system

Abstract

The system according to this embodiment aims to detect the risk of online firestorms on social media in advance and to take appropriate countermeasures. [Solution] The system according to the embodiment comprises a collection unit, an anonymization unit, an analysis unit, an evaluation unit, and a modification unit. The collection unit collects records of online firestorms on social media. The anonymization unit anonymizes the firestorm records collected by the collection unit. The analysis unit analyzes the data anonymized by the anonymization unit and detects firestorm patterns. The evaluation unit quantifies the risk based on the firestorm patterns detected by the analysis unit. The modification unit proposes modifications if the evaluation unit determines the risk is high.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes 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 was a problem that it was difficult to detect in advance the risk of a flare-up on SNS and take appropriate countermeasures.

[0005] The system according to the embodiment aims to detect in advance the risk of a flare-up on SNS and take appropriate countermeasures.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an anonymization unit, an analysis unit, an evaluation unit, and a modification unit. The collection unit collects records of online controversies on social media. The anonymization unit anonymizes the records of controversies collected by the collection unit. The analysis unit analyzes the data anonymized by the anonymization unit and detects controversy patterns. The evaluation unit quantifies the risk based on the controversy patterns detected by the analysis unit. The modification unit proposes modifications if the evaluation unit determines the risk is high. [Effects of the Invention]

[0007] The system according to this embodiment can detect the risk of online firestorms on social media in advance and take appropriate 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 controls 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 firestorm pattern detection system according to an embodiment of the present invention is a system that anonymizes records of online firestorms on social media and uses an LLM (Large-Scale Language Model) to detect and analyze patterns of online firestorms. This system assists companies and individuals in creating guidelines for preventing online firestorms. It also quantifies and calculates the level of risk before a social media post is made, and if the risk is high, it identifies the category of risk and suggests corrective actions. For example, the online firestorm pattern detection system collects and anonymizes records of online firestorms on social media. Next, it analyzes this data using an LLM to detect patterns of online firestorms. For example, it identifies posts containing specific keywords or phrases that are likely to cause online firestorms. This allows for an understanding of online firestorm patterns. Next, based on the detected online firestorm patterns, it creates guidelines for preventing online firestorms for companies and individuals. For example, it proposes specific measures such as avoiding certain keywords or not posting at certain times. This minimizes the risk of online firestorms. Furthermore, the online firestorm pattern detection system quantifies and calculates the risk before a social media post is made. For example, it inputs the content of a post into an LLM and evaluates the risk by comparing it with past online firestorm patterns. If the risk is high, it identifies the category of risk and suggests corrective actions. For example, it can suggest specific revisions, such as changing certain keywords or modifying parts of the post content. This allows companies and individuals to anticipate the risk of online backlash on social media and take appropriate measures. This protects brand image and personal credibility, and improves the safety and reliability of social media activities. In this way, the backlash pattern detection system enables companies and individuals to anticipate the risk of online backlash on social media and take appropriate measures.

[0029] The online firestorm pattern detection system according to this embodiment comprises a collection unit, an anonymization unit, an analysis unit, an evaluation unit, and a correction unit. The collection unit collects records of online firestorms on social media. For example, the collection unit collects posts containing specific keywords or hashtags on social media. The collection unit can also collect posts that are concentrated over a specific period. For example, the collection unit collects posts related to a specific event or incident. The anonymization unit anonymizes the online firestorm records collected by the collection unit. For example, the anonymization unit removes personal information. The anonymization unit can also mask the data. For example, the anonymization unit masks the poster's name or account information. The analysis unit analyzes the data anonymized by the anonymization unit and detects online firestorm patterns. The analysis unit analyzes the data using, for example, LLM. For example, the analysis unit identifies posts containing specific keywords or phrases that are prone to causing online firestorms. The analysis unit can also identify content posted at specific times or on specific days of the week that is prone to causing online firestorms. The evaluation unit quantifies the risk based on the flame war patterns detected by the analysis unit. For example, the evaluation unit inputs the content of a post into LLM and evaluates the risk by comparing it with past flame war patterns. For example, the evaluation unit calculates a risk score. The evaluation unit can also identify risk categories. For example, the evaluation unit identifies posts containing specific keywords or phrases as high-risk. The revision unit proposes revisions if the evaluation unit determines the risk is high. For example, the revision unit proposes revisions that change specific keywords. The revision unit can also propose revisions that partially modify the content of a post. For example, the revision unit proposes revisions that change the tone or expression of the post. Thus, the flame war pattern detection system according to the embodiment can anonymize flame war records on social media, use LLM to detect and analyze flame war patterns, and perform risk assessment and propose revisions.

[0030] The data collection unit collects records of online controversies on social media. For example, the unit collects posts containing specific keywords or hashtags on social media. Specifically, the unit uses social media APIs to monitor posts in real time and automatically collects posts containing specific keywords or hashtags. This allows the unit to detect signs of a controversy early. The unit can also collect posts that are concentrated within a specific period. For example, the unit collects posts related to specific events or incidents. This allows the unit to evaluate whether a particular event is likely to trigger a controversy. Furthermore, the unit also collects post metadata (posting time, number of followers of the poster, number of retweets, etc.) to provide data for evaluating the scale and impact of a controversy. The unit centrally manages this data and makes it accessible to the analysis and evaluation units. For example, the collected data is stored on a cloud server and made accessible to the analysis and evaluation units in real time. This allows the unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The anonymization unit anonymizes the online harassment records collected by the collection unit. The anonymization unit removes personal information, for example. Specifically, the anonymization unit automatically detects and removes or masks personally identifiable information such as the poster's name, account information, and location information. The anonymization unit can also mask data. For example, the anonymization unit masks the poster's name and account information. This allows the anonymization unit to retain information necessary for data analysis while preventing the leakage of personal information. Furthermore, the anonymization unit uses natural language processing technology to extract personally identifiable information from the posts and anonymize it. For example, it replaces place names and organization names included in the posts with more general expressions. This allows the anonymization unit to provide the information required by the analysis unit while protecting data privacy. The anonymization unit has a feedback loop to continuously evaluate and improve the accuracy of the anonymization process. For example, it re-evaluates the anonymized data and performs additional processing if the anonymization is insufficient. This allows the anonymization unit to always anonymize data with high accuracy and improve the overall reliability of the system.

[0032] The analysis unit analyzes the anonymized data from the anonymization unit to detect online controversy patterns. The analysis unit uses, for example, LLM (Language-Language-Related Machine) to analyze the data. Specifically, the analysis unit uses natural language processing (LLM) to analyze post content and identify posts containing specific keywords or phrases that are prone to online controversy. For example, LLM learns from past controversy cases and predicts that posts containing specific keywords or phrases are likely to cause controversy. The analysis unit can also identify content posted at specific times or days of the week that is more likely to cause controversy. For example, based on past data, the analysis unit identifies a tendency for content posted at specific times or days of the week to cause controversy. Furthermore, the analysis unit performs sentiment analysis on posts and identifies posts with strong negative sentiments that are more likely to cause controversy. This allows the analysis unit to quickly and accurately analyze the collected data and detect early signs of online controversy. The analysis unit provides these analysis results to the evaluation unit, which uses them as basic data for risk assessment. For example, the analysis unit provides the evaluation unit with a list of posts containing specific keywords or phrases, which also serves as basic data for risk assessment. This allows the analysis unit to improve the overall system performance.

[0033] The evaluation unit quantifies risk based on the online firestorm patterns detected by the analysis unit. For example, the evaluation unit inputs the content of a post into the LLM (Likely a system for identifying and analyzing online content) and evaluates the risk by comparing it to past online firestorm patterns. Specifically, the evaluation unit uses the LLM to calculate a risk score for the content of a post. For example, it identifies posts containing specific keywords or phrases as high-risk and calculates their risk score. The evaluation unit can also identify risk categories. For example, it identifies posts containing specific keywords or phrases as high-risk and identifies their risk category. Furthermore, the evaluation unit provides basic data for suggesting revisions to the content of posts based on the risk score. For example, the evaluation unit provides basic data for suggesting revisions to the revision unit based on the risk score of posts containing specific keywords or phrases. This allows the evaluation unit to improve the accuracy of risk assessment and enhance the overall system performance.

[0034] The revision unit proposes revisions when the evaluation unit determines the risk is high. For example, the revision unit proposes revisions that change specific keywords. Specifically, the revision unit uses LLM to generate revisions to reduce the risk of the posted content. For example, it proposes revisions that change specific keywords or phrases. The revision unit can also propose revisions that partially modify the posted content. For example, the revision unit proposes revisions that change the tone or expression of the post. Furthermore, the revision unit evaluates the effectiveness of the revisions and re-evaluates them as needed. For example, the revision unit re-evaluates the posted content after applying the revisions to confirm whether the risk has been reduced. This allows the revision unit to always provide the optimal revisions and improve the overall system performance. The revision unit presents revisions to users and encourages them to revise their posted content. For example, the revision unit notifies users of revisions and encourages them to revise their posted content. This allows the revision unit to provide users with concrete means to reduce the risk of online backlash and improve the overall reliability of the system.

[0035] The collection unit can analyze the collection history of past online firestorms and select the optimal collection method. For example, the collection unit can identify and apply the most effective collection method from the past collection history. For example, the collection unit can analyze the past collection history and optimize the collection frequency. For example, the collection unit can determine the priority of collection targets based on the past collection history. This allows for the selection of the optimal collection method and improvement of collection efficiency by analyzing the past collection history. Some or all of the above processes in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input past collection history data into a generating AI and have the generating AI select the optimal collection method.

[0036] The data collection unit can filter the collected records of online controversies based on specific keywords or phrases. For example, the data collection unit can prioritize collecting posts containing specific keywords. For example, the data collection unit can filter and collect posts containing specific phrases. For example, the data collection unit can select data to collect based on the frequency of occurrence of keywords or phrases. This allows for the priority collection of highly relevant data by filtering based on specific keywords or phrases. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input post data containing specific keywords or phrases into a generating AI and have the generating AI perform the filtering.

[0037] The collection unit can prioritize the collection of highly relevant records by considering geographical location information when collecting records of online firestorms. For example, the collection unit can prioritize the collection of records of online firestorms that occurred in geographically close locations. For example, the collection unit can prioritize the collection of records of online firestorms that frequently occur in a specific region. For example, the collection unit can select highly relevant records based on geographical location information. In this way, by considering geographical location information, highly relevant records can be collected preferentially. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input geographical location data into a generating AI and have the generating AI perform the selection of highly relevant records.

[0038] The data collection unit can analyze social media activity and collect relevant records when collecting records of online controversies. For example, the data collection unit can collect relevant records based on the amount of activity on social media. For example, the data collection unit can prioritize the collection of posts containing specific hashtags on social media. For example, the data collection unit can collect relevant records considering the influence of users on social media. This allows for the efficient collection of relevant records by analyzing social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input social media activity data into a generating AI and have the generating AI perform the collection of relevant records.

[0039] The anonymization unit can adjust the level of anonymization based on the importance of the data during the anonymization process. For example, the anonymization unit can apply a detailed anonymization method to data with high importance, and a simpler anonymization method to data with low importance. The anonymization unit can also adjust the level of anonymization in stages based on the importance of the data. This optimizes data security and processing efficiency by adjusting the level of anonymization based on the importance of the data. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the importance of the data into a generating AI and have the generating AI perform the adjustment of the level of anonymization.

[0040] The anonymization unit can apply different anonymization algorithms depending on the data category during anonymization. For example, the anonymization unit can apply a strong anonymization algorithm to personal information. For example, the anonymization unit can apply a simpler anonymization algorithm to public data. The anonymization unit can select the optimal anonymization algorithm for each data category. This ensures data security by applying the optimal anonymization algorithm according to the data category. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the data category into a generating AI and have the generating AI select the optimal anonymization algorithm.

[0041] The anonymization unit can determine the anonymization priority based on the data submission date during the anonymization process. For example, the anonymization unit can prioritize anonymizing data with a more recent submission date. For example, the anonymization unit can postpone anonymizing data with an older submission date. For example, the anonymization unit can adjust the anonymization priority in stages based on the submission date. This allows for priority processing of the latest data by determining the anonymization priority based on the data submission date. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the data submission date into a generating AI and have the generating AI determine the anonymization priority.

[0042] The anonymization unit can adjust the anonymization order based on the relevance of the data during the anonymization process. For example, the anonymization unit can prioritize anonymizing highly relevant data. For example, the anonymization unit can postpone anonymizing less relevant data. For example, the anonymization unit can adjust the anonymization order in stages based on the relevance of the data. This allows for priority processing of highly relevant data by adjusting the anonymization order based on the relevance of the data. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the relevance of the data into a generating AI and have the generating AI perform the adjustment of the anonymization order.

[0043] The analysis unit can improve the accuracy of the analysis by considering the interrelationships between data during the analysis. For example, the analysis unit can improve the accuracy of the analysis based on the interrelationships between data. For example, the analysis unit can correct the analysis results by considering the interrelationships between data. For example, the analysis unit can analyze the interrelationships between data and select the optimal analysis method. In this way, the accuracy of the analysis can be improved by considering the interrelationships between data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the interrelationships between data into a generating AI and have the generating AI perform the improvement of the analysis accuracy.

[0044] The analysis unit can perform analysis while considering the attribute information of the data submitter. The analysis unit can, for example, improve the accuracy of the analysis based on the submitter's attribute information. The analysis unit can, for example, correct the analysis results by considering the submitter's attribute information. The analysis unit can, for example, analyze the submitter's attribute information and select the optimal analysis method. This improves the accuracy of the analysis by considering the attribute information of the data submitter. 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 submitter's attribute information into a generating AI and have the generating AI perform the analysis.

[0045] The analysis unit can perform analysis while considering the geographical distribution of the data. For example, the analysis unit can improve the accuracy of the analysis based on the geographical distribution of the data. For example, the analysis unit can correct the analysis results by considering the geographical distribution of the data. For example, the analysis unit can analyze the geographical distribution of the data and select the optimal analysis method. This improves the accuracy of the analysis by considering the geographical distribution of the data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input geographical distribution data into a generating AI and have the generating AI perform the analysis.

[0046] The analysis unit can improve the accuracy of the analysis by referring to relevant literature during the analysis. For example, the analysis unit can improve the accuracy of the analysis based on relevant literature. For example, the analysis unit can correct the analysis results by referring to relevant literature. For example, the analysis unit can analyze relevant literature and select the optimal analysis method. In this way, the accuracy of the analysis can be improved by referring to relevant literature. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input relevant literature data into a generating AI and have the generating AI perform the analysis.

[0047] The evaluation unit can predict current risk by referring to past risk data during risk assessment. For example, the evaluation unit predicts current risk based on past risk data. For example, the evaluation unit can analyze past risk data to understand risk trends. For example, the evaluation unit can predict risk fluctuations by referring to past risk data. This allows for accurate prediction of current risk by referring to past risk data. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input past risk data into a generating AI and have the generating AI perform risk prediction.

[0048] The evaluation unit can apply different evaluation methods to each data category during risk assessment. For example, the evaluation unit can apply a detailed risk assessment method to personal information. For example, the evaluation unit can apply a simplified risk assessment method to public data. The evaluation unit can select the optimal risk assessment method for each data category. By applying the optimal evaluation method for each data category, the accuracy of the risk assessment can be improved. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input the data categories into a generating AI and have the generating AI select the evaluation method.

[0049] The evaluation unit can analyze changes in risk based on the data submission timing during risk assessment. For example, the evaluation unit can analyze changes in risk based on newer data. For example, the evaluation unit can analyze changes in risk based on older data. For example, the evaluation unit can predict fluctuations in risk based on the submission timing. This allows for accurate prediction of risk fluctuations by analyzing changes in risk based on the data submission timing. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input the data submission timing into a generating AI and have the generating AI perform risk fluctuation predictions.

[0050] The evaluation unit can analyze risk by referring to relevant market data during risk assessment. For example, the evaluation unit can analyze risk based on relevant market data. For example, the evaluation unit can grasp risk trends by referring to relevant market data. For example, the evaluation unit can analyze relevant market data and predict risk fluctuations. This allows for an accurate grasp of risk trends by referring to relevant market data. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input relevant market data into a generating AI and have the generating AI perform the risk analysis.

[0051] The correction unit can improve the accuracy of corrections by considering the interrelationships of data when presenting correction proposals. The correction unit can improve the accuracy of corrections based on the interrelationships of data, for example. The correction unit can refine correction proposals by considering the interrelationships of data, for example. The correction unit can analyze the interrelationships of data and select the optimal correction method, for example. This improves the accuracy of corrections by considering the interrelationships of data. Some or all of the above processing in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can input the interrelationships of data into a generating AI and have the generating AI perform the corrections.

[0052] The revision unit can perform revisions while considering the attribute information of the data submitter when presenting revision proposals. The revision unit can, for example, improve the accuracy of revisions based on the submitter's attribute information. The revision unit can, for example, correct revision proposals while considering the submitter's attribute information. The revision unit can, for example, analyze the submitter's attribute information and select the optimal revision method. This improves the accuracy of revisions by considering the attribute information of the data submitter. Some or all of the above processes in the revision unit may be performed using AI, for example, or without using AI. For example, the revision unit can input the submitter's attribute information into a generating AI and have the generating AI perform the revisions.

[0053] The correction unit can perform corrections while considering the geographical distribution of the data when presenting correction proposals. The correction unit can, for example, improve the accuracy of corrections based on the geographical distribution of the data. The correction unit can, for example, refine correction proposals while considering the geographical distribution of the data. The correction unit can, for example, analyze the geographical distribution of the data and select the optimal correction method. This improves the accuracy of corrections by considering the geographical distribution of the data. Some or all of the above-described processes in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can input geographical distribution data into a generating AI and have the generating AI perform the corrections.

[0054] The revision unit can improve the accuracy of revisions by referring to relevant literature when presenting revision proposals. For example, the revision unit improves the accuracy of revisions based on relevant literature. For example, the revision unit can correct revision proposals by referring to relevant literature. For example, the revision unit can analyze relevant literature and select the optimal revision method. This allows the accuracy of revisions to be improved by referring to relevant literature. Some or all of the above processes in the revision unit may be performed using AI, for example, or without AI. For example, the revision unit can input relevant literature data into a generating AI and have the generating AI perform the revisions.

[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 online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0057] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0058] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0059] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0060] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

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

[0062] Step 1: The collection team collects records of online controversies on social media. For example, the collection team collects posts containing specific keywords or hashtags on social media. The collection team can also collect posts that are concentrated within a specific period. For example, the collection team collects posts related to a specific event or incident. Step 2: The anonymization unit anonymizes the online harassment records collected by the collection unit. The anonymization unit removes personal information, for example. The anonymization unit can also mask data. For example, the anonymization unit masks the poster's name and account information. Step 3: The analysis unit analyzes the anonymized data from the anonymization unit to detect patterns of online firestorms. The analysis unit analyzes the data using, for example, LLM. For example, the analysis unit can identify posts containing specific keywords or phrases that are more likely to cause online firestorms. The analysis unit can also identify content posted at specific times or on specific days of the week that is more likely to cause online firestorms. Step 4: The evaluation unit quantifies the risk based on the online firestorm patterns detected by the analysis unit. For example, the evaluation unit inputs the post content into LLM and evaluates the risk by comparing it with past firestorm patterns. For example, the evaluation unit calculates a risk score. The evaluation unit can also identify risk categories. For example, the evaluation unit identifies posts containing specific keywords or phrases as high-risk. Step 5: The revision team will propose revisions if the evaluation team deems the work to be high-risk. For example, the revision team may propose revisions that change specific keywords. Alternatively, the revision team may propose revisions that modify part of the post content. For example, the revision team may propose revisions that change the tone or expression of the post.

[0063] (Example of form 2) The online firestorm pattern detection system according to an embodiment of the present invention is a system that anonymizes records of online firestorms on social media and uses an LLM (Large-Scale Language Model) to detect and analyze patterns of online firestorms. This system assists companies and individuals in creating guidelines for preventing online firestorms. It also quantifies and calculates the level of risk before a social media post is made, and if the risk is high, it identifies the category of risk and suggests corrective actions. For example, the online firestorm pattern detection system collects and anonymizes records of online firestorms on social media. Next, it analyzes this data using an LLM to detect patterns of online firestorms. For example, it identifies posts containing specific keywords or phrases that are likely to cause online firestorms. This allows for an understanding of online firestorm patterns. Next, based on the detected online firestorm patterns, it creates guidelines for preventing online firestorms for companies and individuals. For example, it proposes specific measures such as avoiding certain keywords or not posting at certain times. This minimizes the risk of online firestorms. Furthermore, the online firestorm pattern detection system quantifies and calculates the risk before a social media post is made. For example, it inputs the content of a post into an LLM and evaluates the risk by comparing it with past online firestorm patterns. If the risk is high, it identifies the category of risk and suggests corrective actions. For example, it can suggest specific revisions, such as changing certain keywords or modifying parts of the post content. This allows companies and individuals to anticipate the risk of online backlash on social media and take appropriate measures. This protects brand image and personal credibility, and improves the safety and reliability of social media activities. In this way, the backlash pattern detection system enables companies and individuals to anticipate the risk of online backlash on social media and take appropriate measures.

[0064] The online firestorm pattern detection system according to this embodiment comprises a collection unit, an anonymization unit, an analysis unit, an evaluation unit, and a correction unit. The collection unit collects records of online firestorms on social media. For example, the collection unit collects posts containing specific keywords or hashtags on social media. The collection unit can also collect posts that are concentrated over a specific period. For example, the collection unit collects posts related to a specific event or incident. The anonymization unit anonymizes the online firestorm records collected by the collection unit. For example, the anonymization unit removes personal information. The anonymization unit can also mask the data. For example, the anonymization unit masks the poster's name or account information. The analysis unit analyzes the data anonymized by the anonymization unit and detects online firestorm patterns. The analysis unit analyzes the data using, for example, LLM. For example, the analysis unit identifies posts containing specific keywords or phrases that are prone to causing online firestorms. The analysis unit can also identify content posted at specific times or on specific days of the week that is prone to causing online firestorms. The evaluation unit quantifies the risk based on the flame war patterns detected by the analysis unit. For example, the evaluation unit inputs the content of a post into LLM and evaluates the risk by comparing it with past flame war patterns. For example, the evaluation unit calculates a risk score. The evaluation unit can also identify risk categories. For example, the evaluation unit identifies posts containing specific keywords or phrases as high-risk. The revision unit proposes revisions if the evaluation unit determines the risk is high. For example, the revision unit proposes revisions that change specific keywords. The revision unit can also propose revisions that partially modify the content of a post. For example, the revision unit proposes revisions that change the tone or expression of the post. Thus, the flame war pattern detection system according to the embodiment can anonymize flame war records on social media, use LLM to detect and analyze flame war patterns, and perform risk assessment and propose revisions.

[0065] The data collection unit collects records of online controversies on social media. For example, the unit collects posts containing specific keywords or hashtags on social media. Specifically, the unit uses social media APIs to monitor posts in real time and automatically collects posts containing specific keywords or hashtags. This allows the unit to detect signs of a controversy early. The unit can also collect posts that are concentrated within a specific period. For example, the unit collects posts related to specific events or incidents. This allows the unit to evaluate whether a particular event is likely to trigger a controversy. Furthermore, the unit also collects post metadata (posting time, number of followers of the poster, number of retweets, etc.) to provide data for evaluating the scale and impact of a controversy. The unit centrally manages this data and makes it accessible to the analysis and evaluation units. For example, the collected data is stored on a cloud server and made accessible to the analysis and evaluation units in real time. This allows the unit to collect data efficiently and effectively, improving the overall system performance.

[0066] The anonymization unit anonymizes the online harassment records collected by the collection unit. The anonymization unit removes personal information, for example. Specifically, the anonymization unit automatically detects and removes or masks personally identifiable information such as the poster's name, account information, and location information. The anonymization unit can also mask data. For example, the anonymization unit masks the poster's name and account information. This allows the anonymization unit to retain information necessary for data analysis while preventing the leakage of personal information. Furthermore, the anonymization unit uses natural language processing technology to extract personally identifiable information from the posts and anonymize it. For example, it replaces place names and organization names included in the posts with more general expressions. This allows the anonymization unit to provide the information required by the analysis unit while protecting data privacy. The anonymization unit has a feedback loop to continuously evaluate and improve the accuracy of the anonymization process. For example, it re-evaluates the anonymized data and performs additional processing if the anonymization is insufficient. This allows the anonymization unit to always anonymize data with high accuracy and improve the overall reliability of the system.

[0067] The analysis unit analyzes the anonymized data from the anonymization unit to detect online controversy patterns. The analysis unit uses, for example, LLM (Language-Language-Related Machine) to analyze the data. Specifically, the analysis unit uses natural language processing (LLM) to analyze post content and identify posts containing specific keywords or phrases that are prone to online controversy. For example, LLM learns from past controversy cases and predicts that posts containing specific keywords or phrases are likely to cause controversy. The analysis unit can also identify content posted at specific times or days of the week that is more likely to cause controversy. For example, based on past data, the analysis unit identifies a tendency for content posted at specific times or days of the week to cause controversy. Furthermore, the analysis unit performs sentiment analysis on posts and identifies posts with strong negative sentiments that are more likely to cause controversy. This allows the analysis unit to quickly and accurately analyze the collected data and detect early signs of online controversy. The analysis unit provides these analysis results to the evaluation unit, which uses them as basic data for risk assessment. For example, the analysis unit provides the evaluation unit with a list of posts containing specific keywords or phrases, which also serves as basic data for risk assessment. This allows the analysis unit to improve the overall system performance.

[0068] The evaluation unit quantifies risk based on the online firestorm patterns detected by the analysis unit. For example, the evaluation unit inputs the content of a post into the LLM (Likely a system for identifying and analyzing online content) and evaluates the risk by comparing it to past online firestorm patterns. Specifically, the evaluation unit uses the LLM to calculate a risk score for the content of a post. For example, it identifies posts containing specific keywords or phrases as high-risk and calculates their risk score. The evaluation unit can also identify risk categories. For example, it identifies posts containing specific keywords or phrases as high-risk and identifies their risk category. Furthermore, the evaluation unit provides basic data for suggesting revisions to the content of posts based on the risk score. For example, the evaluation unit provides basic data for suggesting revisions to the revision unit based on the risk score of posts containing specific keywords or phrases. This allows the evaluation unit to improve the accuracy of risk assessment and enhance the overall system performance.

[0069] The revision unit proposes revisions when the evaluation unit determines the risk is high. For example, the revision unit proposes revisions that change specific keywords. Specifically, the revision unit uses LLM to generate revisions to reduce the risk of the posted content. For example, it proposes revisions that change specific keywords or phrases. The revision unit can also propose revisions that partially modify the posted content. For example, the revision unit proposes revisions that change the tone or expression of the post. Furthermore, the revision unit evaluates the effectiveness of the revisions and re-evaluates them as needed. For example, the revision unit re-evaluates the posted content after applying the revisions to confirm whether the risk has been reduced. This allows the revision unit to always provide the optimal revisions and improve the overall system performance. The revision unit presents revisions to users and encourages them to revise their posted content. For example, the revision unit notifies users of revisions and encourages them to revise their posted content. This allows the revision unit to provide users with concrete means to reduce the risk of online backlash and improve the overall reliability of the system.

[0070] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, if the user is stressed, the data collection unit can delay the collection timing to reduce the user's burden. For example, if the user is relaxed, the data collection unit can advance the collection timing to collect data quickly. For example, if the user is excited, the data collection unit can adjust the collection timing to collect data at an appropriate time. In this way, by adjusting the collection timing according to the user's emotions, the user's burden can be reduced and data can be collected at an appropriate time. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input user emotion data into a generating AI and have the generating AI perform the adjustment of the collection timing.

[0071] The collection unit can analyze the collection history of past online firestorms and select the optimal collection method. For example, the collection unit can identify and apply the most effective collection method from the past collection history. For example, the collection unit can analyze the past collection history and optimize the collection frequency. For example, the collection unit can determine the priority of collection targets based on the past collection history. This allows for the selection of the optimal collection method and improvement of collection efficiency by analyzing the past collection history. Some or all of the above processes in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input past collection history data into a generating AI and have the generating AI select the optimal collection method.

[0072] The data collection unit can filter the collected records of online controversies based on specific keywords or phrases. For example, the data collection unit can prioritize collecting posts containing specific keywords. For example, the data collection unit can filter and collect posts containing specific phrases. For example, the data collection unit can select data to collect based on the frequency of occurrence of keywords or phrases. This allows for the priority collection of highly relevant data by filtering based on specific keywords or phrases. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input post data containing specific keywords or phrases into a generating AI and have the generating AI perform the filtering.

[0073] The data collection unit can estimate the user's emotions and determine the priority of the incident records to collect based on the estimated user emotions. For example, if the user is stressed, the data collection unit can set a lower priority and reduce the collection frequency. For example, if the user is relaxed, the data collection unit can set a higher priority and increase the collection frequency. For example, if the user is excited, the data collection unit can adjust the priority to collect at an appropriate frequency. In this way, by determining the priority of incident records to collect according to the user's emotions, data can be collected at an appropriate frequency. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input user emotion data into a generating AI and have the generating AI perform the determination of collection priorities.

[0074] The collection unit can prioritize the collection of highly relevant records by considering geographical location information when collecting records of online firestorms. For example, the collection unit can prioritize the collection of records of online firestorms that occurred in geographically close locations. For example, the collection unit can prioritize the collection of records of online firestorms that frequently occur in a specific region. For example, the collection unit can select highly relevant records based on geographical location information. In this way, by considering geographical location information, highly relevant records can be collected preferentially. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input geographical location data into a generating AI and have the generating AI perform the selection of highly relevant records.

[0075] The data collection unit can analyze social media activity and collect relevant records when collecting records of online controversies. For example, the data collection unit can collect relevant records based on the amount of activity on social media. For example, the data collection unit can prioritize the collection of posts containing specific hashtags on social media. For example, the data collection unit can collect relevant records considering the influence of users on social media. This allows for the efficient collection of relevant records by analyzing social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input social media activity data into a generating AI and have the generating AI perform the collection of relevant records.

[0076] The anonymization unit can estimate the user's emotions and adjust the anonymization method based on the estimated emotions. For example, if the user is stressed, the anonymization unit can apply a simple anonymization method for rapid processing. For example, if the user is relaxed, the anonymization unit can apply a more detailed anonymization method to improve data accuracy. For example, if the user is excited, the anonymization unit can select an appropriate anonymization method to ensure data security. This optimizes data security and processing speed by adjusting the anonymization method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The 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 anonymization unit may be performed using AI, or not. For example, the anonymization unit can input user emotion data into the generative AI and have the generative AI adjust the anonymization method.

[0077] The anonymization unit can adjust the level of anonymization based on the importance of the data during the anonymization process. For example, the anonymization unit can apply a detailed anonymization method to data with high importance, and a simpler anonymization method to data with low importance. The anonymization unit can also adjust the level of anonymization in stages based on the importance of the data. This optimizes data security and processing efficiency by adjusting the level of anonymization based on the importance of the data. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the importance of the data into a generating AI and have the generating AI perform the adjustment of the level of anonymization.

[0078] The anonymization unit can apply different anonymization algorithms depending on the data category during anonymization. For example, the anonymization unit can apply a strong anonymization algorithm to personal information. For example, the anonymization unit can apply a simpler anonymization algorithm to public data. The anonymization unit can select the optimal anonymization algorithm for each data category. This ensures data security by applying the optimal anonymization algorithm according to the data category. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the data category into a generating AI and have the generating AI select the optimal anonymization algorithm.

[0079] The anonymization unit can estimate the user's emotions and determine the anonymization priority based on the estimated emotions. For example, if the user is stressed, the anonymization unit can set a lower priority to reduce the burden of anonymization. For example, if the user is relaxed, the anonymization unit can set a higher priority to perform anonymization quickly. For example, if the user is excited, the anonymization unit can adjust the priority to perform anonymization at the appropriate time. In this way, by determining the anonymization priority according to the user's emotions, anonymization can be performed at the appropriate time. 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 anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the user's emotion data into the generative AI and have the generative AI perform the determination of the anonymization priority.

[0080] The anonymization unit can determine the anonymization priority based on the data submission date during the anonymization process. For example, the anonymization unit can prioritize anonymizing data with a more recent submission date. For example, the anonymization unit can postpone anonymizing data with an older submission date. For example, the anonymization unit can adjust the anonymization priority in stages based on the submission date. This allows for priority processing of the latest data by determining the anonymization priority based on the data submission date. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the data submission date into a generating AI and have the generating AI determine the anonymization priority.

[0081] The anonymization unit can adjust the anonymization order based on the relevance of the data during the anonymization process. For example, the anonymization unit can prioritize anonymizing highly relevant data. For example, the anonymization unit can postpone anonymizing less relevant data. For example, the anonymization unit can adjust the anonymization order in stages based on the relevance of the data. This allows for priority processing of highly relevant data by adjusting the anonymization order based on the relevance of the data. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the relevance of the data into a generating AI and have the generating AI perform the adjustment of the anonymization order.

[0082] The analysis unit can estimate the user's emotions and adjust the analysis criteria based on the estimated emotions. For example, if the user is stressed, the analysis unit can apply simple analysis criteria and perform a rapid analysis. For example, if the user is relaxed, the analysis unit can apply detailed analysis criteria to improve accuracy. For example, if the user is excited, the analysis unit can select appropriate analysis criteria to ensure data safety. This optimizes data safety and analysis accuracy by adjusting the analysis 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 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 adjust the analysis criteria.

[0083] The analysis unit can improve the accuracy of the analysis by considering the interrelationships between data during the analysis. For example, the analysis unit can improve the accuracy of the analysis based on the interrelationships between data. For example, the analysis unit can correct the analysis results by considering the interrelationships between data. For example, the analysis unit can analyze the interrelationships between data and select the optimal analysis method. In this way, the accuracy of the analysis can be improved by considering the interrelationships between data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the interrelationships between data into a generating AI and have the generating AI perform the improvement of the analysis accuracy.

[0084] The analysis unit can perform analysis while considering the attribute information of the data submitter. The analysis unit can, for example, improve the accuracy of the analysis based on the submitter's attribute information. The analysis unit can, for example, correct the analysis results by considering the submitter's attribute information. The analysis unit can, for example, analyze the submitter's attribute information and select the optimal analysis method. This improves the accuracy of the analysis by considering the attribute information of the data submitter. 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 submitter's attribute information into a generating AI and have the generating AI perform the analysis.

[0085] The analysis unit can estimate the user's emotions and adjust the display order of the analysis results based on the estimated emotions. For example, if the user is stressed, the analysis unit can prioritize displaying important analysis results. For example, if the user is relaxed, the analysis unit can display detailed analysis results. For example, if the user is excited, the analysis unit can display the analysis results in an appropriate order. This allows important information to be displayed preferentially by adjusting the display order 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 a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a 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 adjust the display order.

[0086] The analysis unit can perform analysis while considering the geographical distribution of the data. For example, the analysis unit can improve the accuracy of the analysis based on the geographical distribution of the data. For example, the analysis unit can correct the analysis results by considering the geographical distribution of the data. For example, the analysis unit can analyze the geographical distribution of the data and select the optimal analysis method. This improves the accuracy of the analysis by considering the geographical distribution of the data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input geographical distribution data into a generating AI and have the generating AI perform the analysis.

[0087] The analysis unit can improve the accuracy of the analysis by referring to relevant literature during the analysis. For example, the analysis unit can improve the accuracy of the analysis based on relevant literature. For example, the analysis unit can correct the analysis results by referring to relevant literature. For example, the analysis unit can analyze relevant literature and select the optimal analysis method. In this way, the accuracy of the analysis can be improved by referring to relevant literature. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input relevant literature data into a generating AI and have the generating AI perform the analysis.

[0088] The evaluation unit can estimate the user's emotions and adjust the risk assessment method based on the estimated user emotions. For example, if the user is stressed, the evaluation unit can apply a simple risk assessment method and perform a rapid assessment. For example, if the user is relaxed, the evaluation unit can apply a detailed risk assessment method to improve accuracy. For example, if the user is excited, the evaluation unit can select an appropriate risk assessment method to ensure data security. In this way, data security and assessment accuracy can be optimized by adjusting the risk assessment 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 evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the risk assessment method.

[0089] The evaluation unit can predict current risk by referring to past risk data during risk assessment. For example, the evaluation unit predicts current risk based on past risk data. For example, the evaluation unit can analyze past risk data to understand risk trends. For example, the evaluation unit can predict risk fluctuations by referring to past risk data. This allows for accurate prediction of current risk by referring to past risk data. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input past risk data into a generating AI and have the generating AI perform risk prediction.

[0090] The evaluation unit can apply different evaluation methods to each data category during risk assessment. For example, the evaluation unit can apply a detailed risk assessment method to personal information. For example, the evaluation unit can apply a simplified risk assessment method to public data. The evaluation unit can select the optimal risk assessment method for each data category. By applying the optimal evaluation method for each data category, the accuracy of the risk assessment can be improved. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input the data categories into a generating AI and have the generating AI select the evaluation method.

[0091] The evaluation unit can estimate the user's emotions and adjust the importance of the risk assessment based on the estimated user emotions. For example, if the user is stressed, the evaluation unit can set the importance low and perform a quick assessment. For example, if the user is relaxed, the evaluation unit can set the importance high and perform a detailed assessment. For example, if the user is excited, the evaluation unit can adjust the importance to perform an appropriate assessment. In this way, an appropriate assessment can be performed by adjusting the importance of the risk assessment 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 evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the importance of the risk assessment.

[0092] The evaluation unit can analyze changes in risk based on the data submission timing during risk assessment. For example, the evaluation unit can analyze changes in risk based on newer data. For example, the evaluation unit can analyze changes in risk based on older data. For example, the evaluation unit can predict fluctuations in risk based on the submission timing. This allows for accurate prediction of risk fluctuations by analyzing changes in risk based on the data submission timing. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input the data submission timing into a generating AI and have the generating AI perform risk fluctuation predictions.

[0093] The evaluation unit can analyze risk by referring to relevant market data during risk assessment. For example, the evaluation unit can analyze risk based on relevant market data. For example, the evaluation unit can grasp risk trends by referring to relevant market data. For example, the evaluation unit can analyze relevant market data and predict risk fluctuations. This allows for an accurate grasp of risk trends by referring to relevant market data. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input relevant market data into a generating AI and have the generating AI perform the risk analysis.

[0094] The revision unit can estimate the user's emotions and determine the priority of revision suggestions based on the estimated emotions. For example, if the user is stressed, the revision unit can set a lower priority to reduce the burden of revision suggestions. For example, if the user is relaxed, the revision unit can set a higher priority to quickly present revision suggestions. For example, if the user is excited, the revision unit can adjust the priority to present revision suggestions at the appropriate time. In this way, by determining the priority of revision suggestions according to the user's emotions, revision suggestions can be presented at the appropriate time. 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 revision unit may be performed using AI, for example, or not using AI. For example, the revision unit can input user emotion data into a generative AI and have the generative AI determine the priority of revision suggestions.

[0095] The correction unit can improve the accuracy of corrections by considering the interrelationships of data when presenting correction proposals. The correction unit can improve the accuracy of corrections based on the interrelationships of data, for example. The correction unit can refine correction proposals by considering the interrelationships of data, for example. The correction unit can analyze the interrelationships of data and select the optimal correction method, for example. This improves the accuracy of corrections by considering the interrelationships of data. Some or all of the above processing in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can input the interrelationships of data into a generating AI and have the generating AI perform the corrections.

[0096] The revision unit can perform revisions while considering the attribute information of the data submitter when presenting revision proposals. The revision unit can, for example, improve the accuracy of revisions based on the submitter's attribute information. The revision unit can, for example, correct revision proposals while considering the submitter's attribute information. The revision unit can, for example, analyze the submitter's attribute information and select the optimal revision method. This improves the accuracy of revisions by considering the attribute information of the data submitter. Some or all of the above processes in the revision unit may be performed using AI, for example, or without using AI. For example, the revision unit can input the submitter's attribute information into a generating AI and have the generating AI perform the revisions.

[0097] The editing unit can estimate the user's emotions and adjust the display method of the suggested revisions based on the estimated emotions. For example, if the user is stressed, the editing unit can provide a simple and highly visible display method. For example, if the user is relaxed, the editing unit can provide a display method that includes detailed information. For example, if the user is excited, the editing unit can display the suggested revisions in an appropriate order. This allows for a highly visible display method by adjusting the display method of the suggested revisions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described 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 the generative AI and have the generative AI perform the adjustment of the display method.

[0098] The correction unit can perform corrections while considering the geographical distribution of the data when presenting correction proposals. The correction unit can, for example, improve the accuracy of corrections based on the geographical distribution of the data. The correction unit can, for example, refine correction proposals while considering the geographical distribution of the data. The correction unit can, for example, analyze the geographical distribution of the data and select the optimal correction method. This improves the accuracy of corrections by considering the geographical distribution of the data. Some or all of the above-described processes in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can input geographical distribution data into a generating AI and have the generating AI perform the corrections.

[0099] The revision unit can improve the accuracy of revisions by referring to relevant literature when presenting revision proposals. For example, the revision unit improves the accuracy of revisions based on relevant literature. For example, the revision unit can correct revision proposals by referring to relevant literature. For example, the revision unit can analyze relevant literature and select the optimal revision method. This allows the accuracy of revisions to be improved by referring to relevant literature. Some or all of the above processes in the revision unit may be performed using AI, for example, or without AI. For example, the revision unit can input relevant literature data into a generating AI and have the generating AI perform the revisions.

[0100] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0101] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0102] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0103] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0104] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0105] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0106] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0107] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0108] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0109] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0110] The online crisis pattern detection system can further include a notification unit that estimates the user's emotions and adjusts the notification method for crisis risk based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise and highly visible notification. If the user is relaxed, it can provide a notification containing detailed information. If the user is agitated, the notification unit can provide a notification at an appropriate time. This reduces the burden on the user and allows for quick and appropriate countermeasures by providing the optimal notification method according to the user's emotions.

[0111] The following briefly describes the processing flow for example form 2.

[0112] Step 1: The collection team collects records of online controversies on social media. For example, the collection team collects posts containing specific keywords or hashtags on social media. The collection team can also collect posts that are concentrated within a specific period. For example, the collection team collects posts related to a specific event or incident. Step 2: The anonymization unit anonymizes the online harassment records collected by the collection unit. The anonymization unit removes personal information, for example. The anonymization unit can also mask data. For example, the anonymization unit masks the poster's name and account information. Step 3: The analysis unit analyzes the anonymized data from the anonymization unit to detect patterns of online firestorms. The analysis unit analyzes the data using, for example, LLM. For example, the analysis unit can identify posts containing specific keywords or phrases that are more likely to cause online firestorms. The analysis unit can also identify content posted at specific times or on specific days of the week that is more likely to cause online firestorms. Step 4: The evaluation unit quantifies the risk based on the online firestorm patterns detected by the analysis unit. For example, the evaluation unit inputs the post content into LLM and evaluates the risk by comparing it with past firestorm patterns. For example, the evaluation unit calculates a risk score. The evaluation unit can also identify risk categories. For example, the evaluation unit identifies posts containing specific keywords or phrases as high-risk. Step 5: The revision team will propose revisions if the evaluation team deems the work to be high-risk. For example, the revision team may propose revisions that change specific keywords. Alternatively, the revision team may propose revisions that modify part of the post content. For example, the revision team may propose revisions that change the tone or expression of the post.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] Each of the multiple elements described above, including the collection unit, anonymization unit, analysis unit, evaluation unit, and modification unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects records of online firestorms on social media. The anonymization unit is implemented by the identification processing unit 290 of the data processing unit 12 and anonymizes the collected firestorm records. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the anonymized data to detect firestorm patterns. The evaluation unit is implemented by the identification processing unit 290 of the data processing unit 12 and quantifies the risk based on the detected firestorm patterns. The modification unit is implemented by the control unit 46A of the smart device 14 and suggests modification options if the risk is high. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0117] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] Each of the multiple elements described above, including the collection unit, anonymization unit, analysis unit, evaluation unit, and modification unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects records of online firestorms on social media. The anonymization unit is implemented by the identification processing unit 290 of the data processing unit 12 and anonymizes the collected firestorm records. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the anonymized data to detect firestorm patterns. The evaluation unit is implemented by the identification processing unit 290 of the data processing unit 12 and quantifies the risk based on the detected firestorm patterns. The modification unit is implemented by the control unit 46A of the smart glasses 214 and suggests modification options if the risk is high. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0133] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] Each of the multiple elements described above, including the collection unit, anonymization unit, analysis unit, evaluation unit, and modification unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and collects records of online firestorms on social media. The anonymization unit is implemented by the identification processing unit 290 of the data processing unit 12 and anonymizes the collected firestorm records. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the anonymized data to detect firestorm patterns. The evaluation unit is implemented by the identification processing unit 290 of the data processing unit 12 and quantifies the risk based on the detected firestorm patterns. The modification unit is implemented by the control unit 46A of the headset terminal 314 and suggests modification options when the risk is high. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0149] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] Each of the multiple elements described above, including the collection unit, anonymization unit, analysis unit, evaluation unit, and modification unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects records of online firestorms on social media. The anonymization unit is implemented by the identification processing unit 290 of the data processing unit 12 and anonymizes the collected firestorm records. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the anonymized data to detect firestorm patterns. The evaluation unit is implemented by the identification processing unit 290 of the data processing unit 12 and quantifies the risk based on the detected firestorm patterns. The modification unit is implemented by the control unit 46A of the robot 414 and suggests modification options if the risk is high. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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."

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] (Note 1) A collection department that collects records of online controversies on social media, An anonymization unit that anonymizes the records of online firestorms collected by the aforementioned collection unit, An analysis unit analyzes the data anonymized by the anonymization unit and detects the flame war pattern, An evaluation unit that quantifies the risk based on the fire pattern detected by the analysis unit, The system includes a modification unit that proposes a modification plan if the evaluation unit determines that the risk is high. A system characterized by the following features. (Note 2) The aforementioned collection unit is We estimate user sentiment and adjust the timing of collecting records of online controversies based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is We will analyze the history of collecting records of past online controversies and select the most suitable collection method. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is When collecting records of online controversies, filter them based on specific keywords or phrases. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is It estimates user sentiment and determines the priority of collecting incident records based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is When collecting records of online firestorms, geographical location information is taken into consideration to prioritize the collection of records with high relevance. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is When collecting records of online controversies, analyze social media activity and gather relevant records. The system described in Appendix 1, characterized by the features described herein. (Note 8) The anonymization unit is, The system estimates the user's emotions and adjusts the anonymization method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The anonymization unit is, During anonymization, adjust the level of anonymization based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 10) The anonymization unit is, When anonymizing data, different anonymization algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 11) The anonymization unit is, The system estimates the user's emotions and determines the priority of anonymization based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The anonymization unit is, When anonymizing data, the priority of anonymization is determined based on when the data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 13) The anonymization unit is, During anonymization, the order of anonymization is adjusted based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, We estimate the user's emotions and adjust the analysis criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, consider the interrelationships between data to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, the attribute information of the data submitter will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, It estimates the user's emotions and adjusts the display order of the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, When performing analysis, the geographical distribution of the data should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During analysis, we refer to relevant literature to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 20) The evaluation unit, We estimate user sentiment and adjust the risk assessment method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The evaluation unit, When assessing risk, historical risk data is used to predict current risk. The system described in Appendix 1, characterized by the features described herein. (Note 22) The evaluation unit, When assessing risk, different assessment methods are applied to each data category. The system described in Appendix 1, characterized by the features described herein. (Note 23) The evaluation unit, The system estimates user sentiment and adjusts the importance of risk assessment based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The evaluation unit, When conducting a risk assessment, analyze changes in risk based on the timing of data submission. The system described in Appendix 1, characterized by the features described herein. (Note 25) The evaluation unit, When assessing risk, analyze the risk by referring to relevant market data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned modification section is, The system estimates user sentiment and prioritizes proposed revisions based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned modification section is, When proposing revisions, we improve the accuracy of the revisions by considering the interrelationships between data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned modification section is, When proposing revisions, the data will be revised taking into account the attribute information of the data submitter. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned modification section is, It estimates the user's emotions and adjusts how the suggested revisions are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned modification section is, When presenting revised proposals, the geographical distribution of the data should be taken into consideration during the revision process. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned modification section is, When proposing revisions, refer to relevant literature to improve the accuracy of the revisions. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0185] 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. A collection department that collects records of online controversies on social media, An anonymization unit that anonymizes the records of online firestorms collected by the aforementioned collection unit, An analysis unit analyzes the data anonymized by the anonymization unit and detects the flame war pattern, An evaluation unit that quantifies the risk based on the fire pattern detected by the analysis unit, The system includes a modification unit that proposes a modification plan if the evaluation unit determines that the risk is high. A system characterized by the following features.

2. The aforementioned collection unit is We estimate user sentiment and adjust the timing of collecting records of online controversies based on the estimated user sentiment. The system according to feature 1.

3. The aforementioned collection unit is We will analyze the history of collecting records of past online controversies and select the most suitable collection method. The system according to feature 1.

4. The aforementioned collection unit is When collecting records of online controversies, filter them based on specific keywords or phrases. The system according to feature 1.

5. The aforementioned collection unit is It estimates user sentiment and determines the priority of collecting incident records based on the estimated user sentiment. The system according to feature 1.

6. The aforementioned collection unit is When collecting records of online firestorms, geographical location information is taken into consideration to prioritize the collection of records with high relevance. The system according to feature 1.

7. The aforementioned collection unit is When collecting records of online controversies, analyze social media activity and gather relevant records. The system according to feature 1.

8. The anonymization unit is, The system estimates the user's emotions and adjusts the anonymization method based on those estimated emotions. The system according to feature 1.

Images