system

Abstract

The system according to this embodiment aims to quickly determine and provide appropriate countermeasures when an incident occurs. [Solution] The system according to the embodiment comprises a learning unit, a misconduct information receiving unit, a decision unit, and a provision unit. The learning unit learns information about past misconduct, information on the countermeasures taken, and public opinion as information about past misconduct. The misconduct information receiving unit receives information about misconduct from users. The decision unit determines a method of dealing with the misconduct for which information has been received by the misconduct information receiving unit, based on the learning results by the learning unit. The provision unit provides the user with information on the countermeasures determined by the decision unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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 conventional technology, there is a problem that it is difficult to quickly determine and provide an appropriate countermeasure method when an incident occurs.

[0005] The system according to the embodiment aims to quickly determine and provide an appropriate countermeasure method when an incident occurs.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a learning unit, a misconduct information receiving unit, a decision unit, and a provision unit. The learning unit learns information about past misconduct, information on the actions taken, and public opinion as information about past misconduct. The misconduct information receiving unit receives information about misconduct from users. The decision unit determines how to deal with the misconduct for which information has been received by the misconduct information receiving unit, based on the learning results from the learning unit. The provision unit provides the user with information on the action taken, which has been determined by the decision unit. [Effects of the Invention]

[0007] The system according to this embodiment can quickly determine and provide appropriate countermeasures when an incident occurs. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The online crisis response consulting system according to an embodiment of the present invention is a system in which AI provides consulting on how to respond when an online crisis occurs, in an era where online crises caused by misconduct by both corporations and individuals are rampant due to the spread of social media. The online crisis response consulting system uses AI to learn about past misconduct, how it was handled, and the public's reaction to it. Next, it receives information about the misconduct from the user, and based on that information, the AI ​​presents the optimal response method. It also predicts the impact of the online crisis based on information about the misconduct and the person involved (company size, assets, brand, fame, etc.), and provides the user with a monetary value for that impact. For example, the online crisis response consulting system uses AI to learn about past misconduct, including information about past misconduct, how it was handled, and public reaction to it. For example, it collects data on how companies handled past corporate misconduct and individual scandals, and the resulting public reactions, and the AI ​​analyzes this data. This allows the AI ​​to learn the optimal response method for various types of misconduct. Next, the online crisis response consulting system receives information about the misconduct from the user. The misconduct information reception unit receives detailed information about misconduct entered by users. For example, in the case of corporate misconduct, users enter information such as the nature of the problem and the information of those involved. This information is input into the AI. Subsequently, based on the learning results from the learning unit, the AI ​​determines the optimal course of action for dealing with the misconduct. The decision unit determines the optimal course of action for the current misconduct based on past misconduct data learned by the learning unit. For example, it provides specific suggestions such as the content and method of apology and how to handle media relations. Furthermore, it provides the user with information on the determined course of action. The provision unit provides the user with the course of action determined by the decision unit. This allows the user to implement the optimal course of action presented by the AI. In addition, the crisis management consulting system predicts the impact of a crisis based on information about the misconduct and the people involved. The prediction unit predicts the impact of a crisis based on the nature of the misconduct and information about the people involved (company size, assets, brand, name recognition, etc.). For example, it can quantify the impact of a crisis on a company's sales and brand image. Furthermore, it converts the predicted impact into monetary value.The conversion unit converts the impact predicted by the forecasting unit into monetary terms and provides this information to the user. This allows the user to understand the specific economic impact of a crisis. This mechanism enables the AI ​​to consult with the user on the optimal response to a crisis. This minimizes damage from a crisis and allows for a swift and appropriate response. In this way, the crisis response consulting system allows the AI ​​to consult with the user on the optimal response to their scandal.

[0029] The crisis response consulting system according to this embodiment comprises a learning unit, a scandal information receiving unit, a decision unit, and a provision unit. The learning unit learns information about past scandals, information on how they were handled, and public opinion as information about past scandals. For example, the learning unit collects data on how companies handled past corporate scandals and personal scandals, and the resulting public reactions, and the AI ​​analyzes this data. This allows the learning unit to learn the optimal response methods for various scandals. The scandal information receiving unit receives information about scandals from users. For example, in the case of a corporate scandal, the scandal information receiving unit inputs information such as the details of the problem and information about those involved. This information is input into the AI. Based on the learning results from the learning unit, the decision unit determines how to handle the scandal for which information has been received by the scandal information receiving unit. The decision unit specifically presents, for example, the content of the apology, the response method, and the method of dealing with the media. The provision unit provides the user with information on the response method determined by the decision unit. The provision unit, for example, notifies the user of the action decided by the decision unit. This allows the AI ​​to consult on the optimal action for the user's misconduct in the crisis response consulting system according to the embodiment. Some or all of the above processing in the learning unit may be performed using AI, or not using AI. For example, the learning unit can input data on past misconduct into the AI, and the AI ​​can analyze that data and learn. Some or all of the above processing in the misconduct information receiving unit may be performed using AI, or not using AI. For example, the misconduct information receiving unit can input information on misconduct entered by the user into the AI, and the AI ​​can analyze that information and accept it. Some or all of the above processing in the decision unit may be performed using AI, or not using AI. For example, the decision unit can input the learning results from the learning unit into the AI, and the AI ​​can decide on an action based on those results. Some or all of the above processing in the provision unit may be performed using AI, or not using AI. For example, the provision unit can input the solution determined by the decision unit into the AI, and the AI ​​can then provide that solution to the user.

[0030] The learning unit learns information about past scandals, how they were handled, and public opinion. Specifically, the learning unit collects data on how companies handled past corporate scandals and personal scandals, as well as the resulting public reactions, and the AI ​​analyzes this data. For example, it collects data from a wide range of sources, such as news articles, official statements, social media reactions, and forum comments related to corporate scandals. This data is analyzed using natural language processing technology to extract important keywords and phrases. Furthermore, the AI ​​evaluates the effectiveness of the handling methods and public opinion based on these keywords and phrases. For example, it analyzes how the timing and content of apologies, the responses of those responsible, and whether compensation was provided were evaluated. This allows the learning unit to learn the optimal way to handle various scandals. The learning unit can keep up with the latest trends and evaluation criteria by regularly incorporating new data and updating its learning model. In addition, the learning unit can provide more accurate advice by considering the differences in the characteristics of scandals and handling methods in different industries and regions. This will enable the learning department to build a foundation for providing optimal responses to various incidents that users may encounter.

[0031] The misconduct information reception department receives information about misconduct from users. Specifically, in the case of corporate misconduct, users input details of the problem and information about those involved. This information is then input into AI. For example, users can input detailed information about the misconduct through a dedicated web form or application. Input fields include the date and time the problem occurred, the location, the names and positions of those involved, the specific nature of the problem, and the scope of impact. Furthermore, users can also upload relevant evidence and documents. This information is analyzed by AI, and important elements are extracted. For example, the AI ​​extracts keywords from the input text and classifies the type and severity of the problem. It also identifies stakeholders who may be affected based on the information of those involved. This allows the misconduct information reception department to efficiently organize the information provided by users and provide the data necessary to determine the next step: how to deal with the situation. In addition, the misconduct information reception department has a feedback function to verify the accuracy and completeness of the information entered by users. For example, if there are deficiencies in the input or if additional information is needed, the system can notify the user and encourage them to complete the information. This allows the misconduct information reception department to collect accurate and detailed information, improving the overall accuracy and reliability of the system.

[0032] The decision-making unit determines how to deal with misconduct reported by the misconduct information reception unit, based on the learning results from the learning unit. Specifically, it provides concrete suggestions regarding the content of apologies, response methods, and media relations. For example, the AI ​​proposes the most appropriate response method for the current misconduct based on past misconduct data learned by the learning unit. The AI ​​considers the type and severity of the problem, information about those involved, and the scope of impact to determine the optimal response. For example, regarding the content of apologies, it provides templates for apology letters and suggests specific wording and expressions. Regarding response methods, it presents concrete steps and schedules for resolving the problem. Furthermore, regarding media relations, it provides specific instructions on preparing press conferences, creating press releases, and responding on social media. This allows the decision-making unit to provide quick and appropriate responses to misconduct faced by users. In addition, the decision-making unit can continuously improve the accuracy and effectiveness of its suggestions based on user feedback. For example, it collects the results of responses actually taken by users and evaluates their effectiveness to update the AI's learning model and improve future suggestions. Furthermore, the decision-making unit can take into account the characteristics of different industries and regions and provide customized countermeasures. This allows the decision-making unit to provide users with the optimal countermeasures and minimize the impact of misconduct.

[0033] The service provider provides users with information on the countermeasures decided by the decision-making department. Specifically, it notifies users of the countermeasures decided by the decision-making department. For example, the service provider provides users with detailed information on the countermeasures through a dedicated web portal or application. Users can then implement specific countermeasures based on the information provided by the service provider. The service provider clearly presents detailed procedures, necessary resources, and schedules for the countermeasures, supporting users in smoothly implementing them. Furthermore, the service provider provides real-time support for any questions or problems that arise when users implement the countermeasures. For example, it quickly answers user questions and provides necessary information through chatbots or customer support. The service provider can also monitor the implementation status of the countermeasures and provide additional instructions or advice as needed. This allows the service provider to support users in implementing the optimal countermeasures and minimizing the impact of the incident. In addition, the service provider can collect user feedback and continuously improve the accuracy and effectiveness of the entire system. For example, it evaluates the results and effects of the actions taken by users and updates the AI ​​learning model based on that information to improve future suggestions. This allows the service provider to always offer users the latest and most optimal solutions, minimizing the impact of any misconduct.

[0034] The misconduct information receiving unit includes a unit that predicts the impact of a public outcry based on the misconduct and the individuals involved in the misconduct for which information has been received by the misconduct information receiving unit. The provision unit provides the user with the impact predicted by the prediction unit. The prediction unit predicts the impact of a public outcry based on, for example, the content of the misconduct and information about the individuals involved (company size, assets, brand, name recognition, etc.). For example, the prediction unit can quantify the impact of a public outcry on a company's sales and brand image. The provision unit provides the user with the impact predicted by the prediction unit. For example, the provision unit notifies the user of the impact predicted by the prediction unit. This allows for the prediction of the impact of a public outcry and its provision to the user, enabling them to take concrete countermeasures. Some or all of the above processing in the prediction unit may be performed using, for example, AI, or not using AI. For example, the prediction unit can input information about the content of the misconduct and the individuals involved into AI, and the AI ​​can analyze that information to predict the impact. Some or all of the above processing in the provision unit may be performed using, for example, AI, or not using AI. For example, the provisioning unit can input the impact predicted by the prediction unit into the AI, and the AI ​​can then provide that impact to the user.

[0035] The conversion unit can convert the impact predicted by the forecasting unit into monetary value. For example, the conversion unit can convert the impact predicted by the forecasting unit into monetary value. For example, the conversion unit can convert the impact of a controversy on a company's sales and brand image into monetary value. This allows for a concrete understanding of the economic impact by converting the impact of a controversy into monetary value. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input the impact predicted by the forecasting unit into AI, and the AI ​​can convert that impact into monetary value.

[0036] The learning unit can adjust its learning algorithm during the learning process, taking into account the timing and social context of past scandals. For example, the learning unit can analyze the social context of the time when past scandals occurred and reflect factors specific to that period in the learning algorithm. The learning unit can also adjust its learning algorithm by considering the media's reaction at the time of the scandal. Furthermore, the learning unit can periodically update its learning algorithm in response to changes in the social context to keep up with the latest trends. This enables learning that takes into account the timing and social context of past scandals. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input data on the timing and social context of past scandals into an AI, which can then analyze that data and adjust the learning algorithm.

[0037] The learning unit can broaden its learning scope by cross-referencing misconduct data from different industries and regions during the learning process. For example, the learning unit can cross-referencing misconduct data from different industries to learn common countermeasures. It can also compare misconduct data from different regions to learn region-specific countermeasures. Furthermore, the learning unit can integrate data across industries and regions to enhance its overall response capabilities. This broadens the scope of learning by cross-referencing misconduct data from different industries and regions. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input misconduct data from different industries and regions into an AI, which can then analyze and learn from that data.

[0038] The learning unit can quantify the impact of past misconduct during training and weight the training data based on that quantification. For example, the learning unit can quantify the impact of past misconduct and prioritize learning cases with high impact. The learning unit can also learn cases with low impact, thereby achieving broader capabilities. Furthermore, the learning unit can weight the training data based on the quantified impact to achieve optimal learning. This makes it possible to quantify the impact of past misconduct and weight the training data. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the impact of past misconduct into the AI, which can then quantify that impact and weight the training data.

[0039] The learning unit can analyze responses from different media during training and reflect them in the training data. For example, the learning unit can analyze media responses and reflect the responses of particularly influential media in the training data. The learning unit can also compare responses from different media and learn common elements. Furthermore, the learning unit can periodically update media responses to respond to the latest trends. This makes it possible to analyze responses from different media and reflect them in the training data. Some or all of the above processing in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input response data from different media into an AI, which can then analyze that data and reflect it in the training data.

[0040] The misconduct information receiving department can analyze the user's past misconduct reporting history and select the optimal receiving method when misconduct information is received. For example, the misconduct information receiving department can analyze the user's past misconduct reporting history and select the optimal receiving method. The misconduct information receiving department can also extract specific patterns from past reporting history and propose the optimal receiving method. Furthermore, the misconduct information receiving department can select a quick and efficient receiving method based on the user's reporting history. This makes it possible to analyze the user's past misconduct reporting history and select the optimal receiving method. Some or all of the above processing in the misconduct information receiving department may be performed using AI, for example, or without AI. For example, the misconduct information receiving department can input the user's past misconduct reporting history into AI, and the AI ​​can analyze that history and select the optimal receiving method.

[0041] The misconduct information receiving unit can prioritize receiving highly relevant information by considering the user's geographical location when receiving misconduct information. For example, the misconduct information receiving unit can prioritize receiving highly relevant information based on the user's geographical location. Furthermore, the misconduct information receiving unit can also prioritize receiving region-specific misconduct information by considering the geographical location. In addition, the misconduct information receiving unit can select the optimal receiving method based on the user's location information. This makes it possible to receive misconduct information while considering the user's geographical location. Some or all of the above processing in the misconduct information receiving unit may be performed using AI, for example, or without using AI. For example, the misconduct information receiving unit can input the user's geographical location information into AI, and the AI ​​can analyze that information and prioritize receiving highly relevant information.

[0042] The decision-making unit can adjust the level of detail in the response based on the severity of the misconduct when making a decision. For example, if the severity of the misconduct is high, the decision-making unit will present a detailed response. If the severity of the misconduct is low, the decision-making unit can also present a concise response. Furthermore, the decision-making unit can adjust the level of detail in the response according to the severity to provide the optimal response. This makes it possible to adjust the level of detail in the response based on the severity of the misconduct. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input misconduct severity data into AI, and the AI ​​can analyze that data to adjust the level of detail in the response.

[0043] The decision-making unit can apply different response algorithms depending on the category of misconduct at the time of decision-making. For example, the decision-making unit can select the optimal response algorithm according to the category of misconduct. The decision-making unit can also learn different response methods for each category and apply the optimal algorithm. Furthermore, the decision-making unit can dynamically change the response algorithm based on the category of misconduct. This makes it possible to apply a response algorithm appropriate to the category of misconduct. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without using AI. For example, the decision-making unit can input misconduct category data into AI, and the AI ​​can analyze that data and apply a response algorithm.

[0044] The decision-making unit can determine the priority of countermeasures based on when the misconduct occurred. For example, the decision-making unit can determine the priority of the optimal countermeasures based on when the misconduct occurred. The decision-making unit can also prioritize countermeasures that require a rapid response depending on when the misconduct occurred. Furthermore, the decision-making unit can dynamically change the priority of countermeasures based on when the misconduct occurred. This makes it possible to determine the priority of countermeasures based on when the misconduct occurred. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without using AI. For example, the decision-making unit can input data on when the misconduct occurred into AI, and the AI ​​can analyze that data to determine the priority of countermeasures.

[0045] The decision-making unit can adjust the order of countermeasures based on the relevance of the misconduct at the time of decision-making. For example, the decision-making unit can determine the optimal order of countermeasures based on the relevance of the misconduct. The decision-making unit can also prioritize presenting countermeasures for highly relevant misconduct. Furthermore, the decision-making unit can dynamically change the order of countermeasures based on relevance. This makes it possible to adjust the order of countermeasures based on the relevance of the misconduct. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or not using AI. For example, the decision-making unit can input misconduct relevance data into AI, and the AI ​​can analyze that data to adjust the order of countermeasures.

[0046] The service delivery unit can select the optimal delivery method by referring to the user's past interaction history at the time of delivery. For example, the service delivery unit can refer to the user's past interaction history and select the optimal delivery method. The service delivery unit can also extract specific patterns from the past history and propose the optimal delivery method. Furthermore, the service delivery unit can select a quick and efficient delivery method based on the user's interaction history. This makes it possible to select the optimal delivery method by referring to the user's past interaction history. Some or all of the above processing in the service delivery unit may be performed using AI, for example, or without using AI. For example, the service delivery unit can input the user's past interaction history into AI, and the AI ​​can analyze that history to select the optimal delivery method.

[0047] The service provider can select the optimal service delivery method at the time of delivery, taking into account the user's device information. For example, if the user is using a smartphone, the service provider can provide a display method that matches the screen size. Furthermore, if the user is using a tablet, the service provider can provide a display method optimized for a larger screen. In addition, if the user is using a desktop, the service provider can provide a layout for displaying detailed information. This enables the selection of the optimal service delivery method considering the user's device information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's device information into AI, which can then analyze that information to select the optimal service delivery method.

[0048] The prediction unit can improve the accuracy of its predictions by referring to impact data of similar past incidents. For example, the prediction unit can improve the accuracy of its predictions by referring to impact data of similar past incidents. The prediction unit can also apply the most suitable prediction algorithm based on the impact data of similar incidents. Furthermore, the prediction unit can periodically update the impact data of similar incidents to respond to the latest trends. This makes it possible to improve the accuracy of predictions by referring to the impact data of similar past incidents. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input the impact data of similar past incidents into AI, and the AI ​​can analyze that data to improve the accuracy of its predictions.

[0049] The prediction unit can apply different prediction algorithms to each category of misconduct during the prediction process. For example, the prediction unit can select the optimal prediction algorithm according to the category of misconduct. The prediction unit can also learn different prediction methods for each category and apply the optimal algorithm. Furthermore, the prediction unit can dynamically change the prediction algorithm based on the category of misconduct. This makes it possible to apply different prediction algorithms to each category of misconduct. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input misconduct category data into AI, which can then analyze the data and apply a prediction algorithm.

[0050] The prediction unit can analyze changes in predictions based on the timing of the misconduct. For example, the prediction unit analyzes changes in predictions based on the timing of the misconduct. The prediction unit can also collect data to improve the accuracy of predictions depending on the timing of the incident. Furthermore, the prediction unit can dynamically change the prediction algorithm based on the timing of the incident. This makes it possible to analyze changes in predictions based on the timing of the misconduct. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input data on the timing of the misconduct into AI, and the AI ​​can analyze the data to analyze changes in predictions.

[0051] The forecasting unit can analyze its predictions by referring to relevant market data on scandals during the forecasting process. For example, the forecasting unit can improve the accuracy of its predictions by referring to relevant market data on scandals. It can also apply the most suitable forecasting algorithm based on the relevant market data. Furthermore, the forecasting unit can periodically update the relevant market data to respond to the latest trends. This enables the analysis of predictions by referring to relevant market data on scandals. Some or all of the above processing in the forecasting unit may be performed using AI, for example, or without AI. For example, the forecasting unit can input relevant market data on scandals into an AI, which can then analyze the data and analyze the predictions.

[0052] The conversion unit can improve the accuracy of conversions by referring to economic impact data of similar past incidents during the conversion process. For example, the conversion unit can improve the accuracy of conversions by referring to economic impact data of similar past incidents. The conversion unit can also apply an optimal conversion algorithm based on the impact data of similar incidents. Furthermore, the conversion unit can periodically update the impact data of similar incidents to respond to the latest trends. This makes it possible to improve the accuracy of conversions by referring to economic impact data of similar past incidents. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input economic impact data of similar past incidents into AI, and the AI ​​can analyze that data to improve the accuracy of conversions.

[0053] The conversion unit can weight the converted data based on the timing of the misconduct during the conversion process. For example, the conversion unit weights the converted data based on the timing of the misconduct. The conversion unit can also collect data to improve the accuracy of the conversion depending on the timing of the incidents. Furthermore, the conversion unit can dynamically change the conversion algorithm based on the timing of the incidents. This makes it possible to weight the converted data based on the timing of the misconduct. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input the data on the timing of the misconduct into an AI, which can then analyze the data and weight the converted data.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The crisis management consulting system can refer to the user's past response history and propose the optimal response method. For example, it can analyze how similar incidents were handled in the past and prioritize suggesting successful methods. It can also extract specific patterns from past response history and propose the optimal response method. Furthermore, it can propose quick and efficient response methods based on the user's response history. This makes it possible to propose the optimal response method by referring to the user's past response history. The system inputs the user's past response history data into AI, which then analyzes the data and proposes the optimal response method.

[0056] The crisis management consulting system can prioritize providing highly relevant information by considering the user's geographical location. For example, it can prioritize providing information on incidents specific to a region based on the user's geographical location. It can also propose response methods that are appropriate to the local culture and customs, taking geographical location into consideration. Furthermore, it can select the optimal response method based on the user's location. This makes it possible to provide the most suitable response method considering the user's geographical location. The system inputs the user's geographical location information into an AI, which then analyzes that information and prioritizes providing highly relevant information.

[0057] The crisis management consulting system can broaden its learning scope by cross-referencing scandal data from different industries and regions. For example, it can learn common response methods by cross-referencing scandal data from different industries. It can also learn region-specific response methods by comparing scandal data from different regions. Furthermore, it can enhance overall response capabilities by integrating data that transcends industries and regions. This broadens the scope of learning by cross-referencing scandal data from different industries and regions. The system can input scandal data from different industries and regions into its AI, which then analyzes and learns from that data.

[0058] The crisis management consulting system can quantify the impact of past scandals and weight the training data based on those values. For example, it can quantify the impact of past scandals and prioritize learning cases with high impact. It can also learn from cases with low impact to achieve a broad range of response capabilities. Furthermore, it can weight the training data based on the quantified impact to achieve optimal learning. This makes it possible to quantify the impact of past scandals and weight the training data. The system inputs the impact of past scandals into the AI, which then quantifies that impact and weights the training data.

[0059] The crisis management consulting system can analyze reactions from different media and incorporate them into its training data. For example, it can analyze media reactions and incorporate the reactions of particularly influential media into its training data. It can also compare reactions from different media and learn common elements. Furthermore, it can regularly update media reactions to keep up with the latest trends. This makes it possible to analyze reactions from different media and incorporate them into the training data. The system inputs reaction data from different media into the AI, which then analyzes that data and incorporates it into the training data.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The learning unit learns information about past scandals, how they were handled, and public opinion as information about past misconduct. For example, it collects data on how companies handled past corporate scandals and personal scandals, as well as the resulting public reactions, and the AI ​​analyzes this data. This allows the learning unit to learn the optimal response methods for various types of misconduct. Step 2: The misconduct information reception department receives information about misconduct from users. For example, in the case of corporate misconduct, information such as the details of the problem and the people involved is entered. This information is then entered into the AI. Step 3: The decision-making unit, based on the learning results from the learning unit, determines how to deal with the misconduct reported by the misconduct information receiving unit. For example, it will provide specific details such as the content of the apology, the response method, and how to handle media relations. Step 4: The providing unit provides the user with information about the action decided by the decision-making unit. For example, it notifies the user of the action decided by the decision-making unit.

[0062] (Example of form 2) The online crisis response consulting system according to an embodiment of the present invention is a system in which AI provides consulting on how to respond when an online crisis occurs, in an era where online crises caused by misconduct by both corporations and individuals are rampant due to the spread of social media. The online crisis response consulting system uses AI to learn about past misconduct, how it was handled, and the public's reaction to it. Next, it receives information about the misconduct from the user, and based on that information, the AI ​​presents the optimal response method. It also predicts the impact of the online crisis based on information about the misconduct and the person involved (company size, assets, brand, fame, etc.), and provides the user with a monetary value for that impact. For example, the online crisis response consulting system uses AI to learn about past misconduct, including information about past misconduct, how it was handled, and public reaction to it. For example, it collects data on how companies handled past corporate misconduct and individual scandals, and the resulting public reactions, and the AI ​​analyzes this data. This allows the AI ​​to learn the optimal response method for various types of misconduct. Next, the online crisis response consulting system receives information about the misconduct from the user. The misconduct information reception unit receives detailed information about misconduct entered by users. For example, in the case of corporate misconduct, users enter information such as the nature of the problem and the information of those involved. This information is input into the AI. Subsequently, based on the learning results from the learning unit, the AI ​​determines the optimal course of action for dealing with the misconduct. The decision unit determines the optimal course of action for the current misconduct based on past misconduct data learned by the learning unit. For example, it provides specific suggestions such as the content and method of apology and how to handle media relations. Furthermore, it provides the user with information on the determined course of action. The provision unit provides the user with the course of action determined by the decision unit. This allows the user to implement the optimal course of action presented by the AI. In addition, the crisis management consulting system predicts the impact of a crisis based on information about the misconduct and the people involved. The prediction unit predicts the impact of a crisis based on the nature of the misconduct and information about the people involved (company size, assets, brand, name recognition, etc.). For example, it can quantify the impact of a crisis on a company's sales and brand image. Furthermore, it converts the predicted impact into monetary value.The conversion unit converts the impact predicted by the forecasting unit into monetary terms and provides this information to the user. This allows the user to understand the specific economic impact of a crisis. This mechanism enables the AI ​​to consult with the user on the optimal response to a crisis. This minimizes damage from a crisis and allows for a swift and appropriate response. In this way, the crisis response consulting system allows the AI ​​to consult with the user on the optimal response to their scandal.

[0063] The crisis response consulting system according to this embodiment comprises a learning unit, a scandal information receiving unit, a decision unit, and a provision unit. The learning unit learns information about past scandals, information on how they were handled, and public opinion as information about past scandals. For example, the learning unit collects data on how companies handled past corporate scandals and personal scandals, and the resulting public reactions, and the AI ​​analyzes this data. This allows the learning unit to learn the optimal response methods for various scandals. The scandal information receiving unit receives information about scandals from users. For example, in the case of a corporate scandal, the scandal information receiving unit inputs information such as the details of the problem and information about those involved. This information is input into the AI. Based on the learning results from the learning unit, the decision unit determines how to handle the scandal for which information has been received by the scandal information receiving unit. The decision unit specifically presents, for example, the content of the apology, the response method, and the method of dealing with the media. The provision unit provides the user with information on the response method determined by the decision unit. The provision unit, for example, notifies the user of the action decided by the decision unit. This allows the AI ​​to consult on the optimal action for the user's misconduct in the crisis response consulting system according to the embodiment. Some or all of the above processing in the learning unit may be performed using AI, or not using AI. For example, the learning unit can input data on past misconduct into the AI, and the AI ​​can analyze that data and learn. Some or all of the above processing in the misconduct information receiving unit may be performed using AI, or not using AI. For example, the misconduct information receiving unit can input information on misconduct entered by the user into the AI, and the AI ​​can analyze that information and accept it. Some or all of the above processing in the decision unit may be performed using AI, or not using AI. For example, the decision unit can input the learning results from the learning unit into the AI, and the AI ​​can decide on an action based on those results. Some or all of the above processing in the provision unit may be performed using AI, or not using AI. For example, the provision unit can input the solution determined by the decision unit into the AI, and the AI ​​can then provide that solution to the user.

[0064] The learning unit learns information about past scandals, how they were handled, and public opinion. Specifically, the learning unit collects data on how companies handled past corporate scandals and personal scandals, as well as the resulting public reactions, and the AI ​​analyzes this data. For example, it collects data from a wide range of sources, such as news articles, official statements, social media reactions, and forum comments related to corporate scandals. This data is analyzed using natural language processing technology to extract important keywords and phrases. Furthermore, the AI ​​evaluates the effectiveness of the handling methods and public opinion based on these keywords and phrases. For example, it analyzes how the timing and content of apologies, the responses of those responsible, and whether compensation was provided were evaluated. This allows the learning unit to learn the optimal way to handle various scandals. The learning unit can keep up with the latest trends and evaluation criteria by regularly incorporating new data and updating its learning model. In addition, the learning unit can provide more accurate advice by considering the differences in the characteristics of scandals and handling methods in different industries and regions. This will enable the learning department to build a foundation for providing optimal responses to various incidents that users may encounter.

[0065] The misconduct information reception department receives information about misconduct from users. Specifically, in the case of corporate misconduct, users input details of the problem and information about those involved. This information is then input into AI. For example, users can input detailed information about the misconduct through a dedicated web form or application. Input fields include the date and time the problem occurred, the location, the names and positions of those involved, the specific nature of the problem, and the scope of impact. Furthermore, users can also upload relevant evidence and documents. This information is analyzed by AI, and important elements are extracted. For example, the AI ​​extracts keywords from the input text and classifies the type and severity of the problem. It also identifies stakeholders who may be affected based on the information of those involved. This allows the misconduct information reception department to efficiently organize the information provided by users and provide the data necessary to determine the next step: how to deal with the situation. In addition, the misconduct information reception department has a feedback function to verify the accuracy and completeness of the information entered by users. For example, if there are deficiencies in the input or if additional information is needed, the system can notify the user and encourage them to complete the information. This allows the misconduct information reception department to collect accurate and detailed information, improving the overall accuracy and reliability of the system.

[0066] The decision-making unit determines how to deal with misconduct reported by the misconduct information reception unit, based on the learning results from the learning unit. Specifically, it provides concrete suggestions regarding the content of apologies, response methods, and media relations. For example, the AI ​​proposes the most appropriate response method for the current misconduct based on past misconduct data learned by the learning unit. The AI ​​considers the type and severity of the problem, information about those involved, and the scope of impact to determine the optimal response. For example, regarding the content of apologies, it provides templates for apology letters and suggests specific wording and expressions. Regarding response methods, it presents concrete steps and schedules for resolving the problem. Furthermore, regarding media relations, it provides specific instructions on preparing press conferences, creating press releases, and responding on social media. This allows the decision-making unit to provide quick and appropriate responses to misconduct faced by users. In addition, the decision-making unit can continuously improve the accuracy and effectiveness of its suggestions based on user feedback. For example, it collects the results of responses actually taken by users and evaluates their effectiveness to update the AI's learning model and improve future suggestions. Furthermore, the decision-making unit can take into account the characteristics of different industries and regions and provide customized countermeasures. This allows the decision-making unit to provide users with the optimal countermeasures and minimize the impact of misconduct.

[0067] The service provider provides users with information on the countermeasures decided by the decision-making department. Specifically, it notifies users of the countermeasures decided by the decision-making department. For example, the service provider provides users with detailed information on the countermeasures through a dedicated web portal or application. Users can then implement specific countermeasures based on the information provided by the service provider. The service provider clearly presents detailed procedures, necessary resources, and schedules for the countermeasures, supporting users in smoothly implementing them. Furthermore, the service provider provides real-time support for any questions or problems that arise when users implement the countermeasures. For example, it quickly answers user questions and provides necessary information through chatbots or customer support. The service provider can also monitor the implementation status of the countermeasures and provide additional instructions or advice as needed. This allows the service provider to support users in implementing the optimal countermeasures and minimizing the impact of the incident. In addition, the service provider can collect user feedback and continuously improve the accuracy and effectiveness of the entire system. For example, it evaluates the results and effects of the actions taken by users and updates the AI ​​learning model based on that information to improve future suggestions. This allows the service provider to always offer users the latest and most optimal solutions, minimizing the impact of any misconduct.

[0068] The misconduct information receiving unit includes a unit that predicts the impact of a public outcry based on the misconduct and the individuals involved in the misconduct for which information has been received by the misconduct information receiving unit. The provision unit provides the user with the impact predicted by the prediction unit. The prediction unit predicts the impact of a public outcry based on, for example, the content of the misconduct and information about the individuals involved (company size, assets, brand, name recognition, etc.). For example, the prediction unit can quantify the impact of a public outcry on a company's sales and brand image. The provision unit provides the user with the impact predicted by the prediction unit. For example, the provision unit notifies the user of the impact predicted by the prediction unit. This allows for the prediction of the impact of a public outcry and its provision to the user, enabling them to take concrete countermeasures. Some or all of the above processing in the prediction unit may be performed using, for example, AI, or not using AI. For example, the prediction unit can input information about the content of the misconduct and the individuals involved into AI, and the AI ​​can analyze that information to predict the impact. Some or all of the above processing in the provision unit may be performed using, for example, AI, or not using AI. For example, the provisioning unit can input the impact predicted by the prediction unit into the AI, and the AI ​​can then provide that impact to the user.

[0069] The conversion unit can convert the impact predicted by the forecasting unit into monetary value. For example, the conversion unit can convert the impact predicted by the forecasting unit into monetary value. For example, the conversion unit can convert the impact of a controversy on a company's sales and brand image into monetary value. This allows for a concrete understanding of the economic impact by converting the impact of a controversy into monetary value. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input the impact predicted by the forecasting unit into AI, and the AI ​​can convert that impact into monetary value.

[0070] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is feeling anxious, the learning unit will prioritize selecting training data that reflects particularly successful responses to past incidents. If the user is feeling angry, the learning unit can also select training data that emphasizes cases requiring a quick response. Furthermore, if the user is calm, the learning unit can select training data that includes a wide range of case studies to enhance overall response capabilities. This makes it possible to select training data 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 learning unit may be performed using AI, or not using AI. For example, the learning unit can input user emotion data into an AI, which can then analyze that emotion data to select training data.

[0071] The learning unit can adjust its learning algorithm during the learning process, taking into account the timing and social context of past scandals. For example, the learning unit can analyze the social context of the time when past scandals occurred and reflect factors specific to that period in the learning algorithm. The learning unit can also adjust its learning algorithm by considering the media's reaction at the time of the scandal. Furthermore, the learning unit can periodically update its learning algorithm in response to changes in the social context to keep up with the latest trends. This enables learning that takes into account the timing and social context of past scandals. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input data on the timing and social context of past scandals into an AI, which can then analyze that data and adjust the learning algorithm.

[0072] The learning unit can broaden its learning scope by cross-referencing misconduct data from different industries and regions during the learning process. For example, the learning unit can cross-referencing misconduct data from different industries to learn common countermeasures. It can also compare misconduct data from different regions to learn region-specific countermeasures. Furthermore, the learning unit can integrate data across industries and regions to enhance its overall response capabilities. This broadens the scope of learning by cross-referencing misconduct data from different industries and regions. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input misconduct data from different industries and regions into an AI, which can then analyze and learn from that data.

[0073] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated emotions. For example, if the user is feeling anxious, the learning unit can increase the frequency of learning to strengthen its ability to respond quickly. If the user is calm, the learning unit can also perform regular learning to maintain a stable response ability. Furthermore, if the user is feeling angry, the learning unit can prioritize learning cases that require urgent attention. This makes it possible to adjust the frequency of learning 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 learning unit may be performed using AI, or not using AI. For example, the learning unit can input user emotion data into an AI, and the AI ​​can analyze that emotion data to adjust the frequency of learning.

[0074] The learning unit can quantify the impact of past misconduct during training and weight the training data based on that quantification. For example, the learning unit can quantify the impact of past misconduct and prioritize learning cases with high impact. The learning unit can also learn cases with low impact, thereby achieving broader capabilities. Furthermore, the learning unit can weight the training data based on the quantified impact to achieve optimal learning. This makes it possible to quantify the impact of past misconduct and weight the training data. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the impact of past misconduct into the AI, which can then quantify that impact and weight the training data.

[0075] The learning unit can analyze responses from different media during training and reflect them in the training data. For example, the learning unit can analyze media responses and reflect the responses of particularly influential media in the training data. The learning unit can also compare responses from different media and learn common elements. Furthermore, the learning unit can periodically update media responses to respond to the latest trends. This makes it possible to analyze responses from different media and reflect them in the training data. Some or all of the above processing in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input response data from different media into an AI, which can then analyze that data and reflect it in the training data.

[0076] The misconduct information receiving unit can estimate the user's emotions and adjust the timing of receiving misconduct information based on the estimated emotions. For example, if the user is feeling anxious, the misconduct information receiving unit will receive the information quickly. If the user is calm, the misconduct information receiving unit can extend the reception time to collect more detailed information. Furthermore, if the user is feeling angry, the misconduct information receiving unit can prioritize receiving information that requires urgent attention. This makes it possible to adjust the timing of receiving misconduct information 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 misconduct information receiving unit may be performed using AI, or not using AI. For example, the misconduct information receiving unit can input user emotion data into an AI, and the AI ​​can analyze that emotion data to adjust the reception timing.

[0077] The misconduct information receiving department can analyze the user's past misconduct reporting history and select the optimal receiving method when misconduct information is received. For example, the misconduct information receiving department can analyze the user's past misconduct reporting history and select the optimal receiving method. The misconduct information receiving department can also extract specific patterns from past reporting history and propose the optimal receiving method. Furthermore, the misconduct information receiving department can select a quick and efficient receiving method based on the user's reporting history. This makes it possible to analyze the user's past misconduct reporting history and select the optimal receiving method. Some or all of the above processing in the misconduct information receiving department may be performed using AI, for example, or without AI. For example, the misconduct information receiving department can input the user's past misconduct reporting history into AI, and the AI ​​can analyze that history and select the optimal receiving method.

[0078] The misconduct information receiving unit can estimate the user's emotions and determine the priority of misconduct information to receive based on the estimated user emotions. For example, if the user is feeling anxious, the misconduct information receiving unit will prioritize receiving information that is highly urgent. Also, if the user is calm, the misconduct information receiving unit can prioritize receiving detailed information. Furthermore, if the user is feeling angry, the misconduct information receiving unit can prioritize receiving information that requires a quick response. This makes it possible to determine the priority of misconduct information 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 misconduct information receiving unit may be performed using AI, for example, or not using AI. For example, the misconduct information receiving unit can input user emotion data into an AI, and the AI ​​can analyze that emotion data to determine the priority.

[0079] The misconduct information receiving unit can prioritize receiving highly relevant information by considering the user's geographical location when receiving misconduct information. For example, the misconduct information receiving unit can prioritize receiving highly relevant information based on the user's geographical location. Furthermore, the misconduct information receiving unit can also prioritize receiving region-specific misconduct information by considering the geographical location. In addition, the misconduct information receiving unit can select the optimal receiving method based on the user's location information. This makes it possible to receive misconduct information while considering the user's geographical location. Some or all of the above processing in the misconduct information receiving unit may be performed using AI, for example, or without using AI. For example, the misconduct information receiving unit can input the user's geographical location information into AI, and the AI ​​can analyze that information and prioritize receiving highly relevant information.

[0080] The decision-making unit can estimate the user's emotions and adjust the way the response is expressed based on the estimated emotions. For example, if the user is feeling anxious, the decision-making unit may select a reassuring way of expressing the situation. If the user is calm, the decision-making unit may also select a detailed and logical way of expressing the situation. Furthermore, if the user is feeling angry, the decision-making unit may also select a quick and clear way of expressing the situation. This makes it possible to adjust the way the response is expressed 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 decision-making unit may be performed using AI, or not using AI. For example, the decision-making unit can input user emotion data into an AI, and the AI ​​can analyze that emotion data and adjust the way it is expressed.

[0081] The decision-making unit can adjust the level of detail in the response based on the severity of the misconduct when making a decision. For example, if the severity of the misconduct is high, the decision-making unit will present a detailed response. If the severity of the misconduct is low, the decision-making unit can also present a concise response. Furthermore, the decision-making unit can adjust the level of detail in the response according to the severity to provide the optimal response. This makes it possible to adjust the level of detail in the response based on the severity of the misconduct. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input misconduct severity data into AI, and the AI ​​can analyze that data to adjust the level of detail in the response.

[0082] The decision-making unit can apply different response algorithms depending on the category of misconduct at the time of decision-making. For example, the decision-making unit can select the optimal response algorithm according to the category of misconduct. The decision-making unit can also learn different response methods for each category and apply the optimal algorithm. Furthermore, the decision-making unit can dynamically change the response algorithm based on the category of misconduct. This makes it possible to apply a response algorithm appropriate to the category of misconduct. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without using AI. For example, the decision-making unit can input misconduct category data into AI, and the AI ​​can analyze that data and apply a response algorithm.

[0083] The decision-making unit can estimate the user's emotions and adjust the length of the response based on the estimated emotions. For example, if the user is feeling anxious, the decision-making unit can present a short, concise response. If the user is calm, the decision-making unit can also present a detailed response. Furthermore, if the user is feeling angry, the decision-making unit can present a quick and concise response. This allows for adjustment of the response length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with 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 decision-making unit may be performed using AI, or not using AI. For example, the decision-making unit can input user emotion data into an AI, which can then analyze that emotion data and adjust the length of the response.

[0084] The decision-making unit can determine the priority of countermeasures based on when the misconduct occurred. For example, the decision-making unit can determine the priority of the optimal countermeasures based on when the misconduct occurred. The decision-making unit can also prioritize countermeasures that require a rapid response depending on when the misconduct occurred. Furthermore, the decision-making unit can dynamically change the priority of countermeasures based on when the misconduct occurred. This makes it possible to determine the priority of countermeasures based on when the misconduct occurred. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without using AI. For example, the decision-making unit can input data on when the misconduct occurred into AI, and the AI ​​can analyze that data to determine the priority of countermeasures.

[0085] The decision-making unit can adjust the order of countermeasures based on the relevance of the misconduct at the time of decision-making. For example, the decision-making unit can determine the optimal order of countermeasures based on the relevance of the misconduct. The decision-making unit can also prioritize presenting countermeasures for highly relevant misconduct. Furthermore, the decision-making unit can dynamically change the order of countermeasures based on relevance. This makes it possible to adjust the order of countermeasures based on the relevance of the misconduct. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or not using AI. For example, the decision-making unit can input misconduct relevance data into AI, and the AI ​​can analyze that data to adjust the order of countermeasures.

[0086] The service provider can estimate the user's emotions and adjust the way the information is presented based on the estimated emotions. For example, if the user is feeling anxious, the service provider may select a reassuring way of presenting the information. If the user is calm, the service provider may also select a detailed and logical way of presenting the information. Furthermore, if the user is angry, the service provider may also select a quick and clear way of presenting the information. This allows for adjustment of the way information is presented according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, or not using AI. For example, the service provider can input user emotion data into an AI, and the AI ​​can analyze that emotion data to adjust the way the information is presented.

[0087] The service delivery unit can select the optimal delivery method by referring to the user's past interaction history at the time of delivery. For example, the service delivery unit can refer to the user's past interaction history and select the optimal delivery method. The service delivery unit can also extract specific patterns from the past history and propose the optimal delivery method. Furthermore, the service delivery unit can select a quick and efficient delivery method based on the user's interaction history. This makes it possible to select the optimal delivery method by referring to the user's past interaction history. Some or all of the above processing in the service delivery unit may be performed using AI, for example, or without using AI. For example, the service delivery unit can input the user's past interaction history into AI, and the AI ​​can analyze that history to select the optimal delivery method.

[0088] The information provider can estimate the user's emotions and prioritize the information to be provided based on the estimated emotions. For example, if the user is feeling anxious, the information provider can prioritize providing urgent information. If the user is calm, the information provider can also prioritize providing detailed information. Furthermore, if the user is feeling angry, the information provider can also prioritize providing information that requires a quick response. This makes it possible to prioritize information 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 information provider may be performed using AI, or not using AI. For example, the information provider can input user emotion data into an AI, and the AI ​​can analyze that emotion data to determine the priority of information.

[0089] The service provider can select the optimal service delivery method at the time of delivery, taking into account the user's device information. For example, if the user is using a smartphone, the service provider can provide a display method that matches the screen size. Furthermore, if the user is using a tablet, the service provider can provide a display method optimized for a larger screen. In addition, if the user is using a desktop, the service provider can provide a layout for displaying detailed information. This enables the selection of the optimal service delivery method considering the user's device information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's device information into AI, which can then analyze that information to select the optimal service delivery method.

[0090] The prediction unit can estimate the user's emotions and adjust the display method of the prediction based on the estimated user emotions. For example, if the user is feeling anxious, the prediction unit can select a display method that provides reassurance. If the user is calm, the prediction unit can also select a detailed and logical display method. Furthermore, if the user is feeling angry, the prediction unit can select a quick and clear display method. This allows for adjustment of the prediction display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prediction unit may be performed using AI, or not. For example, the prediction unit can input user emotion data into an AI, which can then analyze that data and adjust the display method.

[0091] The prediction unit can improve the accuracy of its predictions by referring to impact data of similar past incidents. For example, the prediction unit can improve the accuracy of its predictions by referring to impact data of similar past incidents. The prediction unit can also apply the most suitable prediction algorithm based on the impact data of similar incidents. Furthermore, the prediction unit can periodically update the impact data of similar incidents to respond to the latest trends. This makes it possible to improve the accuracy of predictions by referring to the impact data of similar past incidents. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input the impact data of similar past incidents into AI, and the AI ​​can analyze that data to improve the accuracy of its predictions.

[0092] The prediction unit can apply different prediction algorithms to each category of misconduct during the prediction process. For example, the prediction unit can select the optimal prediction algorithm according to the category of misconduct. The prediction unit can also learn different prediction methods for each category and apply the optimal algorithm. Furthermore, the prediction unit can dynamically change the prediction algorithm based on the category of misconduct. This makes it possible to apply different prediction algorithms to each category of misconduct. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input misconduct category data into AI, which can then analyze the data and apply a prediction algorithm.

[0093] The prediction unit can estimate the user's emotions and adjust the importance of predictions based on the estimated emotions. For example, if the user is feeling anxious, the prediction unit can prioritize displaying predictions of high importance. It can also prioritize displaying detailed predictions if the user is calm. Furthermore, if the user is feeling angry, the prediction unit can prioritize displaying predictions requiring immediate attention. This allows for adjustment of prediction importance according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prediction unit may be performed using AI, or not. For example, the prediction unit can input user emotion data into an AI, which can then analyze that data to adjust the importance of predictions.

[0094] The prediction unit can analyze changes in predictions based on the timing of the misconduct. For example, the prediction unit analyzes changes in predictions based on the timing of the misconduct. The prediction unit can also collect data to improve the accuracy of predictions depending on the timing of the incident. Furthermore, the prediction unit can dynamically change the prediction algorithm based on the timing of the incident. This makes it possible to analyze changes in predictions based on the timing of the misconduct. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input data on the timing of the misconduct into AI, and the AI ​​can analyze the data to analyze changes in predictions.

[0095] The forecasting unit can analyze its predictions by referring to relevant market data on scandals during the forecasting process. For example, the forecasting unit can improve the accuracy of its predictions by referring to relevant market data on scandals. It can also apply the most suitable forecasting algorithm based on the relevant market data. Furthermore, the forecasting unit can periodically update the relevant market data to respond to the latest trends. This enables the analysis of predictions by referring to relevant market data on scandals. Some or all of the above processing in the forecasting unit may be performed using AI, for example, or without AI. For example, the forecasting unit can input relevant market data on scandals into an AI, which can then analyze the data and analyze the predictions.

[0096] The conversion unit can estimate the user's emotions and adjust the display method of the converted amount based on the estimated user emotions. For example, if the user is feeling anxious, the conversion unit can select a display method that provides reassurance. If the user is calm, the conversion unit can also select a detailed and logical display method. Furthermore, if the user is feeling angry, the conversion unit can select a quick and clear display method. This makes it possible to adjust the display method of the amount 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 conversion unit may be performed using AI, or not using AI. For example, the conversion unit can input user emotion data into an AI, and the AI ​​can analyze that emotion data to adjust the display method of the amount.

[0097] The conversion unit can improve the accuracy of conversions by referring to economic impact data of similar past incidents during the conversion process. For example, the conversion unit can improve the accuracy of conversions by referring to economic impact data of similar past incidents. The conversion unit can also apply an optimal conversion algorithm based on the impact data of similar incidents. Furthermore, the conversion unit can periodically update the impact data of similar incidents to respond to the latest trends. This makes it possible to improve the accuracy of conversions by referring to economic impact data of similar past incidents. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input economic impact data of similar past incidents into AI, and the AI ​​can analyze that data to improve the accuracy of conversions.

[0098] The conversion unit can estimate the user's emotions and determine the priority of conversions based on the estimated emotions. For example, if the user is feeling anxious, the conversion unit can prioritize conversions that require urgency. If the user is calm, the conversion unit can also prioritize detailed conversions. Furthermore, if the user is feeling angry, the conversion unit can also prioritize conversions that require a quick response. This makes it possible to determine the priority of conversions 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 conversion unit may be performed using AI, or not using AI. For example, the conversion unit can input user emotion data into an AI, and the AI ​​can analyze that emotion data to determine the priority of conversions.

[0099] The conversion unit can weight the converted data based on the timing of the misconduct during the conversion process. For example, the conversion unit weights the converted data based on the timing of the misconduct. The conversion unit can also collect data to improve the accuracy of the conversion depending on the timing of the incidents. Furthermore, the conversion unit can dynamically change the conversion algorithm based on the timing of the incidents. This makes it possible to weight the converted data based on the timing of the misconduct. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input the data on the timing of the misconduct into an AI, which can then analyze the data and weight the converted data.

[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] A crisis response consulting system can estimate a user's emotions and customize response suggestions based on those emotions. For example, if a user is feeling anxious, the system can suggest reassuring responses. If a user is angry, it can suggest quick and clear responses. Furthermore, if a user is calm, it can suggest detailed and logical responses. This allows for the suggestion of the optimal response method tailored to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The system inputs user emotion data into the AI, which then analyzes that data to customize the response method.

[0102] The crisis management consulting system can refer to the user's past response history and propose the optimal response method. For example, it can analyze how similar incidents were handled in the past and prioritize suggesting successful methods. It can also extract specific patterns from past response history and propose the optimal response method. Furthermore, it can propose quick and efficient response methods based on the user's response history. This makes it possible to propose the optimal response method by referring to the user's past response history. The system inputs the user's past response history data into AI, which then analyzes the data and proposes the optimal response method.

[0103] A crisis response consulting system can estimate a user's emotions and prioritize response methods based on those emotions. For example, if a user is feeling anxious, it can prioritize suggesting urgent response methods. If the user is calm, it can prioritize suggesting detailed response methods. Furthermore, if the user is angry, it can prioritize suggesting response methods that require a quick response. This makes it possible to determine the priority of response methods according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The system inputs user emotion data into the AI, which then analyzes that data to determine the priority of response methods.

[0104] The crisis management consulting system can prioritize providing highly relevant information by considering the user's geographical location. For example, it can prioritize providing information on incidents specific to a region based on the user's geographical location. It can also propose response methods that are appropriate to the local culture and customs, taking geographical location into consideration. Furthermore, it can select the optimal response method based on the user's location. This makes it possible to provide the most suitable response method considering the user's geographical location. The system inputs the user's geographical location information into an AI, which then analyzes that information and prioritizes providing highly relevant information.

[0105] A crisis management consulting system can estimate a user's emotions and adjust the way information is presented based on those estimated emotions. For example, if a user is feeling anxious, it can select a reassuring way of presenting information. If the user is calm, it can select a detailed and logical way of presenting information. Furthermore, if the user is angry, it can select a quick and clear way of presenting information. This allows for adjustment of how information is presented according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The system inputs user emotion data into the AI, which then analyzes that data to adjust how information is presented.

[0106] The crisis management consulting system can broaden its learning scope by cross-referencing scandal data from different industries and regions. For example, it can learn common response methods by cross-referencing scandal data from different industries. It can also learn region-specific response methods by comparing scandal data from different regions. Furthermore, it can enhance overall response capabilities by integrating data that transcends industries and regions. This broadens the scope of learning by cross-referencing scandal data from different industries and regions. The system can input scandal data from different industries and regions into its AI, which then analyzes and learns from that data.

[0107] The crisis management consulting system can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is feeling anxious, the learning frequency can be increased to strengthen the ability to respond quickly. If the user is calm, regular learning can be performed to maintain a stable response ability. Furthermore, if the user is feeling angry, the system can prioritize learning cases that require urgent attention. This allows for adjustment of the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The system inputs user emotion data into the AI, which then analyzes that data to adjust the learning frequency.

[0108] The crisis management consulting system can quantify the impact of past scandals and weight the training data based on those values. For example, it can quantify the impact of past scandals and prioritize learning cases with high impact. It can also learn from cases with low impact to achieve a broad range of response capabilities. Furthermore, it can weight the training data based on the quantified impact to achieve optimal learning. This makes it possible to quantify the impact of past scandals and weight the training data. The system inputs the impact of past scandals into the AI, which then quantifies that impact and weights the training data.

[0109] The crisis management consulting system can analyze reactions from different media and incorporate them into its training data. For example, it can analyze media reactions and incorporate the reactions of particularly influential media into its training data. It can also compare reactions from different media and learn common elements. Furthermore, it can regularly update media reactions to keep up with the latest trends. This makes it possible to analyze reactions from different media and incorporate them into the training data. The system inputs reaction data from different media into the AI, which then analyzes that data and incorporates it into the training data.

[0110] The crisis management consulting system can estimate a user's emotions and adjust the timing of receiving information about a scandal based on those emotions. For example, if a user is feeling anxious, the system will quickly receive the information. If the user is calm, the reception time can be extended to gather more detailed information. Furthermore, if the user is angry, the system can prioritize receiving information that requires urgent attention. This allows for adjustment of the timing of receiving information about scandals according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The system inputs user emotion data into the AI, which then analyzes that data to adjust the reception timing.

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

[0112] Step 1: The learning unit learns information about past scandals, how they were handled, and public opinion as information about past misconduct. For example, it collects data on how companies handled past corporate scandals and personal scandals, as well as the resulting public reactions, and the AI ​​analyzes this data. This allows the learning unit to learn the optimal response methods for various types of misconduct. Step 2: The misconduct information reception department receives information about misconduct from users. For example, in the case of corporate misconduct, information such as the details of the problem and the people involved is entered. This information is then entered into the AI. Step 3: The decision-making unit, based on the learning results from the learning unit, determines how to deal with the misconduct reported by the misconduct information receiving unit. For example, it will provide specific details such as the content of the apology, the response method, and how to handle media relations. Step 4: The providing unit provides the user with information about the action decided by the decision-making unit. For example, it notifies the user of the action decided by the decision-making unit.

[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] For example, the learning unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the learning unit can also be implemented by the control unit 46A of the smart device 14. The misconduct information receiving unit is implemented by the receiving device 38 of the smart device 14. For example, the misconduct information receiving unit can also be implemented by the specific processing unit 290 of the data processing device 12. The decision unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the decision unit can also be implemented by the control unit 46A of the smart device 14. The provision unit is implemented by the output device 40 of the smart device 14. For example, the provision unit can also be implemented by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[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] For example, the learning unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the learning unit can also be implemented by the control unit 46A of the smart glasses 214. The misconduct information receiving unit is implemented by the microphone 238 of the smart glasses 214. For example, the misconduct information receiving unit can also be implemented by the specific processing unit 290 of the data processing device 12. The decision unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the decision unit can also be implemented by the control unit 46A of the smart glasses 214. The provision unit is implemented by the speaker 240 of the smart glasses 214. For example, the provision unit can also be implemented by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[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] For example, the learning unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the learning unit can also be implemented by the control unit 46A of the headset terminal 314. The misconduct information receiving unit is implemented by the microphone 238 of the headset terminal 314. For example, the misconduct information receiving unit can also be implemented by the specific processing unit 290 of the data processing device 12. The decision unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the decision unit can also be implemented by the control unit 46A of the headset terminal 314. The provision unit is implemented by the speaker 240 of the headset terminal 314. For example, the provision unit can also be implemented by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[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] For example, the learning unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the learning unit can also be implemented by the control unit 46A of the robot 414. The misconduct information receiving unit is implemented by the microphone 238 of the robot 414. For example, the misconduct information receiving unit can also be implemented by the specific processing unit 290 of the data processing device 12. The decision unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the decision unit can also be implemented by the control unit 46A of the robot 414. The provision unit is implemented by the speaker 240 of the robot 414. For example, the provision unit can also be implemented by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[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) The department learns information about past scandals, including information on past scandals, information on how they were dealt with, and public opinion. The misconduct information reception department receives information about misconduct from users, Based on the learning results from the aforementioned unit, a decision unit determines how to deal with the misconduct for which information has been received by the misconduct information receiving unit, The system includes a provisioning unit that provides the user with information on the countermeasure determined by the determination unit. A system characterized by the following features. (Note 2) Based on the misconduct and the individuals involved in the misconduct, as reported by the misconduct information receiving department, the system includes a department that predicts the impact of online backlash. The providing unit provides the user with the effects predicted by the unit. The system described in Appendix 1, characterized by the features described herein. (Note 3) The system includes a conversion unit that converts the predicted impact into monetary value. The system described in Appendix 2, characterized by the features described herein. (Note 4) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, During the learning process, the learning algorithm is adjusted by considering the timing and social context of past scandals. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned learning unit, During learning, cross-reference scandal data from different industries and regions to broaden the scope of learning. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, During the learning process, the impact of past scandals is quantified, and the learning data is weighted based on that quantification. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, During training, analyze responses from different media and incorporate them into the training data. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned misconduct information receiving department, The system estimates user sentiment and adjusts the timing of receiving misconduct reports based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned misconduct information receiving department, When receiving information about misconduct, the system analyzes the user's past misconduct reporting history and selects the most appropriate method of receiving the information. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned misconduct information receiving department, The system estimates user sentiment and prioritizes the information about misconduct received based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned misconduct information receiving department, When receiving information about misconduct, the system prioritizes receiving information that is highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned determination unit, It estimates the user's emotions and adjusts the way it expresses its response based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned determination unit, When making a decision, adjust the level of detail in the response based on the severity of the misconduct. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned determination unit, When making a decision, different response algorithms are applied depending on the category of misconduct. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned determination unit, The system estimates the user's emotions and adjusts the length of the response based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned determination unit, When making a decision, prioritize the countermeasures based on when the misconduct occurred. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned determination unit, When making a decision, the order of actions taken will be adjusted based on the relevance of the misconduct. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, It estimates the user's emotions and adjusts how the information provided is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, When providing the service, the optimal delivery method is selected by referring to the user's past interaction history. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, It estimates the user's emotions and prioritizes the information provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing the service, the optimal delivery method will be selected, taking into account the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 24) The prediction unit, It estimates the user's emotions and adjusts how predictions are displayed based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 25) The prediction unit, When making predictions, we improve the accuracy of our predictions by referring to data on the impact of similar past incidents. The system described in Appendix 2, characterized by the features described herein. (Note 26) The prediction unit, When making predictions, different prediction algorithms are applied for each category of misconduct. The system described in Appendix 2, characterized by the features described herein. (Note 27) The prediction unit, It estimates the user's emotions and adjusts the importance of the prediction based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The prediction unit, When making predictions, we analyze how the prediction changes based on when the scandal occurred. The system described in Appendix 2, characterized by the features described herein. (Note 29) The prediction unit, When making predictions, we analyze the forecast by referring to market data related to scandals. The system described in Appendix 2, characterized by the features described herein. (Note 30) The conversion unit is, We estimate the user's emotions and adjust how the calculated amount is displayed based on those emotions. The system described in Appendix 3, characterized by the features described herein. (Note 31) The conversion unit is, During conversion, we improve the accuracy of the conversion by referring to economic impact data from similar past scandals. The system described in Appendix 3, characterized by the features described herein. (Note 32) The conversion unit is, The system estimates the user's emotions and determines the conversion priority based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 33) The conversion unit is, During conversion, the conversion data is weighted based on when the scandal occurred. The system described in Appendix 3, 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. The learning unit learns information about past scandals, including information on past scandals, information on how they were dealt with, and public opinion. The misconduct information reception department receives information about misconduct from users, Based on the learning results from the aforementioned unit, a decision unit determines how to deal with the misconduct for which information has been received by the misconduct information receiving unit, The system includes a provisioning unit that provides the user with information on the countermeasure determined by the determination unit. A system characterized by the following features.

2. The system includes a prediction unit that predicts the impact of a public outcry based on the misconduct and the individuals involved in the misconduct, as reported by the misconduct information receiving unit. The providing unit provides the user with the effects predicted by the unit. The system according to feature 1.

3. The system includes a conversion unit that converts the predicted impact into monetary value. The system according to feature 2.

4. The aforementioned learning unit, The system estimates the user's emotions and selects training data based on the estimated user's emotions. The system according to feature 1.

5. The aforementioned learning unit, During the learning process, the learning algorithm is adjusted to take into account the timing and social context of the aforementioned past scandals. The system according to feature 1.

6. The aforementioned learning unit, During learning, cross-reference scandal data from different industries and regions to broaden the scope of learning. The system according to feature 1.

7. The aforementioned learning unit, The system estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system according to feature 1.

8. The aforementioned learning unit, During the learning process, the impact of the aforementioned past scandals is quantified, and the learning data is weighted based on that quantification. The system according to feature 1.

9. The aforementioned learning unit, During training, analyze responses from different media and incorporate them into the training data. The system according to feature 1.

Images