts. This system allows users to input text for social media posts, and the AI ​​analyzes the input text to simulate the risk of online crises, the likelihood of virality, post impressions, follower growth, comments received, and the number of online news articles published. Based on the simulation results, users can revise their posts, and after revisions, a re-simulation is performed. This allows for repeated trial and error until a satisfactory post is created. Furthermore, if a post goes viral, the agent immediately switches to a fire-extinguishing mode, supporting everything from understanding the situation to coordinating with relevant parties. This allows the person in charge to respond without panicking. The agent also features an intuitive UI, making it easy for anyone to operate. This system is offered as an inexpensive solution for small and medium-sized enterprises and sole proprietors, aiming to capture a 1 trillion yen business opportunity in the social media marketing and advertising market. Furthermore, by selling it in conjunction with existing "online crisis insurance," it can strongly appeal to the needs of businesses. This allows the crisis risk management system to help companies protect their brand and respond quickly to online crises.

[0029] The online firestorm risk management system according to this embodiment comprises an analysis unit, a modification unit, a resimulation unit, and a fire suppression unit. The analysis unit analyzes the text of the SNS post entered by the user. The analysis unit analyzes the content of the post using, for example, a text analysis algorithm. The analysis unit can also perform sentiment analysis and evaluate the emotional tone of the post. The analysis unit analyzes the meaning of the content of the post using, for example, natural language processing technology. The modification unit modifies the post based on the simulation results obtained by the analysis unit. The modification unit proposes changes to the content of the post, for example. The modification unit can also adjust the expression and change the tone of the post. The modification unit can also delete, for example, part of the content of the post. The resimulation unit resimulates the post modified by the modification unit. The resimulation unit re-evaluates the modified post, for example. The resimulation unit can also recalculate the risk and re-evaluate the firestorm risk of the modified post. The resimulation unit can also predict the spread of the modified post, for example. The fire suppression unit switches to fire suppression mode when the post goes viral. The fire suppression unit, for example, executes specific measures to suppress the escalation of the fire. The fire suppression unit can also contact relevant parties using notification methods. The fire suppression unit, for example, grasps the situation of the fire and supports a rapid response. In this way, the fire risk management system according to the embodiment can support the protection of a company's brand and rapid response by predicting and taking measures against firestorms in SNS posts.

[0030] The analysis unit analyzes the text of social media posts entered by users. For example, the analysis unit analyzes the content of posts using text analysis algorithms. Specifically, it utilizes natural language processing (NLP) techniques to analyze the grammatical structure and meaning of the post content in detail. The analysis unit can also perform sentiment analysis to evaluate the emotional tone of the post. Sentiment analysis uses machine learning models to identify sentiment categories such as positive, negative, and neutral. For example, it calculates sentiment scores for words and phrases included in the post content to evaluate the overall emotional tone. Furthermore, the analysis unit analyzes the frequency of occurrence of specific keywords and phrases to identify potential risk factors in the post content. For example, it lists words and expressions that are likely to cause controversy and checks whether they are included in the post. This allows the analysis unit to assess the risk of the post content and anticipate the possibility of controversy in advance.

[0031] The editing team modifies posts based on simulation results obtained by the analysis team. For example, the editing team proposes changes to the content of posts. Specifically, it adjusts the wording of posts based on risk factors identified by the analysis team. The editing team can also adjust the tone of posts by adjusting the wording. For example, it may replace negative expressions with positive ones or change aggressive words to neutral ones. The editing team can also delete parts of posts. For example, if certain keywords or phrases are likely to cause controversy, they can be removed to reduce the risk. Furthermore, the editing team also makes suggestions to improve the grammar and style of posts. For example, it may revise the sentence structure and change it to a clearer and easier-to-understand expression. In this way, the editing team can adjust posts in a way that minimizes the risk of the content while not distorting the user's intent.

[0032] The re-simulation unit re-simulates the post that has been modified by the revision unit. For example, the re-simulation unit re-evaluates the revised post. Specifically, it re-analyzes the content of the revised post and performs a risk assessment. The re-simulation unit can also recalculate the risk and re-evaluate the risk of the revised post becoming a controversial topic. For example, it compares the content of the post before and after revision and checks the change in the risk score. The re-simulation unit can also predict the spread of the revised post. For example, it simulates the extent to which the revised post may spread and assesses the risk of it becoming a controversial topic. This allows the re-simulation unit to confirm whether the content of the revised post is appropriate and to make further revisions if necessary. Furthermore, the re-simulation unit can also use past data and statistical information to assess the risk of the revised post. For example, it can refer to past controversial incidents to assess the likelihood of the revised post becoming a controversial topic. This allows the re-simulation unit to accurately assess the risk of the revised post and take appropriate measures.

[0033] The Firefighting Department switches to firefighting mode when a post goes viral. The Firefighting Department takes specific actions to suppress the firefight, such as quickly deleting or modifying the content of the post that caused the firefight. The Firefighting Department can also contact relevant parties using notification methods, such as notifying corporate public relations and crisis management personnel of the situation in real time to encourage a quick response. Furthermore, the Firefighting Department monitors the situation and supports a rapid response, such as monitoring the spread of the firefight on social media and evaluating its scale and impact. The Firefighting Department can also analyze the cause and background of the firefight and propose measures to prevent recurrence, such as identifying the content and expression of the post that caused the firefight and suggesting points to be careful about in future posts. In this way, the Firefighting Department can support a quick and appropriate response while minimizing the risk of a firefight. Furthermore, the Firefighting Department can collect user feedback and use it to improve the system, such as evaluating the effectiveness and problems of the firefight response and improving the system's functions and processes. This allows the fire suppression department to constantly utilize the latest information and technology to improve the performance of the fire risk management system.

[0034] The analytics unit can simulate the risk of a post going viral, the likelihood of it being shared with many users, the post's impressions, follower growth, the number of comments received, and the number of online news articles it will be featured in. For example, the analytics unit can calculate a score for the risk of a post going viral. The analytics unit can also calculate a risk score based on data from past viral incidents. For example, the analytics unit can predict the number of shares a post will receive. The analytics unit can calculate the probability of a post going viral and predict how widely it will be shared. For example, the analytics unit can predict the number of impressions and views a post will receive. The analytics unit can predict impressions and evaluate how many users will see a post. For example, the analytics unit can calculate the follower growth rate. The analytics unit can predict follower growth and evaluate how many new followers a post will gain. For example, the analytics unit can predict the number of comments. The analytics unit can perform sentiment analysis and evaluate the emotional tone of the comments received. For example, the analytics unit can predict the number of news articles it will be featured in. The analytics unit can evaluate media influence and predict how widely a post will be featured in news articles. This allows the analysis unit to predict the impact of a post by simulating various elements of the post. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the text data of the post into a generating AI and have the generating AI perform a prediction of the risk of online backlash and spread.

[0035] The editing unit can modify posts based on simulation results. The editing unit can, for example, suggest changes to the content of the post. The editing unit can also adjust the wording and change the tone of the post. The editing unit can, for example, delete parts of the content of the post. Based on the simulation results, the editing unit can present revised proposals to reduce the risk of the post going viral. The editing unit can, for example, change the content of the post to reduce the risk of going viral. The editing unit can also adjust the wording and change the tone of the post. The editing unit can, for example, delete parts of the content of the post. In this way, the editing unit can reduce the risk of going viral by modifying posts based on simulation results. Some or all of the above processing in the editing unit may be performed using AI, for example, or without AI. For example, the editing unit can input the simulation results into a generating AI and have the generating AI perform revisions to the content of the post.

[0036] The re-simulation unit can re-simulate the revised post. The re-simulation unit can, for example, re-evaluate the revised post. The re-simulation unit can also recalculate the risks and re-evaluate the risk of the revised post going viral. The re-simulation unit can, for example, predict the spread of the revised post. The re-simulation unit can optimize the post based on the simulation results of the revised post. The re-simulation unit can, for example, re-evaluate the revised post and propose the optimal post content. The re-simulation unit can also recalculate the risks and re-evaluate the risk of the revised post going viral. The re-simulation unit can, for example, predict the spread of the revised post. In this way, the re-simulation unit can optimize the post by re-simulating the revised post. Some or all of the above processing in the re-simulation unit may be performed using AI, for example, or without AI. For example, the re-simulation unit can input the revised post data into a generating AI and have the generating AI perform the re-simulation.

[0037] The fire suppression unit can automatically switch to fire suppression mode when a post goes viral, execute a series of processes to suppress the fire, and support everything from understanding the situation to coordinating with relevant parties. The fire suppression unit can, for example, execute specific processes to suppress the fire. The fire suppression unit can also contact relevant parties using notification methods. The fire suppression unit can, for example, understand the fire situation and support a rapid response. The fire suppression unit can execute specific processes to suppress the fire and support everything from understanding the situation to coordinating with relevant parties. The fire suppression unit can, for example, execute specific processes to suppress the fire. The fire suppression unit can also contact relevant parties using notification methods. The fire suppression unit can, for example, understand the fire situation and support a rapid response. This allows the fire suppression unit to respond quickly when a post goes viral. Some or all of the processes described above in the fire suppression unit may be performed using AI, for example, or not. For example, the fire suppression unit can input data on the fire situation into a generating AI and have the generating AI execute processes to suppress the fire.

[0038] The fire suppression unit can provide appropriate guidance to enable personnel to respond calmly. The fire suppression unit can, for example, provide response procedures. The fire suppression unit can also issue alert notifications to encourage personnel to respond quickly. The fire suppression unit can, for example, provide response procedures to support personnel in responding calmly. The fire suppression unit can also issue alert notifications to encourage personnel to respond quickly. The fire suppression unit can, for example, provide response procedures to support personnel in responding calmly. In this way, the fire suppression unit can support personnel in responding calmly. Some or all of the above processes in the fire suppression unit may be performed using AI, for example, or not using AI. For example, the fire suppression unit can have a generating AI provide response procedures to support personnel in responding calmly.

[0039] The analysis unit can optimize its analysis algorithm by referring to past online controversy data during the analysis process. For example, the analysis unit can analyze the frequency of occurrence of specific keywords or phrases based on past online controversy data and assess the risk. The analysis unit can also calculate the probability that a specific posting pattern will lead to an online controversy by referring to past online controversy data. For example, the analysis unit can use past online controversy data to analyze the impact of posting content and timing on online controversies. In this way, the analysis unit can improve the accuracy of its analysis by referring to past online controversy data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past online controversy data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0040] The analysis unit can apply different analysis methods to each category of post during analysis. For example, the analysis unit can apply an analysis method that emphasizes customer ratings and feedback to product review posts. The analysis unit can also apply an analysis method that emphasizes the reliability and source of information to news article posts. For example, the analysis unit can apply an analysis method that emphasizes advertising effectiveness and target audience response to promotional posts. In this way, the analysis unit can improve the accuracy of the analysis by applying the appropriate analysis method to each category of post. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input post category data into a generating AI and have the generating AI execute the application of category-specific analysis methods.

[0041] The analysis unit can perform analysis while considering the geographical distribution of posts. For example, the analysis unit can analyze the response to posts in a specific region and evaluate the risks specific to that region. The analysis unit can also calculate the expected level of virality in a specific region based on the geographical distribution. For example, the analysis unit can analyze the increase in impressions and follower counts for each region while considering the geographical distribution. In this way, the analysis unit can evaluate region-specific risks and expectations by considering the geographical distribution of posts. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input geographical data of posts into a generating AI and have the generating AI perform analysis that considers the geographical distribution.

[0042] The analysis unit can improve the accuracy of its analysis by referring to relevant literature for the submission during the analysis process. For example, the analysis unit can refer to academic papers and articles related to the content of the submission to increase the reliability of the analysis results. The analysis unit can also improve the accuracy of its analysis by supplementing background information on the content of the submission based on relevant literature. For example, the analysis unit can evaluate the expertise and credibility of the content of the submission by referring to relevant literature. In this way, the analysis unit can improve the reliability and accuracy of its analysis by referring to relevant literature for the submission. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the data of relevant literature for the submission into a generating AI and have the generating AI perform the task of improving the accuracy of the analysis.

[0043] The editing unit can adjust the level of detail of revisions based on the importance of the post during the revision process. For example, the editing unit can present detailed revision suggestions and carefully revise high-importance posts. For low-importance posts, the editing unit can also present concise revision suggestions and revise them quickly. The editing unit can also determine revision priorities according to importance and revise efficiently. In this way, the editing unit can perform efficient revisions by adjusting the level of detail of revisions based on the importance of the post. Some or all of the above processes in the editing unit may be performed using AI, for example, or not using AI. For example, the editing unit can input post importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of revisions.

[0044] The editing unit can apply different editing algorithms depending on the category of the post during editing. For example, for product review posts, the editing unit can apply an editing algorithm that emphasizes customer ratings and feedback. For news article posts, the editing unit can also apply an editing algorithm that emphasizes the reliability and source of information. For promotional posts, the editing unit can also apply an editing algorithm that emphasizes advertising effectiveness and the response of the target audience. In this way, the editing unit can improve the accuracy of editing by applying the appropriate editing algorithm according to the category of the post. Some or all of the above processing in the editing unit may be performed using AI, for example, or without AI. For example, the editing unit can input post category data into a generating AI and have the generating AI execute the application of category-specific editing algorithms.

[0045] The editing unit can determine the priority of revisions based on the submission date of each post. For example, the editing unit can prioritize revisions to posts with upcoming submission dates. It can also postpone revisions to posts with later submission dates. The editing unit can also adjust the revision schedule according to the submission dates. This allows the editing unit to perform revisions efficiently by determining the priority of revisions based on the submission dates of each post. Some or all of the above processes in the editing unit may be performed using AI, for example, or not. For example, the editing unit can input submission date data into a generating AI and have the generating AI determine the priority of revisions.

[0046] The editing unit can adjust the order of edits based on the relevance of the posts during the editing process. For example, the editing unit can prioritize editing highly relevant posts. It can also postpone editing less relevant posts. The editing unit can also adjust the editing schedule according to the relevance of the posts. This allows the editing unit to perform edits efficiently by adjusting the order of edits based on the relevance of the posts. Some or all of the above processes in the editing unit may be performed using AI, for example, or not using AI. For example, the editing unit can input post relevance data into a generating AI and have the generating AI adjust the order of edits.

[0047] The resimulation unit can improve the accuracy of the resimulation by considering the interrelationships of posts during the resimulation process. For example, if multiple posts are related, the resimulation unit will perform the resimulation considering the impact of each post. The resimulation unit can also analyze the interrelationships of posts and evaluate the overall impact. For example, the resimulation unit can propose the optimal correction plan by considering the interrelationships of posts. In this way, the resimulation unit can improve the accuracy of the resimulation by considering the interrelationships of posts. Some or all of the above processing in the resimulation unit may be performed using AI, for example, or without AI. For example, the resimulation unit can input the interrelationship data of posts into a generating AI and have the generating AI perform the resimulation accuracy improvement.

[0048] The resimulation unit can perform a resimulation while considering the attribute information of the post submitter. For example, the resimulation unit can perform a resimulation while considering the submitter's number of followers and influence. The resimulation unit can also perform a resimulation by referring to the submitter's past posting history. For example, the resimulation unit can also suggest the most suitable revision based on the submitter's attribute information. In this way, the resimulation unit can improve the accuracy of the resimulation by considering the attribute information of the post submitter. Some or all of the above processing in the resimulation unit may be performed using AI, for example, or without using AI. For example, the resimulation unit can input the submitter's attribute information data into a generating AI and have the generating AI perform the resimulation.

[0049] The resimulation unit can perform resimulations while considering the geographical distribution of posts. For example, the resimulation unit can analyze the response to posts in a specific region and evaluate the risks specific to that region. The resimulation unit can also calculate the expected degree of virality in a specific region based on the geographical distribution. For example, the resimulation unit can analyze the increase in impressions and follower counts for each region while considering the geographical distribution. In this way, the resimulation unit can evaluate region-specific risks and expectations by considering the geographical distribution of posts. Some or all of the above processing in the resimulation unit may be performed using AI, for example, or without using AI. For example, the resimulation unit can input the geographical data of posts into a generating AI and have the generating AI perform a resimulation that considers the geographical distribution.

[0050] The resimulation unit can improve the accuracy of the resimulation by referring to relevant literature for the submission during the resimulation process. For example, the resimulation unit can refer to academic papers and articles related to the submission content to increase the reliability of the resimulation results. The resimulation unit can also improve the accuracy of the resimulation by supplementing background information on the submission content based on relevant literature. For example, the resimulation unit can evaluate the expertise and credibility of the submission content by referring to relevant literature. In this way, the resimulation unit can improve the reliability and accuracy of the resimulation by referring to relevant literature for the submission. Some or all of the above processing in the resimulation unit may be performed using AI, for example, or without AI. For example, the resimulation unit can input the relevant literature data for the submission into a generating AI and have the generating AI perform the resimulation accuracy improvement.

[0051] The fire suppression unit can optimize its fire suppression algorithm by referring to past fire incident data during the fire suppression process. For example, the fire suppression unit can select the most effective fire suppression method based on past fire incident data. The fire suppression unit can also apply the optimal fire suppression method for a specific situation by referring to past fire incident data. For example, the fire suppression unit can use past fire incident data to evaluate the effectiveness of fire suppression methods and select the optimal method. In this way, the fire suppression unit can improve the accuracy of fire suppression by referring to past fire incident data. Some or all of the above processes in the fire suppression unit may be performed using AI, for example, or without AI. For example, the fire suppression unit can input past fire incident data into a generating AI and have the generating AI perform the optimization of the fire suppression algorithm.

[0052] The fire suppression unit can apply different fire suppression methods depending on the category of the post when it is suppressed. For example, the fire suppression unit can apply a fire suppression method that emphasizes customer service to a product review fire. For a news article fire, the fire suppression unit can also apply a fire suppression method that emphasizes correcting or adding information. For a promotional post fire, the fire suppression unit can also apply a fire suppression method that emphasizes modifying the advertisement content or apologizing. In this way, the fire suppression unit can improve the accuracy of fire suppression by applying the appropriate fire suppression method for each category of post. Some or all of the above processing in the fire suppression unit may be performed using AI, for example, or not using AI. For example, the fire suppression unit can input post category data into a generating AI and have the generating AI execute the application of fire suppression methods for each category.

[0053] The fire suppression unit can suppress fires while considering the geographical distribution of posts. For example, the fire suppression unit can implement measures specific to a particular area when a fire erupts in that area. The fire suppression unit can also apply fire suppression methods specific to a particular area based on its geographical distribution. For example, the fire suppression unit can optimize fire suppression methods for each area by considering its geographical distribution. This allows the fire suppression unit to evaluate area-specific risks and expectations by considering the geographical distribution of posts. Some or all of the above processing in the fire suppression unit may be performed using AI, for example, or without AI. For example, the fire suppression unit can input geographical data of posts into a generating AI and have the generating AI perform fire suppression while considering its geographical distribution.

[0054] The fire suppression unit can improve the accuracy of its fire suppression process by referring to relevant literature for the submission. For example, the fire suppression unit can refer to academic papers and articles related to the submission content to enhance the reliability of its fire suppression method. The fire suppression unit can also improve the accuracy of its fire suppression by supplementing background information on the submission content based on relevant literature. For example, the fire suppression unit can evaluate the expertise and credibility of the submission content by referring to relevant literature. In this way, the fire suppression unit can improve the reliability and accuracy of its fire suppression by referring to relevant literature for the submission. Some or all of the above processing in the fire suppression unit may be performed using AI, for example, or without AI. For example, the fire suppression unit can input the relevant literature data for the submission into a generating AI and have the generating AI perform the task of improving the accuracy of fire suppression.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The analysis unit can optimize its analysis algorithm by referring to past online controversy data during the analysis process. For example, it can analyze the frequency of occurrence of specific keywords or phrases based on past controversy data and assess the risk. It can also calculate the probability that a specific posting pattern will lead to a controversy by referring to past controversy data. It can also analyze the impact of posting content and timing on controversies using past controversy data. In this way, the analysis unit can improve the accuracy of its analysis by referring to past controversy data.

[0057] The editing function can adjust the level of detail of revisions based on the importance of the post. For example, for high-priority posts, it can provide detailed revision suggestions and make revisions carefully. For low-priority posts, it can provide concise revision suggestions and make revisions quickly. It can also determine the priority of revisions according to their importance and make revisions efficiently. In this way, the editing function can make revisions efficiently by adjusting the level of detail of revisions based on the importance of the post.

[0058] The resimulation unit can improve the accuracy of the resimulation by considering the interrelationships between posts during the resimulation process. For example, if multiple posts are related, the resimulation will be performed considering the impact of each post. It can also analyze the interrelationships between posts and evaluate the overall impact. It can also propose the optimal correction plan by considering the interrelationships between posts. In this way, the resimulation unit can improve the accuracy of the resimulation by considering the interrelationships between posts.

[0059] The fire suppression unit can optimize its fire suppression algorithm by referring to past fire incident data during the fire suppression process. For example, it can select the most effective fire suppression method based on past fire incident data. It can also apply the optimal fire suppression method for a specific situation by referring to past fire incident data. It can also evaluate the effectiveness of fire suppression methods using past fire incident data and select the optimal method. In this way, the fire suppression unit can improve the accuracy of fire suppression by referring to past fire incident data.

[0060] The fire suppression team can apply different fire suppression methods depending on the category of the post when it is brought under control. For example, a fire suppression method that emphasizes customer service can be applied to a fire suppression of a product review. A fire suppression method that emphasizes correcting or adding information can be applied to a fire suppression of a news article. A fire suppression method that emphasizes revising the advertising content or apologizing can be applied to a fire suppression of a promotional post. In this way, the fire suppression team can improve the accuracy of fire suppression by applying the appropriate fire suppression method for each category of post.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The analysis unit analyzes the text of the SNS post entered by the user. The analysis unit uses text analysis algorithms and natural language processing technology to analyze the content of the post, perform sentiment analysis, and evaluate the emotional tone of the post. Step 2: The editing unit modifies the post based on the simulation results obtained by the analysis unit. The editing unit proposes changes to the post content, such as adjusting the wording, changing the tone of the post, or deleting parts of the post content. Step 3: The resimulation unit resimulates the post that has been modified by the correction unit. The resimulation unit re-evaluates the modified post, recalculates the risks, and predicts its spread. Step 4: The fire suppression unit switches to fire suppression mode if a post escalates into a firestorm. The fire suppression unit takes specific actions to contain the firestorm, contacts relevant parties using notification methods, and supports understanding the firestorm situation and taking a swift response.

[0063] (Example of form 2) The online crisis risk management system according to an embodiment of the present invention is a system that supports corporate brand protection and rapid response by predicting and taking measures against online crises in social media posts. This system allows users to input text for social media posts, and the AI ​​analyzes the input text to simulate the risk of online crises, the likelihood of virality, post impressions, follower growth, comments received, and the number of online news articles published. Based on the simulation results, users can revise their posts, and after revisions, a re-simulation is performed. This allows for repeated trial and error until a satisfactory post is created. Furthermore, if a post goes viral, the agent immediately switches to a fire-extinguishing mode, supporting everything from understanding the situation to coordinating with relevant parties. This allows the person in charge to respond without panicking. The agent also features an intuitive UI, making it easy for anyone to operate. This system is offered as an inexpensive solution for small and medium-sized enterprises and sole proprietors, aiming to capture a 1 trillion yen business opportunity in the social media marketing and advertising market. Furthermore, by selling it in conjunction with existing "online crisis insurance," it can strongly appeal to the needs of businesses. This allows the crisis risk management system to help companies protect their brand and respond quickly to online crises.

[0064] The online firestorm risk management system according to this embodiment comprises an analysis unit, a modification unit, a resimulation unit, and a fire suppression unit. The analysis unit analyzes the text of the SNS post entered by the user. The analysis unit analyzes the content of the post using, for example, a text analysis algorithm. The analysis unit can also perform sentiment analysis and evaluate the emotional tone of the post. The analysis unit analyzes the meaning of the content of the post using, for example, natural language processing technology. The modification unit modifies the post based on the simulation results obtained by the analysis unit. The modification unit proposes changes to the content of the post, for example. The modification unit can also adjust the expression and change the tone of the post. The modification unit can also delete, for example, part of the content of the post. The resimulation unit resimulates the post modified by the modification unit. The resimulation unit re-evaluates the modified post, for example. The resimulation unit can also recalculate the risk and re-evaluate the firestorm risk of the modified post. The resimulation unit can also predict the spread of the modified post, for example. The fire suppression unit switches to fire suppression mode when the post goes viral. The fire suppression unit, for example, executes specific measures to suppress the escalation of the fire. The fire suppression unit can also contact relevant parties using notification methods. The fire suppression unit, for example, grasps the situation of the fire and supports a rapid response. In this way, the fire risk management system according to the embodiment can support the protection of a company's brand and rapid response by predicting and taking measures against firestorms in SNS posts.

[0065] The analysis unit analyzes the text of social media posts entered by users. For example, the analysis unit analyzes the content of posts using text analysis algorithms. Specifically, it utilizes natural language processing (NLP) techniques to analyze the grammatical structure and meaning of the post content in detail. The analysis unit can also perform sentiment analysis to evaluate the emotional tone of the post. Sentiment analysis uses machine learning models to identify sentiment categories such as positive, negative, and neutral. For example, it calculates sentiment scores for words and phrases included in the post content to evaluate the overall emotional tone. Furthermore, the analysis unit analyzes the frequency of occurrence of specific keywords and phrases to identify potential risk factors in the post content. For example, it lists words and expressions that are likely to cause controversy and checks whether they are included in the post. This allows the analysis unit to assess the risk of the post content and anticipate the possibility of controversy in advance.

[0066] The editing team modifies posts based on simulation results obtained by the analysis team. For example, the editing team proposes changes to the content of posts. Specifically, it adjusts the wording of posts based on risk factors identified by the analysis team. The editing team can also adjust the tone of posts by adjusting the wording. For example, it may replace negative expressions with positive ones or change aggressive words to neutral ones. The editing team can also delete parts of posts. For example, if certain keywords or phrases are likely to cause controversy, they can be removed to reduce the risk. Furthermore, the editing team also makes suggestions to improve the grammar and style of posts. For example, it may revise the sentence structure and change it to a clearer and easier-to-understand expression. In this way, the editing team can adjust posts in a way that minimizes the risk of the content while not distorting the user's intent.

[0067] The re-simulation unit re-simulates the post that has been modified by the revision unit. For example, the re-simulation unit re-evaluates the revised post. Specifically, it re-analyzes the content of the revised post and performs a risk assessment. The re-simulation unit can also recalculate the risk and re-evaluate the risk of the revised post becoming a controversial topic. For example, it compares the content of the post before and after revision and checks the change in the risk score. The re-simulation unit can also predict the spread of the revised post. For example, it simulates the extent to which the revised post may spread and assesses the risk of it becoming a controversial topic. This allows the re-simulation unit to confirm whether the content of the revised post is appropriate and to make further revisions if necessary. Furthermore, the re-simulation unit can also use past data and statistical information to assess the risk of the revised post. For example, it can refer to past controversial incidents to assess the likelihood of the revised post becoming a controversial topic. This allows the re-simulation unit to accurately assess the risk of the revised post and take appropriate measures.

[0068] The Firefighting Department switches to firefighting mode when a post goes viral. The Firefighting Department takes specific actions to suppress the firefight, such as quickly deleting or modifying the content of the post that caused the firefight. The Firefighting Department can also contact relevant parties using notification methods, such as notifying corporate public relations and crisis management personnel of the situation in real time to encourage a quick response. Furthermore, the Firefighting Department monitors the situation and supports a rapid response, such as monitoring the spread of the firefight on social media and evaluating its scale and impact. The Firefighting Department can also analyze the cause and background of the firefight and propose measures to prevent recurrence, such as identifying the content and expression of the post that caused the firefight and suggesting points to be careful about in future posts. In this way, the Firefighting Department can support a quick and appropriate response while minimizing the risk of a firefight. Furthermore, the Firefighting Department can collect user feedback and use it to improve the system, such as evaluating the effectiveness and problems of the firefight response and improving the system's functions and processes. This allows the fire suppression department to constantly utilize the latest information and technology to improve the performance of the fire risk management system.

[0069] The analytics unit can simulate the risk of a post going viral, the likelihood of it being shared with many users, the post's impressions, follower growth, the number of comments received, and the number of online news articles it will be featured in. For example, the analytics unit can calculate a score for the risk of a post going viral. The analytics unit can also calculate a risk score based on data from past viral incidents. For example, the analytics unit can predict the number of shares a post will receive. The analytics unit can calculate the probability of a post going viral and predict how widely it will be shared. For example, the analytics unit can predict the number of impressions and views a post will receive. The analytics unit can predict impressions and evaluate how many users will see a post. For example, the analytics unit can calculate the follower growth rate. The analytics unit can predict follower growth and evaluate how many new followers a post will gain. For example, the analytics unit can predict the number of comments. The analytics unit can perform sentiment analysis and evaluate the emotional tone of the comments received. For example, the analytics unit can predict the number of news articles it will be featured in. The analytics unit can evaluate media influence and predict how widely a post will be featured in news articles. This allows the analysis unit to predict the impact of a post by simulating various elements of the post. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the text data of the post into a generating AI and have the generating AI perform a prediction of the risk of online backlash and spread.

[0070] The editing unit can modify posts based on simulation results. The editing unit can, for example, suggest changes to the content of the post. The editing unit can also adjust the wording and change the tone of the post. The editing unit can, for example, delete parts of the content of the post. Based on the simulation results, the editing unit can present revised proposals to reduce the risk of the post going viral. The editing unit can, for example, change the content of the post to reduce the risk of going viral. The editing unit can also adjust the wording and change the tone of the post. The editing unit can, for example, delete parts of the content of the post. In this way, the editing unit can reduce the risk of going viral by modifying posts based on simulation results. Some or all of the above processing in the editing unit may be performed using AI, for example, or without AI. For example, the editing unit can input the simulation results into a generating AI and have the generating AI perform revisions to the content of the post.

[0071] The re-simulation unit can re-simulate the revised post. The re-simulation unit can, for example, re-evaluate the revised post. The re-simulation unit can also recalculate the risks and re-evaluate the risk of the revised post going viral. The re-simulation unit can, for example, predict the spread of the revised post. The re-simulation unit can optimize the post based on the simulation results of the revised post. The re-simulation unit can, for example, re-evaluate the revised post and propose the optimal post content. The re-simulation unit can also recalculate the risks and re-evaluate the risk of the revised post going viral. The re-simulation unit can, for example, predict the spread of the revised post. In this way, the re-simulation unit can optimize the post by re-simulating the revised post. Some or all of the above processing in the re-simulation unit may be performed using AI, for example, or without AI. For example, the re-simulation unit can input the revised post data into a generating AI and have the generating AI perform the re-simulation.

[0072] The fire suppression unit can automatically switch to fire suppression mode when a post goes viral, execute a series of processes to suppress the fire, and support everything from understanding the situation to coordinating with relevant parties. The fire suppression unit can, for example, execute specific processes to suppress the fire. The fire suppression unit can also contact relevant parties using notification methods. The fire suppression unit can, for example, understand the fire situation and support a rapid response. The fire suppression unit can execute specific processes to suppress the fire and support everything from understanding the situation to coordinating with relevant parties. The fire suppression unit can, for example, execute specific processes to suppress the fire. The fire suppression unit can also contact relevant parties using notification methods. The fire suppression unit can, for example, understand the fire situation and support a rapid response. This allows the fire suppression unit to respond quickly when a post goes viral. Some or all of the processes described above in the fire suppression unit may be performed using AI, for example, or not. For example, the fire suppression unit can input data on the fire situation into a generating AI and have the generating AI execute processes to suppress the fire.

[0073] The fire suppression unit can provide appropriate guidance to enable personnel to respond calmly. The fire suppression unit can, for example, provide response procedures. The fire suppression unit can also issue alert notifications to encourage personnel to respond quickly. The fire suppression unit can, for example, provide response procedures to support personnel in responding calmly. The fire suppression unit can also issue alert notifications to encourage personnel to respond quickly. The fire suppression unit can, for example, provide response procedures to support personnel in responding calmly. In this way, the fire suppression unit can support personnel in responding calmly. Some or all of the above processes in the fire suppression unit may be performed using AI, for example, or not using AI. For example, the fire suppression unit can have a generating AI provide response procedures to support personnel in responding calmly.

[0074] The analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the user is stressed, the analysis unit can display the analysis results concisely, highlighting only the important points. If the user is relaxed, the analysis unit can also display detailed analysis results and add explanations for each item. If the user is in a hurry, the analysis unit can display a summary of the analysis results for quick understanding. In this way, the analysis unit can help the user understand by adjusting how the analysis results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's emotion data into the generative AI and have the generative AI adjust how the analysis results are displayed.

[0075] The analysis unit can optimize its analysis algorithm by referring to past online controversy data during the analysis process. For example, the analysis unit can analyze the frequency of occurrence of specific keywords or phrases based on past online controversy data and assess the risk. The analysis unit can also calculate the probability that a specific posting pattern will lead to an online controversy by referring to past online controversy data. For example, the analysis unit can use past online controversy data to analyze the impact of posting content and timing on online controversies. In this way, the analysis unit can improve the accuracy of its analysis by referring to past online controversy data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past online controversy data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0076] The analysis unit can apply different analysis methods to each category of post during analysis. For example, the analysis unit can apply an analysis method that emphasizes customer ratings and feedback to product review posts. The analysis unit can also apply an analysis method that emphasizes the reliability and source of information to news article posts. For example, the analysis unit can apply an analysis method that emphasizes advertising effectiveness and target audience response to promotional posts. In this way, the analysis unit can improve the accuracy of the analysis by applying the appropriate analysis method to each category of post. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input post category data into a generating AI and have the generating AI execute the application of category-specific analysis methods.

[0077] The analysis unit can estimate the user's emotions and determine the priority of the analysis results based on the estimated user emotions. For example, if the user is feeling anxious, the analysis unit can prioritize displaying items with a high risk of causing controversy. If the user is excited, the analysis unit can also prioritize displaying items with a high expectation of going viral. If the user is calm, the analysis unit can also display the overall analysis results in a balanced manner. In this way, the analysis unit can prioritize important information by determining the priority of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI determine the priority of the analysis results.

[0078] The analysis unit can perform analysis while considering the geographical distribution of posts. For example, the analysis unit can analyze the response to posts in a specific region and evaluate the risks specific to that region. The analysis unit can also calculate the expected level of virality in a specific region based on the geographical distribution. For example, the analysis unit can analyze the increase in impressions and follower counts for each region while considering the geographical distribution. In this way, the analysis unit can evaluate region-specific risks and expectations by considering the geographical distribution of posts. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input geographical data of posts into a generating AI and have the generating AI perform analysis that considers the geographical distribution.

[0079] The analysis unit can improve the accuracy of its analysis by referring to relevant literature for the submission during the analysis process. For example, the analysis unit can refer to academic papers and articles related to the content of the submission to increase the reliability of the analysis results. The analysis unit can also improve the accuracy of its analysis by supplementing background information on the content of the submission based on relevant literature. For example, the analysis unit can evaluate the expertise and credibility of the content of the submission by referring to relevant literature. In this way, the analysis unit can improve the reliability and accuracy of its analysis by referring to relevant literature for the submission. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the data of relevant literature for the submission into a generating AI and have the generating AI perform the task of improving the accuracy of the analysis.

[0080] The editing unit can estimate the user's emotions and adjust the way the corrections are expressed based on the estimated emotions. For example, if the user is stressed, the editing unit will present a concise and clear correction. If the user is relaxed, the editing unit may also present a more detailed correction, offering more options. If the user is in a hurry, the editing unit will quickly present a correction, making it immediately applicable. In this way, the editing unit can help the user understand by adjusting the way the corrections are expressed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editing unit may be performed using AI, or not using AI. For example, the editing unit can input user emotion data into a generative AI and have the generative AI adjust the way the corrections are expressed.

[0081] The editing unit can adjust the level of detail of revisions based on the importance of the post during the revision process. For example, the editing unit can present detailed revision suggestions and carefully revise high-importance posts. For low-importance posts, the editing unit can also present concise revision suggestions and revise them quickly. The editing unit can also determine revision priorities according to importance and revise efficiently. In this way, the editing unit can perform efficient revisions by adjusting the level of detail of revisions based on the importance of the post. Some or all of the above processes in the editing unit may be performed using AI, for example, or not using AI. For example, the editing unit can input post importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of revisions.

[0082] The editing unit can apply different editing algorithms depending on the category of the post during editing. For example, for product review posts, the editing unit can apply an editing algorithm that emphasizes customer ratings and feedback. For news article posts, the editing unit can also apply an editing algorithm that emphasizes the reliability and source of information. For promotional posts, the editing unit can also apply an editing algorithm that emphasizes advertising effectiveness and the response of the target audience. In this way, the editing unit can improve the accuracy of editing by applying the appropriate editing algorithm according to the category of the post. Some or all of the above processing in the editing unit may be performed using AI, for example, or without AI. For example, the editing unit can input post category data into a generating AI and have the generating AI execute the application of category-specific editing algorithms.

[0083] The editing unit can estimate the user's emotions and adjust the length of the revision based on the estimated emotions. For example, if the user is stressed, the editing unit may present a short, concise revision. If the user is relaxed, the editing unit may present a longer revision with a more detailed explanation. If the user is in a hurry, the editing unit may present a short revision that can be applied quickly. In this way, the editing unit can help the user understand by adjusting the length of the revision according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editing unit may be performed using AI or not using AI. For example, the editing unit can input user emotion data into a generative AI and have the generative AI adjust the length of the revision.

[0084] The editing unit can determine the priority of revisions based on the submission date of each post. For example, the editing unit can prioritize revisions to posts with upcoming submission dates. It can also postpone revisions to posts with later submission dates. The editing unit can also adjust the revision schedule according to the submission dates. This allows the editing unit to perform revisions efficiently by determining the priority of revisions based on the submission dates of each post. Some or all of the above processes in the editing unit may be performed using AI, for example, or not. For example, the editing unit can input submission date data into a generating AI and have the generating AI determine the priority of revisions.

[0085] The editing unit can adjust the order of edits based on the relevance of the posts during the editing process. For example, the editing unit can prioritize editing highly relevant posts. It can also postpone editing less relevant posts. The editing unit can also adjust the editing schedule according to the relevance of the posts. This allows the editing unit to perform edits efficiently by adjusting the order of edits based on the relevance of the posts. Some or all of the above processes in the editing unit may be performed using AI, for example, or not using AI. For example, the editing unit can input post relevance data into a generating AI and have the generating AI adjust the order of edits.

[0086] The resimulation unit can estimate the user's emotions and adjust the resimulation criteria based on the estimated user emotions. For example, if the user is feeling anxious, the resimulation unit will perform a resimulation that emphasizes the assessment of the risk of backlash. If the user is excited, the resimulation unit may also perform a resimulation that emphasizes the expectation of virality. If the user is calm, the resimulation unit may also perform a resimulation that considers the overall balance. In this way, the resimulation unit can perform an appropriate resimulation by adjusting the resimulation criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the resimulation unit may be performed using AI, for example, or not using AI. For example, the resimulation unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the resimulation criteria.

[0087] The resimulation unit can improve the accuracy of the resimulation by considering the interrelationships of posts during the resimulation process. For example, if multiple posts are related, the resimulation unit will perform the resimulation considering the impact of each post. The resimulation unit can also analyze the interrelationships of posts and evaluate the overall impact. For example, the resimulation unit can propose the optimal correction plan by considering the interrelationships of posts. In this way, the resimulation unit can improve the accuracy of the resimulation by considering the interrelationships of posts. Some or all of the above processing in the resimulation unit may be performed using AI, for example, or without AI. For example, the resimulation unit can input the interrelationship data of posts into a generating AI and have the generating AI perform the resimulation accuracy improvement.

[0088] The resimulation unit can perform a resimulation while considering the attribute information of the post submitter. For example, the resimulation unit can perform a resimulation while considering the submitter's number of followers and influence. The resimulation unit can also perform a resimulation by referring to the submitter's past posting history. For example, the resimulation unit can also suggest the most suitable revision based on the submitter's attribute information. In this way, the resimulation unit can improve the accuracy of the resimulation by considering the attribute information of the post submitter. Some or all of the above processing in the resimulation unit may be performed using AI, for example, or without using AI. For example, the resimulation unit can input the submitter's attribute information data into a generating AI and have the generating AI perform the resimulation.

[0089] The resimulation unit can estimate the user's emotions and adjust the order in which the resimulation results are displayed based on the estimated user emotions. For example, if the user is feeling anxious, the resimulation unit may prioritize displaying items with a high risk of backlash. If the user is excited, the resimulation unit may also prioritize displaying items with a high expectation of going viral. If the user is calm, the resimulation unit may also display items considering the overall balance. In this way, the resimulation unit can prioritize providing important information by adjusting the order in which the resimulation results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the resimulation unit may be performed using AI, for example, or without AI. For example, the resimulation unit can input user emotion data into the generative AI and have the generative AI adjust the display order of the resimulation results.

[0090] The resimulation unit can perform resimulations while considering the geographical distribution of posts. For example, the resimulation unit can analyze the response to posts in a specific region and evaluate the risks specific to that region. The resimulation unit can also calculate the expected degree of virality in a specific region based on the geographical distribution. For example, the resimulation unit can analyze the increase in impressions and follower counts for each region while considering the geographical distribution. In this way, the resimulation unit can evaluate region-specific risks and expectations by considering the geographical distribution of posts. Some or all of the above processing in the resimulation unit may be performed using AI, for example, or without using AI. For example, the resimulation unit can input the geographical data of posts into a generating AI and have the generating AI perform a resimulation that considers the geographical distribution.

[0091] The resimulation unit can improve the accuracy of the resimulation by referring to relevant literature for the submission during the resimulation process. For example, the resimulation unit can refer to academic papers and articles related to the submission content to increase the reliability of the resimulation results. The resimulation unit can also improve the accuracy of the resimulation by supplementing background information on the submission content based on relevant literature. For example, the resimulation unit can evaluate the expertise and credibility of the submission content by referring to relevant literature. In this way, the resimulation unit can improve the reliability and accuracy of the resimulation by referring to relevant literature for the submission. Some or all of the above processing in the resimulation unit may be performed using AI, for example, or without AI. For example, the resimulation unit can input the relevant literature data for the submission into a generating AI and have the generating AI perform the resimulation accuracy improvement.

[0092] The fire suppression unit can estimate the user's emotions and adjust the fire suppression method based on the estimated emotions. For example, if the user is in a state of panic, the fire suppression unit can calmly explain the situation and suggest specific countermeasures. If the user is calm, the fire suppression unit can also suggest multiple countermeasures along with a detailed explanation of the situation. For example, if the user is anxious, the fire suppression unit will prioritize suggesting countermeasures that can be implemented quickly. In this way, the fire suppression unit can take appropriate action by adjusting the fire suppression method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the fire suppression unit may be performed using AI, for example, or without AI. For example, the fire suppression unit can input the user's emotion data into the generative AI and have the generative AI adjust the fire suppression method.

[0093] The fire suppression unit can optimize its fire suppression algorithm by referring to past fire incident data during the fire suppression process. For example, the fire suppression unit can select the most effective fire suppression method based on past fire incident data. The fire suppression unit can also apply the optimal fire suppression method for a specific situation by referring to past fire incident data. For example, the fire suppression unit can use past fire incident data to evaluate the effectiveness of fire suppression methods and select the optimal method. In this way, the fire suppression unit can improve the accuracy of fire suppression by referring to past fire incident data. Some or all of the above processes in the fire suppression unit may be performed using AI, for example, or without AI. For example, the fire suppression unit can input past fire incident data into a generating AI and have the generating AI perform the optimization of the fire suppression algorithm.

[0094] The fire suppression unit can apply different fire suppression methods depending on the category of the post when it is suppressed. For example, the fire suppression unit can apply a fire suppression method that emphasizes customer service to a product review fire. For a news article fire, the fire suppression unit can also apply a fire suppression method that emphasizes correcting or adding information. For a promotional post fire, the fire suppression unit can also apply a fire suppression method that emphasizes modifying the advertisement content or apologizing. In this way, the fire suppression unit can improve the accuracy of fire suppression by applying the appropriate fire suppression method for each category of post. Some or all of the above processing in the fire suppression unit may be performed using AI, for example, or not using AI. For example, the fire suppression unit can input post category data into a generating AI and have the generating AI execute the application of fire suppression methods for each category.

[0095] The fire suppression unit can estimate the user's emotions and determine the priority of fire suppression based on the estimated emotions. For example, if the user is in a state of panic, the fire suppression unit will prioritize the most urgent measures. If the user is calm, the fire suppression unit can also determine priorities by considering the overall situation. For example, if the user is anxious, the fire suppression unit will prioritize measures that can be implemented quickly. In this way, the fire suppression unit can respond quickly by determining the priority of fire suppression according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the fire suppression unit may be performed using AI, for example, or not using AI. For example, the fire suppression unit can input user emotion data into a generative AI and have the generative AI determine the priority of fire suppression.

[0096] The fire suppression unit can suppress fires while considering the geographical distribution of posts. For example, the fire suppression unit can implement measures specific to a particular area when a fire erupts in that area. The fire suppression unit can also apply fire suppression methods specific to a particular area based on its geographical distribution. For example, the fire suppression unit can optimize fire suppression methods for each area by considering its geographical distribution. This allows the fire suppression unit to evaluate area-specific risks and expectations by considering the geographical distribution of posts. Some or all of the above processing in the fire suppression unit may be performed using AI, for example, or without AI. For example, the fire suppression unit can input geographical data of posts into a generating AI and have the generating AI perform fire suppression while considering its geographical distribution.

[0097] The fire suppression unit can improve the accuracy of its fire suppression process by referring to relevant literature for the submission. For example, the fire suppression unit can refer to academic papers and articles related to the submission content to enhance the reliability of its fire suppression method. The fire suppression unit can also improve the accuracy of its fire suppression by supplementing background information on the submission content based on relevant literature. For example, the fire suppression unit can evaluate the expertise and credibility of the submission content by referring to relevant literature. In this way, the fire suppression unit can improve the reliability and accuracy of its fire suppression by referring to relevant literature for the submission. Some or all of the above processing in the fire suppression unit may be performed using AI, for example, or without AI. For example, the fire suppression unit can input the relevant literature data for the submission into a generating AI and have the generating AI perform the task of improving the accuracy of fire suppression.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on those emotions. For example, if the user is stressed, the analysis results can be displayed concisely, highlighting only the important points. If the user is relaxed, detailed analysis results can be displayed, and explanations for each item can be added. If the user is in a hurry, the analysis results can be summarized for quick understanding. In this way, the analysis unit can help the user understand the results by adjusting how they are displayed according to their emotions.

[0100] The correction unit can estimate the user's emotions and adjust the way the correction is presented based on those emotions. For example, if the user is stressed, it can present a concise and clear correction. If the user is relaxed, it can present a more detailed correction and offer more options. If the user is in a hurry, it can present a correction quickly so that it can be applied immediately. In this way, the correction unit can help the user understand the correction by adjusting the way it is presented according to the user's emotions.

[0101] The resimulation unit can estimate the user's emotions and adjust the resimulation criteria based on those emotions. For example, if the user is feeling anxious, the resimulation can prioritize the assessment of the risk of online backlash. If the user is excited, the resimulation can prioritize the expectation of virality. If the user is calm, the resimulation can consider the overall balance. In this way, the resimulation unit can perform an appropriate resimulation by adjusting the resimulation criteria according to the user's emotions.

[0102] The fire suppression unit can estimate the user's emotions and adjust its fire suppression method based on those emotions. For example, if the user is in a state of panic, it will calmly explain the situation and present specific countermeasures. If the user is calm, it can also present multiple countermeasures along with a detailed explanation of the situation. If the user is anxious, it will prioritize presenting countermeasures that can be implemented quickly. In this way, the fire suppression unit can respond appropriately by adjusting its fire suppression method according to the user's emotions.

[0103] The fire suppression unit can estimate the user's emotions and determine the priority of fire suppression based on those emotions. For example, if the user is in a state of panic, it will prioritize the most urgent measures. If the user is calm, it can also determine priorities by considering the overall situation. If the user is anxious, it will prioritize measures that can be implemented quickly. In this way, the fire suppression unit can respond quickly by determining the priority of fire suppression according to the user's emotions.

[0104] The analysis unit can optimize its analysis algorithm by referring to past online controversy data during the analysis process. For example, it can analyze the frequency of occurrence of specific keywords or phrases based on past controversy data and assess the risk. It can also calculate the probability that a specific posting pattern will lead to a controversy by referring to past controversy data. It can also analyze the impact of posting content and timing on controversies using past controversy data. In this way, the analysis unit can improve the accuracy of its analysis by referring to past controversy data.

[0105] The editing function can adjust the level of detail of revisions based on the importance of the post. For example, for high-priority posts, it can provide detailed revision suggestions and make revisions carefully. For low-priority posts, it can provide concise revision suggestions and make revisions quickly. It can also determine the priority of revisions according to their importance and make revisions efficiently. In this way, the editing function can make revisions efficiently by adjusting the level of detail of revisions based on the importance of the post.

[0106] The resimulation unit can improve the accuracy of the resimulation by considering the interrelationships between posts during the resimulation process. For example, if multiple posts are related, the resimulation will be performed considering the impact of each post. It can also analyze the interrelationships between posts and evaluate the overall impact. It can also propose the optimal correction plan by considering the interrelationships between posts. In this way, the resimulation unit can improve the accuracy of the resimulation by considering the interrelationships between posts.

[0107] The fire suppression unit can optimize its fire suppression algorithm by referring to past fire incident data during the fire suppression process. For example, it can select the most effective fire suppression method based on past fire incident data. It can also apply the optimal fire suppression method for a specific situation by referring to past fire incident data. It can also evaluate the effectiveness of fire suppression methods using past fire incident data and select the optimal method. In this way, the fire suppression unit can improve the accuracy of fire suppression by referring to past fire incident data.

[0108] The fire suppression team can apply different fire suppression methods depending on the category of the post when it is brought under control. For example, a fire suppression method that emphasizes customer service can be applied to a fire suppression of a product review. A fire suppression method that emphasizes correcting or adding information can be applied to a fire suppression of a news article. A fire suppression method that emphasizes revising the advertising content or apologizing can be applied to a fire suppression of a promotional post. In this way, the fire suppression team can improve the accuracy of fire suppression by applying the appropriate fire suppression method for each category of post.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The analysis unit analyzes the text of the SNS post entered by the user. The analysis unit uses text analysis algorithms and natural language processing technology to analyze the content of the post, perform sentiment analysis, and evaluate the emotional tone of the post. Step 2: The editing unit modifies the post based on the simulation results obtained by the analysis unit. The editing unit proposes changes to the post content, such as adjusting the wording, changing the tone of the post, or deleting parts of the post content. Step 3: The resimulation unit resimulates the post that has been modified by the correction unit. The resimulation unit re-evaluates the modified post, recalculates the risks, and predicts its spread. Step 4: The fire suppression unit switches to fire suppression mode if a post escalates into a firestorm. The fire suppression unit takes specific actions to contain the firestorm, contacts relevant parties using notification methods, and supports understanding the firestorm situation and taking a swift response.

[0111] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0112] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0113] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0114] Each of the multiple elements described above, including the analysis unit, modification unit, resimulation unit, and fire suppression unit, is implemented, for example, in at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The modification unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The resimulation unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The fire suppression unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0122] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0126] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0129] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the analysis unit, modification unit, resimulation unit, and fire suppression unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The modification unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The resimulation unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The fire suppression unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0139] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the analysis unit, modification unit, resimulation unit, and fire suppression unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The modification unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The resimulation unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The fire suppression unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0151] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0154] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0155] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0156] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements described above, including the analysis unit, modification unit, resimulation unit, and fire suppression unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The modification unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The resimulation unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The fire suppression unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0164] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0166] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0167] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0168] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0172] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0173] 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.

[0174] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0175] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0176] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0177] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0179] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0180] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0181] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0182] (Note 1) An analysis unit that analyzes the text of SNS posts entered by users, A modification unit modifies the post based on the simulation results obtained by the analysis unit, A resimulation unit that resimulates the post modified by the aforementioned modification unit, The system includes a fire suppression unit that, when a post goes viral, automatically switches to fire suppression mode and executes a series of processes to suppress the fire. A system characterized by the following features. (Note 2) The aforementioned analysis unit, This simulates the risk of online backlash, the likelihood of a post being shared with many users, post impressions, follower growth, comments received, and the number of online news articles that publish the post. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned modification section is, Modify the post based on the simulation results. The system described in Appendix 1, characterized by the features described herein. (Note 4) The resimulation unit, Re-simulate the revised post. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned fire extinguishing unit is If a post goes viral and causes a firestorm, the system automatically switches to fire suppression mode, executes a series of processes to contain the situation, and supports everything from understanding the situation to coordinating with relevant parties. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned fire extinguishing unit is The system provides appropriate guidance so that the person in charge can respond calmly. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, During analysis, the analysis algorithm is optimized by referring to past online controversy data. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, During analysis, different analysis methods are applied to each category of post. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, It estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, During the analysis, the geographical distribution of the posts will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During analysis, we refer to relevant literature related to the submission to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned modification section is, It estimates the user's emotions and adjusts the way the correction is expressed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned modification section is, When making revisions, adjust the level of detail of the revisions based on the importance of the post. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned modification section is, When making corrections, different correction algorithms are applied depending on the category of the post. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned modification section is, It estimates the user's emotions and adjusts the length of the correction based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned modification section is, When making revisions, prioritize revisions based on when the submission was made. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned modification section is, When making revisions, adjust the order of revisions based on the relevance of the posts. The system described in Appendix 1, characterized by the features described herein. (Note 19) The resimulation unit, The system estimates the user's emotions and adjusts the resimulation criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The resimulation unit, When resimulating, the accuracy of the resimulation will be improved by considering the interrelationships between posts. The system described in Appendix 1, characterized by the features described herein. (Note 21) The resimulation unit, During resimulation, the attribute information of the submitter of the post will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The resimulation unit, It estimates the user's emotions and adjusts the order in which the re-simulation results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The resimulation unit, When resimulating, the geographical distribution of posts will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The resimulation unit, When resimulating, refer to the relevant literature in the submission to improve the accuracy of the resimulation. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned fire extinguishing unit is It estimates the user's emotions and adjusts the fire extinguishing method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned fire extinguishing unit is During fire suppression, the fire suppression algorithm is optimized by referring to data from past fire incidents. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned fire extinguishing unit is When extinguishing a fire, different extinguishing methods will be applied depending on the category of the post. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned fire extinguishing unit is It estimates the user's emotions and determines the priority for extinguishing the fire based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned fire extinguishing unit is When extinguishing a fire, the geographical distribution of posts will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned fire extinguishing unit is When extinguishing a fire, refer to the relevant literature in the post to improve the accuracy of the fire extinguishing process. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An analysis unit that analyzes the text of SNS posts entered by users, A modification unit modifies the post based on the simulation results obtained by the analysis unit, A resimulation unit that resimulates the post modified by the aforementioned modification unit, The system includes a fire suppression unit that, when a post goes viral, automatically switches to fire suppression mode and executes a series of processes to suppress the fire. A system characterized by the following features.

2. The aforementioned analysis unit, This simulates the risk of online backlash, the likelihood of a post being shared with many users, post impressions, follower growth, comments received, and the number of online news articles that publish the post. The system according to feature 1.

3. The aforementioned modification section is, Modify the post based on the simulation results. The system according to feature 1.

4. The resimulation unit, Re-simulate the revised post. The system according to feature 1.

5. The aforementioned fire extinguishing unit is If a post goes viral and causes a firestorm, the system automatically switches to fire suppression mode, executes a series of processes to contain the situation, and supports everything from understanding the situation to coordinating with relevant parties. The system according to feature 1.

6. The aforementioned fire extinguishing unit is The system provides appropriate guidance so that the person in charge can respond calmly. The system according to feature 1.

7. The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system according to feature 1.

8. The aforementioned analysis unit, During analysis, the analysis algorithm is optimized by referring to past online controversy data. The system according to feature 1.

9. The aforementioned analysis unit, During analysis, different analysis methods are applied to each category of post. The system according to feature 1.

10. The aforementioned analysis unit, It estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The system according to feature 1.

Images