system

Abstract

The system according to the embodiment aims to automatically detect problems contained in the contents of an email and provide an appropriate solution. [Solution] A system according to an embodiment includes an analysis unit, a detection unit, a warning unit, an advice unit, and a confidentiality management unit. The analysis unit analyzes the content of emails. The detection unit detects problems based on the content analyzed by the analysis unit. The warning unit issues a warning about problems detected by the detection unit. The advice unit provides advice on how to improve the problem based on the content warned about by the warning unit. The confidentiality management unit keeps the content of the advice provided by the advice unit confidential and automatically deletes it after, for example, 30 days.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the drawback of making it difficult to automatically detect and appropriately address issues such as power harassment, sexual harassment, and unconscious bias contained in email content.

[0005] The system according to the embodiment aims to automatically detect problems contained in the contents of an email and provide an appropriate solution. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a detection unit, a warning unit, an advice unit, and a confidentiality management unit. The analysis unit analyzes the content of the email. The detection unit detects problems based on the content analyzed by the analysis unit. The warning unit issues a warning about the problem detected by the detection unit. The advice unit provides advice on how to improve the problem based on the content warned about by the warning unit. The confidentiality management unit keeps the content of the advice provided by the advice unit confidential and automatically deletes it after, for example, 30 days. [Effects of the Invention]

[0007] The system according to the embodiment can automatically detect problems contained in the contents of an email and provide an appropriate solution. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

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

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) An AI system according to an embodiment of the present invention uses natural language processing technology to analyze the content of emails sent by managers and above, or by all employees, and provides warnings and advice on how to improve against behaviors that individuals may not be aware of, such as power harassment, sexual harassment, and unconscious bias. In this AI system, the AI ​​first analyzes the content of the email and detects problematic behavior. Next, it issues warnings about the detected problems and provides advice on how to improve. Furthermore, certain confidentiality rules must be disclosed when understanding the content, including personnel matters. For example, when analyzing email content, the AI ​​uses natural language processing technology to analyze the context and wording of the email to detect problematic behaviors such as power harassment, sexual harassment, and unconscious bias. For example, the AI ​​detects offensive language or discriminatory language. Next, it issues warnings about the detected problems. The AI ​​sends warning messages to senders of emails containing problematic behaviors. For example, it sends a message such as, "This expression may be power harassment. Please revise it to an appropriate expression." It then provides advice on how to improve. AI can suggest specific ways to improve problematic behavior. For example, it can provide advice such as, "In this case, it would be better to use the following expression." Furthermore, certain confidentiality rules must be adhered to when identifying content, including that of human resources. Specifically, the details of problems detected by AI and warning messages should only be visible to the sender and the human resources department. Furthermore, the details of problems and warning messages should be automatically deleted after a certain period of time. This system can quickly detect issues such as power harassment, sexual harassment, and unconscious bias in emails used by managers and above or all employees, and provide appropriate warnings and advice on how to improve them. This can improve the work environment and raise employee awareness. This allows the AI ​​system to improve the work environment and raise employee awareness.

[0029] The AI ​​system according to the embodiment includes an analysis unit, a detection unit, a warning unit, an advice unit, and a confidentiality management unit. The analysis unit analyzes the content of an email. The analysis unit analyzes the context and wording of the email using, for example, natural language processing technology. Natural language processing technology includes morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to divide words in the email, grammatical analysis to analyze the structure of the sentence, and semantic analysis to understand the meaning of the sentence. The detection unit detects problems based on the content analyzed by the analysis unit. The detection unit detects, for example, offensive language and discriminatory language. For example, the detection unit detects insulting language and threatening language and identifies racist and sexist language. The warning unit issues a warning about the problem detected by the detection unit. For example, the warning unit sends a warning message to the sender of an email containing problematic language or behavior. For example, the warning unit sends a message such as, "This expression may be power harassment. Please revise it to an appropriate expression." The advice department provides advice on how to improve based on the content of the warnings issued by the warning department. For example, the advice department suggests specific ways to improve problematic words and actions. For example, the advice department may provide advice such as, "In this case, it would be good to use the following expression." The confidentiality management department keeps the content of the advice provided by the advice department confidential and automatically deletes it after a certain period of time. For example, the confidentiality management department may make it possible for only the sender and the human resources department to view the advice, and automatically delete it after, for example, 30 days. In this way, the AI ​​system analyzes the content of emails, detects problems, provides warnings and advice on how to improve, and performs confidentiality management, thereby improving the work environment and raising employee awareness.

[0030] The analysis unit can analyze the context and wording of an email using natural language processing technology. Natural language processing technology includes morphological analysis, grammatical analysis, semantic analysis, etc. For example, the analysis unit uses morphological analysis to divide the words in the email, uses grammatical analysis to analyze the structure of the sentence, and uses semantic analysis to understand the meaning of the sentence. In this way, the use of natural language processing technology allows the context and wording of the email to be accurately analyzed. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the content of the email into AI, which performs morphological analysis, grammatical analysis, and semantic analysis and outputs the analysis results.

[0031] The detection unit can detect offensive language and discriminatory expressions. The detection unit can detect, for example, insulting words and threatening expressions. For example, the detection unit can detect insulting words such as "idiot" and "die." The detection unit can also identify racist and sexist expressions. For example, the detection unit can detect discriminatory expressions such as "black people are inferior" and "women should stay at home." By detecting offensive language and discriminatory expressions, problematic speech and behavior can be discovered early. Some or all of the above-described processing in the detection unit can be performed using, for example, AI, or without AI. For example, the detection unit can input the content analyzed by the analysis unit into AI, which can then detect offensive language and discriminatory expressions.

[0032] The warning unit can send a warning message to the sender of an email containing problematic behavior. For example, the warning unit can send a message such as, "This expression may be power harassment. Please revise it to an appropriate expression." The warning unit can also display a pop-up notification to the sender of an email containing problematic behavior. For example, the warning unit can display a pop-up notification such as, "This expression may be power harassment. Do you really want to send it?" before sending the email. By doing so, by warning the sender of an email containing problematic behavior, it is possible to prevent the recurrence of the problem. Some or all of the above-described processing in the warning unit may be performed using, or without, AI. For example, the warning unit can input the problem detected by the detection unit into AI, which can then generate and send a warning message.

[0033] The advice unit can suggest specific ways to improve problematic behavior. For example, the advice unit provides advice such as, "In this case, it would be good to use the following expression." The advice unit can also suggest educational programs for problematic behavior. For example, the advice unit can provide advice such as, "To prevent this type of problem, please take the following educational program." The advice unit can also suggest specific guidelines for action. For example, the advice unit can provide advice such as, "In this case, it would be good to take the following action." This can promote problem resolution by suggesting specific ways to improve. Some or all of the above-described processing in the advice unit may be performed using, or without, AI. For example, the advice unit can input the content of the warning issued by the warning unit into AI, which can then generate and provide specific ways to improve.

[0034] The confidentiality management unit can ensure that only the sender and the human resources department can view the data and can automatically delete it after, for example, 30 days. The confidentiality management unit performs access control, for example, to ensure that only the sender and the human resources department can view the data. For example, the confidentiality management unit grants access rights only to the sender and the human resources department and does not grant access rights to other users. The confidentiality management unit can also encrypt data. For example, the confidentiality management unit decrypts the data when the sender and the human resources department view it and keeps the data encrypted when other users access it. Furthermore, the confidentiality management unit can set the timing of deletion to automatically delete the data after a certain period of time. For example, the confidentiality management unit can set the timing to automatically delete the data after 30 days. This allows only the sender and the human resources department to view the data and automatically delete it after a certain period of time, thereby managing issues while protecting privacy. Some or all of the above-mentioned processing in the confidentiality management unit may be performed using, or without, AI. For example, the confidentiality management unit can input the content of advice provided by the advice unit into AI, which can then set access control, data encryption, and the timing of deletion.

[0035] When analyzing email content, the analysis unit can optimize the analysis algorithm by referring to past email data. The analysis unit, for example, learns frequently occurring expressions from past email data and optimizes the analysis algorithm. For example, the analysis unit uses past email data to calculate the frequency of specific expressions and phrases and reflects this in the analysis algorithm. The analysis unit can also extract problematic patterns of speech and behavior from past email data and reflect this in the analysis algorithm. For example, the analysis unit uses past email data to learn patterns of offensive language and discriminatory language and reflect this in the analysis algorithm. Furthermore, the analysis unit can also build an analysis algorithm suited to a specific industry or corporate culture based on past email data. For example, the analysis unit learns expressions and language specific to a specific industry or corporate culture and reflects this in the analysis algorithm. By referring to past email data, the analysis algorithm can be optimized and the analysis accuracy can be improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input past email data into AI, which learns the data and optimizes the analysis algorithm.

[0036] The analysis unit can include not only the context and wording of emails, but also the time and frequency of email transmission in its analysis. For example, the analysis unit can analyze the time of email transmission and pay special attention to emails sent late at night. For example, the analysis unit can analyze the time of email transmission and apply a specific analysis algorithm to emails sent late at night. The analysis unit can also analyze the frequency of email transmission and perform special analysis on frequently sent emails. For example, the analysis unit can analyze the frequency of email transmission and apply a specific analysis algorithm to frequently sent emails. Furthermore, the analysis unit can analyze a combination of the time and frequency of email transmission to detect abnormal patterns. For example, the analysis unit can analyze the time and frequency of email transmission, detect abnormal patterns, and apply a specific analysis algorithm. By including the time and frequency of email transmission in the analysis, more detailed analysis is possible. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input data on the time and frequency of email transmission into AI, which can analyze the data and detect abnormal patterns.

[0037] When analyzing the content of an email, the analysis unit can take into account the sender's job title and department information. For example, if the sender is a manager, the analysis unit performs a particularly rigorous analysis. For example, the analysis unit reflects the sender's job title information in the analysis and applies a specific analysis algorithm to emails from managers. Furthermore, if the sender belongs to a specific department, the analysis unit can also take into account the characteristics of that department when performing the analysis. For example, the analysis unit reflects the sender's department information in the analysis and applies a specific analysis algorithm to emails from the specific department. Furthermore, the analysis unit can select an appropriate analysis algorithm based on the sender's job title and department information. For example, the analysis unit selects an optimal analysis algorithm based on the sender's job title and department information and performs the analysis. This enables more appropriate analysis by taking the sender's job title and department information into account. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the sender's job title and department information into AI, which then analyzes the data and selects an appropriate analysis algorithm.

[0038] When analyzing the content of an email, the analysis unit can refer to the sender's past behavioral history. The analysis unit, for example, refers to the sender's past email history and reflects specific patterns in the analysis. For example, the analysis unit may analyze the sender's past email history, calculate the frequency of specific expressions and phrases, and reflect this in the analysis algorithm. The analysis unit can also analyze trends in problematic behavior based on the sender's past behavioral history. For example, the analysis unit may analyze the sender's past behavioral history to identify trends in offensive language and discriminatory language and reflect this in the analysis algorithm. Furthermore, the analysis unit can adjust the accuracy of the analysis by taking the sender's past behavioral history into consideration. For example, the analysis unit may adjust the accuracy of the analysis based on the sender's past behavioral history to provide more appropriate analysis results. In this way, the accuracy of the analysis can be improved by referring to the sender's past behavioral history. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may input the sender's past behavioral history into AI, which then analyzes the data and optimizes the analysis algorithm.

[0039] The detection unit can detect not only offensive language and discriminatory expressions, but also subtle nuances and potential problems. For example, the detection unit detects offensive language and identifies problematic emails. For example, the detection unit detects insulting words such as "idiot" and "die." The detection unit can also detect discriminatory expressions and prompt appropriate action. For example, the detection unit detects discriminatory expressions such as "black people are inferior" and "women should stay at home." Furthermore, the detection unit can detect subtle nuances and potential problems and issue warnings. For example, the detection unit detects sarcastic and suggestive expressions and identifies potential problems. This allows for the early detection of a wider range of problems by detecting subtle nuances and potential problems. Some or all of the above-described processing in the detection unit may be performed using, or without, AI. For example, the detection unit can input the content analyzed by the analysis unit into AI, which can then detect offensive language, discriminatory expressions, subtle nuances, and potential problems.

[0040] The detection unit can improve the detection accuracy of a detected problem by referring to past similar cases. The detection unit, for example, improves the detection accuracy by referring to past similar cases. For example, the detection unit optimizes the detection algorithm based on past problem cases. The detection unit can also improve the detection accuracy by utilizing past case data. For example, the detection unit analyzes past problem cases, extracts specific patterns, and reflects them in the detection algorithm. The detection unit can also update the detection algorithm based on past similar cases. For example, the detection unit analyzes past similar cases and improves the detection algorithm. In this way, the detection accuracy can be improved by referring to past similar cases. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input past similar case data into AI, which analyzes the data and optimizes the detection algorithm.

[0041] The detection unit can display detection results for detected problems by taking into account the sender's job title and department information. For example, if the sender is a manager, the detection unit displays particularly strict detection results. For example, the detection unit reflects the sender's job title information in the detection results and displays specific detection results for emails from managers. Furthermore, if the sender belongs to a specific department, the detection unit can also display detection results by taking into account the characteristics of the department. For example, the detection unit reflects the sender's department information in the detection results and displays specific detection results for emails from the specific department. Furthermore, the detection unit can display appropriate detection results based on the sender's job title and department information. For example, the detection unit displays and analyzes optimal detection results based on the sender's job title and department information. This allows for more appropriate detection results to be provided by taking the sender's job title and department information into consideration. Some or all of the above-described processing in the detection unit may be performed using, or without, AI. For example, the detection unit can input the sender's job title and department information into AI, which then analyzes the data and displays appropriate detection results.

[0042] The detection unit can display the detection results for the detected problem by referring to the sender's past behavioral history. The detection unit, for example, refers to the sender's past email history and reflects specific patterns in the detection results. For example, the detection unit analyzes the sender's past email history, calculates the frequency of specific expressions and phrases, and reflects the results in the detection. The detection unit can also display trends in problematic behavior based on the sender's past behavioral history. For example, the detection unit analyzes the sender's past behavioral history, identifies trends in offensive language and discriminatory expressions, and reflects the results in the detection. Furthermore, the detection unit can adjust the accuracy of the detection results by taking the sender's past behavioral history into consideration. For example, the detection unit adjusts the accuracy of the detection results based on the sender's past behavioral history to provide more appropriate detection results. In this way, the accuracy of the detection results can be improved by referring to the sender's past behavioral history. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the sender's past behavioral history into the AI, which can then analyze the data and optimize the detection results.

[0043] When sending a warning message, the warning unit can generate an optimal message by referring to past warning history. The warning unit, for example, references past warning history to generate an optimal message. For example, the warning unit analyzes past warning history, extracts effective expressions, and reflects them in the message. The warning unit can also transmit a message at an appropriate timing based on the past warning history. For example, the warning unit analyzes past warning history and transmits a message at an optimal timing. Furthermore, the warning unit can customize the warning message based on the past warning history. For example, the warning unit analyzes past warning history to generate a message appropriate for a specific situation. This makes it possible to generate an optimal message and issue an effective warning by referring to the past warning history. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input past warning history data into AI, which analyzes the data and generates an optimal message.

[0044] When sending a warning message, the warning unit can customize the message taking into account the sender's job title and department information. For example, if the sender is a manager, the warning unit sends a particularly strict warning message. For example, the warning unit reflects the sender's job title information in the message and generates a specific message for managers. Furthermore, if the sender belongs to a specific department, the warning unit can customize the message taking into account the characteristics of the department. For example, the warning unit reflects the sender's department information in the message and generates a specific message for the specific department. Furthermore, the warning unit can generate an appropriate message based on the sender's job title and department information. For example, the warning unit generates and sends an optimal message based on the sender's job title and department information. In this way, by taking the sender's job title and department information into account, a more appropriate warning message can be generated. Some or all of the above-described processing in the warning unit may be performed, for example, using AI or without AI. For example, the warning unit can input the sender's job title and department information into the AI, which can then analyze the data and generate an appropriate message.

[0045] When sending a warning message, the warning unit can customize the message by referring to the sender's past behavioral history. The warning unit, for example, refers to the sender's past behavioral history and reflects a specific pattern in the message. For example, the warning unit analyzes the sender's past email sending history, calculates the frequency of specific expressions or phrases, and reflects the frequency in the message. The warning unit can also reflect effective expressions in the message based on the sender's past behavioral history. For example, the warning unit analyzes the sender's past behavioral history, extracts effective expressions, and reflects the expressions in the message. Furthermore, the warning unit can send the message at an appropriate timing by taking the sender's past behavioral history into consideration. For example, the warning unit analyzes the sender's past behavioral history and sends the message at an optimal timing. In this way, by referring to the sender's past behavioral history, a more effective warning message can be generated. Some or all of the above-described processing in the warning unit may be performed, for example, using AI or without AI. For example, the warning unit can input the sender's past behavioral history data into AI, which can then analyze the data and generate an appropriate message.

[0046] When sending a warning message, the warning unit can customize the message by taking into account the geographical location information of the sender. The warning unit, for example, references the geographical location information of the sender and reflects expressions appropriate for a specific region in the message. For example, the warning unit analyzes the location information of the sender, extracts expressions appropriate for a specific region, and reflects them in the message. The warning unit can also send the message at an appropriate time based on the geographical location information of the sender. For example, the warning unit analyzes the location information of the sender and sends the message at an optimal time. Furthermore, the warning unit can generate an effective warning message by taking into account the geographical location information of the sender. For example, the warning unit analyzes the location information of the sender, extracts effective expressions, and reflects them in the message. In this way, by taking the geographical location information of the sender into consideration, a more appropriate warning message can be generated. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the geographical location information of the sender into AI, which analyzes the data and generates an appropriate message.

[0047] When providing advice, the advice unit can generate optimal advice by referring to past advice history. The advice unit, for example, refers to past advice history and generates optimal advice. For example, the advice unit analyzes past advice history, extracts effective expressions, and reflects them in the advice. The advice unit can also provide advice at an appropriate timing based on the past advice history. For example, the advice unit analyzes past advice history and provides advice at an optimal timing. Furthermore, the advice unit can customize the content of the advice based on the past advice history. For example, the advice unit analyzes past advice history and generates advice appropriate for a specific situation. In this way, optimal advice can be generated by referring to the past advice history, and effective advice can be provided. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input past advice history data into AI, which analyzes the data and generates optimal advice.

[0048] When providing advice, the advice unit can customize the advice by taking into account the sender's job title and department information. For example, if the sender is a manager, the advice unit can provide particularly strict advice. For example, the advice unit can reflect the sender's job title information in the advice and generate specific advice for managers. Furthermore, if the sender belongs to a specific department, the advice unit can customize the advice by taking into account the characteristics of the department. For example, the advice unit can reflect the sender's department information in the advice and generate specific advice for the specific department. Furthermore, the advice unit can generate appropriate advice based on the sender's job title and department information. For example, the advice unit can generate and provide optimal advice based on the sender's job title and department information. In this way, more appropriate advice can be generated by taking the sender's job title and department information into consideration. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the sender's job title and department information into AI, which can analyze the data and generate appropriate advice.

[0049] When providing advice, the advice unit can customize the advice by referring to the sender's past behavioral history. The advice unit, for example, refers to the sender's past behavioral history and reflects specific patterns in the advice. For example, the advice unit analyzes the sender's past email sending history, calculates the frequency of specific expressions and phrases, and reflects the results in the advice. The advice unit can also reflect effective expressions in the advice based on the sender's past behavioral history. For example, the advice unit analyzes the sender's past behavioral history, extracts effective expressions, and reflects them in the advice. Furthermore, the advice unit can provide advice at an appropriate time by taking the sender's past behavioral history into consideration. For example, the advice unit analyzes the sender's past behavioral history and provides advice at an optimal time. This allows more effective advice to be generated by referring to the sender's past behavioral history. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the sender's past behavioral history data into AI, which then analyzes the data and generates appropriate advice.

[0050] When providing advice, the advice unit can customize the advice by taking into account the geographical location information of the sender. The advice unit, for example, references the geographical location information of the sender and reflects expressions appropriate for a specific region in the advice. For example, the advice unit analyzes the location information of the sender, extracts expressions appropriate for a specific region, and reflects them in the advice. The advice unit can also provide advice at an appropriate time based on the geographical location information of the sender. For example, the advice unit analyzes the location information of the sender and provides advice at an optimal time. Furthermore, the advice unit can generate effective advice by taking into account the geographical location information of the sender. For example, the advice unit analyzes the location information of the sender, extracts effective expressions, and reflects them in the advice. In this way, more appropriate advice can be generated by taking the geographical location information of the sender into account. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the geographical location information of the sender into AI, which analyzes the data and generates appropriate advice.

[0051] When performing secret management, the secret management unit can select an optimal management method by referring to past secret management history. The secret management unit, for example, refers to past secret management history and selects an optimal management method. For example, the secret management unit analyzes past secret management history and extracts and applies an effective management method. The secret management unit can also perform management at an appropriate time based on the past secret management history. For example, the secret management unit analyzes past secret management history and performs management at an optimal time. Furthermore, the secret management unit can customize the management method based on the past secret management history. For example, the secret management unit analyzes past secret management history and selects a management method suitable for a specific situation. This enables the optimal management method to be selected by referring to the past secret management history, enabling effective secret management. Some or all of the above-described processing in the secret management unit may be performed using, for example, AI, or may be performed without AI. For example, the secret management unit can input past secret management history data into AI, which analyzes the data and selects the optimal management method.

[0052] When performing confidentiality management, the confidentiality management unit can customize the management method taking into account the sender's job title and department information. For example, if the sender is a manager, the confidentiality management unit performs particularly strict confidentiality management. For example, the confidentiality management unit reflects the sender's job title information in the management method and applies a specific management method to managers. Furthermore, if the sender belongs to a specific department, the confidentiality management unit can also customize the management method taking into account the characteristics of the department. For example, the confidentiality management unit reflects the sender's department information in the management method and applies a specific management method to a specific department. Furthermore, the confidentiality management unit can select an appropriate management method based on the sender's job title and department information. For example, the confidentiality management unit selects and applies the optimal management method based on the sender's job title and department information. This makes it possible to select a more appropriate management method by taking the sender's job title and department information into account. Some or all of the above-described processing in the confidentiality management unit may be performed using, for example, AI, or may be performed without using AI. For example, the confidentiality management department can input the sender's job title and department information into the AI, which can then analyze the data and select an appropriate management method.

[0053] When performing confidentiality management, the confidentiality management unit can customize the management method by referring to the sender's past behavioral history. The confidentiality management unit, for example, refers to the sender's past behavioral history and reflects specific patterns in the management method. For example, the confidentiality management unit analyzes the sender's past email sending history, calculates the frequency of specific expressions or phrases, and reflects the frequency in the management method. The confidentiality management unit can also apply an effective management method based on the sender's past behavioral history. For example, the confidentiality management unit analyzes the sender's past behavioral history and extracts and applies an effective management method. Furthermore, the confidentiality management unit can perform management at an appropriate time by taking the sender's past behavioral history into consideration. For example, the confidentiality management unit analyzes the sender's past behavioral history and performs management at the optimal time. In this way, by referring to the sender's past behavioral history, a more effective management method can be selected. Some or all of the above-mentioned processing in the confidentiality management unit may be performed, for example, using AI or without AI. For example, the confidentiality management unit can input the sender's past behavioral history data into AI, which can then analyze the data and select an appropriate management method.

[0054] When performing confidentiality management, the confidentiality management unit can customize the management method by taking into account the geographical location information of the sender. For example, the confidentiality management unit refers to the geographical location information of the sender and applies a management method suitable for a specific region. For example, the confidentiality management unit analyzes the location information of the sender and extracts and applies a management method suitable for a specific region. The confidentiality management unit can also perform management at an appropriate time based on the geographical location information of the sender. For example, the confidentiality management unit analyzes the location information of the sender and performs management at the optimal time. Furthermore, the confidentiality management unit can select an effective management method by taking into account the geographical location information of the sender. For example, the confidentiality management unit analyzes the location information of the sender and extracts and applies an effective management method. In this way, a more appropriate management method can be selected by taking into account the geographical location information of the sender. Some or all of the above-described processing in the confidentiality management unit may be performed using, for example, AI, or may be performed without using AI. For example, the confidentiality management unit can input the geographical location information of the sender into AI, which analyzes the data and selects an appropriate management method.

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

[0056] When analyzing the content of an email, the analysis unit can refer to the sender's past behavioral history to perform the analysis. For example, the analysis unit can refer to the sender's past email history and reflect specific patterns in the analysis. For example, the analysis unit can analyze the sender's past email history, calculate the frequency of specific expressions and phrases, and reflect this in the analysis algorithm. The analysis unit can also analyze trends in problematic behavior based on the sender's past behavioral history. For example, the analysis unit can analyze the sender's past behavioral history to identify trends in offensive language and discriminatory language and reflect this in the analysis algorithm. Furthermore, the analysis unit can adjust the accuracy of the analysis by taking the sender's past behavioral history into consideration. For example, the analysis unit can adjust the accuracy of the analysis based on the sender's past behavioral history to provide more appropriate analysis results. In this way, the accuracy of the analysis can be improved by referring to the sender's past behavioral history. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the sender's past behavioral history into AI, which can analyze the data and optimize the analysis algorithm.

[0057] When sending a warning message, the warning unit can generate an optimal message by referring to past warning history. For example, the warning unit generates an optimal message by referring to past warning history. For example, the warning unit analyzes past warning history, extracts effective expressions, and reflects them in the message. The warning unit can also transmit a message at an appropriate timing based on the past warning history. For example, the warning unit analyzes past warning history and transmits a message at an optimal timing. Furthermore, the warning unit can customize the warning message based on the past warning history. For example, the warning unit analyzes past warning history and generates a message appropriate for a specific situation. This makes it possible to generate an optimal message and issue an effective warning by referring to the past warning history. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input past warning history data into AI, which analyzes the data and generates an optimal message.

[0058] When analyzing the content of an email, the analysis unit can take into account the sender's job title and department information. For example, if the sender is a manager, the analysis can be particularly strict. For example, the analysis unit can reflect the sender's job title information in the analysis and apply a specific analysis algorithm to emails from managers. Furthermore, if the sender belongs to a specific department, the analysis unit can also take into account the characteristics of that department when analyzing. For example, the analysis unit can reflect the sender's department information in the analysis and apply a specific analysis algorithm to emails from the specific department. Furthermore, the analysis unit can select an appropriate analysis algorithm based on the sender's job title and department information. For example, the analysis unit selects an optimal analysis algorithm based on the sender's job title and department information and performs the analysis. This enables more appropriate analysis by taking the sender's job title and department information into account. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the sender's job title and department information into AI, which can analyze the data and select an appropriate analysis algorithm.

[0059] The detection unit can improve the detection accuracy of a detected problem by referring to past similar cases. For example, the detection unit improves the detection accuracy by referring to past similar cases. For example, the detection unit optimizes the detection algorithm based on past problem cases. The detection unit can also improve the detection accuracy by utilizing past case data. For example, the detection unit analyzes past problem cases, extracts specific patterns, and reflects them in the detection algorithm. Furthermore, the detection unit can update the detection algorithm based on past similar cases. For example, the detection unit analyzes past similar cases and improves the detection algorithm. In this way, the detection accuracy can be improved by referring to past similar cases. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input past similar case data into AI, which analyzes the data and optimizes the detection algorithm.

[0060] When sending a warning message, the warning unit can customize the message taking into account the sender's job title and department information. For example, if the sender is a manager, the warning unit can send a particularly strict warning message. For example, the warning unit can reflect the sender's job title information in the message and generate a specific message for managers. Furthermore, if the sender belongs to a specific department, the warning unit can customize the message taking into account the characteristics of the department. For example, the warning unit can reflect the sender's department information in the message and generate a specific message for the specific department. Furthermore, the warning unit can generate an appropriate message based on the sender's job title and department information. For example, the warning unit can generate and send an optimal message based on the sender's job title and department information. In this way, by taking the sender's job title and department information into account, a more appropriate warning message can be generated. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the sender's job title and department information into AI, which can analyze the data and generate an appropriate message.

[0061] When providing advice, the advice unit can generate optimal advice by referring to the past advice history. The advice unit generates appropriate advice. For example, the advice unit analyzes past advice history, extracts effective expressions, and reflects them in the advice. The advice unit can also provide advice at an appropriate time based on the past advice history. For example, the advice unit analyzes past advice history and provides advice at an optimal time. The advice unit can also customize the content of the advice based on the past advice history. For example, the advice unit analyzes past advice history and generates advice suitable for a specific situation. This makes it possible to generate optimal advice and provide effective advice by referring to the past advice history. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input past advice history data into AI, which analyzes the data and generates optimal advice.

[0062] When performing confidentiality management, the confidentiality management unit can customize the management method by referring to the sender's past behavioral history. For example, the confidentiality management unit can refer to the sender's past behavioral history and reflect specific patterns in the management method. For example, the confidentiality management unit can analyze the sender's past email sending history, calculate the frequency of specific expressions or phrases, and reflect the results in the management method. The confidentiality management unit can also apply an effective management method based on the sender's past behavioral history. For example, the confidentiality management unit can analyze the sender's past behavioral history, extract an effective management method, and apply it. Furthermore, the confidentiality management unit can perform management at an appropriate time by taking the sender's past behavioral history into consideration. For example, the confidentiality management unit can analyze the sender's past behavioral history and perform management at the optimal time. This allows a more effective management method to be selected by referring to the sender's past behavioral history. Some or all of the above-described processing in the confidentiality management unit may be performed using, for example, AI, or may be performed without AI. For example, the confidentiality management unit can input the sender's past behavioral history data into AI, which can analyze the data and select an appropriate management method.

[0063] The processing flow of the first embodiment will be briefly explained below.

[0064] Step 1: The analysis unit analyzes the content of the email. For example, the analysis unit uses natural language processing technology to analyze the context and wording of the email. Natural language processing technology includes morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to divide the words in the email, grammatical analysis to analyze the structure of the sentence, and semantic analysis to understand the meaning of the sentence. Step 2: The detection unit detects problems based on the content analyzed by the analysis unit. The detection unit detects, for example, offensive language and discriminatory expressions. For example, the detection unit detects insulting words and threatening expressions, and identifies racist and sexist expressions. Step 3: The warning unit issues a warning about the problem detected by the detection unit. The warning unit, for example, sends a warning message to the sender of the email containing the problematic speech or behavior. For example, the warning unit sends a message such as, "This expression may be power harassment. Please revise it to an appropriate expression." Step 4: The advice unit provides advice on how to improve based on the content of the warning issued by the warning unit. The advice unit, for example, suggests specific ways to improve problematic speech or behavior. For example, the advice unit provides advice such as, "In this case, it would be good to use the following expression." Step 5: The confidentiality management unit keeps the advice provided by the advice unit confidential and automatically deletes it after a certain period of time. For example, the confidentiality management unit makes it possible for only the sender and the human resources department to view it, and automatically deletes it after, for example, 30 days.

[0065] (Example 2) An AI system according to an embodiment of the present invention uses natural language processing technology to analyze the content of emails sent by managers and above, or by all employees, and provides warnings and advice on how to improve against behaviors that individuals may not be aware of, such as power harassment, sexual harassment, and unconscious bias. In this AI system, the AI ​​first analyzes the content of the email and detects problematic behavior. Next, it issues warnings about the detected problems and provides advice on how to improve. Furthermore, certain confidentiality rules must be disclosed when understanding the content, including personnel matters. For example, when analyzing email content, the AI ​​uses natural language processing technology to analyze the context and wording of the email to detect problematic behaviors such as power harassment, sexual harassment, and unconscious bias. For example, the AI ​​detects offensive language or discriminatory language. Next, it issues warnings about the detected problems. The AI ​​sends warning messages to senders of emails containing problematic behaviors. For example, it sends a message such as, "This expression may be power harassment. Please revise it to an appropriate expression." It then provides advice on how to improve. AI can suggest specific ways to improve problematic behavior. For example, it can provide advice such as, "In this case, it would be better to use the following expression." Furthermore, certain confidentiality rules must be adhered to when identifying content, including that of human resources. Specifically, the details of problems detected by AI and warning messages should only be visible to the sender and the human resources department. Furthermore, the details of problems and warning messages should be automatically deleted after a certain period of time. This system can quickly detect issues such as power harassment, sexual harassment, and unconscious bias in emails used by managers and above or all employees, and provide appropriate warnings and advice on how to improve them. This can improve the work environment and raise employee awareness. This allows the AI ​​system to improve the work environment and raise employee awareness.

[0066] The AI ​​system according to the embodiment includes an analysis unit, a detection unit, a warning unit, an advice unit, and a confidentiality management unit. The analysis unit analyzes the content of an email. The analysis unit analyzes the context and wording of the email using, for example, natural language processing technology. Natural language processing technology includes morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to divide words in the email, grammatical analysis to analyze the structure of the sentence, and semantic analysis to understand the meaning of the sentence. The detection unit detects problems based on the content analyzed by the analysis unit. The detection unit detects, for example, offensive language and discriminatory language. For example, the detection unit detects insulting language and threatening language and identifies racist and sexist language. The warning unit issues a warning about the problem detected by the detection unit. For example, the warning unit sends a warning message to the sender of an email containing problematic language or behavior. For example, the warning unit sends a message such as, "This expression may be power harassment. Please revise it to an appropriate expression." The advice department provides advice on how to improve based on the content of the warnings issued by the warning department. For example, the advice department suggests specific ways to improve problematic words and actions. For example, the advice department may provide advice such as, "In this case, it would be good to use the following expression." The confidentiality management department keeps the content of the advice provided by the advice department confidential and automatically deletes it after a certain period of time. For example, the confidentiality management department may make it possible for only the sender and the human resources department to view the advice, and automatically delete it after, for example, 30 days. In this way, the AI ​​system analyzes the content of emails, detects problems, provides warnings and advice on how to improve, and performs confidentiality management, thereby improving the work environment and raising employee awareness.

[0067] The analysis unit can analyze the context and wording of an email using natural language processing technology. Natural language processing technology includes morphological analysis, grammatical analysis, semantic analysis, etc. For example, the analysis unit uses morphological analysis to divide the words in the email, uses grammatical analysis to analyze the structure of the sentence, and uses semantic analysis to understand the meaning of the sentence. In this way, the use of natural language processing technology allows the context and wording of the email to be accurately analyzed. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the content of the email into AI, which performs morphological analysis, grammatical analysis, and semantic analysis and outputs the analysis results.

[0068] The detection unit can detect offensive language and discriminatory expressions. The detection unit can detect, for example, insulting words and threatening expressions. For example, the detection unit can detect insulting words such as "idiot" and "die." The detection unit can also identify racist and sexist expressions. For example, the detection unit can detect discriminatory expressions such as "black people are inferior" and "women should stay at home." By detecting offensive language and discriminatory expressions, problematic speech and behavior can be discovered early. Some or all of the above-described processing in the detection unit can be performed using, for example, AI, or without AI. For example, the detection unit can input the content analyzed by the analysis unit into AI, which can then detect offensive language and discriminatory expressions.

[0069] The warning unit can send a warning message to the sender of an email containing problematic behavior. For example, the warning unit can send a message such as, "This expression may be power harassment. Please revise it to an appropriate expression." The warning unit can also display a pop-up notification to the sender of an email containing problematic behavior. For example, the warning unit can display a pop-up notification such as, "This expression may be power harassment. Do you really want to send it?" before sending the email. By doing so, by warning the sender of an email containing problematic behavior, it is possible to prevent the recurrence of the problem. Some or all of the above-described processing in the warning unit may be performed using, or without, AI. For example, the warning unit can input the problem detected by the detection unit into AI, which can then generate and send a warning message.

[0070] The advice unit can suggest specific ways to improve problematic behavior. For example, the advice unit provides advice such as, "In this case, it would be good to use the following expression." The advice unit can also suggest educational programs for problematic behavior. For example, the advice unit can provide advice such as, "To prevent this type of problem, please take the following educational program." The advice unit can also suggest specific guidelines for action. For example, the advice unit can provide advice such as, "In this case, it would be good to take the following action." This can promote problem resolution by suggesting specific ways to improve. Some or all of the above-described processing in the advice unit may be performed using, or without, AI. For example, the advice unit can input the content of the warning issued by the warning unit into AI, which can then generate and provide specific ways to improve.

[0071] The confidentiality management unit can ensure that only the sender and the human resources department can view the data and can automatically delete it after, for example, 30 days. The confidentiality management unit performs access control, for example, to ensure that only the sender and the human resources department can view the data. For example, the confidentiality management unit grants access rights only to the sender and the human resources department and does not grant access rights to other users. The confidentiality management unit can also encrypt data. For example, the confidentiality management unit decrypts the data when the sender and the human resources department view it and keeps the data encrypted when other users access it. Furthermore, the confidentiality management unit can set the timing of deletion to automatically delete the data after a certain period of time. For example, the confidentiality management unit can set the timing to automatically delete the data after 30 days. This allows only the sender and the human resources department to view the data and automatically delete it after a certain period of time, thereby managing issues while protecting privacy. Some or all of the above-mentioned processing in the confidentiality management unit may be performed using, or without, AI. For example, the confidentiality management unit can input the content of advice provided by the advice unit into AI, which can then set access control, data encryption, and the timing of deletion.

[0072] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit can increase the accuracy of the analysis and reduce false positives. For example, the analysis unit uses an emotion analysis algorithm to estimate the user's emotions. The emotion analysis algorithm, for example, analyzes the user's facial expressions, voice, and text data and assigns an emotion label. The analysis unit then adjusts the accuracy of the analysis based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit sets a strict threshold to increase the analysis accuracy. On the other hand, if the user is relaxed, the analysis unit maintains normal analysis accuracy. Furthermore, if the user is in a hurry, the analysis unit prioritizes analysis speed and provides results quickly. This allows for more appropriate analysis results to be provided by adjusting the analysis accuracy based on the user's emotions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's emotion data into AI, which then performs emotion analysis and adjusts the analysis accuracy.

[0073] When analyzing email content, the analysis unit can optimize the analysis algorithm by referring to past email data. The analysis unit, for example, learns frequently occurring expressions from past email data and optimizes the analysis algorithm. For example, the analysis unit uses past email data to calculate the frequency of specific expressions and phrases and reflects this in the analysis algorithm. The analysis unit can also extract problematic patterns of speech and behavior from past email data and reflect this in the analysis algorithm. For example, the analysis unit uses past email data to learn patterns of offensive language and discriminatory language and reflect this in the analysis algorithm. Furthermore, the analysis unit can also build an analysis algorithm suited to a specific industry or corporate culture based on past email data. For example, the analysis unit learns expressions and language specific to a specific industry or corporate culture and reflects this in the analysis algorithm. By referring to past email data, the analysis algorithm can be optimized and the analysis accuracy can be improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input past email data into AI, which learns the data and optimizes the analysis algorithm.

[0074] The analysis unit can include not only the context and wording of emails, but also the time and frequency of email transmission in its analysis. For example, the analysis unit can analyze the time of email transmission and pay special attention to emails sent late at night. For example, the analysis unit can analyze the time of email transmission and apply a specific analysis algorithm to emails sent late at night. The analysis unit can also analyze the frequency of email transmission and perform special analysis on frequently sent emails. For example, the analysis unit can analyze the frequency of email transmission and apply a specific analysis algorithm to frequently sent emails. Furthermore, the analysis unit can analyze a combination of the time and frequency of email transmission to detect abnormal patterns. For example, the analysis unit can analyze the time and frequency of email transmission, detect abnormal patterns, and apply a specific analysis algorithm. By including the time and frequency of email transmission in the analysis, more detailed analysis is possible. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input data on the time and frequency of email transmission into AI, which can analyze the data and detect abnormal patterns.

[0075] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit displays the analysis results concisely. For example, the analysis unit uses an emotion analysis algorithm to estimate the user's emotions. The emotion analysis algorithm, for example, analyzes the user's facial expressions, voice, and text data and assigns an emotion label. Next, the analysis unit adjusts the display method of the analysis results based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit displays the analysis results concisely. On the other hand, if the user is relaxed, the analysis unit displays detailed analysis results. Furthermore, if the user is in a hurry, the analysis unit displays analysis results that are concise. In this way, by adjusting the display method of the analysis results based on the user's emotions, it is possible to display analysis results that are easy for the user to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's emotion data into AI, which performs emotion analysis and adjusts the display method of the analysis results.

[0076] When analyzing the content of an email, the analysis unit can take into account the sender's job title and department information. For example, if the sender is a manager, the analysis unit performs a particularly rigorous analysis. For example, the analysis unit reflects the sender's job title information in the analysis and applies a specific analysis algorithm to emails from managers. Furthermore, if the sender belongs to a specific department, the analysis unit can also take into account the characteristics of that department when performing the analysis. For example, the analysis unit reflects the sender's department information in the analysis and applies a specific analysis algorithm to emails from the specific department. Furthermore, the analysis unit can select an appropriate analysis algorithm based on the sender's job title and department information. For example, the analysis unit selects an optimal analysis algorithm based on the sender's job title and department information and performs the analysis. This enables more appropriate analysis by taking the sender's job title and department information into account. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the sender's job title and department information into AI, which then analyzes the data and selects an appropriate analysis algorithm.

[0077] When analyzing the content of an email, the analysis unit can refer to the sender's past behavioral history. The analysis unit, for example, refers to the sender's past email history and reflects specific patterns in the analysis. For example, the analysis unit may analyze the sender's past email history, calculate the frequency of specific expressions and phrases, and reflect this in the analysis algorithm. The analysis unit can also analyze trends in problematic behavior based on the sender's past behavioral history. For example, the analysis unit may analyze the sender's past behavioral history to identify trends in offensive language and discriminatory language and reflect this in the analysis algorithm. Furthermore, the analysis unit can adjust the accuracy of the analysis by taking the sender's past behavioral history into consideration. For example, the analysis unit may adjust the accuracy of the analysis based on the sender's past behavioral history to provide more appropriate analysis results. In this way, the accuracy of the analysis can be improved by referring to the sender's past behavioral history. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may input the sender's past behavioral history into AI, which then analyzes the data and optimizes the analysis algorithm.

[0078] The detection unit can estimate the user's emotions and adjust the detection criteria based on the estimated user emotions. For example, if the user is feeling stressed, the detection unit tightens the detection criteria to reduce false positives. For example, the detection unit uses an emotion analysis algorithm to estimate the user's emotions. The emotion analysis algorithm analyzes, for example, the user's facial expressions, voice, and text data and assigns an emotion label. The detection unit then adjusts the detection criteria based on the estimated user emotions. For example, if the user is feeling stressed, the detection unit sets stricter detection criteria to reduce false positives. On the other hand, if the user is relaxed, the detection unit applies normal detection criteria. Furthermore, if the user is in a hurry, the detection unit prioritizes detection speed and provides results quickly. This allows for more appropriate detection results to be provided by adjusting the detection criteria based on the user's emotions. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without AI. For example, the detection unit can input the user's emotion data into AI, which then performs emotion analysis and adjusts the detection criteria.

[0079] The detection unit can detect not only offensive language and discriminatory expressions, but also subtle nuances and potential problems. For example, the detection unit detects offensive language and identifies problematic emails. For example, the detection unit detects insulting words such as "idiot" and "die." The detection unit can also detect discriminatory expressions and prompt appropriate action. For example, the detection unit detects discriminatory expressions such as "black people are inferior" and "women should stay at home." Furthermore, the detection unit can detect subtle nuances and potential problems and issue warnings. For example, the detection unit detects sarcastic and suggestive expressions and identifies potential problems. This allows for the early detection of a wider range of problems by detecting subtle nuances and potential problems. Some or all of the above-described processing in the detection unit may be performed using, or without, AI. For example, the detection unit can input the content analyzed by the analysis unit into AI, which can then detect offensive language, discriminatory expressions, subtle nuances, and potential problems.

[0080] The detection unit can improve the detection accuracy of a detected problem by referring to past similar cases. The detection unit, for example, improves the detection accuracy by referring to past similar cases. For example, the detection unit optimizes the detection algorithm based on past problem cases. The detection unit can also improve the detection accuracy by utilizing past case data. For example, the detection unit analyzes past problem cases, extracts specific patterns, and reflects them in the detection algorithm. The detection unit can also update the detection algorithm based on past similar cases. For example, the detection unit analyzes past similar cases and improves the detection algorithm. In this way, the detection accuracy can be improved by referring to past similar cases. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input past similar case data into AI, which analyzes the data and optimizes the detection algorithm.

[0081] The detection unit can estimate the user's emotion and adjust the display method of the detection result based on the estimated user's emotion. For example, if the user is feeling stressed, the detection unit displays the detection result concisely. For example, the detection unit uses an emotion analysis algorithm to estimate the user's emotion. The emotion analysis algorithm, for example, analyzes the user's facial expressions, voice, and text data and assigns an emotion label. Next, the detection unit adjusts the display method of the detection result based on the estimated user's emotion. For example, if the user is feeling stressed, the detection unit displays the detection result concisely. On the other hand, if the user is relaxed, the detection unit displays detailed detection results. Furthermore, if the user is in a hurry, the detection unit displays detection results that are concise. In this way, by adjusting the display method of the detection result based on the user's emotion, it is possible to display the detection result in a way that is easy for the user to understand. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the user's emotion data into AI, which performs emotion analysis and adjusts the display method of the detection result.

[0082] The detection unit can display detection results for detected problems by taking into account the sender's job title and department information. For example, if the sender is a manager, the detection unit displays particularly strict detection results. For example, the detection unit reflects the sender's job title information in the detection results and displays specific detection results for emails from managers. Furthermore, if the sender belongs to a specific department, the detection unit can also display detection results by taking into account the characteristics of the department. For example, the detection unit reflects the sender's department information in the detection results and displays specific detection results for emails from the specific department. Furthermore, the detection unit can display appropriate detection results based on the sender's job title and department information. For example, the detection unit displays and analyzes optimal detection results based on the sender's job title and department information. This allows for more appropriate detection results to be provided by taking the sender's job title and department information into consideration. Some or all of the above-described processing in the detection unit may be performed using, or without, AI. For example, the detection unit can input the sender's job title and department information into AI, which then analyzes the data and displays appropriate detection results.

[0083] The detection unit can display the detection results for the detected problem by referring to the sender's past behavioral history. The detection unit, for example, refers to the sender's past email history and reflects specific patterns in the detection results. For example, the detection unit analyzes the sender's past email history, calculates the frequency of specific expressions and phrases, and reflects the results in the detection. The detection unit can also display trends in problematic behavior based on the sender's past behavioral history. For example, the detection unit analyzes the sender's past behavioral history, identifies trends in offensive language and discriminatory expressions, and reflects the results in the detection. Furthermore, the detection unit can adjust the accuracy of the detection results by taking the sender's past behavioral history into consideration. For example, the detection unit adjusts the accuracy of the detection results based on the sender's past behavioral history to provide more appropriate detection results. In this way, the accuracy of the detection results can be improved by referring to the sender's past behavioral history. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the sender's past behavioral history into the AI, which can then analyze the data and optimize the detection results.

[0084] The alert unit can estimate the user's emotions and adjust the way the alert is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the alert unit uses gentle expressions to alert the user. For example, the alert unit uses an emotion analysis algorithm to estimate the user's emotions. The emotion analysis algorithm analyzes, for example, the user's facial expressions, voice, and text data, and assigns an emotion label. Next, the alert unit adjusts the way the alert is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the alert unit uses gentle expressions to alert the user. Furthermore, if the user is relaxed, the alert unit uses normal expressions to alert the user. Furthermore, if the user is in a hurry, the alert unit uses concise and quick expressions to alert the user. This enables more effective alerting by adjusting the way the alert is expressed based on the user's emotions. Some or all of the above-mentioned processing in the alert unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the user's emotional data into the AI, which can then perform emotional analysis and adjust the way the warning is expressed.

[0085] When sending a warning message, the warning unit can generate an optimal message by referring to past warning history. The warning unit, for example, references past warning history to generate an optimal message. For example, the warning unit analyzes past warning history, extracts effective expressions, and reflects them in the message. The warning unit can also transmit a message at an appropriate timing based on the past warning history. For example, the warning unit analyzes past warning history and transmits a message at an optimal timing. Furthermore, the warning unit can customize the warning message based on the past warning history. For example, the warning unit analyzes past warning history to generate a message appropriate for a specific situation. This makes it possible to generate an optimal message and issue an effective warning by referring to the past warning history. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input past warning history data into AI, which analyzes the data and generates an optimal message.

[0086] When sending a warning message, the warning unit can customize the message taking into account the sender's job title and department information. For example, if the sender is a manager, the warning unit sends a particularly strict warning message. For example, the warning unit reflects the sender's job title information in the message and generates a specific message for managers. Furthermore, if the sender belongs to a specific department, the warning unit can customize the message taking into account the characteristics of the department. For example, the warning unit reflects the sender's department information in the message and generates a specific message for the specific department. Furthermore, the warning unit can generate an appropriate message based on the sender's job title and department information. For example, the warning unit generates and sends an optimal message based on the sender's job title and department information. In this way, by taking the sender's job title and department information into account, a more appropriate warning message can be generated. Some or all of the above-described processing in the warning unit may be performed, for example, using AI or without AI. For example, the warning unit can input the sender's job title and department information into the AI, which can then analyze the data and generate an appropriate message.

[0087] The alert unit can estimate the user's emotions and adjust the timing of the alert based on the estimated user's emotions. For example, if the user is feeling stressed, the alert unit delays the timing of the alert. For example, the alert unit uses an emotion analysis algorithm to estimate the user's emotions. The emotion analysis algorithm analyzes, for example, the user's facial expressions, voice, and text data and assigns an emotion label. Next, the alert unit adjusts the timing of the alert based on the estimated user's emotions. For example, if the user is feeling stressed, the alert unit delays the timing of the alert. Furthermore, if the user is relaxed, the alert unit issues an alert at a normal timing. Furthermore, if the user is in a hurry, the alert unit issues an alert quickly. In this way, by adjusting the timing of the alert based on the user's emotions, it is possible to issue an alert at a more appropriate timing. Some or all of the above-mentioned processing in the alert unit may be performed, for example, using AI or without using AI. For example, the warning unit can input the user's emotional data into the AI, which then performs emotional analysis and adjusts the timing of the warning.

[0088] When sending a warning message, the warning unit can customize the message by referring to the sender's past behavioral history. The warning unit, for example, refers to the sender's past behavioral history and reflects a specific pattern in the message. For example, the warning unit analyzes the sender's past email sending history, calculates the frequency of specific expressions or phrases, and reflects the frequency in the message. The warning unit can also reflect effective expressions in the message based on the sender's past behavioral history. For example, the warning unit analyzes the sender's past behavioral history, extracts effective expressions, and reflects the expressions in the message. Furthermore, the warning unit can send the message at an appropriate timing by taking the sender's past behavioral history into consideration. For example, the warning unit analyzes the sender's past behavioral history and sends the message at an optimal timing. In this way, by referring to the sender's past behavioral history, a more effective warning message can be generated. Some or all of the above-described processing in the warning unit may be performed, for example, using AI or without AI. For example, the warning unit can input the sender's past behavioral history data into AI, which can then analyze the data and generate an appropriate message.

[0089] When sending a warning message, the warning unit can customize the message by taking into account the geographical location information of the sender. The warning unit, for example, references the geographical location information of the sender and reflects expressions appropriate for a specific region in the message. For example, the warning unit analyzes the location information of the sender, extracts expressions appropriate for a specific region, and reflects them in the message. The warning unit can also send the message at an appropriate time based on the geographical location information of the sender. For example, the warning unit analyzes the location information of the sender and sends the message at an optimal time. Furthermore, the warning unit can generate an effective warning message by taking into account the geographical location information of the sender. For example, the warning unit analyzes the location information of the sender, extracts effective expressions, and reflects them in the message. In this way, by taking the geographical location information of the sender into consideration, a more appropriate warning message can be generated. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the geographical location information of the sender into AI, which analyzes the data and generates an appropriate message.

[0090] The advice unit can estimate the user's emotions and adjust the way the advice is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the advice unit provides advice in a gentle manner. For example, the advice unit uses an emotion analysis algorithm to estimate the user's emotions. The emotion analysis algorithm, for example, analyzes the user's facial expressions, voice, and text data and assigns an emotion label. Next, the advice unit adjusts the way the advice is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the advice unit provides advice in a gentle manner. Furthermore, if the user is relaxed, the advice unit provides advice in a normal manner. Furthermore, if the user is in a hurry, the advice unit provides advice in a concise and quick manner. This enables more effective advice by adjusting the way the advice is expressed based on the user's emotions. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the user's emotion data into AI, which performs emotion analysis and adjusts the way the advice is expressed.

[0091] When providing advice, the advice unit can generate optimal advice by referring to past advice history. The advice unit, for example, refers to past advice history and generates optimal advice. For example, the advice unit analyzes past advice history, extracts effective expressions, and reflects them in the advice. The advice unit can also provide advice at an appropriate timing based on the past advice history. For example, the advice unit analyzes past advice history and provides advice at an optimal timing. Furthermore, the advice unit can customize the content of the advice based on the past advice history. For example, the advice unit analyzes past advice history and generates advice appropriate for a specific situation. In this way, optimal advice can be generated by referring to the past advice history, and effective advice can be provided. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input past advice history data into AI, which analyzes the data and generates optimal advice.

[0092] When providing advice, the advice unit can customize the advice by taking into account the sender's job title and department information. For example, if the sender is a manager, the advice unit can provide particularly strict advice. For example, the advice unit can reflect the sender's job title information in the advice and generate specific advice for managers. Furthermore, if the sender belongs to a specific department, the advice unit can customize the advice by taking into account the characteristics of the department. For example, the advice unit can reflect the sender's department information in the advice and generate specific advice for the specific department. Furthermore, the advice unit can generate appropriate advice based on the sender's job title and department information. For example, the advice unit can generate and provide optimal advice based on the sender's job title and department information. In this way, more appropriate advice can be generated by taking the sender's job title and department information into consideration. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the sender's job title and department information into AI, which can analyze the data and generate appropriate advice.

[0093] The advice unit can estimate the user's emotions and adjust the timing of advice based on the estimated user emotions. For example, if the user is feeling stressed, the advice unit delays the timing of advice. For example, the advice unit uses an emotion analysis algorithm to estimate the user's emotions. The emotion analysis algorithm, for example, analyzes the user's facial expressions, voice, and text data and assigns an emotion label. Next, the advice unit adjusts the timing of advice based on the estimated user emotions. For example, if the user is feeling stressed, the advice unit delays the timing of advice. Furthermore, if the user is relaxed, the advice unit provides advice at a normal timing. Furthermore, if the user is in a hurry, the advice unit provides advice quickly. In this way, by adjusting the timing of advice based on the user's emotions, advice can be provided at a more appropriate timing. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the user's emotion data into AI, which performs emotion analysis and adjusts the timing of advice.

[0094] When providing advice, the advice unit can customize the advice by referring to the sender's past behavioral history. The advice unit, for example, refers to the sender's past behavioral history and reflects specific patterns in the advice. For example, the advice unit analyzes the sender's past email sending history, calculates the frequency of specific expressions and phrases, and reflects the results in the advice. The advice unit can also reflect effective expressions in the advice based on the sender's past behavioral history. For example, the advice unit analyzes the sender's past behavioral history, extracts effective expressions, and reflects them in the advice. Furthermore, the advice unit can provide advice at an appropriate time by taking the sender's past behavioral history into consideration. For example, the advice unit analyzes the sender's past behavioral history and provides advice at an optimal time. This allows more effective advice to be generated by referring to the sender's past behavioral history. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the sender's past behavioral history data into AI, which then analyzes the data and generates appropriate advice.

[0095] When providing advice, the advice unit can customize the advice by taking into account the geographical location information of the sender. The advice unit, for example, references the geographical location information of the sender and reflects expressions appropriate for a specific region in the advice. For example, the advice unit analyzes the location information of the sender, extracts expressions appropriate for a specific region, and reflects them in the advice. The advice unit can also provide advice at an appropriate time based on the geographical location information of the sender. For example, the advice unit analyzes the location information of the sender and provides advice at an optimal time. Furthermore, the advice unit can generate effective advice by taking into account the geographical location information of the sender. For example, the advice unit analyzes the location information of the sender, extracts effective expressions, and reflects them in the advice. In this way, more appropriate advice can be generated by taking the geographical location information of the sender into account. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the geographical location information of the sender into AI, which analyzes the data and generates appropriate advice.

[0096] The confidentiality management unit can estimate the user's emotions and adjust the confidentiality management method based on the estimated user emotions. For example, if the user is feeling stressed, the confidentiality management unit increases the strictness of the confidentiality management. For example, the confidentiality management unit uses an emotion analysis algorithm to estimate the user's emotions. The emotion analysis algorithm analyzes, for example, the user's facial expressions, voice, and text data and assigns an emotion label. Next, the confidentiality management unit adjusts the confidentiality management method based on the estimated user emotions. For example, if the user is feeling stressed, the confidentiality management unit increases the strictness of the confidentiality management. Furthermore, if the user is relaxed, the confidentiality management unit performs normal confidentiality management. Furthermore, if the user is in a hurry, the confidentiality management unit performs confidentiality management quickly. This enables more appropriate confidentiality management by adjusting the confidentiality management method based on the user's emotions. Some or all of the above-mentioned processing in the confidentiality management unit may be performed using, for example, AI, or may be performed without using AI. For example, the confidentiality management unit can input user emotional data into AI, which can then perform emotional analysis and adjust the confidentiality management method.

[0097] When performing secret management, the secret management unit can select an optimal management method by referring to past secret management history. The secret management unit, for example, refers to past secret management history and selects an optimal management method. For example, the secret management unit analyzes past secret management history and extracts and applies an effective management method. The secret management unit can also perform management at an appropriate time based on the past secret management history. For example, the secret management unit analyzes past secret management history and performs management at an optimal time. Furthermore, the secret management unit can customize the management method based on the past secret management history. For example, the secret management unit analyzes past secret management history and selects a management method suitable for a specific situation. This enables the optimal management method to be selected by referring to the past secret management history, enabling effective secret management. Some or all of the above-described processing in the secret management unit may be performed using, for example, AI, or may be performed without AI. For example, the secret management unit can input past secret management history data into AI, which analyzes the data and selects the optimal management method.

[0098] When performing confidentiality management, the confidentiality management unit can customize the management method taking into account the sender's job title and department information. For example, if the sender is a manager, the confidentiality management unit performs particularly strict confidentiality management. For example, the confidentiality management unit reflects the sender's job title information in the management method and applies a specific management method to managers. Furthermore, if the sender belongs to a specific department, the confidentiality management unit can also customize the management method taking into account the characteristics of the department. For example, the confidentiality management unit reflects the sender's department information in the management method and applies a specific management method to a specific department. Furthermore, the confidentiality management unit can select an appropriate management method based on the sender's job title and department information. For example, the confidentiality management unit selects and applies the optimal management method based on the sender's job title and department information. This makes it possible to select a more appropriate management method by taking the sender's job title and department information into account. Some or all of the above-described processing in the confidentiality management unit may be performed using, for example, AI, or may be performed without using AI. For example, the confidentiality management department can input the sender's job title and department information into the AI, which can then analyze the data and select an appropriate management method.

[0099] The confidentiality management unit can estimate the user's emotions and adjust the timing of confidentiality management based on the estimated user emotions. For example, if the user is feeling stressed, the confidentiality management unit delays the timing of confidentiality management. For example, the confidentiality management unit uses an emotion analysis algorithm to estimate the user's emotions. The emotion analysis algorithm analyzes, for example, the user's facial expressions, voice, and text data and assigns an emotion label. Next, the confidentiality management unit adjusts the timing of confidentiality management based on the estimated user emotions. For example, if the user is feeling stressed, the confidentiality management unit delays the timing of confidentiality management. Furthermore, if the user is relaxed, the confidentiality management unit performs confidentiality management at a normal timing. Furthermore, if the user is in a hurry, the confidentiality management unit performs confidentiality management quickly. In this way, by adjusting the timing of confidentiality management based on the user's emotions, confidentiality management can be performed at a more appropriate timing. Some or all of the above-mentioned processing in the confidentiality management unit may be performed using, for example, AI, or may be performed without using AI. For example, the confidentiality management unit can input the user's emotional data into AI, which then performs emotional analysis and adjusts the timing of confidentiality management.

[0100] When performing confidentiality management, the confidentiality management unit can customize the management method by referring to the sender's past behavioral history. The confidentiality management unit, for example, refers to the sender's past behavioral history and reflects specific patterns in the management method. For example, the confidentiality management unit analyzes the sender's past email sending history, calculates the frequency of specific expressions or phrases, and reflects the frequency in the management method. The confidentiality management unit can also apply an effective management method based on the sender's past behavioral history. For example, the confidentiality management unit analyzes the sender's past behavioral history and extracts and applies an effective management method. Furthermore, the confidentiality management unit can perform management at an appropriate time by taking the sender's past behavioral history into consideration. For example, the confidentiality management unit analyzes the sender's past behavioral history and performs management at the optimal time. In this way, by referring to the sender's past behavioral history, a more effective management method can be selected. Some or all of the above-mentioned processing in the confidentiality management unit may be performed, for example, using AI or without AI. For example, the confidentiality management unit can input the sender's past behavioral history data into AI, which can then analyze the data and select an appropriate management method.

[0101] When performing confidentiality management, the confidentiality management unit can customize the management method by taking into account the geographical location information of the sender. For example, the confidentiality management unit refers to the geographical location information of the sender and applies a management method suitable for a specific region. For example, the confidentiality management unit analyzes the location information of the sender and extracts and applies a management method suitable for a specific region. The confidentiality management unit can also perform management at an appropriate time based on the geographical location information of the sender. For example, the confidentiality management unit analyzes the location information of the sender and performs management at the optimal time. Furthermore, the confidentiality management unit can select an effective management method by taking into account the geographical location information of the sender. For example, the confidentiality management unit analyzes the location information of the sender and extracts and applies an effective management method. In this way, a more appropriate management method can be selected by taking into account the geographical location information of the sender. Some or all of the above-described processing in the confidentiality management unit may be performed using, for example, AI, or may be performed without using AI. For example, the confidentiality management unit can input the geographical location information of the sender into AI, which analyzes the data and selects an appropriate management method. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned analysis unit, detection unit, warning unit, advice unit, and confidentiality management unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14 and analyzes the content of emails. The detection unit is realized by the specific processing unit 290 of the data processing device 12 and detects problems based on the analyzed content. The warning unit is realized by the control unit 46A of the smart device 14 and sends a warning message to the sender of an email containing problematic words or actions. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and suggests specific improvement methods. The confidentiality management unit is realized by the control unit 46A of the smart device 14 and keeps the advice content confidential and automatically deletes it after a certain period of time. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned analysis unit, detection unit, warning unit, advice unit, and confidentiality management unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 and analyzes the content of emails. The detection unit is realized by the specific processing unit 290 of the data processing device 12 and detects problems based on the analyzed content. The warning unit is realized by the control unit 46A of the smart glasses 214 and sends a warning message to the sender of an email containing problematic words or actions. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and suggests specific improvement methods. The confidentiality management unit is realized by the control unit 46A of the smart glasses 214 and keeps the advice content confidential and automatically deletes it after a certain period of time. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, detection unit, warning unit, advice unit, and confidentiality management unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset type terminal 314 and analyzes the content of emails. The detection unit is realized by the specific processing unit 290 of the data processing device 12 and detects problems based on the analyzed content. The warning unit is realized by the control unit 46A of the headset type terminal 314 and sends a warning message to the sender of an email containing problematic words or actions. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and suggests specific improvement methods. The confidentiality management unit is realized by the control unit 46A of the headset type terminal 314 and keeps the content of advice confidential and automatically deletes it after a certain period of time. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, detection unit, warning unit, advice unit, and confidentiality management unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 and analyzes the content of emails. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects problems based on the analyzed content. The warning unit is realized, for example, by the control unit 46A of the robot 414 and sends a warning message to the sender of an email containing problematic words or actions. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suggests specific improvement methods. The confidentiality management unit is realized, for example, by the control unit 46A of the robot 414 and keeps the content of advice confidential and automatically deletes it after a certain period of time.

[0102] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0103] When analyzing the content of an email, the analysis unit can refer to the sender's past behavioral history to perform the analysis. For example, the analysis unit can refer to the sender's past email history and reflect specific patterns in the analysis. For example, the analysis unit can analyze the sender's past email history, calculate the frequency of specific expressions and phrases, and reflect this in the analysis algorithm. The analysis unit can also analyze trends in problematic behavior based on the sender's past behavioral history. For example, the analysis unit can analyze the sender's past behavioral history to identify trends in offensive language and discriminatory language and reflect this in the analysis algorithm. Furthermore, the analysis unit can adjust the accuracy of the analysis by taking the sender's past behavioral history into consideration. For example, the analysis unit can adjust the accuracy of the analysis based on the sender's past behavioral history to provide more appropriate analysis results. In this way, the accuracy of the analysis can be improved by referring to the sender's past behavioral history. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the sender's past behavioral history into AI, which can analyze the data and optimize the analysis algorithm.

[0104] The detection unit can estimate the user's emotions and adjust the detection criteria based on the estimated user emotions. For example, if the user is feeling stressed, the detection criteria can be tightened to reduce false positives. For example, the detection unit uses an emotion analysis algorithm to estimate the user's emotions. The emotion analysis algorithm, for example, analyzes the user's facial expressions, voice, and text data and assigns an emotion label. The detection unit then adjusts the detection criteria based on the estimated user emotions. For example, if the user is feeling stressed, the detection unit sets stricter detection criteria to reduce false positives. On the other hand, if the user is relaxed, the detection unit applies normal detection criteria. Furthermore, if the user is in a hurry, the detection unit prioritizes detection speed and provides results quickly. This allows for more appropriate detection results to be provided by adjusting the detection criteria based on the user's emotions. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without AI. For example, the detection unit can input the user's emotion data into AI, which then performs emotion analysis and adjusts the detection criteria.

[0105] When sending a warning message, the warning unit can generate an optimal message by referring to past warning history. For example, the warning unit generates an optimal message by referring to past warning history. For example, the warning unit analyzes past warning history, extracts effective expressions, and reflects them in the message. The warning unit can also transmit a message at an appropriate timing based on the past warning history. For example, the warning unit analyzes past warning history and transmits a message at an optimal timing. Furthermore, the warning unit can customize the warning message based on the past warning history. For example, the warning unit analyzes past warning history and generates a message appropriate for a specific situation. This makes it possible to generate an optimal message and issue an effective warning by referring to the past warning history. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input past warning history data into AI, which analyzes the data and generates an optimal message.

[0106] The advice unit can estimate the user's emotions and adjust the way the advice is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the advice unit can provide the advice in a more gentle way. For example, the advice unit uses an emotion analysis algorithm to estimate the user's emotions. The emotion analysis algorithm can analyze, for example, the user's facial expressions, voice, and text data and assign an emotion label. The advice unit then adjusts the way the advice is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the advice unit can provide the advice in a more gentle way. If the user is relaxed, the advice unit can provide the advice in a more normal way. If the user is in a hurry, the advice unit can provide the advice in a concise and quick way. This allows for more effective advice by adjusting the way the advice is expressed based on the user's emotions. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the user's emotion data into AI, which can then perform emotion analysis and adjust the way the advice is expressed.

[0107] The confidentiality management unit can estimate the user's emotions and adjust the confidentiality management method based on the estimated user emotions. For example, if the user is feeling stressed, the confidentiality management method can be made stricter. For example, the confidentiality management unit uses an emotion analysis algorithm to estimate the user's emotions. The emotion analysis algorithm analyzes, for example, the user's facial expressions, voice, and text data and assigns an emotion label. Next, the confidentiality management unit adjusts the confidentiality management method based on the estimated user emotions. For example, if the user is feeling stressed, the confidentiality management unit increases the strictness of the confidentiality management. Furthermore, if the user is relaxed, the confidentiality management unit performs normal confidentiality management. Furthermore, if the user is in a hurry, the confidentiality management unit performs confidentiality management quickly. This allows for more appropriate confidentiality management by adjusting the confidentiality management method based on the user's emotions. Some or all of the above-described processing in the confidentiality management unit may be performed using AI, for example, or without AI. For example, the confidentiality management unit can input user emotional data into AI, which can then perform emotional analysis and adjust the confidentiality management method.

[0108] When analyzing the content of an email, the analysis unit can take into account the sender's job title and department information. For example, if the sender is a manager, the analysis can be particularly strict. For example, the analysis unit can reflect the sender's job title information in the analysis and apply a specific analysis algorithm to emails from managers. Furthermore, if the sender belongs to a specific department, the analysis unit can also take into account the characteristics of that department when analyzing. For example, the analysis unit can reflect the sender's department information in the analysis and apply a specific analysis algorithm to emails from the specific department. Furthermore, the analysis unit can select an appropriate analysis algorithm based on the sender's job title and department information. For example, the analysis unit selects an optimal analysis algorithm based on the sender's job title and department information and performs the analysis. This enables more appropriate analysis by taking the sender's job title and department information into account. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the sender's job title and department information into AI, which can analyze the data and select an appropriate analysis algorithm.

[0109] The detection unit can improve the detection accuracy of a detected problem by referring to past similar cases. For example, the detection unit improves the detection accuracy by referring to past similar cases. For example, the detection unit optimizes the detection algorithm based on past problem cases. The detection unit can also improve the detection accuracy by utilizing past case data. For example, the detection unit analyzes past problem cases, extracts specific patterns, and reflects them in the detection algorithm. Furthermore, the detection unit can update the detection algorithm based on past similar cases. For example, the detection unit analyzes past similar cases and improves the detection algorithm. In this way, the detection accuracy can be improved by referring to past similar cases. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input past similar case data into AI, which analyzes the data and optimizes the detection algorithm.

[0110] When sending a warning message, the warning unit can customize the message taking into account the sender's job title and department information. For example, if the sender is a manager, the warning unit can send a particularly strict warning message. For example, the warning unit can reflect the sender's job title information in the message and generate a specific message for managers. Furthermore, if the sender belongs to a specific department, the warning unit can customize the message taking into account the characteristics of the department. For example, the warning unit can reflect the sender's department information in the message and generate a specific message for the specific department. Furthermore, the warning unit can generate an appropriate message based on the sender's job title and department information. For example, the warning unit can generate and send an optimal message based on the sender's job title and department information. In this way, by taking the sender's job title and department information into account, a more appropriate warning message can be generated. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the sender's job title and department information into AI, which can analyze the data and generate an appropriate message.

[0111] When providing advice, the advice unit can generate optimal advice by referring to the past advice history. The advice unit generates appropriate advice. For example, the advice unit analyzes past advice history, extracts effective expressions, and reflects them in the advice. The advice unit can also provide advice at an appropriate time based on the past advice history. For example, the advice unit analyzes past advice history and provides advice at an optimal time. The advice unit can also customize the content of the advice based on the past advice history. For example, the advice unit analyzes past advice history and generates advice suitable for a specific situation. This makes it possible to generate optimal advice and provide effective advice by referring to the past advice history. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input past advice history data into AI, which analyzes the data and generates optimal advice.

[0112] When performing confidentiality management, the confidentiality management unit can customize the management method by referring to the sender's past behavioral history. For example, the confidentiality management unit can refer to the sender's past behavioral history and reflect specific patterns in the management method. For example, the confidentiality management unit can analyze the sender's past email sending history, calculate the frequency of specific expressions or phrases, and reflect the results in the management method. The confidentiality management unit can also apply an effective management method based on the sender's past behavioral history. For example, the confidentiality management unit can analyze the sender's past behavioral history, extract an effective management method, and apply it. Furthermore, the confidentiality management unit can perform management at an appropriate time by taking the sender's past behavioral history into consideration. For example, the confidentiality management unit can analyze the sender's past behavioral history and perform management at the optimal time. This allows a more effective management method to be selected by referring to the sender's past behavioral history. Some or all of the above-described processing in the confidentiality management unit may be performed using, for example, AI, or may be performed without AI. For example, the confidentiality management unit can input the sender's past behavioral history data into AI, which can analyze the data and select an appropriate management method.

[0113] The processing flow of the second embodiment will be briefly explained below.

[0114] Step 1: The analysis unit analyzes the content of the email. For example, the analysis unit uses natural language processing technology to analyze the context and wording of the email. Natural language processing technology includes morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to divide the words in the email, grammatical analysis to analyze the structure of the sentence, and semantic analysis to understand the meaning of the sentence. Step 2: The detection unit detects problems based on the content analyzed by the analysis unit. The detection unit detects, for example, offensive language and discriminatory expressions. For example, the detection unit detects insulting words and threatening expressions, and identifies racist and sexist expressions. Step 3: The warning unit issues a warning about the problem detected by the detection unit. The warning unit, for example, sends a warning message to the sender of the email containing the problematic speech or behavior. For example, the warning unit sends a message such as, "This expression may be power harassment. Please revise it to an appropriate expression." Step 4: The advice unit provides advice on how to improve based on the content of the warning issued by the warning unit. The advice unit, for example, suggests specific ways to improve problematic speech or behavior. For example, the advice unit provides advice such as, "In this case, it would be good to use the following expression." Step 5: The confidentiality management unit keeps the advice provided by the advice unit confidential and automatically deletes it after a certain period of time. For example, the confidentiality management unit makes it possible for only the sender and the human resources department to view it, and automatically deletes it after, for example, 30 days.

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0117] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0118] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0119] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0120] 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.

[0121] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0122] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0123] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0125] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0126] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0127] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0128] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0129] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0130] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0131] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0133] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0134] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0135] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0136] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0137] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0138] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0139] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0141] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0142] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0143] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0145] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0146] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0147] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0148] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0149] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0150] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0151] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0152] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0153] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0154] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0155] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0157] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0158] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0159] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0160] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0161] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0162] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0163] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0164] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0165] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0166] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0167] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0168] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0169] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0170] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0171] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0172] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0173] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0174] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0175] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0176] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0177] 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.

[0178] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0179] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0180] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0181] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0182] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0183] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0184] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0185] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0186] [Explanation of symbols]

[0187] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes the content of the email; a detection unit that detects a problem based on the content analyzed by the analysis unit; a warning unit that issues a warning about the problem detected by the detection unit; an advice unit that provides advice on an improvement method based on the content of the warning issued by the warning unit; a confidentiality management unit that keeps the contents of the advice provided by the advice unit confidential and automatically deletes them after, for example, 30 days. A system characterized by:

2. The analysis unit Use natural language processing technology to analyze email context and wording 2. The system of claim 1.

3. The detection unit Detect offensive language and hate speech 2. The system of claim 1.

4. The attention drawing unit Send a warning message to the sender of the email containing the problematic words and actions 2. The system of claim 1.

5. The advice unit Suggest specific ways to improve problematic behavior 2. The system of claim 1.

6. The confidentiality management unit Only the sender and the HR department can see it, and it will be automatically deleted after, say, 30 days.

2. The system of claim 1.

7. The analysis unit Estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions.

2. The system of claim 1.

8. The analysis unit When analyzing email content, the analysis algorithm is optimized by referencing past email data.

2. The system of claim 1.

Images