System

Abstract

An object of the system according to the embodiment is to convert a text document into a "passing sentence" that does not cause misunderstanding, and to suppress and make harmless violent phrases and sensitive information.SOLUTION: A system includes a text analysis unit, a conversion unit, a deterrence unit, and a detoxification unit. The text analysis unit analyzes a text document input by a user. The conversion unit converts the text document analyzed by the text analysis unit into a "message" that does not cause misunderstanding. The suppression unit suppresses abuse and sensitive information included in the text document. The detoxification unit detoxifies the abuse and the sensitive information suppressed by the suppression unit.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 technologies have had the problem that text documents are often misleading, making it difficult to prevent damage, especially when they contain abusive language or sensitive information.

[0005] The system according to the embodiment aims to convert text documents into "understandable sentences" that do not invite misunderstandings, and to prevent and neutralize abusive language and sensitive information. [Means for solving the problem]

[0006] The system according to the embodiment includes a text analysis unit, a conversion unit, a suppression unit, and a neutralization unit. The text analysis unit analyzes a text document input by a user. The conversion unit converts the text document analyzed by the text analysis unit into "understandable sentences" that are not misleading. The suppression unit suppresses abusive language and sensitive information contained in the text document. The neutralization unit neutralizes the abusive language and sensitive information suppressed by the suppression unit. [Effects of the Invention]

[0007] The system according to the embodiment can convert text documents into "understandable sentences" that are not misleading, and can prevent and neutralize abusive language and sensitive information. [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) The communication support system according to an embodiment of the present invention converts text documents such as emails and chats into understandable sentences that do not invite misunderstandings, and prevents and neutralizes abusive language and sensitive information such as personal information. This allows users to communicate with peace of mind and prevents misunderstandings and trouble before they occur.

[0029] A communication support system according to an embodiment includes a text analysis unit, a conversion unit, a suppression unit, and a neutralization unit. The text analysis unit analyzes a text document input by a user. For example, the text analysis unit analyzes the structure of the document using morphological analysis. The text analysis unit can also detect grammatical errors using grammatical analysis. The text analysis unit can also understand the meaning of the document using semantic analysis. The conversion unit converts the text document analyzed by the text analysis unit into "understandable sentences" that are not misleading. For example, the conversion unit replaces ambiguous expressions with clear and concise expressions. The conversion unit can also convert misleading expressions into concrete expressions. The conversion unit can also learn the user's past communication history and select optimal expressions. The suppression unit suppresses abusive language and sensitive information contained in the text document. For example, the suppression unit deletes abusive language if the text document contains such language. The suppression unit can also replace abusive language with milder language. The suppression unit can also anonymize personal information if the text document contains such information. The sanitization unit sanitizes the abusive language and sensitive information suppressed by the suppression unit. For example, the sanitization unit further filters the anonymized personal information. The sanitization unit can also completely delete abusive language. The sanitization unit can also mask sensitive information. As a result, the communication support system according to the embodiment allows users to communicate with peace of mind and can prevent misunderstandings and problems. For example, in an internal email system for a company, communication between employees can be facilitated, and misunderstandings and problems can be prevented. Furthermore, in customer support chat, interactions with customers can be made smoother, which is expected to improve customer satisfaction.

[0030] The conversion unit can replace ambiguous or misleading expressions with clear and concise ones. For example, the generation AI in the conversion unit analyzes the user's past email and chat history to learn the user's writing style and expression habits. This allows the text entered by the user to be optimized to match that writing style and convert it into sentences that are less likely to lead to misunderstandings. The conversion unit also selects appropriate expressions for specific recipients based on the user's past communication history. For example, emails to superiors may use more honorific language, while chats with colleagues may use more casual language. The generation AI in the conversion unit also learns the user's past communication history and suggests the optimal expressions for specific situations. For example, when sending a meeting reminder, the generation AI can refer to the expressions used in past reminders to generate more effective sentences. This allows the generation of sentences that are easier to understand by replacing ambiguous or misleading expressions with clear and concise ones.

[0031] If abusive language is included, the suppression unit can delete that part or replace it with milder language. For example, the suppression unit's generation AI learns the context of a specific industry and uses appropriate terminology commonly used in that industry. For example, in the medical industry, it uses terms such as "diagnosis" and "treatment" accurately. The suppression unit also understands the context of a specific project or team and uses appropriate terminology used in that project or team. For example, in a software development team, it uses terms such as "release" and "bug fix." The suppression unit also learns the latest trends and news in a specific industry and uses appropriate terminology based on that. For example, in the financial industry, it uses the latest terms such as "blockchain" and "fintech." This allows the suppression unit to prevent communication problems by deleting abusive language or replacing it with milder language.

[0032] If personal information is included, the sanitization unit can anonymize that portion. For example, the sanitization unit uses a generation AI to analyze the user's emotional state at the time of input and select expressions that elicit positive emotions. For example, if the user is feeling happy, it uses bright and optimistic expressions. The sanitization unit also uses an emotion estimation function to select calm and reassuring expressions if the user is feeling stressed. For example, if the user is feeling anxious, it generates sentences containing encouraging words. The sanitization unit also analyzes the user's emotional state in real time and suggests appropriate expressions according to that emotion. For example, if the user is feeling angry, it uses calm and rational expressions. In this way, if personal information is included, the risk of information leakage can be reduced by anonymizing that portion.

[0033] Generative AI can learn a user's past communication history and generate "understandable sentences" optimized for the user. For example, generative AI analyzes a user's past email and chat history to learn the user's writing style and expression habits. This allows it to optimize the text entered by the user to match that writing style and convert it into sentences that are less likely to lead to misunderstandings. Generative AI also selects appropriate expressions for specific recipients based on the user's past communication history. For example, it may use honorific language in emails to superiors and use casual language in chats with colleagues. Generative AI also learns a user's past communication history and suggests the optimal expression for a specific situation. For example, when sending a meeting reminder, it may refer to the expressions used in past reminders to generate more effective sentences. This allows the system to learn a user's past communication history and generate "understandable sentences" optimized for each individual user, thereby achieving more effective communication.

[0034] Generative AI can facilitate professional communication by understanding context and using specific industry jargon and technical terms appropriately. For example, generative AI can learn the context of a specific industry and use the technical terms commonly used in that industry appropriately. For example, in the medical industry, it would accurately use terms such as "diagnosis" and "treatment." Generative AI can also understand the context of a specific project or team and use the technical terms used in that project or team appropriately. For example, a software development team would use terms such as "release" and "bug fix." Generative AI can also learn the latest trends and news in a specific industry and use appropriate technical terms based on that. For example, in the financial industry, it would use the latest terms such as "blockchain" and "fintech." This allows generative AI to facilitate professional communication by understanding context and using specific industry jargon and technical terms appropriately.

[0035] Generative AI can convert between different languages ​​into "intelligible sentences" and support international communication. For example, generative AI can translate between different languages ​​and convert them into "intelligible sentences" that do not lead to misunderstandings. For example, when translating a Japanese email into English, it can select appropriate expressions by taking cultural nuances into consideration. Generative AI can also provide multilingual chat systems to facilitate communication between users who speak different languages. For example, it can enable English-speaking users and Spanish-speaking users to chat in real time. Generative AI can also appropriately translate technical terms and industry jargon when converting between different languages ​​into "intelligible sentences." For example, when translating technical documents, it can accurately translate technical terms. This allows generative AI to convert between different languages ​​into "intelligible sentences" and support international communication.

[0036] Generative AI can analyze voice input and simultaneously convert it from voice to text and into understandable sentences. For example, generative AI can analyze voice input and simultaneously convert it into understandable sentences that do not lead to misunderstandings. For example, it can convert meeting recordings into text and generate clear and concise minutes. Generative AI can also analyze voice input and facilitate professional communication by appropriately using specific industry and technical terms. For example, it can analyze voice input in medical settings and generate accurate medical certificates. Generative AI can also analyze voice input in real time and convert it into understandable sentences on the spot. For example, it can convert what is said during a conference call into text in real time and share it with all participants. This improves the convenience of voice input by analyzing voice input and simultaneously converting it into understandable sentences.

[0037] The generation AI can learn a user's past speech patterns and predict in advance the possibility of abusive language or sensitive information being included, issuing a warning. For example, the generation AI can analyze a user's past speech patterns and predict in advance the possibility of abusive language or sensitive information being included. For example, it can display a warning message to a user who has made abusive language in the past. The generation AI can also predict the possibility of abusive language or sensitive information being included in a specific situation based on the user's past speech patterns. For example, it can analyze speech made in stressful situations and issue a warning. The generation AI can also learn a user's past speech patterns and predict in real time the possibility of abusive language or sensitive information being included. For example, it can display a warning message if there is a high possibility of abusive language being included in a chat. In this way, by learning a user's past speech patterns and predicting in advance the possibility of abusive language or sensitive information being included and issuing a warning, trouble can be prevented before it occurs.

[0038] Generative AI can understand the context and select appropriate expressions for specific situations, thereby preventing abusive language and sensitive information from being leaked. For example, generative AI analyzes the context and selects appropriate expressions for specific situations. For example, if an emotional discussion is taking place, it will suggest milder expressions. Generative AI also understands the context and selects appropriate expressions in situations where abusive language or sensitive information is likely to be included. For example, if there is a possibility that personal information may be included, it will suggest anonymized expressions. Generative AI also analyzes the context in real time and suggests expressions to prevent abusive language and sensitive information from being included. For example, if there is a high possibility that abusive language will be included in a chat, it will suggest milder expressions. This makes it possible to understand the context and select appropriate expressions for specific situations, thereby preventing abusive language and sensitive information from being leaked.

[0039] Generative AI analyzes the content of images and videos and can deter or neutralize abusive language or sensitive information if it is included. For example, generative AI analyzes the content of images and videos and, if abusive language or sensitive information is included, automatically blurs out the relevant parts. For example, it anonymizes images that contain personal information. Generative AI also analyzes the content of images and videos and, if abusive language is included, deletes the relevant parts. For example, it mutes the audio of videos that contain abusive language. Generative AI also analyzes the content of images and videos in real time and displays a warning message if abusive language or sensitive information is included. For example, it issues a warning if an image containing abusive language is attempted to be uploaded. This allows the content of images and videos to be analyzed and, if abusive language or sensitive information is included, deterred or neutralized, thereby preventing trouble before it occurs.

[0040] The generation AI can instantly analyze input text in real-time chat, detect abusive language or sensitive information, and issue a warning. For example, the generation AI can instantly analyze input text in real-time chat and display a warning message if abusive language or sensitive information is included. For example, it can issue a warning if an attempt is made to send a message containing abusive language. The generation AI can also analyze input text in real-time chat and automatically delete abusive language or sensitive information if it contains such information. For example, it can anonymize messages containing personal information. The generation AI can also analyze input text in real-time chat and replace abusive language or sensitive information with milder language if it contains such information. For example, it can convert a message containing abusive language into milder language. This allows the generation AI to instantly analyze input text in real-time chat, detect abusive language or sensitive information, and issue a warning, thereby preventing trouble before it occurs.

[0041] The server can achieve individualized support by applying different settings and filtering rules to each user when the generation AI operates. For example, the server can apply different filtering rules to each user when the generation AI operates. For example, it can strengthen the abusive language filter for certain users and relax it for other users. The server can also manage different settings for each user, and the generation AI operates based on those settings. For example, it can apply settings that use a lot of technical jargon to certain users. The server can also provide different feedback to each user when the generation AI operates. For example, it can provide detailed feedback to certain users and concise feedback to other users. This allows the server to achieve individualized support by applying different settings and filtering rules to each user when the generation AI operates on the server.

[0042] The server saves the processing results of the generation AI as a log, which can be used for later review and improvement. For example, the server saves the processing results of the generation AI as a log, which can be used for later review and improvement. For example, it evaluates the quality of the generated sentences and identifies areas for improvement. The server also saves the processing results of the generation AI as a log and makes improvements based on user feedback. For example, it identifies areas that users are dissatisfied with and reflects them in the next generation. The server also saves the processing results of the generation AI as a log and reviews them regularly. For example, it evaluates the generated sentences monthly and improves their overall quality. In this way, the quality of the system can be improved by saving the processing results of the generation AI as a log and using the log for later review and improvement.

[0043] The server can link the processing results of the generation AI with other systems to improve the efficiency of the entire business. For example, the server can link the processing results of the generation AI with a CRM system to improve the efficiency of customer support. For example, it can generate automatic responses to customer inquiries. The server can also link the processing results of the generation AI with an ERP system to improve the efficiency of business processes. For example, it can automatically generate appropriate instructions for inventory management and ordering. The server can also link the processing results of the generation AI with other systems to improve the efficiency of the entire business. For example, it can link with a project management system to automatically generate progress reports. In this way, the efficiency of business processes can be improved by linking the processing results of the generation AI with other systems to improve the efficiency of the entire business.

[0044] The server can also apply the processing results of the generation AI to mobile applications, allowing users to use "communicative sentences" anywhere. For example, the server can apply the processing results of the generation AI to mobile applications, allowing users to use "communicative sentences" anywhere. For example, the generation AI runs when composing an email on a smartphone. The server can also integrate the functions of the generation AI into mobile applications, allowing users to generate "communicative sentences" even when they are on the go. For example, the generation AI runs when composing a message in a chat app. The server can also reflect the processing results of the generation AI in real time in mobile applications, allowing users to use "communicative sentences" anywhere. For example, the generation AI runs when creating minutes on a smartphone during a meeting. This allows the processing results of the generation AI to be applied to mobile applications, allowing users to use "communicative sentences" anywhere, thereby improving convenience.

[0045] Generative AI can learn the communication styles of each department within a company and generate "easy-to-understand sentences" that match that style. For example, the sales department uses polite language when speaking to customers, while the technical department uses a lot of technical jargon. Generative AI can also analyze each department's past email and chat history to generate sentences that match that style. For example, the marketing department uses specific expressions related to promotions. Generative AI can also learn the communication styles of each department in real time and generate optimal sentences that match that style. For example, the human resources department uses clear expressions related to recruitment. In this way, it can learn the communication styles of each department within a company and generate "easy-to-understand sentences" that match that style, thereby facilitating smooth internal communication.

[0046] The generation AI can refer to a customer's past inquiry history and suggest the optimal response. For example, the generation AI can analyze a customer's past inquiry history and suggest the optimal response based on that history. For example, if a similar inquiry has been made in the past, it will suggest a way to respond to it. The generation AI also suggests an appropriate response based on the customer's past inquiry history. For example, if a customer inquires about a product they previously purchased, it will provide detailed information about that product. The generation AI also refers to a customer's past inquiry history in real time and suggests the optimal response based on that history. For example, if a customer inquires about a problem they previously solved, it will again suggest a solution to that problem. In this way, by referring to a customer's past inquiry history and suggesting the optimal response, it is possible to improve the efficiency of customer response and customer satisfaction.

[0047] Generative AI can analyze the content of posts on social media and blogs and convert them into "easy-to-understand sentences" that do not lead to misunderstandings. For example, generative AI can analyze the content of posts on social media and blogs and convert them into "easy-to-understand sentences" that do not lead to misunderstandings. For example, it can replace ambiguous expressions with clear and concise ones. Generative AI can also analyze the content of posts on social media and blogs and select appropriate expressions for specific situations. For example, it can convert emotional posts into calmer expressions. Generative AI can also analyze the content of posts on social media and blogs in real time and convert them into "easy-to-understand sentences" that do not lead to misunderstandings. For example, it can anonymize posts that contain personal information. In this way, by analyzing the content of posts on social media and blogs and converting them into "easy-to-understand sentences" that do not lead to misunderstandings, misunderstandings and trouble can be prevented before they occur.

[0048] Generative AI can analyze students' questions and comments and provide appropriate feedback in online classes at educational institutions. For example, generative AI can analyze students' questions and comments in online classes at educational institutions and provide appropriate feedback. For example, it can generate clear and concise answers to students' questions. Generative AI can also analyze students' comments during online classes and provide appropriate feedback. For example, it can provide additional explanations based on the student's level of understanding. Generative AI can also analyze students' questions and comments in real time in online classes at educational institutions and provide appropriate feedback. For example, it can provide words of encouragement if a student is experiencing difficulty. This makes it possible to improve the quality of education in online classes at educational institutions by analyzing students' questions and comments and providing appropriate feedback.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The communication support system can further include an action suggestion unit that analyzes user input in real time and suggests appropriate actions based on the input. For example, when a user sends a meeting reminder, the system can suggest more effective sentences by referring to expressions used in past reminders. Also, when a user reports on the progress of a project, the system can suggest appropriate formats and expressions. Furthermore, when a user deals with customers, the system can suggest optimal ways to deal with them based on past customer service history. In this way, by suggesting appropriate actions based on the user's input, it is possible to improve work efficiency and the quality of communication.

[0051] The communication support system can also be equipped with a terminology suggestion unit that analyzes user input and suggests expressions specialized for specific industries or fields of expertise. For example, in the medical industry, terms such as "diagnosis" and "treatment" can be used accurately. In the financial industry, the latest terms such as "blockchain" and "fintech" can be used. Furthermore, software development teams can use terms such as "release" and "bug fix." This allows for smoother professional communication by suggesting expressions specialized for specific industries or fields of expertise.

[0052] The communication support system can also be equipped with a terminology suggestion unit that analyzes user input and suggests expressions specialized for specific industries or fields of expertise. For example, in the medical industry, terms such as "diagnosis" and "treatment" can be used accurately. In the financial industry, the latest terms such as "blockchain" and "fintech" can be used. Furthermore, software development teams can use terms such as "release" and "bug fix." This allows for smoother professional communication by suggesting expressions specialized for specific industries or fields of expertise.

[0053] The communication support system can also be equipped with a terminology suggestion unit that analyzes user input and suggests expressions specialized for specific industries or fields of expertise. For example, in the medical industry, terms such as "diagnosis" and "treatment" can be used accurately. In the financial industry, the latest terms such as "blockchain" and "fintech" can be used. Furthermore, software development teams can use terms such as "release" and "bug fix." This allows for smoother professional communication by suggesting expressions specialized for specific industries or fields of expertise.

[0054] The communication support system can also be equipped with a terminology suggestion unit that analyzes user input and suggests expressions specialized for specific industries or fields of expertise. For example, in the medical industry, terms such as "diagnosis" and "treatment" can be used accurately. In the financial industry, the latest terms such as "blockchain" and "fintech" can be used. Furthermore, software development teams can use terms such as "release" and "bug fix." This allows for smoother professional communication by suggesting expressions specialized for specific industries or fields of expertise.

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

[0056] Step 1: The text analysis unit analyzes the text document entered by the user. For example, it uses morphological analysis to analyze the structure of the document, grammatical analysis to detect grammatical errors, and semantic analysis to understand the meaning of the document. Step 2: The conversion unit converts the text document analyzed by the text analysis unit into "understandable sentences" that do not invite misunderstandings. For example, it replaces ambiguous expressions with clear and concise expressions, converts misleading expressions into concrete expressions, and learns the user's past communication history to select the most appropriate expressions. Step 3: The suppression unit suppresses abusive language and sensitive information contained in the text document. For example, if abusive language is included, it will be deleted, or if abusive language is replaced with a milder expression, it will be anonymized if personal information is included. Step 4: The sanitization unit sanitizes the abusive language and sensitive information suppressed by the suppression unit. For example, it further filters the anonymized personal information, completely removes abusive language, and masks sensitive information.

[0057] (Example 2) The communication support system according to an embodiment of the present invention converts text documents such as emails and chats into understandable sentences that do not invite misunderstandings, and prevents and neutralizes abusive language and sensitive information such as personal information. This allows users to communicate with peace of mind and prevents misunderstandings and trouble before they occur.

[0058] A communication support system according to an embodiment includes a text analysis unit, a conversion unit, a suppression unit, and a neutralization unit. The text analysis unit analyzes a text document input by a user. For example, the text analysis unit analyzes the structure of the document using morphological analysis. The text analysis unit can also detect grammatical errors using grammatical analysis. The text analysis unit can also understand the meaning of the document using semantic analysis. The conversion unit converts the text document analyzed by the text analysis unit into "understandable sentences" that are not misleading. For example, the conversion unit replaces ambiguous expressions with clear and concise expressions. The conversion unit can also convert misleading expressions into concrete expressions. The conversion unit can also learn the user's past communication history and select optimal expressions. The suppression unit suppresses abusive language and sensitive information contained in the text document. For example, the suppression unit deletes abusive language if the text document contains such language. The suppression unit can also replace abusive language with milder language. The suppression unit can also anonymize personal information if the text document contains such information. The sanitization unit sanitizes the abusive language and sensitive information suppressed by the suppression unit. For example, the sanitization unit further filters the anonymized personal information. The sanitization unit can also completely delete abusive language. The sanitization unit can also mask sensitive information. As a result, the communication support system according to the embodiment allows users to communicate with peace of mind and can prevent misunderstandings and problems. For example, in an internal email system for a company, communication between employees can be facilitated, and misunderstandings and problems can be prevented. Furthermore, in customer support chat, interactions with customers can be made smoother, which is expected to improve customer satisfaction.

[0059] The conversion unit can replace ambiguous or misleading expressions with clear and concise ones. For example, the generation AI in the conversion unit analyzes the user's past email and chat history to learn the user's writing style and expression habits. This allows the text entered by the user to be optimized to match that writing style and convert it into sentences that are less likely to lead to misunderstandings. The conversion unit also selects appropriate expressions for specific recipients based on the user's past communication history. For example, emails to superiors may use more honorific language, while chats with colleagues may use more casual language. The generation AI in the conversion unit also learns the user's past communication history and suggests the optimal expressions for specific situations. For example, when sending a meeting reminder, the generation AI can refer to the expressions used in past reminders to generate more effective sentences. This allows the generation of sentences that are easier to understand by replacing ambiguous or misleading expressions with clear and concise ones.

[0060] If abusive language is included, the suppression unit can delete that part or replace it with milder language. For example, the suppression unit's generation AI learns the context of a specific industry and uses appropriate terminology commonly used in that industry. For example, in the medical industry, it uses terms such as "diagnosis" and "treatment" accurately. The suppression unit also understands the context of a specific project or team and uses appropriate terminology used in that project or team. For example, in a software development team, it uses terms such as "release" and "bug fix." The suppression unit also learns the latest trends and news in a specific industry and uses appropriate terminology based on that. For example, in the financial industry, it uses the latest terms such as "blockchain" and "fintech." This allows the suppression unit to prevent communication problems by deleting abusive language or replacing it with milder language.

[0061] If personal information is included, the sanitization unit can anonymize that portion. For example, the sanitization unit uses a generation AI to analyze the user's emotional state at the time of input and select expressions that elicit positive emotions. For example, if the user is feeling happy, it uses bright and optimistic expressions. The sanitization unit also uses an emotion estimation function to select calm and reassuring expressions if the user is feeling stressed. For example, if the user is feeling anxious, it generates sentences containing encouraging words. The sanitization unit also analyzes the user's emotional state in real time and suggests appropriate expressions according to that emotion. For example, if the user is feeling angry, it uses calm and rational expressions. In this way, if personal information is included, the risk of information leakage can be reduced by anonymizing that portion.

[0062] Generative AI can learn a user's past communication history and generate "understandable sentences" optimized for the user. For example, generative AI analyzes a user's past email and chat history to learn the user's writing style and expression habits. This allows it to optimize the text entered by the user to match that writing style and convert it into sentences that are less likely to lead to misunderstandings. Generative AI also selects appropriate expressions for specific recipients based on the user's past communication history. For example, it may use honorific language in emails to superiors and use casual language in chats with colleagues. Generative AI also learns a user's past communication history and suggests the optimal expression for a specific situation. For example, when sending a meeting reminder, it may refer to the expressions used in past reminders to generate more effective sentences. This allows the system to learn a user's past communication history and generate "understandable sentences" optimized for each individual user, thereby achieving more effective communication.

[0063] Generative AI can facilitate professional communication by understanding context and using specific industry jargon and technical terms appropriately. For example, generative AI can learn the context of a specific industry and use the technical terms commonly used in that industry appropriately. For example, in the medical industry, it would accurately use terms such as "diagnosis" and "treatment." Generative AI can also understand the context of a specific project or team and use the technical terms used in that project or team appropriately. For example, a software development team would use terms such as "release" and "bug fix." Generative AI can also learn the latest trends and news in a specific industry and use appropriate technical terms based on that. For example, in the financial industry, it would use the latest terms such as "blockchain" and "fintech." This allows generative AI to facilitate professional communication by understanding context and using specific industry jargon and technical terms appropriately.

[0064] The generation AI uses its emotion estimation function to estimate the user's emotional state and select expressions that correspond to those emotions, thereby converting the text into one that is more likely to garner empathy. For example, the generation AI analyzes the user's emotional state at the time of input and selects expressions that elicit positive emotions. For example, if the user is feeling happy, it uses bright and optimistic expressions. The generation AI also uses its emotion estimation function to select calm and reassuring expressions if the user is feeling stressed. For example, if the user is feeling anxious, it generates text that includes encouraging words. The generation AI also analyzes the user's emotional state in real time and suggests appropriate expressions according to that emotion. For example, if the user is feeling angry, it uses calm and rational expressions. In this way, the emotion estimation function can be used to estimate the user's emotional state and select expressions that correspond to that emotion, thereby converting the text into one that is more likely to garner empathy.

[0065] Generative AI can convert between different languages ​​into "intelligible sentences" and support international communication. For example, generative AI can translate between different languages ​​and convert them into "intelligible sentences" that do not lead to misunderstandings. For example, when translating a Japanese email into English, it can select appropriate expressions by taking cultural nuances into consideration. Generative AI can also provide multilingual chat systems to facilitate communication between users who speak different languages. For example, it can enable English-speaking users and Spanish-speaking users to chat in real time. Generative AI can also appropriately translate technical terms and industry jargon when converting between different languages ​​into "intelligible sentences." For example, when translating technical documents, it can accurately translate technical terms. This allows generative AI to convert between different languages ​​into "intelligible sentences" and support international communication.

[0066] Generative AI can analyze voice input and simultaneously convert it from voice to text and into understandable sentences. For example, generative AI can analyze voice input and simultaneously convert it into understandable sentences that do not lead to misunderstandings. For example, it can convert meeting recordings into text and generate clear and concise minutes. Generative AI can also analyze voice input and facilitate professional communication by appropriately using specific industry and technical terms. For example, it can analyze voice input in medical settings and generate accurate medical certificates. Generative AI can also analyze voice input in real time and convert it into understandable sentences on the spot. For example, it can convert what is said during a conference call into text in real time and share it with all participants. This improves the convenience of voice input by analyzing voice input and simultaneously converting it into understandable sentences.

[0067] The generative AI can use the emotion estimation function to analyze the emotions of the user as they type in real time and make suggestions to elicit positive emotions. For example, the generative AI can use the emotion estimation function to analyze the emotions of the user as they type in real time and make suggestions to elicit positive emotions. For example, if the user is feeling stressed, it can suggest words of encouragement. The generative AI can also analyze the user's emotional state and provide an interface for eliciting positive emotions. For example, it can display guidelines for eliciting positive emotions as the user types. The generative AI can also use the emotion estimation function to analyze the emotions of the user as they type in real time and provide feedback for eliciting positive emotions. For example, it can display advice for eliciting positive emotions as the user types. In this way, the user's emotional state can be improved by using the emotion estimation function to analyze the emotions of the user as they type in real time and make suggestions to elicit positive emotions.

[0068] The generation AI can learn a user's past speech patterns and predict in advance the possibility of abusive language or sensitive information being included, issuing a warning. For example, the generation AI can analyze a user's past speech patterns and predict in advance the possibility of abusive language or sensitive information being included. For example, it can display a warning message to a user who has made abusive language in the past. The generation AI can also predict the possibility of abusive language or sensitive information being included in a specific situation based on the user's past speech patterns. For example, it can analyze speech made in stressful situations and issue a warning. The generation AI can also learn a user's past speech patterns and predict in real time the possibility of abusive language or sensitive information being included. For example, it can display a warning message if there is a high possibility of abusive language being included in a chat. In this way, by learning a user's past speech patterns and predicting in advance the possibility of abusive language or sensitive information being included and issuing a warning, trouble can be prevented before it occurs.

[0069] Generative AI can understand the context and select appropriate expressions for specific situations, thereby preventing abusive language and sensitive information from being leaked. For example, generative AI analyzes the context and selects appropriate expressions for specific situations. For example, if an emotional discussion is taking place, it will suggest milder expressions. Generative AI also understands the context and selects appropriate expressions in situations where abusive language or sensitive information is likely to be included. For example, if there is a possibility that personal information may be included, it will suggest anonymized expressions. Generative AI also analyzes the context in real time and suggests expressions to prevent abusive language and sensitive information from being included. For example, if there is a high possibility that abusive language will be included in a chat, it will suggest milder expressions. This makes it possible to understand the context and select appropriate expressions for specific situations, thereby preventing abusive language and sensitive information from being leaked.

[0070] The generation AI can use the emotion estimation function to estimate the user's emotional state and suggest calmer expressions when negative emotions are rising. For example, the generation AI can use the emotion estimation function to analyze the user's emotional state in real time and suggest calmer expressions when negative emotions are rising. For example, it can suggest calmer expressions to a user who is feeling angry. The generation AI can also analyze the user's emotional state and select calmer expressions when negative emotions are rising. For example, it can suggest expressions that give a sense of security to a user who is feeling stressed. The generation AI can also use the emotion estimation function to monitor the user's emotional state in real time and suggest calmer expressions when negative emotions are rising. For example, it can suggest words of encouragement to a user who is feeling anxious. In this way, by using the emotion estimation function to estimate the user's emotional state and suggesting calmer expressions when negative emotions are rising, trouble can be prevented before they occur.

[0071] Generative AI analyzes the content of images and videos and can deter or neutralize abusive language or sensitive information if it is included. For example, generative AI analyzes the content of images and videos and, if abusive language or sensitive information is included, automatically blurs out the relevant parts. For example, it anonymizes images that contain personal information. Generative AI also analyzes the content of images and videos and, if abusive language is included, deletes the relevant parts. For example, it mutes the audio of videos that contain abusive language. Generative AI also analyzes the content of images and videos in real time and displays a warning message if abusive language or sensitive information is included. For example, it issues a warning if an image containing abusive language is attempted to be uploaded. This allows the content of images and videos to be analyzed and, if abusive language or sensitive information is included, deterred or neutralized, thereby preventing trouble before it occurs.

[0072] The generation AI can instantly analyze input text in real-time chat, detect abusive language or sensitive information, and issue a warning. For example, the generation AI can instantly analyze input text in real-time chat and display a warning message if abusive language or sensitive information is included. For example, it can issue a warning if an attempt is made to send a message containing abusive language. The generation AI can also analyze input text in real-time chat and automatically delete abusive language or sensitive information if it contains such information. For example, it can anonymize messages containing personal information. The generation AI can also analyze input text in real-time chat and replace abusive language or sensitive information with milder language if it contains such information. For example, it can convert a message containing abusive language into milder language. This allows the generation AI to instantly analyze input text in real-time chat, detect abusive language or sensitive information, and issue a warning, thereby preventing trouble before it occurs.

[0073] The generation AI can use the emotion estimation function to analyze the emotions of the user when they enter text in real time and make suggestions to alleviate negative emotions. For example, the generation AI can use the emotion estimation function to analyze the emotions of the user when they enter text in real time and suggest calmer expressions when negative emotions are rising. For example, it can suggest calmer expressions to a user who is feeling angry. The generation AI can also analyze the user's emotional state and select calmer expressions when negative emotions are rising. For example, it can suggest expressions that give a sense of security to a user who is feeling stressed. The generation AI can also use the emotion estimation function to monitor the user's emotional state in real time and suggest calmer expressions when negative emotions are rising. For example, it can suggest words of encouragement to a user who is feeling anxious. In this way, the emotion estimation function can be used to analyze the emotions of the user when they enter text in real time and make suggestions to alleviate negative emotions, thereby improving the user's emotional state.

[0074] The server can achieve individualized support by applying different settings and filtering rules to each user when the generation AI operates. For example, the server can apply different filtering rules to each user when the generation AI operates. For example, it can strengthen the abusive language filter for certain users and relax it for other users. The server can also manage different settings for each user, and the generation AI operates based on those settings. For example, it can apply settings that use a lot of technical jargon to certain users. The server can also provide different feedback to each user when the generation AI operates. For example, it can provide detailed feedback to certain users and concise feedback to other users. This allows the server to achieve individualized support by applying different settings and filtering rules to each user when the generation AI operates on the server.

[0075] The server saves the processing results of the generation AI as a log, which can be used for later review and improvement. For example, the server saves the processing results of the generation AI as a log, which can be used for later review and improvement. For example, it evaluates the quality of the generated sentences and identifies areas for improvement. The server also saves the processing results of the generation AI as a log and makes improvements based on user feedback. For example, it identifies areas that users are dissatisfied with and reflects them in the next generation. The server also saves the processing results of the generation AI as a log and reviews them regularly. For example, it evaluates the generated sentences monthly and improves their overall quality. In this way, the quality of the system can be improved by saving the processing results of the generation AI as a log and using the log for later review and improvement.

[0076] The server can use the emotion estimation function to monitor the user's emotional state in real time and provide appropriate feedback. For example, the server can use the emotion estimation function to monitor the user's emotional state in real time and provide appropriate feedback. For example, if the user is feeling stressed, the server can provide advice to relax. The server can also analyze the user's emotional state and, if negative emotions are rising, suggest calmer expressions. For example, if the user is feeling anger, the server can suggest calmer expressions. The server can also use the emotion estimation function to monitor the user's emotional state in real time and provide feedback to elicit positive emotions. For example, if the user is feeling anxious, the server can provide words of encouragement. In this way, the server can use the emotion estimation function to monitor the user's emotional state in real time and provide appropriate feedback to improve the user's emotional state.

[0077] The server can link the processing results of the generation AI with other systems to improve the efficiency of the entire business. For example, the server can link the processing results of the generation AI with a CRM system to improve the efficiency of customer support. For example, it can generate automatic responses to customer inquiries. The server can also link the processing results of the generation AI with an ERP system to improve the efficiency of business processes. For example, it can automatically generate appropriate instructions for inventory management and ordering. The server can also link the processing results of the generation AI with other systems to improve the efficiency of the entire business. For example, it can link with a project management system to automatically generate progress reports. In this way, the efficiency of business processes can be improved by linking the processing results of the generation AI with other systems to improve the efficiency of the entire business.

[0078] The server can also apply the processing results of the generation AI to mobile applications, allowing users to use "communicative sentences" anywhere. For example, the server can apply the processing results of the generation AI to mobile applications, allowing users to use "communicative sentences" anywhere. For example, the generation AI runs when composing an email on a smartphone. The server can also integrate the functions of the generation AI into mobile applications, allowing users to generate "communicative sentences" even when they are on the go. For example, the generation AI runs when composing a message in a chat app. The server can also reflect the processing results of the generation AI in real time in mobile applications, allowing users to use "communicative sentences" anywhere. For example, the generation AI runs when creating minutes on a smartphone during a meeting. This allows the processing results of the generation AI to be applied to mobile applications, allowing users to use "communicative sentences" anywhere, thereby improving convenience.

[0079] The server can use the emotion estimation function to analyze the user's emotional state and provide customized feedback to elicit positive emotions. For example, the server uses the emotion estimation function to analyze the user's emotional state and provide customized feedback to elicit positive emotions. For example, if the user is feeling stressed, the server provides advice to relax. The server also analyzes the user's emotional state and suggests calmer expressions if negative emotions are rising. For example, if the user is feeling angry, the server suggests calmer expressions. The server also uses the emotion estimation function to monitor the user's emotional state in real time and provide feedback to elicit positive emotions. For example, if the user is feeling anxious, the server provides words of encouragement. In this way, the server can use the emotion estimation function to analyze the user's emotional state and provide customized feedback to elicit positive emotions, thereby improving the user's emotional state.

[0080] Generative AI can learn the communication styles of each department within a company and generate "easy-to-understand sentences" that match that style. For example, the sales department uses polite language when speaking to customers, while the technical department uses a lot of technical jargon. Generative AI can also analyze each department's past email and chat history to generate sentences that match that style. For example, the marketing department uses specific expressions related to promotions. Generative AI can also learn the communication styles of each department in real time and generate optimal sentences that match that style. For example, the human resources department uses clear expressions related to recruitment. In this way, it can learn the communication styles of each department within a company and generate "easy-to-understand sentences" that match that style, thereby facilitating smooth internal communication.

[0081] The generation AI can refer to a customer's past inquiry history and suggest the optimal response. For example, the generation AI can analyze a customer's past inquiry history and suggest the optimal response based on that history. For example, if a similar inquiry has been made in the past, it will suggest a way to respond to it. The generation AI also suggests an appropriate response based on the customer's past inquiry history. For example, if a customer inquires about a product they previously purchased, it will provide detailed information about that product. The generation AI also refers to a customer's past inquiry history in real time and suggests the optimal response based on that history. For example, if a customer inquires about a problem they previously solved, it will again suggest a solution to that problem. In this way, by referring to a customer's past inquiry history and suggesting the optimal response, it is possible to improve the efficiency of customer response and customer satisfaction.

[0082] The emotion estimation function can analyze a customer's emotional state in a customer support chat in real time and suggest an appropriate response. For example, if a customer is feeling dissatisfied, the emotion estimation function can suggest a quick response. The emotion estimation function also uses a generative AI to analyze a customer's emotional state and suggest calmer expressions if negative emotions are rising. For example, if a customer is feeling angry, the function can suggest calmer expressions. The emotion estimation function also monitors a customer's emotional state in a customer support chat in real time and suggests responses to elicit positive emotions. For example, if a customer is feeling anxious, the function can provide words of encouragement. This makes it possible to analyze a customer's emotional state in a customer support chat in real time and suggest appropriate responses, thereby improving customer satisfaction.

[0083] Generative AI can analyze the content of posts on social media and blogs and convert them into "easy-to-understand sentences" that do not lead to misunderstandings. For example, generative AI can analyze the content of posts on social media and blogs and convert them into "easy-to-understand sentences" that do not lead to misunderstandings. For example, it can replace ambiguous expressions with clear and concise ones. Generative AI can also analyze the content of posts on social media and blogs and select appropriate expressions for specific situations. For example, it can convert emotional posts into calmer expressions. Generative AI can also analyze the content of posts on social media and blogs in real time and convert them into "easy-to-understand sentences" that do not lead to misunderstandings. For example, it can anonymize posts that contain personal information. In this way, by analyzing the content of posts on social media and blogs and converting them into "easy-to-understand sentences" that do not lead to misunderstandings, misunderstandings and trouble can be prevented before they occur.

[0084] Generative AI can analyze students' questions and comments and provide appropriate feedback in online classes at educational institutions. For example, generative AI can analyze students' questions and comments in online classes at educational institutions and provide appropriate feedback. For example, it can generate clear and concise answers to students' questions. Generative AI can also analyze students' comments during online classes and provide appropriate feedback. For example, it can provide additional explanations based on the student's level of understanding. Generative AI can also analyze students' questions and comments in real time in online classes at educational institutions and provide appropriate feedback. For example, it can provide words of encouragement if a student is experiencing difficulty. This makes it possible to improve the quality of education in online classes at educational institutions by analyzing students' questions and comments and providing appropriate feedback.

[0085] The emotion estimation function can analyze a user's emotional response to content posted on social media or a blog and make suggestions to elicit a positive response. For example, the emotion estimation function can analyze a user's emotional response to content posted on social media or a blog in real time and make suggestions to elicit a positive response. For example, it can suggest expressions that make the user feel happy. The emotion estimation function also analyzes the content of the post using a generative AI, and if there are many negative emotional responses, it can suggest expressions that elicit a positive response. For example, if the user is feeling dissatisfied, it can suggest words of encouragement. The emotion estimation function also analyzes a user's emotional response to content posted on social media or a blog and provides feedback to elicit a positive response. For example, if the user is feeling anxious, it can suggest expressions that give a sense of security. In this way, the user's emotional state can be improved by analyzing the user's emotional response to content posted on social media or a blog and making suggestions to elicit a positive response.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The communication support system can further include a feedback unit that estimates the user's emotions and provides appropriate feedback based on the estimated emotions. For example, if the user is feeling stressed, advice to relax can be provided. If the user is feeling happy, positive feedback can be provided to further enhance that emotion. Furthermore, if the user is feeling anxious, it is possible to suggest expressions that will give a sense of security. In this way, the quality of communication can be improved by providing appropriate feedback according to the user's emotional state.

[0088] The communication support system can further include an action suggestion unit that analyzes user input in real time and suggests appropriate actions based on the input. For example, when a user sends a meeting reminder, the system can suggest more effective sentences by referring to expressions used in past reminders. Also, when a user reports on the progress of a project, the system can suggest appropriate formats and expressions. Furthermore, when a user deals with customers, the system can suggest optimal ways to deal with them based on past customer service history. In this way, by suggesting appropriate actions based on the user's input, it is possible to improve work efficiency and the quality of communication.

[0089] The communication support system can further include an expression selection unit that estimates the user's emotions and selects an appropriate expression based on the estimated emotions. For example, if the user is feeling angry, a calm and rational expression can be suggested. If the user is feeling happy, a cheerful expression can be suggested to further enhance that emotion. Furthermore, if the user is feeling anxious, an expression that gives a sense of security can be suggested. In this way, the quality of communication can be improved by selecting an appropriate expression according to the user's emotional state.

[0090] The communication support system can also be equipped with a terminology suggestion unit that analyzes user input and suggests expressions specialized for specific industries or fields of expertise. For example, in the medical industry, terms such as "diagnosis" and "treatment" can be used accurately. In the financial industry, the latest terms such as "blockchain" and "fintech" can be used. Furthermore, software development teams can use terms such as "release" and "bug fix." This allows for smoother professional communication by suggesting expressions specialized for specific industries or fields of expertise.

[0091] The communication support system can further include a feedback unit that estimates the user's emotions and provides appropriate feedback based on the estimated emotions. For example, if the user is feeling stressed, advice to relax can be provided. If the user is feeling happy, positive feedback can be provided to further enhance that emotion. Furthermore, if the user is feeling anxious, it is possible to suggest expressions that will give a sense of security. In this way, the quality of communication can be improved by providing appropriate feedback according to the user's emotional state.

[0092] The communication support system can also be equipped with a terminology suggestion unit that analyzes user input and suggests expressions specialized for specific industries or fields of expertise. For example, in the medical industry, terms such as "diagnosis" and "treatment" can be used accurately. In the financial industry, the latest terms such as "blockchain" and "fintech" can be used. Furthermore, software development teams can use terms such as "release" and "bug fix." This allows for smoother professional communication by suggesting expressions specialized for specific industries or fields of expertise.

[0093] The communication support system can further include an expression selection unit that estimates the user's emotions and selects an appropriate expression based on the estimated emotions. For example, if the user is feeling angry, a calm and rational expression can be suggested. If the user is feeling happy, a cheerful expression can be suggested to further enhance that emotion. Furthermore, if the user is feeling anxious, an expression that gives a sense of security can be suggested. In this way, the quality of communication can be improved by selecting an appropriate expression according to the user's emotional state.

[0094] The communication support system can also be equipped with a terminology suggestion unit that analyzes user input and suggests expressions specialized for specific industries or fields of expertise. For example, in the medical industry, terms such as "diagnosis" and "treatment" can be used accurately. In the financial industry, the latest terms such as "blockchain" and "fintech" can be used. Furthermore, software development teams can use terms such as "release" and "bug fix." This allows for smoother professional communication by suggesting expressions specialized for specific industries or fields of expertise.

[0095] The communication support system can further include a feedback unit that estimates the user's emotions and provides appropriate feedback based on the estimated emotions. For example, if the user is feeling stressed, advice to relax can be provided. If the user is feeling happy, positive feedback can be provided to further enhance that emotion. Furthermore, if the user is feeling anxious, it is possible to suggest expressions that will give a sense of security. In this way, the quality of communication can be improved by providing appropriate feedback according to the user's emotional state.

[0096] The communication support system can also be equipped with a terminology suggestion unit that analyzes user input and suggests expressions specialized for specific industries or fields of expertise. For example, in the medical industry, terms such as "diagnosis" and "treatment" can be used accurately. In the financial industry, the latest terms such as "blockchain" and "fintech" can be used. Furthermore, software development teams can use terms such as "release" and "bug fix." This allows for smoother professional communication by suggesting expressions specialized for specific industries or fields of expertise.

[0097] The processing flow of the second embodiment will be briefly explained below.

[0098] Step 1: The text analysis unit analyzes the text document entered by the user. For example, it uses morphological analysis to analyze the structure of the document, grammatical analysis to detect grammatical errors, and semantic analysis to understand the meaning of the document. Step 2: The conversion unit converts the text document analyzed by the text analysis unit into "understandable sentences" that do not invite misunderstandings. For example, it replaces ambiguous expressions with clear and concise expressions, converts misleading expressions into concrete expressions, and learns the user's past communication history to select the most appropriate expressions. Step 3: The suppression unit suppresses abusive language and sensitive information contained in the text document. For example, if abusive language is included, it will be deleted, or if abusive language is replaced with a milder expression, it will be anonymized if personal information is included. Step 4: The sanitization unit sanitizes the abusive language and sensitive information suppressed by the suppression unit. For example, it further filters the anonymized personal information, completely removes abusive language, and masks sensitive information.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0103] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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).

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0118] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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."

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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]

[0166] 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. a text analysis unit that analyzes a text document input by a user; a conversion unit that converts the text document analyzed by the text analysis unit into a "communicative sentence" that does not invite misunderstanding; a suppression unit that suppresses abusive language and sensitive information contained in the text document; a neutralization unit that neutralizes the abusive language and sensitive information inhibited by the inhibition unit. A system characterized by:

2. The conversion unit Replace ambiguous or misleading language with clear and concise language.

2. The system of claim 1.

3. The suppression portion is If the abusive language is included, delete it or replace it with the milder language.

2. The system of claim 1.

4. The detoxification unit If personal information is included, that information will be anonymized 2. The system of claim 1.

5. The generating AI is The communication history of the user is learned, and the sentences that are optimized for the user are generated.

2. The system of claim 1.

Images