system

Abstract

The system according to this embodiment aims to predict errors in email communication and propose preventive measures. [Solution] The system according to the embodiment comprises a registration unit, an acquisition unit, an analysis unit, a prediction unit, and a proposal unit. The registration unit registers past error cases in a database. The acquisition unit acquires emails. The analysis unit analyzes the language or context within the emails acquired by the acquisition unit. The prediction unit compares the analysis results from the analysis unit with the results from the database and predicts the risk. The proposal unit proposes preventive measures based on the prediction results from the prediction unit.

Description

Technical Field

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

Background Art

[0002] Patent Document No. 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003] 2]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, mistakes in email communication have not been sufficiently predicted and prevented in advance, and there is room for improvement.

[0005] The system according to the embodiment aims to predict mistakes in email communication and propose preventive measures.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a registration unit, an acquisition unit, an analysis unit, a prediction unit, and a proposal unit. The registration unit registers past error cases in a database. The acquisition unit retrieves emails. The analysis unit analyzes the language or context within the emails retrieved by the acquisition unit. The prediction unit compares the analysis results from the analysis unit with the results from the database and predicts the risk. The proposal unit proposes preventive measures based on the prediction results from the prediction unit. [Effects of the Invention]

[0007] The system according to this embodiment can predict errors in email communication and suggest preventive measures. [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, etc. The communication I / F manages communication between multiple 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 communication error prevention system according to an embodiment of the present invention is a system that uses generative AI to analyze employees' email communications and accumulate past error cases. The purpose of this system is to predict communication errors that may occur in the future and propose preventive measures. Specifically, first, past error cases are registered in a database. This database stores examples of communication errors that have occurred in the past. Next, the system retrieves employees' emails and analyzes the language and context within them. Generative AI is used for this analysis, and natural language processing technology is used to analyze the text data of the emails. The analysis results are compared with past error cases registered in the database. This comparison allows for the prediction of future risks. For example, if an error occurred in the past due to specific language or context, the system checks whether a similar pattern can be seen in current emails. Based on the predicted risks, the system proposes specific communication guidance and improvement measures to employees. For example, it may instruct employees to avoid specific language or provide advice to clarify the context. In this way, it learns from past errors and provides specific advice to prevent future errors. The unique aspect of this system is that it uses past error cases to predict future risks and proposes specific preventive measures. This prevents miscommunication and misunderstandings caused by communication errors, thereby preventing project delays and financial losses. The communication error prevention system analyzes employees' email communications, accumulates past error cases, predicts future risks, and proposes specific preventative measures.

[0029] The communication error prevention system according to this embodiment comprises a registration unit, an acquisition unit, an analysis unit, a prediction unit, and a proposal unit. The registration unit registers past error cases in a database. Past error cases include, but are not limited to, technical errors, communication errors, and procedural errors. The registration unit can, for example, manually input past error cases. The registration unit can also automatically collect past error cases and register them in the database. For example, the registration unit analyzes past email data, extracts error cases, and registers them in the database. The acquisition unit acquires emails. The acquisition unit can, for example, periodically scan emails and acquire emails with specific triggers. For example, the acquisition unit scans emails daily, weekly, or at specific times. The acquisition unit can also acquire emails triggered by the appearance of specific keywords or emails from specific senders. The analysis unit uses a generation AI to analyze the language and context within emails acquired by the acquisition unit. The analysis unit, for example, analyzes the frequency of appearance of specific keywords and the semantic analysis of the context. For example, the analysis unit uses generative AI to analyze email text data and extract patterns in wording and context. The prediction unit compares the analysis results from the analysis unit with the results from a database to predict future risks. The prediction unit predicts risks using, for example, correlation analysis with past data or machine learning models. For example, the prediction unit checks whether similar patterns can be seen in current emails if errors occurred in the past due to specific wording or context. The proposal unit proposes preventive measures based on the prediction results from the prediction unit. For example, the proposal unit proposes specific action guidelines or methods for raising awareness. For example, the proposal unit provides guidance to avoid specific wording or advice to clarify the context. In this way, the communication error prevention system according to the embodiment can predict future risks by utilizing past error cases and propose specific preventive measures.

[0030] The registration unit registers past error cases in a database. Past error cases include, but are not limited to, technical errors, communication errors, and procedural errors. The registration unit can, for example, manually input past error cases. Alternatively, the registration unit can automatically collect past error cases and register them in the database. For example, the registration unit can analyze past email data, extract error cases, and register them in the database. Specifically, the registration unit has an algorithm that periodically scans logs from the company's email servers and communication tools and automatically extracts error cases. This algorithm uses natural language processing technology to analyze the content of emails and messages and identify error patterns. For example, if a particular keyword or phrase appears frequently, it is determined that it is likely to be the cause of an error and is registered in the database. The registration unit also provides an interface for users to manually input error cases. This allows users to add important error cases to the database based on their past experience and knowledge. Furthermore, the registration unit classifies and tags error cases to enable efficient searching and referencing of information within the database. For example, errors can be categorized into different types, such as technical errors, communication errors, and procedural errors, and each error case can be assigned a tag related to that category. This allows users to quickly search and refer to past error cases based on specific categories or tags.

[0031] The retrieval unit retrieves emails. For example, it can periodically scan emails and retrieve them based on specific triggers. For instance, it can scan emails daily, weekly, or at specific times. It can also retrieve emails triggered by the appearance of specific keywords or emails from specific senders. Specifically, the retrieval unit accesses the company's email server and scans email data at specified time intervals. During the scan, all content, including the email subject, body, and attachments, is targeted. Furthermore, the retrieval unit has a filtering function to prioritize the retrieval of emails containing specific keywords or phrases. For example, it automatically detects and retrieves emails containing keywords such as "important," "urgent," or "confirmation." It is also possible to set triggers based on emails from specific senders or recipients. This allows the retrieval unit to efficiently retrieve emails without missing important communications. Additionally, the retrieval unit temporarily stores the retrieved email data, making it accessible to the analysis unit. The stored email data is encrypted as a security measure to protect it from unauthorized access. This allows the acquisition unit to safely and efficiently acquire and store email data, thereby improving the overall reliability of the system.

[0032] The analysis unit uses generative AI to analyze the language and context within emails acquired by the acquisition unit. For example, the analysis unit analyzes the frequency of occurrence of specific keywords and the semantic analysis of the context. Specifically, the analysis unit uses generative AI to analyze the text data of emails and extract patterns in language and context. In particular, the generative AI utilizes natural language processing techniques to analyze the email content in detail. For example, it calculates the frequency of occurrence of words and phrases within emails and detects specific patterns. It also performs contextual analysis to determine the intentions and emotions contained within the email content. The generative AI compares the current email with a database of past error cases to identify similar patterns and detect high-risk communications. For example, if an error occurred in the past due to specific language or context, it checks whether similar patterns are present in the current email. Furthermore, the generative AI can classify the email content into different categories, such as technical errors, communication errors, and procedural errors. This allows the analysis unit to quickly and accurately analyze acquired email data and identify potential risks. Additionally, the analysis unit visualizes the analysis results and provides a dashboard to present them clearly to the user. This allows users to intuitively understand the analysis results and take quick action.

[0033] The prediction unit compares the analysis results from the analysis unit with the results from the database to predict future risks. For example, the prediction unit predicts risks using correlation analysis with past data or machine learning models. For instance, if errors occurred in the past due to specific wording or context, the prediction unit checks whether similar patterns are present in current emails. Specifically, the prediction unit uses machine learning algorithms to compare past error data with current email data to identify high-risk patterns. For example, if errors occurred in the past due to "insufficient confirmation" or "misunderstanding," the prediction unit detects whether similar wording or context is included in current emails. The prediction unit also performs correlation analysis to evaluate the extent to which specific wording or context influences the occurrence of errors. This allows the prediction unit to predict future risks with high accuracy and provide information for taking appropriate countermeasures. Furthermore, the prediction unit can update prediction results in real time to respond to the latest situation. For example, each time a new email is acquired, the prediction unit immediately updates the analysis results and performs a risk assessment. The prediction unit can also perform trend analysis based on past data to predict long-term risk fluctuations. This allows the prediction unit to provide highly accurate risk predictions based on the latest information at all times, supporting quick and appropriate responses.

[0034] The proposal department proposes preventative measures based on the prediction results from the prediction department. For example, the proposal department proposes specific action guidelines and methods of raising awareness. For instance, it may instruct users to avoid certain wording or provide advice to clarify context. Specifically, the proposal department uses generative AI to propose specific improvement measures based on the content of emails. For example, if a high risk is predicted due to "insufficient confirmation," the proposal department will instruct users to reconfirm the content of the email and provide specific points to check. Also, if a high risk is predicted due to "misunderstanding," the proposal department will propose specific phrases and expressions to clarify the context. Furthermore, the proposal department can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. For example, it collects feedback on the results of users acting on the suggestions and uses that data to improve the suggestion algorithm. The proposal department can also reliably transmit information using multiple communication methods. For example, it can ensure that important information is delivered reliably by using not only email notifications but also pop-up notifications and alerts on the dashboard. This allows the proposal department to provide users with quick and specific preventative measures and minimize the risk of communication errors.

[0035] The analysis unit can analyze the wording and context of emails using a generative AI. For example, the analysis unit can analyze the text data of an email using a generative AI. For example, the analysis unit can input a prompt to the generative AI such as "Please analyze the wording and context of this email," and the generative AI will output the analysis results. The analysis unit can also analyze the frequency of occurrence of specific keywords using a generative AI. For example, the analysis unit can input a prompt to the generative AI such as "Please analyze the frequency of occurrence of a specific keyword in this email," and the generative AI will output the analysis results. The analysis unit can also perform semantic analysis of the context using a generative AI. For example, the analysis unit can input a prompt to the generative AI such as "Please analyze the meaning of the context of this email," and the generative AI will output the analysis results. As a result, using a generative AI improves the accuracy of the analysis of the wording and context of emails. Some or all of the above-described processes in the analysis unit may be performed using a generative AI, or they may not be performed using a generative AI. For example, the analysis unit can input the text data of an email into a generative AI and have the generative AI perform the analysis of wording and context.

[0036] The registration unit can analyze the language and context within emails from past error cases and register them in a database. For example, the registration unit analyzes the language and context within emails from past error cases. For example, the registration unit analyzes the frequency of occurrence of specific keywords and the semantic analysis of the context. The registration unit also registers the analysis results in a database. For example, the registration unit can manually input the analysis results into the database. Alternatively, the registration unit can automatically register the analysis results into the database. For example, the registration unit can use an algorithm to automatically register the analysis results into the database. This improves the accuracy of future risk predictions by analyzing past error cases in detail and registering them in the database. Some or all of the above processing in the registration unit may be performed using AI, or not. For example, the registration unit can input email data from past error cases into AI and have the AI ​​perform the analysis of language and context.

[0037] The retrieval unit can periodically scan emails and retrieve them based on triggers. For example, the retrieval unit can periodically scan emails. For example, the retrieval unit can scan emails daily, weekly, or at specific times. The retrieval unit can also retrieve emails based on specific triggers. For example, the retrieval unit can retrieve emails based on the appearance of specific keywords or emails from specific senders. This ensures that important emails are not missed by periodically scanning emails and retrieving them based on specific triggers. Some or all of the above processes in the retrieval unit may be performed using AI, for example, or not. For example, the retrieval unit can have AI perform email scanning and triggered email retrieval.

[0038] The proposal department can propose specific preventative measures. For example, the proposal department can propose specific action guidelines. For example, the proposal department can advise against certain wording. The proposal department can also provide advice on clarifying context. For example, the proposal department can provide specific advice on clarifying the context of an email. By proposing specific preventative measures, future communication errors can be prevented. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can have AI execute the proposal of preventative measures.

[0039] The registration unit can analyze past error cases and determine registration priorities based on the severity of the errors. For example, the registration unit can immediately register serious error cases and postpone minor ones. It can also prioritize registration of errors with a wide impact and register those with a narrow impact later. Furthermore, it can prioritize registration of errors with a high recurrence rate and register those with a low recurrence rate later. This allows for the priority registration of important error cases based on their severity. Some or all of the above processing in the registration unit may be performed using AI, for example, or not. For example, the registration unit can input data on past error cases into an AI and have the AI ​​evaluate the severity of the errors and determine the registration priorities.

[0040] The registration unit can adjust the level of detail in the registration of error cases based on the frequency of the errors. For example, the registration unit can register frequently occurring errors in detail and rarely occurring errors in a simplified manner. The registration unit can also register high-frequency errors with detailed cause analysis. Furthermore, the registration unit can register low-frequency errors with only a brief summary, allowing for the addition of details later. This enables efficient registration of error cases by adjusting the level of detail based on the frequency of errors. Some or all of the above processing in the registration unit may be performed using AI, for example, or without AI. For example, the registration unit can input error frequency data into AI and have the AI ​​adjust the level of detail of the registration.

[0041] The registration unit can register error cases while considering the location and time of the error. For example, the registration unit can automatically acquire the location where the error occurred and reflect it during registration. The registration unit can also consider the time of the error and prioritize the registration of errors that occur during the same time period. Furthermore, if the location of errors is concentrated in a particular department or team, the registration unit can reflect that information during registration. This allows for efficient registration of error cases by considering the location and time of the error. Some or all of the above processing in the registration unit may be performed using AI, for example, or not. For example, the registration unit can input data on the location and time of the error into the AI ​​and have the AI ​​determine the priority of registration.

[0042] The registration unit can determine the priority of registration when registering error cases, taking into account the scope of the error's impact. For example, the registration unit can prioritize registration of errors with a wide scope of impact and register errors with a narrow scope later. Furthermore, the registration unit can immediately register errors with a significant impact and postpone registration of errors with a minor impact. Additionally, the registration unit can prioritize registration of errors affecting multiple departments and register errors limited to a single department later. This allows for the priority registration of important error cases by considering the scope of the error's impact. Some or all of the above processing in the registration unit may be performed using AI, or not. For example, the registration unit can input data on the scope of the error's impact into the AI ​​and have the AI ​​determine the registration priority.

[0043] The retrieval unit can analyze the user's past email history and select the optimal retrieval method. For example, the retrieval unit can prioritize retrieving emails from people the user has frequently communicated with in the past. The retrieval unit can also automatically filter important emails from the user's past email history. Furthermore, the retrieval unit can analyze the user's past email history and prioritize retrieving emails containing specific keywords. In this way, the optimal email retrieval method can be selected by analyzing the user's past email history. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or without AI. For example, the retrieval unit can input the user's past email history data into AI and have the AI ​​select the optimal retrieval method.

[0044] The retrieval unit can filter emails based on the user's current projects and areas of interest when retrieving them. For example, the retrieval unit can prioritize retrieving emails related to projects the user is currently working on. The retrieval unit can also filter relevant emails based on the user's areas of interest. Furthermore, if the user is focused on a specific project, the retrieval unit can prioritize retrieving emails related to that project. This allows for the priority retrieval of important emails by filtering them based on the user's current projects and areas of interest. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or not. For example, the retrieval unit can input the user's project data and area of ​​interest data into an AI and have the AI ​​perform the email filtering.

[0045] The retrieval unit can prioritize retrieving highly relevant emails by considering the user's geographical location information when retrieving emails. For example, if the user is in a specific location, the retrieval unit will prioritize retrieving emails related to that location. Furthermore, if the user is on a business trip, the retrieval unit can prioritize retrieving emails related to the business trip destination. Additionally, if the user is in the office, the retrieval unit can prioritize retrieving emails related to the office. This allows for the prioritization of highly relevant emails by considering the user's geographical location information. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or without AI. For example, the retrieval unit can input the user's geographical location data into AI and have the AI ​​retrieve highly relevant emails.

[0046] The retrieval unit can analyze the user's social media activity when retrieving emails and retrieve relevant emails. For example, the retrieval unit can prioritize retrieving emails related to topics mentioned by the user on social media. It can also prioritize retrieving emails from people the user follows on social media. Furthermore, the retrieval unit can analyze the user's social media activity and filter relevant emails. This allows for the priority retrieval of relevant emails by analyzing the user's social media activity. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or not. For example, the retrieval unit can input the user's social media activity data into AI and have the AI ​​retrieve relevant emails.

[0047] The analysis unit can adjust the level of detail in its analysis based on the importance of each email. For example, it can analyze important emails in detail and less important emails in a simplified manner. It can also analyze high-importance emails, including detailed root cause analysis. Furthermore, it can analyze low-importance emails with only a brief overview, allowing for the addition of details later. This allows for efficient analysis by adjusting the level of detail based on the importance of each email. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input email importance data into AI and have the AI ​​adjust the level of detail in its analysis.

[0048] The analysis unit can apply different analysis algorithms depending on the email category during analysis. For example, the analysis unit can apply a business-specific analysis algorithm to business emails. It can also apply a private-specific analysis algorithm to private emails. Furthermore, it can apply a spam-specific analysis algorithm to spam emails. This improves analysis accuracy by applying the most appropriate analysis algorithm for each email category. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input email category data into AI and have the AI ​​apply different analysis algorithms.

[0049] The analysis unit can determine the priority of analysis based on the email sending date during the analysis process. For example, the analysis unit may prioritize the analysis of recently sent emails and postpone older emails. It can also prioritize the analysis of emails sent at important times. Furthermore, it can prioritize the analysis of emails related to specific events. This enables efficient analysis by determining the priority of analysis based on the email sending date. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input email sending date data into AI and have the AI ​​determine the analysis priority.

[0050] The analysis unit can adjust the order of analysis based on the relevance of the emails during the analysis process. For example, the analysis unit can prioritize the analysis of highly relevant emails and postpone the analysis of less relevant emails. It can also prioritize the analysis of emails related to a specific project. Furthermore, it can prioritize the analysis of emails related to the user's areas of interest. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the emails. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input email relevance data into an AI and have the AI ​​adjust the order of analysis.

[0051] The prediction unit can predict current risk by referring to past risk data during the prediction process. For example, the prediction unit predicts current risk based on past risk data. The prediction unit can also extract specific patterns from past risk data and predict current risk. Furthermore, the prediction unit can analyze past risk data and quantitatively evaluate current risk. This allows for accurate prediction of current risk by referring to past risk data. Some or all of the above processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input past risk data into AI and have the AI ​​perform the prediction of current risk.

[0052] The prediction unit can apply different risk prediction methods to each email category during prediction. For example, the prediction unit can apply a business-specific risk prediction method to business emails. It can also apply a private-specific risk prediction method to private emails. Furthermore, it can apply a spam-specific risk prediction method to spam emails. This improves the accuracy of risk prediction by applying the most appropriate risk prediction method to each email category. 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 email category data into AI and have the AI ​​apply different risk prediction methods.

[0053] The prediction unit can analyze changes in risk based on the timing of email transmission during the prediction process. For example, the prediction unit may prioritize the analysis of risks associated with recently sent emails. It can also prioritize the analysis of risks associated with emails sent at important times. Furthermore, it can prioritize the analysis of risks associated with emails related to specific events. This enables accurate risk prediction by analyzing changes in risk based on the timing of email transmission. 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 email transmission timing data into AI and have the AI ​​perform the analysis of changes in risk.

[0054] The forecasting unit can analyze risk by referring to relevant market data for emails during the forecasting process. For example, the forecasting unit analyzes email risk based on relevant market data. The forecasting unit can also predict email risk by referring to market trends. Furthermore, the forecasting unit can analyze market data and quantitatively evaluate email risk. This allows for accurate risk analysis by referring to relevant market data for emails. 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 into AI and have the AI ​​perform the risk analysis.

[0055] The proposal unit can adjust the level of detail of its recommendations based on the severity of the risk when proposing preventive measures. For example, it can propose detailed preventive measures for significant risks and simplified preventive measures for minor risks. It can also propose detailed preventive measures if the risk has a wide scope of impact. Furthermore, it can propose detailed preventive measures if the risk has a high recurrence rate. This allows for the provision of appropriate preventive measures by adjusting the level of detail of recommendations based on the severity of the risk. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input risk severity data into AI and have the AI ​​adjust the level of detail of the recommendations.

[0056] The proposal unit can apply different proposal algorithms depending on the risk category when proposing preventive measures. For example, the proposal unit can propose business-specific preventive measures for business risks. It can also propose private-specific preventive measures for private risks. Furthermore, it can propose spam-specific preventive measures for spam risks. This improves the accuracy of preventive measures by applying the most appropriate proposal algorithm for each risk category. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not. For example, the proposal unit can input risk category data into an AI and have the AI ​​apply different proposal algorithms.

[0057] The proposal unit can prioritize preventive measures based on when the risks occurred. For example, the proposal unit may prioritize preventive measures for recently occurring risks. It can also prioritize preventive measures for risks that occurred at critical times. Furthermore, it can prioritize preventive measures for risks associated with specific events. This allows for the provision of appropriate preventive measures by prioritizing proposals based on when the risks occurred. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not. For example, the proposal unit can input risk occurrence timing data into AI and have the AI ​​perform the determination of proposal priorities.

[0058] The suggestion unit can adjust the order of suggestions based on the relevance of the risks when proposing preventive measures. For example, the suggestion unit can prioritize suggesting preventive measures for highly relevant risks. It can also prioritize suggesting preventive measures for risks related to a specific project. Furthermore, it can prioritize suggesting preventive measures for risks related to the user's area of ​​interest. This allows for the provision of appropriate preventive measures by adjusting the order of suggestions based on the relevance of the risks. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not. For example, the suggestion unit can input risk relevance data into AI and have the AI ​​perform the adjustment of the suggestion order.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The communication error prevention system can also include a feedback unit. The feedback unit evaluates the effectiveness of the preventative measures provided by the suggestion unit and feeds the evaluation results back into a database. For example, the feedback unit monitors the quality of communication after employees implement the suggested preventative measures and evaluates whether improvements have been made. The feedback unit can also collect feedback from employees to verify whether the suggested preventative measures were actually effective. Furthermore, the feedback unit can adjust the suggestion unit's algorithm based on the evaluation results to propose more effective preventative measures. This allows the system to continuously learn and improve the accuracy of its preventative measures.

[0061] The registration unit can analyze past error cases and adjust the level of detail in the registration based on the cause of the error. For example, technical errors can be registered in detail, while communication errors can be registered in a simplified manner. Procedural errors can also be registered with detailed procedures. Furthermore, if there are multiple causes for the error, the registration can include a detailed analysis of each cause. This allows for efficient registration of error cases by adjusting the level of detail based on the cause of the error.

[0062] A communication error prevention system can also include a training department. This department provides employees with training to improve their communication skills. For example, it can conduct simulations based on past error cases, allowing employees to learn by actually experiencing the mistakes. The training department can also offer courses teaching basic communication rules and best practices. Furthermore, it can evaluate employees' communication skills and provide individual feedback. This helps improve employees' communication skills and prevent errors from occurring.

[0063] The communication error prevention system can also include a notification function. This function notifies employees in real time of important or high-risk emails. For example, it can instantly notify employees of emails containing specific keywords. It can also prioritize emails deemed high-risk based on past error cases. Furthermore, it can filter emails based on specific conditions set by employees, notifying only important emails. This ensures employees don't miss important emails and can respond accordingly.

[0064] The analysis unit can analyze not only the content of the email but also the relationship between the sender and recipient. For example, the analysis unit can analyze the past interactions between the sender and recipient to assess the depth of their relationship. It can also consider the positions and departments of the sender and recipient to evaluate the importance of the communication. Furthermore, the analysis unit can analyze the tone and emotions of past interactions between the sender and recipient to more accurately understand the context of the current email. This enables analysis that considers not only the content of the email but also the relationship between the sender and recipient.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The registration unit registers past error cases in the database. Past error cases include technical errors, communication errors, procedural errors, etc. The registration unit can either manually input past error cases or automatically collect and register them in the database. For example, it can analyze past email data, extract error cases, and register them in the database. Step 2: The retrieval unit retrieves emails. The retrieval unit periodically scans for emails and retrieves them based on specific triggers. For example, it can scan for emails daily, weekly, or at specific times of day. It can also retrieve emails based on the appearance of specific keywords or emails from specific senders. Step 3: The analysis unit uses a generation AI to analyze the language and context within the emails acquired by the acquisition unit. The analysis unit analyzes the frequency of occurrence of specific keywords and the semantic analysis of the context. For example, it analyzes the text data of the emails and extracts patterns of language and context. Step 4: The prediction unit compares the analysis results from the analysis unit with the results from the database to predict future risks. The prediction unit predicts risks using correlation analysis with past data and machine learning models. For example, if errors occurred in the past due to specific wording or context, it checks whether similar patterns can be seen in current emails. Step 5: The proposal team proposes preventive measures based on the prediction results from the forecasting team. The proposal team proposes specific action guidelines and methods for raising awareness. For example, they may instruct people to avoid certain wording or provide advice to clarify context.

[0067] (Example of form 2) The communication error prevention system according to an embodiment of the present invention is a system that uses generative AI to analyze employees' email communications and accumulate past error cases. The purpose of this system is to predict communication errors that may occur in the future and propose preventive measures. Specifically, first, past error cases are registered in a database. This database stores examples of communication errors that have occurred in the past. Next, the system retrieves employees' emails and analyzes the language and context within them. Generative AI is used for this analysis, and natural language processing technology is used to analyze the text data of the emails. The analysis results are compared with past error cases registered in the database. This comparison allows for the prediction of future risks. For example, if an error occurred in the past due to specific language or context, the system checks whether a similar pattern can be seen in current emails. Based on the predicted risks, the system proposes specific communication guidance and improvement measures to employees. For example, it may instruct employees to avoid specific language or provide advice to clarify the context. In this way, it learns from past errors and provides specific advice to prevent future errors. The unique aspect of this system is that it uses past error cases to predict future risks and proposes specific preventive measures. This prevents miscommunication and misunderstandings caused by communication errors, thereby preventing project delays and financial losses. The communication error prevention system analyzes employees' email communications, accumulates past error cases, predicts future risks, and proposes specific preventative measures.

[0068] The communication error prevention system according to this embodiment comprises a registration unit, an acquisition unit, an analysis unit, a prediction unit, and a proposal unit. The registration unit registers past error cases in a database. Past error cases include, but are not limited to, technical errors, communication errors, and procedural errors. The registration unit can, for example, manually input past error cases. The registration unit can also automatically collect past error cases and register them in the database. For example, the registration unit analyzes past email data, extracts error cases, and registers them in the database. The acquisition unit acquires emails. The acquisition unit can, for example, periodically scan emails and acquire emails with specific triggers. For example, the acquisition unit scans emails daily, weekly, or at specific times. The acquisition unit can also acquire emails triggered by the appearance of specific keywords or emails from specific senders. The analysis unit uses a generation AI to analyze the language and context within emails acquired by the acquisition unit. The analysis unit, for example, analyzes the frequency of appearance of specific keywords and the semantic analysis of the context. For example, the analysis unit uses generative AI to analyze email text data and extract patterns in wording and context. The prediction unit compares the analysis results from the analysis unit with the results from a database to predict future risks. The prediction unit predicts risks using, for example, correlation analysis with past data or machine learning models. For example, the prediction unit checks whether similar patterns can be seen in current emails if errors occurred in the past due to specific wording or context. The proposal unit proposes preventive measures based on the prediction results from the prediction unit. For example, the proposal unit proposes specific action guidelines or methods for raising awareness. For example, the proposal unit provides guidance to avoid specific wording or advice to clarify the context. In this way, the communication error prevention system according to the embodiment can predict future risks by utilizing past error cases and propose specific preventive measures.

[0069] The registration unit registers past error cases in a database. Past error cases include, but are not limited to, technical errors, communication errors, and procedural errors. The registration unit can, for example, manually input past error cases. Alternatively, the registration unit can automatically collect past error cases and register them in the database. For example, the registration unit can analyze past email data, extract error cases, and register them in the database. Specifically, the registration unit has an algorithm that periodically scans logs from the company's email servers and communication tools and automatically extracts error cases. This algorithm uses natural language processing technology to analyze the content of emails and messages and identify error patterns. For example, if a particular keyword or phrase appears frequently, it is determined that it is likely to be the cause of an error and is registered in the database. The registration unit also provides an interface for users to manually input error cases. This allows users to add important error cases to the database based on their past experience and knowledge. Furthermore, the registration unit classifies and tags error cases to enable efficient searching and referencing of information within the database. For example, errors can be categorized into different types, such as technical errors, communication errors, and procedural errors, and each error case can be assigned a tag related to that category. This allows users to quickly search and refer to past error cases based on specific categories or tags.

[0070] The retrieval unit retrieves emails. For example, it can periodically scan emails and retrieve them based on specific triggers. For instance, it can scan emails daily, weekly, or at specific times. It can also retrieve emails triggered by the appearance of specific keywords or emails from specific senders. Specifically, the retrieval unit accesses the company's email server and scans email data at specified time intervals. During the scan, all content, including the email subject, body, and attachments, is targeted. Furthermore, the retrieval unit has a filtering function to prioritize the retrieval of emails containing specific keywords or phrases. For example, it automatically detects and retrieves emails containing keywords such as "important," "urgent," or "confirmation." It is also possible to set triggers based on emails from specific senders or recipients. This allows the retrieval unit to efficiently retrieve emails without missing important communications. Additionally, the retrieval unit temporarily stores the retrieved email data, making it accessible to the analysis unit. The stored email data is encrypted as a security measure to protect it from unauthorized access. This allows the acquisition unit to safely and efficiently acquire and store email data, thereby improving the overall reliability of the system.

[0071] The analysis unit uses generative AI to analyze the language and context within emails acquired by the acquisition unit. For example, the analysis unit analyzes the frequency of occurrence of specific keywords and the semantic analysis of the context. Specifically, the analysis unit uses generative AI to analyze the text data of emails and extract patterns in language and context. In particular, the generative AI utilizes natural language processing techniques to analyze the email content in detail. For example, it calculates the frequency of occurrence of words and phrases within emails and detects specific patterns. It also performs contextual analysis to determine the intentions and emotions contained within the email content. The generative AI compares the current email with a database of past error cases to identify similar patterns and detect high-risk communications. For example, if an error occurred in the past due to specific language or context, it checks whether similar patterns are present in the current email. Furthermore, the generative AI can classify the email content into different categories, such as technical errors, communication errors, and procedural errors. This allows the analysis unit to quickly and accurately analyze acquired email data and identify potential risks. Additionally, the analysis unit visualizes the analysis results and provides a dashboard to present them clearly to the user. This allows users to intuitively understand the analysis results and take quick action.

[0072] The prediction unit compares the analysis results from the analysis unit with the results from the database to predict future risks. For example, the prediction unit predicts risks using correlation analysis with past data or machine learning models. For instance, if errors occurred in the past due to specific wording or context, the prediction unit checks whether similar patterns are present in current emails. Specifically, the prediction unit uses machine learning algorithms to compare past error data with current email data to identify high-risk patterns. For example, if errors occurred in the past due to "insufficient confirmation" or "misunderstanding," the prediction unit detects whether similar wording or context is included in current emails. The prediction unit also performs correlation analysis to evaluate the extent to which specific wording or context influences the occurrence of errors. This allows the prediction unit to predict future risks with high accuracy and provide information for taking appropriate countermeasures. Furthermore, the prediction unit can update prediction results in real time to respond to the latest situation. For example, each time a new email is acquired, the prediction unit immediately updates the analysis results and performs a risk assessment. The prediction unit can also perform trend analysis based on past data to predict long-term risk fluctuations. This allows the prediction unit to provide highly accurate risk predictions based on the latest information at all times, supporting quick and appropriate responses.

[0073] The proposal department proposes preventative measures based on the prediction results from the prediction department. For example, the proposal department proposes specific action guidelines and methods of raising awareness. For instance, it may instruct users to avoid certain wording or provide advice to clarify context. Specifically, the proposal department uses generative AI to propose specific improvement measures based on the content of emails. For example, if a high risk is predicted due to "insufficient confirmation," the proposal department will instruct users to reconfirm the content of the email and provide specific points to check. Also, if a high risk is predicted due to "misunderstanding," the proposal department will propose specific phrases and expressions to clarify the context. Furthermore, the proposal department can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. For example, it collects feedback on the results of users acting on the suggestions and uses that data to improve the suggestion algorithm. The proposal department can also reliably transmit information using multiple communication methods. For example, it can ensure that important information is delivered reliably by using not only email notifications but also pop-up notifications and alerts on the dashboard. This allows the proposal department to provide users with quick and specific preventative measures and minimize the risk of communication errors.

[0074] The analysis unit can analyze the wording and context of emails using a generative AI. For example, the analysis unit can analyze the text data of an email using a generative AI. For example, the analysis unit can input a prompt to the generative AI such as "Please analyze the wording and context of this email," and the generative AI will output the analysis results. The analysis unit can also analyze the frequency of occurrence of specific keywords using a generative AI. For example, the analysis unit can input a prompt to the generative AI such as "Please analyze the frequency of occurrence of a specific keyword in this email," and the generative AI will output the analysis results. The analysis unit can also perform semantic analysis of the context using a generative AI. For example, the analysis unit can input a prompt to the generative AI such as "Please analyze the meaning of the context of this email," and the generative AI will output the analysis results. As a result, using a generative AI improves the accuracy of the analysis of the wording and context of emails. Some or all of the above-described processes in the analysis unit may be performed using a generative AI, or they may not be performed using a generative AI. For example, the analysis unit can input the text data of an email into a generative AI and have the generative AI perform the analysis of wording and context.

[0075] The registration unit can analyze the language and context within emails from past error cases and register them in a database. For example, the registration unit analyzes the language and context within emails from past error cases. For example, the registration unit analyzes the frequency of occurrence of specific keywords and the semantic analysis of the context. The registration unit also registers the analysis results in a database. For example, the registration unit can manually input the analysis results into the database. Alternatively, the registration unit can automatically register the analysis results into the database. For example, the registration unit can use an algorithm to automatically register the analysis results into the database. This improves the accuracy of future risk predictions by analyzing past error cases in detail and registering them in the database. Some or all of the above processing in the registration unit may be performed using AI, or not. For example, the registration unit can input email data from past error cases into AI and have the AI ​​perform the analysis of language and context.

[0076] The retrieval unit can periodically scan emails and retrieve them based on triggers. For example, the retrieval unit can periodically scan emails. For example, the retrieval unit can scan emails daily, weekly, or at specific times. The retrieval unit can also retrieve emails based on specific triggers. For example, the retrieval unit can retrieve emails based on the appearance of specific keywords or emails from specific senders. This ensures that important emails are not missed by periodically scanning emails and retrieving them based on specific triggers. Some or all of the above processes in the retrieval unit may be performed using AI, for example, or not. For example, the retrieval unit can have AI perform email scanning and triggered email retrieval.

[0077] The proposal department can propose specific preventative measures. For example, the proposal department can propose specific action guidelines. For example, the proposal department can advise against certain wording. The proposal department can also provide advice on clarifying context. For example, the proposal department can provide specific advice on clarifying the context of an email. By proposing specific preventative measures, future communication errors can be prevented. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can have AI execute the proposal of preventative measures.

[0078] The registration unit can estimate the user's emotions and adjust the timing of error registration based on the estimated emotions. For example, if the user is stressed, the registration unit may postpone error registration and prompt registration when the user is relaxed. Alternatively, if the user is focused, the registration unit may prompt registration of errors at that time and allow for detailed information input. Furthermore, if the user is tired, the registration unit may provide a simplified registration form, allowing for the addition of details later. This allows for efficient registration by adjusting the timing of error registration 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 registration unit may be performed using AI or not. For example, the registration unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0079] The registration unit can analyze past error cases and determine registration priorities based on the severity of the errors. For example, the registration unit can immediately register serious error cases and postpone minor ones. It can also prioritize registration of errors with a wide impact and register those with a narrow impact later. Furthermore, it can prioritize registration of errors with a high recurrence rate and register those with a low recurrence rate later. This allows for the priority registration of important error cases based on their severity. Some or all of the above processing in the registration unit may be performed using AI, for example, or not. For example, the registration unit can input data on past error cases into an AI and have the AI ​​evaluate the severity of the errors and determine the registration priorities.

[0080] The registration unit can adjust the level of detail in the registration of error cases based on the frequency of the errors. For example, the registration unit can register frequently occurring errors in detail and rarely occurring errors in a simplified manner. The registration unit can also register high-frequency errors with detailed cause analysis. Furthermore, the registration unit can register low-frequency errors with only a brief summary, allowing for the addition of details later. This enables efficient registration of error cases by adjusting the level of detail based on the frequency of errors. Some or all of the above processing in the registration unit may be performed using AI, for example, or without AI. For example, the registration unit can input error frequency data into AI and have the AI ​​adjust the level of detail of the registration.

[0081] The registration unit can estimate the user's emotions and adjust the error registration method based on the estimated emotions. For example, if the user is stressed, the registration unit can provide a simple interface and minimize the input steps. If the user is relaxed, the registration unit can also provide detailed input options and suggest a customizable input method. Furthermore, if the user is in a hurry, the registration unit can prioritize voice input to allow for quick error registration. This enables efficient registration by adjusting the error registration method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the registration unit may be performed using AI or not. For example, the registration unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0082] The registration unit can register error cases while considering the location and time of the error. For example, the registration unit can automatically acquire the location where the error occurred and reflect it during registration. The registration unit can also consider the time of the error and prioritize the registration of errors that occur during the same time period. Furthermore, if the location of errors is concentrated in a particular department or team, the registration unit can reflect that information during registration. This allows for efficient registration of error cases by considering the location and time of the error. Some or all of the above processing in the registration unit may be performed using AI, for example, or not. For example, the registration unit can input data on the location and time of the error into the AI ​​and have the AI ​​determine the priority of registration.

[0083] The registration unit can determine the priority of registration when registering error cases, taking into account the scope of the error's impact. For example, the registration unit can prioritize registration of errors with a wide scope of impact and register errors with a narrow scope later. Furthermore, the registration unit can immediately register errors with a significant impact and postpone registration of errors with a minor impact. Additionally, the registration unit can prioritize registration of errors affecting multiple departments and register errors limited to a single department later. This allows for the priority registration of important error cases by considering the scope of the error's impact. Some or all of the above processing in the registration unit may be performed using AI, or not. For example, the registration unit can input data on the scope of the error's impact into the AI ​​and have the AI ​​determine the registration priority.

[0084] The retrieval unit can estimate the user's emotions and adjust the timing of email retrieval based on the estimated emotions. For example, if the user is stressed, the retrieval unit can delay email retrieval and retrieve it when the user is relaxed. Alternatively, if the user is focused, the retrieval unit can retrieve emails at that time and prioritize displaying important emails. Furthermore, if the user is tired, the retrieval unit can provide a simplified email list so that the details can be reviewed later. This allows for efficient email retrieval by adjusting the timing of email retrieval 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 retrieval unit may be performed using AI or not. For example, the retrieval unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0085] The retrieval unit can analyze the user's past email history and select the optimal retrieval method. For example, the retrieval unit can prioritize retrieving emails from people the user has frequently communicated with in the past. The retrieval unit can also automatically filter important emails from the user's past email history. Furthermore, the retrieval unit can analyze the user's past email history and prioritize retrieving emails containing specific keywords. In this way, the optimal email retrieval method can be selected by analyzing the user's past email history. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or without AI. For example, the retrieval unit can input the user's past email history data into AI and have the AI ​​select the optimal retrieval method.

[0086] The retrieval unit can filter emails based on the user's current projects and areas of interest when retrieving them. For example, the retrieval unit can prioritize retrieving emails related to projects the user is currently working on. The retrieval unit can also filter relevant emails based on the user's areas of interest. Furthermore, if the user is focused on a specific project, the retrieval unit can prioritize retrieving emails related to that project. This allows for the priority retrieval of important emails by filtering them based on the user's current projects and areas of interest. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or not. For example, the retrieval unit can input the user's project data and area of ​​interest data into an AI and have the AI ​​perform the email filtering.

[0087] The retrieval unit can estimate the user's emotions and determine the priority of emails to retrieve based on the estimated emotions. For example, if the user is stressed, the retrieval unit can prioritize displaying important emails and postpone other emails. If the user is relaxed, the retrieval unit can also display all emails equally. Furthermore, if the user is in a hurry, the retrieval unit can prioritize displaying urgent emails and allow other emails to be reviewed later. This allows important emails to be displayed preferentially by prioritizing emails 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 retrieval unit may be performed using AI or not. For example, the retrieval unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0088] The retrieval unit can prioritize retrieving highly relevant emails by considering the user's geographical location information when retrieving emails. For example, if the user is in a specific location, the retrieval unit will prioritize retrieving emails related to that location. Furthermore, if the user is on a business trip, the retrieval unit can prioritize retrieving emails related to the business trip destination. Additionally, if the user is in the office, the retrieval unit can prioritize retrieving emails related to the office. This allows for the prioritization of highly relevant emails by considering the user's geographical location information. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or without AI. For example, the retrieval unit can input the user's geographical location data into AI and have the AI ​​retrieve highly relevant emails.

[0089] The retrieval unit can analyze the user's social media activity when retrieving emails and retrieve relevant emails. For example, the retrieval unit can prioritize retrieving emails related to topics mentioned by the user on social media. It can also prioritize retrieving emails from people the user follows on social media. Furthermore, the retrieval unit can analyze the user's social media activity and filter relevant emails. This allows for the priority retrieval of relevant emails by analyzing the user's social media activity. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or not. For example, the retrieval unit can input the user's social media activity data into AI and have the AI ​​retrieve relevant emails.

[0090] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the user is tense, the analysis unit can provide simple and easy-to-understand analysis results. If the user is relaxed, the analysis unit can also provide detailed analysis results. Furthermore, if the user is in a hurry, the analysis unit can provide concise analysis results. In this way, by adjusting the presentation of the analysis according to the user's emotions, it is possible to provide highly easy-to-understand analysis results. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0091] The analysis unit can adjust the level of detail in its analysis based on the importance of each email. For example, it can analyze important emails in detail and less important emails in a simplified manner. It can also analyze high-importance emails, including detailed root cause analysis. Furthermore, it can analyze low-importance emails with only a brief overview, allowing for the addition of details later. This allows for efficient analysis by adjusting the level of detail based on the importance of each email. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input email importance data into AI and have the AI ​​adjust the level of detail in its analysis.

[0092] The analysis unit can apply different analysis algorithms depending on the email category during analysis. For example, the analysis unit can apply a business-specific analysis algorithm to business emails. It can also apply a private-specific analysis algorithm to private emails. Furthermore, it can apply a spam-specific analysis algorithm to spam emails. This improves analysis accuracy by applying the most appropriate analysis algorithm for each email category. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input email category data into AI and have the AI ​​apply different analysis algorithms.

[0093] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the user is in a hurry, the analysis unit can provide a short, concise analysis result. If the user is relaxed, the analysis unit can also provide a detailed analysis result. Furthermore, if the user is excited, the analysis unit can provide a visually stimulating analysis result. By adjusting the length of the analysis according to the user's emotions, highly visual analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0094] The analysis unit can determine the priority of analysis based on the email sending date during the analysis process. For example, the analysis unit may prioritize the analysis of recently sent emails and postpone older emails. It can also prioritize the analysis of emails sent at important times. Furthermore, it can prioritize the analysis of emails related to specific events. This enables efficient analysis by determining the priority of analysis based on the email sending date. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input email sending date data into AI and have the AI ​​determine the analysis priority.

[0095] The analysis unit can adjust the order of analysis based on the relevance of the emails during the analysis process. For example, the analysis unit can prioritize the analysis of highly relevant emails and postpone the analysis of less relevant emails. It can also prioritize the analysis of emails related to a specific project. Furthermore, it can prioritize the analysis of emails related to the user's areas of interest. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the emails. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input email relevance data into an AI and have the AI ​​adjust the order of analysis.

[0096] The prediction unit can estimate the user's emotions and adjust the risk prediction criteria based on the estimated user emotions. For example, if the user is tense, the prediction unit can set stricter risk prediction criteria. Conversely, if the user is relaxed, the prediction unit can also set looser risk prediction criteria. Furthermore, if the user is in a hurry, the prediction unit can set rapid risk prediction criteria. This allows for accurate risk prediction by adjusting the risk prediction criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI 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 using AI. For example, the prediction unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0097] The prediction unit can predict current risk by referring to past risk data during the prediction process. For example, the prediction unit predicts current risk based on past risk data. The prediction unit can also extract specific patterns from past risk data and predict current risk. Furthermore, the prediction unit can analyze past risk data and quantitatively evaluate current risk. This allows for accurate prediction of current risk by referring to past risk data. Some or all of the above processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can input past risk data into AI and have the AI ​​perform the prediction of current risk.

[0098] The prediction unit can apply different risk prediction methods to each email category during prediction. For example, the prediction unit can apply a business-specific risk prediction method to business emails. It can also apply a private-specific risk prediction method to private emails. Furthermore, it can apply a spam-specific risk prediction method to spam emails. This improves the accuracy of risk prediction by applying the most appropriate risk prediction method to each email category. 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 email category data into AI and have the AI ​​apply different risk prediction methods.

[0099] The prediction unit can estimate the user's emotions and adjust the importance of risk predictions based on the estimated emotions. For example, if the user is stressed, the prediction unit can set the importance of risk predictions higher. Conversely, if the user is relaxed, the prediction unit can also set the importance of risk predictions lower. Furthermore, if the user is in a hurry, the prediction unit can set the importance of predicting risks quickly. This allows for appropriate risk predictions by adjusting the importance of risk predictions 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 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 using AI. For example, the prediction unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0100] The prediction unit can analyze changes in risk based on the timing of email transmission during the prediction process. For example, the prediction unit may prioritize the analysis of risks associated with recently sent emails. It can also prioritize the analysis of risks associated with emails sent at important times. Furthermore, it can prioritize the analysis of risks associated with emails related to specific events. This enables accurate risk prediction by analyzing changes in risk based on the timing of email transmission. 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 email transmission timing data into AI and have the AI ​​perform the analysis of changes in risk.

[0101] The forecasting unit can analyze risk by referring to relevant market data for emails during the forecasting process. For example, the forecasting unit analyzes email risk based on relevant market data. The forecasting unit can also predict email risk by referring to market trends. Furthermore, the forecasting unit can analyze market data and quantitatively evaluate email risk. This allows for accurate risk analysis by referring to relevant market data for emails. 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 into AI and have the AI ​​perform the risk analysis.

[0102] The suggestion unit can estimate the user's emotions and adjust the way preventive measures are presented based on the estimated emotions. For example, if the user is tense, the suggestion unit can provide simple and easily understandable preventive measures. If the user is relaxed, the suggestion unit can also provide detailed preventive measures. Furthermore, if the user is in a hurry, the suggestion unit can provide concise preventive measures. This allows for the provision of easily understandable preventive measures by adjusting the presentation of preventive measures 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 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 suggestion unit may be performed using AI or not using AI. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0103] The proposal unit can adjust the level of detail of its recommendations based on the severity of the risk when proposing preventive measures. For example, it can propose detailed preventive measures for significant risks and simplified preventive measures for minor risks. It can also propose detailed preventive measures if the risk has a wide scope of impact. Furthermore, it can propose detailed preventive measures if the risk has a high recurrence rate. This allows for the provision of appropriate preventive measures by adjusting the level of detail of recommendations based on the severity of the risk. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input risk severity data into AI and have the AI ​​adjust the level of detail of the recommendations.

[0104] The proposal unit can apply different proposal algorithms depending on the risk category when proposing preventive measures. For example, the proposal unit can propose business-specific preventive measures for business risks. It can also propose private-specific preventive measures for private risks. Furthermore, it can propose spam-specific preventive measures for spam risks. This improves the accuracy of preventive measures by applying the most appropriate proposal algorithm for each risk category. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not. For example, the proposal unit can input risk category data into an AI and have the AI ​​apply different proposal algorithms.

[0105] The suggestion unit can estimate the user's emotions and adjust the length of the precautions based on the estimated emotions. For example, if the user is in a hurry, the suggestion unit can provide short, concise precautions. If the user is relaxed, the suggestion unit can also provide detailed precautions. Furthermore, if the user is excited, the suggestion unit can provide visually stimulating precautions. By adjusting the length of the precautions according to the user's emotions, highly visible precautions can be provided. 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 processing described above in the suggestion unit may be performed using AI or not using AI. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0106] The proposal unit can prioritize preventive measures based on when the risks occurred. For example, the proposal unit may prioritize preventive measures for recently occurring risks. It can also prioritize preventive measures for risks that occurred at critical times. Furthermore, it can prioritize preventive measures for risks associated with specific events. This allows for the provision of appropriate preventive measures by prioritizing proposals based on when the risks occurred. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not. For example, the proposal unit can input risk occurrence timing data into AI and have the AI ​​perform the determination of proposal priorities.

[0107] The suggestion unit can adjust the order of suggestions based on the relevance of the risks when proposing preventive measures. For example, the suggestion unit can prioritize suggesting preventive measures for highly relevant risks. It can also prioritize suggesting preventive measures for risks related to a specific project. Furthermore, it can prioritize suggesting preventive measures for risks related to the user's area of ​​interest. This allows for the provision of appropriate preventive measures by adjusting the order of suggestions based on the relevance of the risks. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not. For example, the suggestion unit can input risk relevance data into AI and have the AI ​​perform the adjustment of the suggestion order.

[0108] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0109] The communication error prevention system can also include a feedback unit. The feedback unit evaluates the effectiveness of the preventative measures provided by the suggestion unit and feeds the evaluation results back into a database. For example, the feedback unit monitors the quality of communication after employees implement the suggested preventative measures and evaluates whether improvements have been made. The feedback unit can also collect feedback from employees to verify whether the suggested preventative measures were actually effective. Furthermore, the feedback unit can adjust the suggestion unit's algorithm based on the evaluation results to propose more effective preventative measures. This allows the system to continuously learn and improve the accuracy of its preventative measures.

[0110] The analysis unit can estimate the user's emotions and adjust the analysis priority based on that estimation. For example, if the user is stressed, it can prioritize analyzing important emails and postpone other emails. If the user is relaxed, it can analyze all emails equally. Furthermore, if the user is in a hurry, it can prioritize analyzing urgent emails and analyze other emails later. This allows for the rapid analysis of important emails by adjusting the analysis priority according to the user's emotions.

[0111] The registration unit can analyze past error cases and adjust the level of detail in the registration based on the cause of the error. For example, technical errors can be registered in detail, while communication errors can be registered in a simplified manner. Procedural errors can also be registered with detailed procedures. Furthermore, if there are multiple causes for the error, the registration can include a detailed analysis of each cause. This allows for efficient registration of error cases by adjusting the level of detail based on the cause of the error.

[0112] The retrieval unit can estimate the user's emotions and adjust how emails are retrieved based on those emotions. For example, if the user is stressed, only important emails will be retrieved, and other emails will be retrieved later. If the user is relaxed, all emails can be retrieved at once. Furthermore, if the user is in a hurry, urgent emails can be prioritized, and other emails can be retrieved later. This allows for efficient email retrieval by adjusting the retrieval method according to the user's emotions.

[0113] The suggestion function can estimate the user's emotions and adjust the way preventative measures are suggested based on those emotions. For example, if the user is stressed, it can provide simple and easily visible preventative measures. If the user is relaxed, it can provide more detailed preventative measures. Furthermore, if the user is in a hurry, it can provide concise preventative measures. By adjusting the way preventative measures are suggested according to the user's emotions, it is possible to provide highly visible preventative measures.

[0114] A communication error prevention system can also include a training department. This department provides employees with training to improve their communication skills. For example, it can conduct simulations based on past error cases, allowing employees to learn by actually experiencing the mistakes. The training department can also offer courses teaching basic communication rules and best practices. Furthermore, it can evaluate employees' communication skills and provide individual feedback. This helps improve employees' communication skills and prevent errors from occurring.

[0115] The prediction unit can estimate the user's emotions and adjust the accuracy of the risk prediction based on those emotions. For example, if the user is stressed, detailed data can be used to improve the accuracy of the risk prediction. Conversely, if the user is relaxed, the accuracy of the risk prediction can be relaxed. Furthermore, if the user is in a hurry, simplified data can be used to quickly predict the risk. This allows for accurate risk prediction by adjusting the accuracy of the risk prediction according to the user's emotions.

[0116] The communication error prevention system can also include a notification function. This function notifies employees in real time of important or high-risk emails. For example, it can instantly notify employees of emails containing specific keywords. It can also prioritize emails deemed high-risk based on past error cases. Furthermore, it can filter emails based on specific conditions set by employees, notifying only important emails. This ensures employees don't miss important emails and can respond accordingly.

[0117] The analysis unit can analyze not only the content of the email but also the relationship between the sender and recipient. For example, the analysis unit can analyze the past interactions between the sender and recipient to assess the depth of their relationship. It can also consider the positions and departments of the sender and recipient to evaluate the importance of the communication. Furthermore, the analysis unit can analyze the tone and emotions of past interactions between the sender and recipient to more accurately understand the context of the current email. This enables analysis that considers not only the content of the email but also the relationship between the sender and recipient.

[0118] The suggestion function can estimate the user's emotions and prioritize preventative measures based on those emotions. For example, if the user is stressed, it can prioritize suggesting important preventative measures and postpone others. If the user is relaxed, it can suggest all preventative measures equally. Furthermore, if the user is in a hurry, it can prioritize suggesting urgent preventative measures and suggest other measures later. This allows for the rapid suggestion of important preventative measures by prioritizing them according to the user's emotions.

[0119] The following briefly describes the processing flow for example form 2.

[0120] Step 1: The registration unit registers past error cases in the database. Past error cases include technical errors, communication errors, procedural errors, etc. The registration unit can either manually input past error cases or automatically collect and register them in the database. For example, it can analyze past email data, extract error cases, and register them in the database. Step 2: The retrieval unit retrieves emails. The retrieval unit periodically scans for emails and retrieves them based on specific triggers. For example, it can scan for emails daily, weekly, or at specific times of day. It can also retrieve emails based on the appearance of specific keywords or emails from specific senders. Step 3: The analysis unit uses a generation AI to analyze the language and context within the emails acquired by the acquisition unit. The analysis unit analyzes the frequency of occurrence of specific keywords and the semantic analysis of the context. For example, it analyzes the text data of the emails and extracts patterns of language and context. Step 4: The prediction unit compares the analysis results from the analysis unit with the results from the database to predict future risks. The prediction unit predicts risks using correlation analysis with past data and machine learning models. For example, if errors occurred in the past due to specific wording or context, it checks whether similar patterns can be seen in current emails. Step 5: The proposal team proposes preventive measures based on the prediction results from the forecasting team. The proposal team proposes specific action guidelines and methods for raising awareness. For example, they may instruct people to avoid certain wording or provide advice to clarify context.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] For example, each of the multiple elements, including the registration unit, acquisition unit, analysis unit, prediction unit, and proposal unit, is implemented by at least one of the smart device 14 and the data processing unit 12. For example, the registration unit is implemented by the specific processing unit 290 of the data processing unit 12 and registers past error cases in the database 24. The acquisition unit is implemented by the control unit 46A of the smart device 14 and acquires emails. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the wording and context of emails using generation AI. The prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and predicts future risks by comparing the analysis results with the database 24. The proposal unit is implemented by the control unit 46A of the smart device 14 and proposes specific preventive measures based on the prediction results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0125] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] For example, each of the multiple elements, including the registration unit, acquisition unit, analysis unit, prediction unit, and proposal unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the registration unit is implemented by the identification processing unit 290 of the data processing unit 12 and registers past error cases in the database 24. The acquisition unit is implemented by the control unit 46A of the smart glasses 214 and acquires emails. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the wording and context of emails using generation AI. The prediction unit is implemented by the identification processing unit 290 of the data processing unit 12 and predicts future risks by comparing the analysis results with the database 24. The proposal unit is implemented by the control unit 46A of the smart glasses 214 and proposes specific preventive measures based on the prediction results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0141] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] For example, each of the multiple elements, including the registration unit, acquisition unit, analysis unit, prediction unit, and proposal unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the registration unit is implemented by the specific processing unit 290 of the data processing unit 12 and registers past error cases in the database 24. The acquisition unit is implemented by the control unit 46A of the headset terminal 314 and acquires emails. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the wording and context of emails using generation AI. The prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and predicts future risks by comparing the analysis results with the database 24. The proposal unit is implemented by the control unit 46A of the headset terminal 314 and proposes specific preventive measures based on the prediction results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0157] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.).

[0170] 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.

[0171] 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.

[0172] 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.

[0173] For example, each of the multiple elements, including the registration unit, acquisition unit, analysis unit, prediction unit, and proposal unit, is implemented by at least one of the robot 414 and the data processing unit 12. For example, the registration unit is implemented by the specific processing unit 290 of the data processing unit 12 and registers past error cases in the database 24. The acquisition unit is implemented by the control unit 46A of the robot 414 and acquires emails. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the wording and context of emails using generating AI. The prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and predicts future risks by comparing the analysis results with the database 24. The proposal unit is implemented by the control unit 46A of the robot 414 and proposes specific preventive measures based on the prediction results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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."

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] (Note 1) A registration unit that registers past error cases in a database, The retrieval unit for obtaining emails, An analysis unit analyzes the wording or context within the email obtained by the acquisition unit, A prediction unit compares the analysis results from the aforementioned analysis unit with the results of a comparison with the aforementioned database and predicts the risk. The system includes a proposal unit that proposes preventive measures based on the prediction results from the prediction unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Use generative AI to analyze the wording and context of emails. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned registration unit is The wording and context in emails from past error cases are analyzed and registered in the aforementioned database. The system described in Appendix 1, characterized by the features described herein. (Note 4) The acquisition unit is, Regularly scan emails and retrieve them using triggers. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned proposal section is, We propose specific preventative measures. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned registration unit is The system estimates the user's emotions and adjusts the timing of error registration based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned registration unit is We analyze past error cases and determine registration priorities based on the severity of the errors. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned registration unit is When registering error cases, adjust the level of detail in the registration based on the frequency of the error. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned registration unit is The system estimates the user's emotions and adjusts the method of registering error cases based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned registration unit is When registering error cases, the registration is based on the location and time the error occurred. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned registration unit is When registering error cases, the priority of registration is determined by considering the scope of the error's impact. The system described in Appendix 1, characterized by the features described herein. (Note 12) The acquisition unit is, It estimates the user's emotions and adjusts the timing of email retrieval based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The acquisition unit is, Analyze the user's past email history and select the optimal method for retrieval. The system described in Appendix 1, characterized by the features described herein. (Note 14) The acquisition unit is, When retrieving emails, filtering is performed based on the user's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 15) The acquisition unit is, It estimates the user's emotions and determines the priority of emails to retrieve based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The acquisition unit is, When retrieving emails, the system prioritizes retrieving highly relevant emails by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 17) The acquisition unit is, When retrieving emails, the system analyzes the user's social media activity and retrieves relevant emails. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During analysis, the level of detail of the analysis is adjusted based on the importance of the email. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the email category. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit, It estimates the user's emotions and adjusts the length of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit, During analysis, the priority of the analysis is determined based on when the emails were sent. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the emails. The system described in Appendix 1, characterized by the features described herein. (Note 24) The prediction unit, We estimate user sentiment and adjust risk prediction criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The prediction unit, When making predictions, historical risk data is referenced to forecast current risks. The system described in Appendix 1, characterized by the features described herein. (Note 26) The prediction unit, When making predictions, different risk prediction methods are applied to each email category. The system described in Appendix 1, characterized by the features described herein. (Note 27) The prediction unit, It estimates the user's emotions and adjusts the importance of risk predictions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The prediction unit, When making predictions, we analyze changes in risk based on when the email was sent. The system described in Appendix 1, characterized by the features described herein. (Note 29) The prediction unit, When making predictions, we analyze risks by referring to relevant market data via email. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned proposal section is, The system estimates the user's emotions and adjusts the way preventative measures are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned proposal section is, When proposing preventive measures, adjust the level of detail of the proposal based on the severity of the risk. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned proposal section is, When proposing preventive measures, different proposal algorithms are applied depending on the risk category. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned proposal section is, The system estimates the user's emotions and adjusts the length of preventative measures based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned proposal section is, When proposing preventive measures, prioritize the proposals based on when the risk occurred. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned proposal section is, When proposing preventive measures, adjust the order of suggestions based on the relevance of the risks. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0193] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A registration unit that registers past error cases in a database, The retrieval unit for obtaining emails, An analysis unit analyzes the wording or context within the email obtained by the acquisition unit, A prediction unit compares the analysis results from the aforementioned analysis unit with the results of a comparison with the aforementioned database and predicts the risk. The system includes a proposal unit that proposes preventive measures based on the prediction results from the prediction unit. A system characterized by the following features.

2. The aforementioned analysis unit, We use generative AI to analyze the wording and context of emails. The system according to feature 1.

3. The aforementioned registration unit is The wording and context in emails from past error cases are analyzed and registered in the aforementioned database. The system according to feature 1.

4. The acquisition unit is, Regularly scan emails and retrieve them using triggers. The system according to feature 1.

5. The aforementioned proposal section is, We propose specific preventative measures. The system according to feature 1.

6. The aforementioned registration unit is The system estimates the user's emotions and adjusts the timing of error registration based on those estimated emotions. The system according to feature 1.

7. The aforementioned registration unit is We analyze past error cases and determine registration priorities based on the severity of the errors. The system according to feature 1.

8. The aforementioned registration unit is When registering error cases, adjust the level of detail in the registration based on the frequency of the error. The system according to feature 1.

9. The aforementioned registration unit is The system estimates the user's emotions and adjusts the method of registering error cases based on those estimated emotions. The system according to feature 1.

Images