System

Abstract

An object of the system according to the embodiment is to stop the transmission when the content of the mail corresponds to the harassment and cause the transmission source to learn the point of caution.SOLUTION: A system includes a mail analysis part, a harassment detection part, a transmission stop part, and a correction result display part. The mail analysis part analyzes mail contents. The harassment detection unit detects a content corresponding to a harassment from the mail content analyzed by the mail analysis unit. The transmission stop section stops the transmission of the mail when the content corresponding to the harassment is detected by the harassment detection section. The correction result display portion displays the correction result of the mail whose transmission has been stopped by the transmission stop portion.SELECTED DRAWING: Figure 1

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 does not have sufficient mechanisms in place to automatically detect whether the content of an email constitutes harassment and stop it from being sent, so there is room for improvement.

[0005] The system according to the embodiment aims to stop sending emails if the content of the emails constitutes harassment, and to teach the sender what to be careful of. [Means for solving the problem]

[0006] The system according to the embodiment includes a mail analysis unit, a harassment detection unit, a transmission stop unit, and a correction result display unit. The mail analysis unit analyzes the contents of the mail. The harassment detection unit detects content that constitutes harassment from the mail content analyzed by the mail analysis unit. The transmission stop unit stops sending the mail when content that constitutes harassment is detected by the harassment detection unit. The correction result display unit displays the correction results of the mail whose sending has been stopped by the transmission stop unit. [Effects of the Invention]

[0007] The system according to the embodiment can stop sending an email if the content of the email constitutes harassment, and can teach the sender what to be careful of. [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) In the harassment prevention system according to an embodiment of the present invention, the AI ​​generation system considers the relationship between the sender and the recipient when sending an email, detects content that constitutes harassment, and stops the transmission. This allows the harassment prevention system to prevent harassment from occurring and learn what senders should be careful of.

[0029] A harassment prevention system according to an embodiment includes an email analysis unit, a harassment detection unit, a transmission stop unit, and a correction result display unit. The email analysis unit analyzes email content. For example, the email analysis unit analyzes email text using natural language processing technology. The email analysis unit can also detect specific expressions using keyword matching technology. The email analysis unit can also analyze email content using a machine learning algorithm. For example, the email analysis unit understands the context of an email using natural language processing technology and detects specific expressions. The keyword matching technology analyzes email content based on a predefined keyword list. The machine learning algorithm learns from large amounts of email data and identifies expressions that pose a high risk of harassment. The harassment detection unit detects content that constitutes harassment from the email content analyzed by the email analysis unit. For example, the harassment detection unit detects expressions such as verbal abuse, sexual harassment, and power harassment. The harassment detection unit can also analyze the tone and nuance of emails using sentiment analysis technology to detect potential signs of harassment. The harassment detection unit can also detect harassing expressions specific to a particular industry or culture. For example, the harassment detection unit detects the expression "incompetent doctor" as verbal abuse. Sentiment analysis technology analyzes the tone and nuance of an email to identify offensive expressions. Harassing expressions specific to a particular industry or culture are detected based on a predefined list. The transmission stopping unit stops sending an email if the harassment detection unit detects content that constitutes harassment. For example, the transmission stopping unit stops sending if a specific keyword is included. The transmission stopping unit can also stop sending if the result of the sentiment analysis exceeds a certain threshold. The transmission stopping unit can also stop sending based on the content detected by the harassment detection unit. For example, the transmission stopping unit stops sending if the expression "incompetent doctor" is included. The transmission stopping unit stops sending if the result of the sentiment analysis indicates an aggressive tone. The transmission stopping unit stops sending if the content detected by the harassment detection unit poses a high risk of harassment.The correction result display unit displays the correction results for the email whose transmission was stopped by the transmission stopping unit. For example, the correction result display unit displays correction suggestions and alternative expressions. The correction result display unit can also display the correction results in the form of feedback. The correction result display unit can also refer to past email history and provide advice to prevent similar problems from recurring. For example, the correction result display unit displays a suggestion to change the expression "incompetent doctor" to "doctor with room for improvement." In the form of feedback, the correction result display unit displays "This expression is offensive. Please use alternative expressions." By referring to past email history, the correction result display unit provides advice such as "Similar expressions have been pointed out in the past. Please be careful." This allows the harassment prevention system according to the embodiment to prevent harassment from occurring and learn what points the sender should pay attention to. For example, the sender can check the correction results for the email and avoid expressions that pose a high risk of harassment. The sender can modify the content of the email and use appropriate expressions based on the feedback. The sender can refer to past email history and take care to prevent similar problems from recurring.

[0030] The email analysis unit can perform analysis taking into account the relationship between the sender and the recipient. The email analysis unit performs analysis taking into account, for example, the relationship between the sender and the recipient. For example, the analysis taking into account the relationship between a superior and a subordinate. The email analysis unit can also perform analysis taking into account the relationship between colleagues. The email analysis unit can also perform analysis taking into account the relationship with a business partner. For example, in a relationship between a superior and a subordinate, the email analysis unit determines that an expression from a superior to a subordinate saying, "You're always slow at work," may constitute power harassment. In a relationship between colleagues, the email analysis unit determines that the expression "you" may constitute harassment. In a relationship with a business partner, the email analysis unit determines that the expression "you're an incompetent doctor" may constitute harassment. This enables appropriate judgment to be made based on the relationship between the sender and the recipient.

[0031] The harassment detection unit can detect harassment expressions specific to specific industries or cultures. For example, in the IT industry, the expression "messy code" may be considered harassment. The harassment detection unit can also learn harassment expressions in specific cultures and analyze email content. For example, in Japanese workplace culture, the expression "omae" (you) may be considered harassment. The harassment detection unit can also analyze industry-specific terms and expressions and evaluate the risk of harassment. For example, in the medical industry, the expression "incompetent doctor" may be considered harassment. This enables the detection of harassment expressions specific to specific industries or cultures with high accuracy.

[0032] The harassment detection unit analyzes the tone and nuance of email content to detect potential signs of harassment early on. The harassment detection unit analyzes the tone and nuance of email content to detect potential signs of harassment early on. For example, the generation AI analyzes the tone of an email to detect expressions with aggressive nuances. For example, the expression "How many times do I have to tell you?" is judged to be aggressive. The generation AI can also analyze the nuance of an email to detect potential signs of harassment. For example, the expression "You're really useless" is considered to be harassment. The generation AI can also analyze the tone of an email to detect expressions that the recipient may find offensive. For example, the expression "You're delaying the project because of you" is considered to be harassment. This allows for early detection of potential signs of harassment.

[0033] The email analysis unit can also analyze the content of voicemails and video messages to detect harassment. For example, the generation AI in the email analysis unit analyzes the content of voicemails and detects expressions that pose a risk of harassment. For example, it converts audio data into text and identifies offensive expressions. The generation AI can also analyze the content of video messages and detect expressions that pose a risk of harassment. For example, it extracts audio from video data and performs text analysis. It is also possible to build a system in which the generation AI analyzes the content of voicemails and video messages and evaluates the risk of harassment. For example, it uses voice recognition technology to identify offensive expressions. This makes it possible to analyze the content of voicemails and video messages and detect harassment.

[0034] The email analysis unit can also analyze messages on social media and chat apps to detect harassment. For example, the generation AI in the email analysis unit analyzes social media messages to detect expressions that pose a risk of harassment. For example, it analyzes posts on Twitter and Facebook to identify offensive expressions. The generation AI can also analyze messages on chat apps to detect expressions that pose a risk of harassment. For example, it can analyze messages on Slack and Teams to identify offensive expressions. It is also possible to build a system in which the generation AI analyzes messages on social media and chat apps to evaluate the risk of harassment. For example, it can analyze messages in real time to identify offensive expressions. This makes it possible to analyze messages on social media and chat apps and detect harassment.

[0035] The correction result display unit can suggest specific alternative expressions, allowing the sender to make corrections immediately. For example, when the generation AI displays the correction results for an email, the correction result display unit suggests specific alternative expressions. For example, it could suggest "You're always slow at work" as "There's room for improvement in your recent project." The generation AI can also display the correction results for an email, allowing the sender to make corrections immediately. For example, it could suggest specific alternative expressions that soften offensive expressions. It is also possible to build a system in which the generation AI displays the correction results for an email, allowing the sender to make corrections immediately. For example, it could suggest replacing negative expressions with positive ones. This makes it possible to suggest specific alternative expressions, allowing the sender to make corrections immediately.

[0036] The correction result display unit can refer to past email history and provide advice to prevent similar problems from recurring. For example, the generation AI can refer to past email history and provide advice to prevent similar problems from recurring. For example, it can suggest avoiding expressions that have been pointed out in the past. The generation AI can also analyze past email history and provide advice to prevent similar problems from recurring. For example, it can suggest areas for improvement based on past correction results. It is also possible to build a system in which the generation AI refers to past email history and provides advice to prevent similar problems from recurring. For example, it can suggest specific improvement measures based on past problems. This makes it possible to provide advice to prevent similar problems from recurring.

[0037] The correction result display unit provides the email correction results by voice, making it possible to accommodate visually impaired people. For example, the correction result display unit uses a generation AI to provide the email correction results by voice, building a system that also accommodates visually impaired people. For example, the correction results are read aloud using voice synthesis technology. The generation AI can also provide the email correction results by voice, making them easy to understand for visually impaired people. For example, specific alternative expressions are suggested by voice. The generation AI can also provide the email correction results by voice, making it possible to accommodate visually impaired people. For example, the correction results are explained using audio guidance. This makes it possible to accommodate visually impaired people.

[0038] The correction result display unit can display the email correction results in real time, allowing the sender to correct problems while composing the email. The correction result display unit, for example, builds a system in which the generation AI displays the email correction results in real time, allowing the sender to correct problems while composing the email. For example, it points out offensive expressions in real time. The generation AI can also display the email correction results in real time, allowing the sender to correct problems while composing the email. For example, it can make suggestions to immediately correct negative expressions. The generation AI can also display the email correction results in real time, allowing the sender to correct problems while composing the email. For example, it can suggest alternative expressions in real time. This allows the sender to correct problems while composing the email.

[0039] The email analysis unit can perform a detailed analysis of the relationship between the sender and the recipient and evaluate the risk of harassment in specific relationships. For example, the email analysis unit constructs a system in which the generation AI analyzes the relationship between the sender and the recipient in detail and evaluates the risk of harassment in specific relationships. For example, it considers the relationship between a superior and a subordinate. The generation AI can also analyze the relationship between the sender and the recipient and evaluate the risk of harassment in specific relationships. For example, it can evaluate the risk in emails between colleagues. The generation AI can also analyze the relationship between the sender and the recipient in detail and evaluate the risk of harassment in specific relationships. For example, it can evaluate the risk in emails with business partners. This makes it possible to evaluate the risk of harassment in specific relationships.

[0040] The email analysis unit can refer to past exchanges between the sender and recipient and perform analysis taking into account changes in the relationship. For example, the email analysis unit can build a system in which the generation AI refers to past exchanges between the sender and recipient and performs analysis taking into account changes in the relationship. For example, it evaluates the relationship based on past email history. The generation AI can also analyze past exchanges between the sender and recipient and evaluate the risk of harassment taking into account changes in the relationship. For example, it evaluates the risk when there has been an increase in recent exchanges. The generation AI can also refer to past exchanges between the sender and recipient and perform analysis taking into account changes in the relationship. For example, it evaluates the risk when there has been little past exchange. This makes it possible to perform analysis taking into account changes in the relationship.

[0041] The email analysis unit can suggest an appropriate communication style by taking into account the relationship between the sender and the recipient. The email analysis unit, for example, builds a system in which a generation AI considers the relationship between the sender and the recipient and suggests an appropriate communication style. For example, it proposes expressions that are appropriate for the relationship between a superior and a subordinate. The generation AI can also consider the relationship between the sender and the recipient and suggest an appropriate communication style. For example, it proposes appropriate expressions for emails between colleagues. The generation AI can also consider the relationship between the sender and the recipient and suggest an appropriate communication style. For example, it proposes appropriate expressions for emails with business partners. This makes it possible to suggest an appropriate communication style.

[0042] The email analysis unit can automatically generate email templates taking into account the relationship between sender and recipient. The email analysis unit, for example, builds a system in which a generation AI automatically generates email templates taking into account the relationship between sender and recipient. For example, it generates a template that is appropriate for the relationship between a superior and a subordinate. The generation AI can also automatically generate email templates taking into account the relationship between sender and recipient. For example, it generates an appropriate template for emails between colleagues. The generation AI can also automatically generate email templates taking into account the relationship between sender and recipient. For example, it generates an appropriate template for emails with business partners. This makes it possible to automatically generate email templates.

[0043] The email analysis unit analyzes the sender's past email history and can learn expressions that pose a high risk of harassment. The email analysis unit, for example, builds a system in which the generation AI analyzes the sender's past email history and learns expressions that pose a high risk of harassment. For example, it learns expressions that have been pointed out in the past. The generation AI can also analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can identify offensive expressions and add them to the learning data. The generation AI can also analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can learn negative expressions and evaluate the risk. This allows it to learn expressions that pose a high risk of harassment.

[0044] The email analysis unit can analyze the sender's email creation patterns and recommend expressions that pose a low risk of harassment. For example, the email analysis unit constructs a system in which a generation AI analyzes the sender's email creation patterns and recommends expressions that pose a low risk of harassment. For example, it prioritizes recommendations of positive expressions. The generation AI can also analyze the sender's email creation patterns and recommend expressions that pose a low risk of harassment. For example, it makes suggestions to avoid offensive expressions. The generation AI can also analyze the sender's email creation patterns and recommend expressions that pose a low risk of harassment. For example, it presents specific alternative expressions. This makes it possible to recommend expressions that pose a low risk of harassment.

[0045] The email analysis unit can provide a training module for preventing harassment, allowing the sender to learn independently. The email analysis unit, for example, builds a system in which a generation AI provides a training module for preventing harassment, allowing the sender to learn independently. For example, an online course can be provided. The generation AI can also provide a training module for preventing harassment, allowing the sender to learn independently. For example, interactive training can be provided. The generation AI can also provide a training module for preventing harassment, allowing the sender to learn independently. For example, training using a simulation can be provided. In this way, a training module can be provided to allow the sender to learn independently.

[0046] The email analysis unit can automatically generate guidelines for preventing harassment and provide them to the sender. The email analysis unit, for example, builds a system in which a generation AI automatically generates guidelines for preventing harassment and provides them to the sender. For example, it presents specific examples of expression. The generation AI can also automatically generate guidelines for preventing harassment and provide them to the sender. For example, it can provide guidelines for avoiding offensive expression. The generation AI can also automatically generate guidelines for preventing harassment and provide them to the sender. For example, it can provide guidelines that encourage positive expression. In this way, guidelines for preventing harassment can be automatically generated and provided to the sender.

[0047] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0048] The email analysis unit can analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can learn expressions that have been pointed out in the past. The generation AI can also analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can identify offensive expressions and add them to the learning data. The generation AI can also analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can learn negative expressions and evaluate the risk. This allows it to learn expressions that pose a high risk of harassment.

[0049] The email analysis unit can analyze the sender's email composition patterns and recommend expressions that pose a low risk of harassment. For example, a generation AI can analyze the sender's email composition patterns and build a system that recommends expressions that pose a low risk of harassment. For example, it can prioritize and recommend positive expressions. The generation AI can also analyze the sender's email composition patterns and recommend expressions that pose a low risk of harassment. For example, it can make suggestions to avoid offensive expressions. The generation AI can also analyze the sender's email composition patterns and recommend expressions that pose a low risk of harassment. For example, it can present specific alternative expressions. This makes it possible to recommend expressions that pose a low risk of harassment.

[0050] The email analysis unit can provide a training module for preventing harassment, allowing senders to learn independently. For example, a system can be constructed in which the generation AI provides a training module for preventing harassment, allowing senders to learn independently. For example, an online course can be provided. The generation AI can also provide a training module for preventing harassment, allowing senders to learn independently. For example, interactive training can be provided. The generation AI can also provide a training module for preventing harassment, allowing senders to learn independently. For example, training using a simulation can be provided. In this way, a training module can be provided to allow senders to learn independently.

[0051] The email analysis unit can automatically generate guidelines for preventing harassment and provide them to the sender. For example, a system can be built in which the generation AI automatically generates guidelines for preventing harassment and provides them to the sender. For example, it can present specific examples of expression. The generation AI can also automatically generate guidelines for preventing harassment and provide them to the sender. For example, it can provide guidelines for avoiding offensive language. The generation AI can also automatically generate guidelines for preventing harassment and provide them to the sender. For example, it can provide guidelines that encourage positive language. In this way, guidelines for preventing harassment can be automatically generated and provided to the sender.

[0052] The email analysis unit can consider the relationship between the sender and the recipient to suggest an appropriate communication style. For example, a system can be constructed in which the generation AI considers the relationship between the sender and the recipient to suggest an appropriate communication style. For example, it can suggest expressions that are appropriate for the relationship between a superior and a subordinate. The generation AI can also consider the relationship between the sender and the recipient to suggest an appropriate communication style. For example, it can suggest appropriate expressions for emails between colleagues. The generation AI can also consider the relationship between the sender and the recipient to suggest an appropriate communication style. For example, it can suggest appropriate expressions for emails with business partners. This makes it possible to suggest an appropriate communication style.

[0053] The email analysis unit can automatically generate email templates by taking into account the relationship between sender and recipient. For example, a system can be built in which the generation AI automatically generates email templates by taking into account the relationship between sender and recipient. For example, it generates a template that is appropriate for the relationship between a superior and a subordinate. The generation AI can also automatically generate email templates by taking into account the relationship between sender and recipient. For example, it can generate an appropriate template for emails between colleagues. The generation AI can also automatically generate email templates by taking into account the relationship between sender and recipient. For example, it can generate an appropriate template for emails with business partners. This makes it possible to automatically generate email templates.

[0054] The email analysis unit can analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, a system can be built in which the generation AI analyzes the sender's past email history and learns expressions that pose a high risk of harassment. For example, it learns expressions that have been pointed out in the past. The generation AI can also analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can identify offensive expressions and add them to the learning data. The generation AI can also analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can learn negative expressions and evaluate the risk. This allows it to learn expressions that pose a high risk of harassment.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The email analysis unit analyzes the email content. For example, it can use natural language processing technology to analyze the email text and keyword matching technology to detect specific expressions. It can also use machine learning algorithms to analyze the email content. Step 2: The harassment detection unit detects harassment from the email content analyzed by the email analysis unit. For example, it can detect verbal abuse, sexual harassment, power harassment, and other expressions, and can also analyze the tone and nuance of the email using emotion analysis technology. Step 3: The transmission stop unit stops sending emails if the harassment detection unit detects content that constitutes harassment. For example, it can stop sending emails if they contain specific keywords or if the results of sentiment analysis exceed a certain threshold. Step 4: The correction result display unit displays the correction results for the email whose sending has been stopped by the sending stopping unit. For example, the correction results can be displayed in the form of feedback, such as by displaying suggested corrections or alternative expressions.

[0057] (Example 2) In the harassment prevention system according to an embodiment of the present invention, the AI ​​generation system considers the relationship between the sender and the recipient when sending an email, detects content that constitutes harassment, and stops the transmission. This allows the harassment prevention system to prevent harassment from occurring and learn what senders should be careful of.

[0058] A harassment prevention system according to an embodiment includes an email analysis unit, a harassment detection unit, a transmission stop unit, and a correction result display unit. The email analysis unit analyzes email content. For example, the email analysis unit analyzes email text using natural language processing technology. The email analysis unit can also detect specific expressions using keyword matching technology. The email analysis unit can also analyze email content using a machine learning algorithm. For example, the email analysis unit understands the context of an email using natural language processing technology and detects specific expressions. The keyword matching technology analyzes email content based on a predefined keyword list. The machine learning algorithm learns from large amounts of email data and identifies expressions that pose a high risk of harassment. The harassment detection unit detects content that constitutes harassment from the email content analyzed by the email analysis unit. For example, the harassment detection unit detects expressions such as verbal abuse, sexual harassment, and power harassment. The harassment detection unit can also analyze the tone and nuance of emails using sentiment analysis technology to detect potential signs of harassment. The harassment detection unit can also detect harassing expressions specific to a particular industry or culture. For example, the harassment detection unit detects the expression "incompetent doctor" as verbal abuse. Sentiment analysis technology analyzes the tone and nuance of an email to identify offensive expressions. Harassing expressions specific to a particular industry or culture are detected based on a predefined list. The transmission stopping unit stops sending an email if the harassment detection unit detects content that constitutes harassment. For example, the transmission stopping unit stops sending if a specific keyword is included. The transmission stopping unit can also stop sending if the result of the sentiment analysis exceeds a certain threshold. The transmission stopping unit can also stop sending based on the content detected by the harassment detection unit. For example, the transmission stopping unit stops sending if the expression "incompetent doctor" is included. The transmission stopping unit stops sending if the result of the sentiment analysis indicates an aggressive tone. The transmission stopping unit stops sending if the content detected by the harassment detection unit poses a high risk of harassment.The correction result display unit displays the correction results for the email whose transmission was stopped by the transmission stopping unit. For example, the correction result display unit displays correction suggestions and alternative expressions. The correction result display unit can also display the correction results in the form of feedback. The correction result display unit can also refer to past email history and provide advice to prevent similar problems from recurring. For example, the correction result display unit displays a suggestion to change the expression "incompetent doctor" to "doctor with room for improvement." In the form of feedback, the correction result display unit displays "This expression is offensive. Please use alternative expressions." By referring to past email history, the correction result display unit provides advice such as "Similar expressions have been pointed out in the past. Please be careful." This allows the harassment prevention system according to the embodiment to prevent harassment from occurring and learn what points the sender should pay attention to. For example, the sender can check the correction results for the email and avoid expressions that pose a high risk of harassment. The sender can modify the content of the email and use appropriate expressions based on the feedback. The sender can refer to past email history and take care to prevent similar problems from recurring.

[0059] The email analysis unit can perform analysis taking into account the relationship between the sender and the recipient. The email analysis unit performs analysis taking into account, for example, the relationship between the sender and the recipient. For example, the analysis taking into account the relationship between a superior and a subordinate. The email analysis unit can also perform analysis taking into account the relationship between colleagues. The email analysis unit can also perform analysis taking into account the relationship with a business partner. For example, in a relationship between a superior and a subordinate, the email analysis unit determines that an expression from a superior to a subordinate saying, "You're always slow at work," may constitute power harassment. In a relationship between colleagues, the email analysis unit determines that the expression "you" may constitute harassment. In a relationship with a business partner, the email analysis unit determines that the expression "you're an incompetent doctor" may constitute harassment. This enables appropriate judgment to be made based on the relationship between the sender and the recipient.

[0060] The harassment detection unit can detect harassment expressions specific to specific industries or cultures. For example, in the IT industry, the expression "messy code" may be considered harassment. The harassment detection unit can also learn harassment expressions in specific cultures and analyze email content. For example, in Japanese workplace culture, the expression "omae" (you) may be considered harassment. The harassment detection unit can also analyze industry-specific terms and expressions and evaluate the risk of harassment. For example, in the medical industry, the expression "incompetent doctor" may be considered harassment. This enables the detection of harassment expressions specific to specific industries or cultures with high accuracy.

[0061] The harassment detection unit analyzes the tone and nuance of email content to detect potential signs of harassment early on. The harassment detection unit analyzes the tone and nuance of email content to detect potential signs of harassment early on. For example, the generation AI analyzes the tone of an email to detect expressions with aggressive nuances. For example, the expression "How many times do I have to tell you?" is judged to be aggressive. The generation AI can also analyze the nuance of an email to detect potential signs of harassment. For example, the expression "You're really useless" is considered to be harassment. The generation AI can also analyze the tone of an email to detect expressions that the recipient may find offensive. For example, the expression "You're delaying the project because of you" is considered to be harassment. This allows for early detection of potential signs of harassment.

[0062] The harassment detection unit can use the emotion estimation function to analyze the emotional state of the email creator and prevent emails from being sent when the creator is emotionally unstable. The harassment detection unit can, for example, use the emotion estimation function to analyze the emotional state of the email creator in real time and prevent emails from being sent when the creator is emotionally unstable. For example, a warning can be displayed if the creator is feeling strong anger. The emotion estimation function can also be used to analyze the emotional state of the email creator and encourage the creator to send the email in a calm state. For example, sending can be temporarily suspended if the creator is under high stress. The emotion estimation function can also be used to build a system that analyzes the emotional state of the email creator and prevents emails from being sent when the creator is emotionally unstable. For example, sending can be suspended if the creator is feeling strong negative emotions. This makes it possible to prevent emails from being sent when the creator is emotionally unstable.

[0063] The email analysis unit can also analyze the content of voicemails and video messages to detect harassment. For example, the generation AI in the email analysis unit analyzes the content of voicemails and detects expressions that pose a risk of harassment. For example, it converts audio data into text and identifies offensive expressions. The generation AI can also analyze the content of video messages and detect expressions that pose a risk of harassment. For example, it extracts audio from video data and performs text analysis. It is also possible to build a system in which the generation AI analyzes the content of voicemails and video messages and evaluates the risk of harassment. For example, it uses voice recognition technology to identify offensive expressions. This makes it possible to analyze the content of voicemails and video messages and detect harassment.

[0064] The email analysis unit can also analyze messages on social media and chat apps to detect harassment. For example, the generation AI in the email analysis unit analyzes social media messages to detect expressions that pose a risk of harassment. For example, it analyzes posts on Twitter and Facebook to identify offensive expressions. The generation AI can also analyze messages on chat apps to detect expressions that pose a risk of harassment. For example, it can analyze messages on Slack and Teams to identify offensive expressions. It is also possible to build a system in which the generation AI analyzes messages on social media and chat apps to evaluate the risk of harassment. For example, it can analyze messages in real time to identify offensive expressions. This makes it possible to analyze messages on social media and chat apps and detect harassment.

[0065] The harassment detection unit can use the emotion estimation function to predict the emotional reaction of an email recipient and correct expressions that may cause the recipient to feel uncomfortable in advance. The harassment detection unit, for example, uses the emotion estimation function to predict the emotional reaction of an email recipient and build a system that corrects expressions that may cause the recipient to feel uncomfortable in advance. For example, the system makes suggestions to tone down offensive expressions. The emotion estimation function can also be used to predict the emotional reaction of an email recipient and correct expressions that may cause the recipient to feel uncomfortable in advance. For example, the expression "You are useless" can be changed to "There is room for improvement." The emotion estimation function can also be used to develop a system that predicts the emotional reaction of an email recipient and corrects expressions that may cause the recipient to feel uncomfortable in advance. For example, negative expressions can be replaced with positive expressions. This makes it possible to correct expressions that may cause the recipient to feel uncomfortable in advance.

[0066] The correction result display unit can suggest specific alternative expressions, allowing the sender to make corrections immediately. For example, when the generation AI displays the correction results for an email, the correction result display unit suggests specific alternative expressions. For example, it could suggest "You're always slow at work" as "There's room for improvement in your recent project." The generation AI can also display the correction results for an email, allowing the sender to make corrections immediately. For example, it could suggest specific alternative expressions that soften offensive expressions. It is also possible to build a system in which the generation AI displays the correction results for an email, allowing the sender to make corrections immediately. For example, it could suggest replacing negative expressions with positive ones. This makes it possible to suggest specific alternative expressions, allowing the sender to make corrections immediately.

[0067] The correction result display unit can refer to past email history and provide advice to prevent similar problems from recurring. For example, the generation AI can refer to past email history and provide advice to prevent similar problems from recurring. For example, it can suggest avoiding expressions that have been pointed out in the past. The generation AI can also analyze past email history and provide advice to prevent similar problems from recurring. For example, it can suggest areas for improvement based on past correction results. It is also possible to build a system in which the generation AI refers to past email history and provides advice to prevent similar problems from recurring. For example, it can suggest specific improvement measures based on past problems. This makes it possible to provide advice to prevent similar problems from recurring.

[0068] The correction result display unit can use the emotion estimation function to provide feedback in a format that makes it easy for the sender to accept the email correction results. The correction result display unit can, for example, use the emotion estimation function to provide feedback in a format that makes it easy for the sender to accept the email correction results. For example, positive expressions can be used to point out areas for improvement. It is also possible to use the emotion estimation function to build a system that provides feedback in a format that makes it easy for the sender to accept the email correction results. For example, encouraging words can be used to suggest areas for improvement. It is also possible to use the emotion estimation function to provide feedback in a format that makes it easy for the sender to accept the email correction results. For example, constructive feedback can be provided, avoiding negative expressions. This makes it possible to provide feedback in a format that makes it easy for the sender to accept the email correction results.

[0069] The correction result display unit provides the email correction results by voice, making it possible to accommodate visually impaired people. For example, the correction result display unit uses a generation AI to provide the email correction results by voice, building a system that also accommodates visually impaired people. For example, the correction results are read aloud using voice synthesis technology. The generation AI can also provide the email correction results by voice, making them easy to understand for visually impaired people. For example, specific alternative expressions are suggested by voice. The generation AI can also provide the email correction results by voice, making it possible to accommodate visually impaired people. For example, the correction results are explained using audio guidance. This makes it possible to accommodate visually impaired people.

[0070] The correction result display unit can display the email correction results in real time, allowing the sender to correct problems while composing the email. The correction result display unit, for example, builds a system in which the generation AI displays the email correction results in real time, allowing the sender to correct problems while composing the email. For example, it points out offensive expressions in real time. The generation AI can also display the email correction results in real time, allowing the sender to correct problems while composing the email. For example, it can make suggestions to immediately correct negative expressions. The generation AI can also display the email correction results in real time, allowing the sender to correct problems while composing the email. For example, it can suggest alternative expressions in real time. This allows the sender to correct problems while composing the email.

[0071] The correction result display unit can use the emotion estimation function to predict how the sender will feel about the email correction results and provide appropriate feedback. The correction result display unit can, for example, use the emotion estimation function to predict how the sender will feel about the email correction results and build a system that provides appropriate feedback. For example, positive feedback can be prioritized. The emotion estimation function can also be used to predict how the sender will feel about the email correction results and provide appropriate feedback. For example, expressions that alleviate negative emotions can be used. The emotion estimation function can also be used to predict how the sender will feel about the email correction results and provide appropriate feedback. For example, encouraging words can be added to point out areas for improvement. This makes it possible to predict how the sender will feel about the email correction results and provide appropriate feedback.

[0072] The email analysis unit can perform a detailed analysis of the relationship between the sender and the recipient and evaluate the risk of harassment in specific relationships. For example, the email analysis unit constructs a system in which the generation AI analyzes the relationship between the sender and the recipient in detail and evaluates the risk of harassment in specific relationships. For example, it considers the relationship between a superior and a subordinate. The generation AI can also analyze the relationship between the sender and the recipient and evaluate the risk of harassment in specific relationships. For example, it can evaluate the risk in emails between colleagues. The generation AI can also analyze the relationship between the sender and the recipient in detail and evaluate the risk of harassment in specific relationships. For example, it can evaluate the risk in emails with business partners. This makes it possible to evaluate the risk of harassment in specific relationships.

[0073] The email analysis unit can refer to past exchanges between the sender and recipient and perform analysis taking into account changes in the relationship. For example, the email analysis unit can build a system in which the generation AI refers to past exchanges between the sender and recipient and performs analysis taking into account changes in the relationship. For example, it evaluates the relationship based on past email history. The generation AI can also analyze past exchanges between the sender and recipient and evaluate the risk of harassment taking into account changes in the relationship. For example, it evaluates the risk when there has been an increase in recent exchanges. The generation AI can also refer to past exchanges between the sender and recipient and perform analysis taking into account changes in the relationship. For example, it evaluates the risk when there has been little past exchange. This makes it possible to perform analysis taking into account changes in the relationship.

[0074] The email analysis unit can use the emotion estimation function to analyze the emotional relationship between the sender and the recipient and reduce the risk of harassment. The email analysis unit, for example, uses the emotion estimation function to analyze the emotional relationship between the sender and the recipient and build a system that reduces the risk of harassment. For example, the risk is evaluated based on an emotion score. The emotion estimation function can also be used to analyze the emotional relationship between the sender and the recipient and reduce the risk of harassment. For example, the risk is reduced when positive emotions are strong. The emotion estimation function can also be used to analyze the emotional relationship between the sender and the recipient and reduce the risk of harassment. For example, a warning is displayed when negative emotions are strong. In this way, the emotional relationship can be analyzed and the risk of harassment can be reduced.

[0075] The email analysis unit can suggest an appropriate communication style by taking into account the relationship between the sender and the recipient. The email analysis unit, for example, builds a system in which a generation AI considers the relationship between the sender and the recipient and suggests an appropriate communication style. For example, it proposes expressions that are appropriate for the relationship between a superior and a subordinate. The generation AI can also consider the relationship between the sender and the recipient and suggest an appropriate communication style. For example, it proposes appropriate expressions for emails between colleagues. The generation AI can also consider the relationship between the sender and the recipient and suggest an appropriate communication style. For example, it proposes appropriate expressions for emails with business partners. This makes it possible to suggest an appropriate communication style.

[0076] The email analysis unit can automatically generate email templates taking into account the relationship between sender and recipient. The email analysis unit, for example, builds a system in which a generation AI automatically generates email templates taking into account the relationship between sender and recipient. For example, it generates a template that is appropriate for the relationship between a superior and a subordinate. The generation AI can also automatically generate email templates taking into account the relationship between sender and recipient. For example, it generates an appropriate template for emails between colleagues. The generation AI can also automatically generate email templates taking into account the relationship between sender and recipient. For example, it generates an appropriate template for emails with business partners. This makes it possible to automatically generate email templates.

[0077] The email analysis unit can use the emotion estimation function to provide emotional feedback based on the relationship between the sender and the recipient. The email analysis unit, for example, uses the emotion estimation function to build a system that provides emotional feedback based on the relationship between the sender and the recipient. For example, it prioritizes positive feedback. The emotion estimation function can also be used to provide emotional feedback based on the relationship between the sender and the recipient. For example, it can use expressions that alleviate negative emotions. The emotion estimation function can also be used to provide emotional feedback based on the relationship between the sender and the recipient. For example, it can point out areas for improvement with words of encouragement. In this way, it is possible to provide emotional feedback based on the relationship.

[0078] The email analysis unit analyzes the sender's past email history and can learn expressions that pose a high risk of harassment. The email analysis unit, for example, builds a system in which the generation AI analyzes the sender's past email history and learns expressions that pose a high risk of harassment. For example, it learns expressions that have been pointed out in the past. The generation AI can also analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can identify offensive expressions and add them to the learning data. The generation AI can also analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can learn negative expressions and evaluate the risk. This allows it to learn expressions that pose a high risk of harassment.

[0079] The email analysis unit can analyze the sender's email creation patterns and recommend expressions that pose a low risk of harassment. For example, the email analysis unit constructs a system in which a generation AI analyzes the sender's email creation patterns and recommends expressions that pose a low risk of harassment. For example, it prioritizes recommendations of positive expressions. The generation AI can also analyze the sender's email creation patterns and recommend expressions that pose a low risk of harassment. For example, it makes suggestions to avoid offensive expressions. The generation AI can also analyze the sender's email creation patterns and recommend expressions that pose a low risk of harassment. For example, it presents specific alternative expressions. This makes it possible to recommend expressions that pose a low risk of harassment.

[0080] The email analysis unit can use the emotion estimation function to provide emotional feedback to the sender to increase their awareness of harassment prevention. The email analysis unit, for example, uses the emotion estimation function to build a system that provides emotional feedback to the sender to increase their awareness of harassment prevention. For example, positive feedback is prioritized. The emotion estimation function can also be used to provide emotional feedback to the sender to increase their awareness of harassment prevention. For example, expressions that soften negative emotions are used. The emotion estimation function can also be used to provide emotional feedback to the sender to increase their awareness of harassment prevention. For example, encouraging words are added to point out areas for improvement. In this way, emotional feedback can be provided to the sender to increase their awareness of harassment prevention.

[0081] The email analysis unit can provide a training module for preventing harassment, allowing the sender to learn independently. The email analysis unit, for example, builds a system in which a generation AI provides a training module for preventing harassment, allowing the sender to learn independently. For example, an online course can be provided. The generation AI can also provide a training module for preventing harassment, allowing the sender to learn independently. For example, interactive training can be provided. The generation AI can also provide a training module for preventing harassment, allowing the sender to learn independently. For example, training using a simulation can be provided. In this way, a training module can be provided to allow the sender to learn independently.

[0082] The email analysis unit can automatically generate guidelines for preventing harassment and provide them to the sender. The email analysis unit, for example, builds a system in which a generation AI automatically generates guidelines for preventing harassment and provides them to the sender. For example, it presents specific examples of expression. The generation AI can also automatically generate guidelines for preventing harassment and provide them to the sender. For example, it can provide guidelines for avoiding offensive expression. The generation AI can also automatically generate guidelines for preventing harassment and provide them to the sender. For example, it can provide guidelines that encourage positive expression. In this way, guidelines for preventing harassment can be automatically generated and provided to the sender.

[0083] The email analysis unit can use the emotion estimation function to analyze how the sender feels about learning about harassment prevention and suggest an appropriate learning method. The email analysis unit can, for example, use the emotion estimation function to analyze how the sender feels about learning about harassment prevention and build a system that suggests an appropriate learning method. For example, it can prioritize positive feedback. The emotion estimation function can also be used to analyze how the sender feels about learning about harassment prevention and suggest an appropriate learning method. For example, it can use expressions that alleviate negative emotions. The emotion estimation function can also be used to analyze how the sender feels about learning about harassment prevention and suggest an appropriate learning method. For example, it can include words of encouragement to promote learning. In this way, it is possible to analyze how the sender feels about learning about harassment prevention and suggest an appropriate learning method.

[0084] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0085] The email analysis unit can analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can learn expressions that have been pointed out in the past. The generation AI can also analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can identify offensive expressions and add them to the learning data. The generation AI can also analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can learn negative expressions and evaluate the risk. This allows it to learn expressions that pose a high risk of harassment.

[0086] The email analysis unit can analyze the sender's email composition patterns and recommend expressions that pose a low risk of harassment. For example, a generation AI can analyze the sender's email composition patterns and build a system that recommends expressions that pose a low risk of harassment. For example, it can prioritize and recommend positive expressions. The generation AI can also analyze the sender's email composition patterns and recommend expressions that pose a low risk of harassment. For example, it can make suggestions to avoid offensive expressions. The generation AI can also analyze the sender's email composition patterns and recommend expressions that pose a low risk of harassment. For example, it can present specific alternative expressions. This makes it possible to recommend expressions that pose a low risk of harassment.

[0087] The email analysis unit can use the emotion estimation function to provide emotional feedback to the sender to raise awareness of harassment prevention. For example, the emotion estimation function can be used to build a system that provides emotional feedback to the sender to raise awareness of harassment prevention. For example, positive feedback can be prioritized. The emotion estimation function can also be used to provide emotional feedback to the sender to raise awareness of harassment prevention. For example, expressions that soften negative emotions can be used. The emotion estimation function can also be used to provide emotional feedback to the sender to raise awareness of harassment prevention. For example, encouraging words can be added to point out areas for improvement. In this way, emotional feedback can be provided to the sender to raise awareness of harassment prevention.

[0088] The email analysis unit can provide a training module for preventing harassment, allowing senders to learn independently. For example, a system can be constructed in which the generation AI provides a training module for preventing harassment, allowing senders to learn independently. For example, an online course can be provided. The generation AI can also provide a training module for preventing harassment, allowing senders to learn independently. For example, interactive training can be provided. The generation AI can also provide a training module for preventing harassment, allowing senders to learn independently. For example, training using a simulation can be provided. In this way, a training module can be provided to allow senders to learn independently.

[0089] The email analysis unit can automatically generate guidelines for preventing harassment and provide them to the sender. For example, a system can be built in which the generation AI automatically generates guidelines for preventing harassment and provides them to the sender. For example, it can present specific examples of expression. The generation AI can also automatically generate guidelines for preventing harassment and provide them to the sender. For example, it can provide guidelines for avoiding offensive language. The generation AI can also automatically generate guidelines for preventing harassment and provide them to the sender. For example, it can provide guidelines that encourage positive language. In this way, guidelines for preventing harassment can be automatically generated and provided to the sender.

[0090] The email analysis unit can use the emotion estimation function to analyze how the sender feels about anti-harassment learning and suggest an appropriate learning method. For example, a system can be constructed that uses the emotion estimation function to analyze how the sender feels about anti-harassment learning and suggest an appropriate learning method. For example, positive feedback can be prioritized. The emotion estimation function can also be used to analyze how the sender feels about anti-harassment learning and suggest an appropriate learning method. For example, expressions that alleviate negative emotions can be used. The emotion estimation function can also be used to analyze how the sender feels about anti-harassment learning and suggest an appropriate learning method. For example, encouraging words can be added to promote learning. In this way, it is possible to analyze how the sender feels about anti-harassment learning and suggest an appropriate learning method.

[0091] The email analysis unit can consider the relationship between the sender and the recipient to suggest an appropriate communication style. For example, a system can be constructed in which the generation AI considers the relationship between the sender and the recipient to suggest an appropriate communication style. For example, it can suggest expressions that are appropriate for the relationship between a superior and a subordinate. The generation AI can also consider the relationship between the sender and the recipient to suggest an appropriate communication style. For example, it can suggest appropriate expressions for emails between colleagues. The generation AI can also consider the relationship between the sender and the recipient to suggest an appropriate communication style. For example, it can suggest appropriate expressions for emails with business partners. This makes it possible to suggest an appropriate communication style.

[0092] The email analysis unit can automatically generate email templates by taking into account the relationship between sender and recipient. For example, a system can be built in which the generation AI automatically generates email templates by taking into account the relationship between sender and recipient. For example, it generates a template that is appropriate for the relationship between a superior and a subordinate. The generation AI can also automatically generate email templates by taking into account the relationship between sender and recipient. For example, it can generate an appropriate template for emails between colleagues. The generation AI can also automatically generate email templates by taking into account the relationship between sender and recipient. For example, it can generate an appropriate template for emails with business partners. This makes it possible to automatically generate email templates.

[0093] The email analysis unit can use the emotion estimation function to provide emotional feedback based on the relationship between the sender and the recipient. For example, the emotion estimation function can be used to build a system that provides emotional feedback based on the relationship between the sender and the recipient. For example, positive feedback can be prioritized. The emotion estimation function can also be used to provide emotional feedback based on the relationship between the sender and the recipient. For example, expressions that alleviate negative emotions can be used. The emotion estimation function can also be used to provide emotional feedback based on the relationship between the sender and the recipient. For example, areas for improvement can be pointed out with words of encouragement. In this way, emotional feedback based on the relationship can be provided.

[0094] The email analysis unit can analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, a system can be built in which the generation AI analyzes the sender's past email history and learns expressions that pose a high risk of harassment. For example, it learns expressions that have been pointed out in the past. The generation AI can also analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can identify offensive expressions and add them to the learning data. The generation AI can also analyze the sender's past email history and learn expressions that pose a high risk of harassment. For example, it can learn negative expressions and evaluate the risk. This allows it to learn expressions that pose a high risk of harassment.

[0095] The processing flow of the second embodiment will be briefly explained below.

[0096] Step 1: The email analysis unit analyzes the email content. For example, it can use natural language processing technology to analyze the email text and keyword matching technology to detect specific expressions. It can also use machine learning algorithms to analyze the email content. Step 2: The harassment detection unit detects harassment from the email content analyzed by the email analysis unit. For example, it can detect verbal abuse, sexual harassment, power harassment, and other expressions, and can also analyze the tone and nuance of the email using emotion analysis technology. Step 3: The transmission stop unit stops sending emails if the harassment detection unit detects content that constitutes harassment. For example, it can stop sending emails if they contain specific keywords or if the results of sentiment analysis exceed a certain threshold. Step 4: The correction result display unit displays the correction results for the email whose sending has been stopped by the sending stopping unit. For example, the correction results can be displayed in the form of feedback, such as by displaying suggested corrections or alternative expressions.

[0097] 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.

[0098] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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 a data format such as voice data and text data. 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0099] 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.

[0100] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0101] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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).

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0114] 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.

[0115] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0116] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0126] 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.

[0127] 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.

[0128] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0129] 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.

[0130] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0131] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] In the robot 414, 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 robot 414 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.

[0142] 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.

[0143] 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.

[0144] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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.

[0151] 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."

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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. [Explanation of symbols]

[0164] 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 email analysis unit that analyzes email content; a harassment detection unit that detects content that corresponds to harassment from the email content analyzed by the email analysis unit; a transmission stopping unit that stops sending emails when content that corresponds to harassment is detected by the harassment detection unit; a correction result display unit that displays the correction result of the email whose transmission has been stopped by the transmission stopping unit. A system characterized by:

2. The email analysis unit Analyzes the relationship between the sender and the recipient 2. The system of claim 1.

3. The harassment detection unit Detect harassment specific to a particular industry or culture 2. The system of claim 1.

4. The harassment detection unit Analyze the tone and nuance of the email content to detect early signs of potential harassment 2. The system of claim 1.

5. The harassment detection unit Analyze the emotional state of the email author to prevent them from sending emails in an emotionally unstable state 2. The system of claim 1.

6. The email analysis unit The content of voicemails and video messages is also analyzed to detect harassment.

2. The system of claim 1.

7. The email analysis unit It also analyzes messages on social media and chat apps to detect harassment.

2. The system of claim 1.

8. The harassment detection unit Anticipate the emotional response of email recipients and proactively correct language that may be offensive to the recipient 2. The system of claim 1.

Images