System

Abstract

An object of the system according to the embodiment is to detect an unconscious inappropriate utterance and prevent it in advance.SOLUTION: A system according to an embodiment includes a reception unit, an analysis unit, a warning unit, and a proposal unit. The reception unit receives an utterance. The analysis unit analyzes the utterance input by the reception unit. The warning unit displays a warning when a statement determined to be inappropriate based on a specific criterion is detected by the analysis unit. The suggestion unit suggests a correction to the remark warned by the warning 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 not adequately prevented unintentional inappropriate comments from being made in advance, and there is room for improvement.

[0005] The system according to the embodiment aims to detect unintentional inappropriate remarks and prevent them in advance. [Means for solving the problem]

[0006] The system according to the embodiment includes a receiving unit, an analysis unit, a warning unit, and a suggestion unit. The receiving unit inputs a comment. The analysis unit analyzes the comment input by the receiving unit. The warning unit displays a warning when it detects a comment that the analysis unit determines to be inappropriate based on specific criteria. The suggestion unit suggests corrections to the comment warned about by the warning unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect unintentional inappropriate remarks and prevent them in advance. [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) A tool according to an embodiment of the present invention is a system that detects unintentional inappropriate comments and prevents them by issuing warnings and suggesting corrections. In this system, a user inputs a comment, and a generation AI analyzes the comment to detect whether it contains inappropriate content. If so, a warning is displayed to the user and a suggestion for correction is made. For example, when a user inputs a comment via chat or social media, the comment is input to a generation AI. The generation AI uses natural language processing technology to understand the content of the comment and detect whether it contains inappropriate content. For example, it detects discriminatory or offensive language. If so, a warning message is displayed to the user, such as "This comment is inappropriate." Specific suggestions for correction, such as "Avoid using this expression," are also made. This allows users to recognize and correct their own inappropriate comments. Furthermore, this tool can be used in a variety of settings, including educational settings and the workplace. For example, it can prevent students from making inappropriate comments during class and prevent workplace harassment. This tool can improve the quality of communication by detecting unintentional inappropriate comments and issuing warnings and suggesting corrections. For example, communication on chat and social media will become smoother. It will also help maintain a healthy environment by preventing inappropriate comments in educational settings and the workplace.

[0029] An inappropriate remark prevention system according to an embodiment includes a receiving unit, an analysis unit, a warning unit, and a suggestion unit. The receiving unit receives a user's input of a remark. The remark may be, for example, a verbal remark, a text message, or a social media post, but is not limited to these examples. The receiving unit receives the remark through, for example, a chat application or a social networking platform. The receiving unit may also receive the remark using voice input. The analysis unit uses a generation AI to analyze the remark input. The analysis may be performed using, for example, natural language processing technology, but is not limited to these examples. For example, the generation AI understands the content of the remark using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The analysis unit may also use the generation AI to understand the context of the remark and detect whether the remark contains inappropriate content. For example, the generation AI detects discriminatory language or offensive language. The warning unit displays a warning to the user when the analysis unit detects an inappropriate remark. The warning may be, for example, a message such as "This remark is inappropriate," but is not limited to these examples. For example, the warning unit displays the warning using a pop-up message or a voice alert. The warning unit can also issue a warning using an email notification. The suggestion unit makes a suggestion for correcting a statement warned by the warning unit. The suggestion may be displayed with specific content such as, for example, "Avoid using this expression," but is not limited to such an example. For example, the suggestion unit presents alternative expressions or provides specific examples of correction. The suggestion unit can also make suggestions including specific use scenarios in educational settings or the workplace. For example, the suggestion unit makes suggestions for correcting statements made during class or meetings. In this way, the inappropriate remarks prevention system according to the embodiment can detect unintentional inappropriate remarks and prevent them in advance by issuing a warning or suggesting corrections. For example, the user can realize that their remarks are inappropriate and correct them. Furthermore, preventing inappropriate remarks in educational settings or the workplace can maintain a healthy environment.

[0030] The analysis unit can use natural language processing technology to understand the content of a utterance and detect whether it contains content deemed inappropriate based on specific criteria. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit can use morphological analysis to break down the words in a utterance and grammatical analysis to analyze the structure of the sentence. The analysis unit can also use semantic analysis to understand the meaning of the utterance. For example, the analysis unit can understand the context of the utterance and detect whether it contains content deemed inappropriate based on specific criteria. In this way, natural language processing technology can accurately understand the content of the utterance and detect inappropriate content. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input a utterance into a generation AI, which can analyze the content of the utterance and detect inappropriate content.

[0031] The warning unit can display a message such as "This comment has been determined to be inappropriate based on specific criteria." For example, the warning unit displays a pop-up message such as "This comment has been determined to be inappropriate based on specific criteria." The warning unit can also issue a warning using an audio alert. For example, the warning unit issues an audio warning such as "This comment is inappropriate." The warning unit can also issue a warning using an email notification. For example, the warning unit can send a warning message to the user by email. By doing so, the user can be warned of inappropriate comments and be prompted to correct the comment. Some or all of the above-described processing in the warning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the warning unit displays a warning message when the generation AI detects an inappropriate comment.

[0032] The suggestion unit can display specific suggestions such as, "This expression is determined to be inappropriate based on specific criteria, so please avoid using it." For example, the suggestion unit displays specific suggestions such as, "This expression is determined to be inappropriate based on specific criteria, so please avoid using it," in a pop-up. The suggestion unit can also present alternative expressions and provide specific correction examples. For example, the suggestion unit can make suggestions such as, "Instead of this expression, try using this expression." The suggestion unit can also make suggestions including specific usage scenarios in educational settings or the workplace. For example, the suggestion unit can make correction suggestions for comments made during class or meetings. This can encourage the user to use appropriate expressions by providing specific correction suggestions to the user. Some or all of the above-mentioned processing in the suggestion unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the suggestion unit can make correction suggestions when the generation AI detects inappropriate comments.

[0033] The analysis unit can detect expressions that are judged to be discriminatory or offensive based on specific criteria. The analysis unit, for example, uses a specific keyword list to detect discriminatory expressions or offensive language. For example, the analysis unit scans statements based on the keyword list and detects whether they contain discriminatory expressions or offensive language. The analysis unit can also use context analysis to understand the context of a statement and detect discriminatory expressions or offensive language. For example, the analysis unit analyzes the context before and after a statement to determine whether it contains discriminatory expressions or offensive language. This detection of discriminatory expressions or offensive language enables more specific prevention of inappropriate statements. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input statements into a generation AI, which then detects discriminatory expressions or offensive language.

[0034] The suggestion unit may include specific usage scenarios in educational settings or the workplace (e.g., utterances made during class, utterances made during meetings). The suggestion unit makes suggestions including specific usage scenarios in educational settings or the workplace. For example, the suggestion unit may make a suggestion such as "This expression is not appropriate for use during class" in response to a utterance made during class. The suggestion unit may also make a suggestion such as "This expression is not appropriate for use during meetings" in response to a utterance made during a meeting. By including specific usage scenarios in educational settings or the workplace, suggestions tailored to actual usage scenarios are possible. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI, for example. For example, when the generation AI detects an inappropriate utterance, the suggestion unit makes a suggestion including a specific usage scenario in educational settings or the workplace.

[0035] The reception unit can analyze the user's past speech history and select the optimal reception method. The reception unit, for example, uses data mining technology to analyze the user's past speech history. For example, the reception unit collects the user's past speech data and identifies frequently used expressions and patterns. Furthermore, if the user has made inappropriate statements in the past, the reception unit can filter out those expressions and restrict reception. For example, the reception unit filters out specific keywords and phrases based on the user's past speech history. Furthermore, the reception unit can analyze the user's past speech patterns and receive messages at an appropriate time. For example, the reception unit selects the optimal reception method by taking into account the time period and circumstances in which the user made past statements. Thus, by analyzing the user's past speech history, a more appropriate reception method can be selected. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input the user's speech history data into a generation AI, which can select the optimal reception method.

[0036] When receiving a comment, the reception unit can filter the comment based on the user's current situation and areas of interest. The reception unit, for example, uses sensor technology to grasp the user's current situation. For example, the reception unit detects the user's location information and activity status using a sensor to grasp the current situation. The reception unit can also analyze social media data to grasp the user's areas of interest. For example, the reception unit analyzes the topics the user follows and the content of posts to identify the user's areas of interest. When receiving a comment, the reception unit filters the comment based on the user's current situation and areas of interest. For example, if the user is at work, only work-related comments can be preferentially accepted. Also, if the user is on vacation, relaxing comments can be preferentially accepted. Also, if the user is participating in a specific event, comments related to the event can be preferentially accepted. In this way, by filtering comments based on the user's current situation and areas of interest, more relevant comments can be accepted. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's location information data into the generation AI, which can then analyze the current situation and filter comments.

[0037] When receiving a utterance, the reception unit can select the optimal reception means depending on the user's input method. The reception unit, for example, acquires information about the input device to detect the user's input method. For example, the reception unit acquires information from an input device such as a microphone, keyboard, or touch screen and identifies the user's input method. When receiving a utterance, the reception unit selects the optimal reception means depending on the user's input method. For example, if the user uses voice input, the reception unit can accept the utterance using voice recognition technology. Also, if the user uses text input, the reception unit can accept the utterance using text analysis technology. Also, if the user uses images, the reception unit can understand and accept the content of the utterance using image analysis technology. This enables smoother utterance reception by selecting the optimal reception means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input information from the input device to a generation AI, which can select the optimal reception means.

[0038] When receiving a utterance, the reception unit can prioritize receiving highly relevant utterances by taking into account the user's geographical location information. The reception unit, for example, uses GPS technology to acquire the user's geographical location information. For example, the reception unit acquires GPS data from the user's smartphone or device to identify the user's current location. The reception unit can also acquire the user's geographical location information using an IP address. For example, the reception unit analyzes the user's IP address to identify the user's geographical location. When receiving a utterance, the reception unit prioritizes receiving highly relevant utterances by taking into account the user's geographical location information. For example, if the user is in a specific area, the reception unit prioritizes receiving utterances related to that area. Also, if the user is traveling, the reception unit can prioritize receiving utterances related to the user's travel destination. Also, if the user is at home, the reception unit can prioritize receiving utterances related to the user's home. In this way, by taking into account the user's geographical location information, it is possible to prioritize receiving more relevant utterances. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's GPS data into the generation AI, which can then analyze the geographical location information and determine the priority of the comments.

[0039] The reception unit can analyze the user's social media activity and receive related comments when receiving a comment. The reception unit, for example, uses data mining technology to analyze the user's social media activity. For example, the reception unit collects and analyzes data such as the content of posts, the number of followers, and the number of likes from the user's social media account. The reception unit can also analyze the topics and hashtags the user follows to identify areas of interest. When receiving a comment, the reception unit analyzes the user's social media activity and receives related comments. For example, the reception unit can prioritize expressions frequently used by the user on social media. The reception unit can also prioritize posts related to topics the user follows on social media. The reception unit can also analyze the user's social media activity history and receive related comments. In this way, by analyzing the user's social media activity, more relevant comments can be received. Some or all of the above-described processing by the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input the user's social media data into a generation AI, which analyzes the data and receives related comments.

[0040] When receiving a comment, the reception unit can customize the reception method by reflecting the user's past feedback. The reception unit, for example, uses a feedback form or a questionnaire to collect the user's past feedback. For example, the reception unit collects ratings and comments provided by the user and stores them in a database. The reception unit can also analyze the user's past comment history and behavioral patterns and reflect the feedback. When receiving a comment, the reception unit customizes the reception method by reflecting the user's past feedback. For example, the reception unit adjusts the reception method for comments based on feedback provided by the user in the past. If the user has made inappropriate comments in the past, the reception unit can filter those expressions to limit reception. The reception unit can also analyze the user's past feedback and suggest an optimal reception method. In this way, a more appropriate reception method can be customized by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input the user's feedback data into a generation AI, which analyzes the data and customizes the optimal reception method.

[0041] The analysis unit can adjust the level of detail of the analysis based on the importance of the statement during analysis. The analysis unit, for example, uses text analysis technology to evaluate the importance of the statement. For example, the analysis unit analyzes the content and influence of the statement and evaluates the importance. The analysis unit can also analyze the user's past statement history and behavioral patterns to evaluate the importance of the statement. During analysis, the analysis unit adjusts the level of detail of the analysis based on the importance of the statement. For example, a detailed analysis can be performed for statements with high importance. A simplified analysis can be performed for statements with low importance. The depth of the analysis can also be adjusted depending on the importance of the statement. In this way, by adjusting the level of detail of the analysis based on the importance of the statement, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input statement data to a generation AI, which evaluates the importance of the statement, and adjust the level of detail of the analysis based on the evaluation result.

[0042] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the statement. The analysis unit, for example, uses text classification technology to classify the category of the statement. For example, the analysis unit analyzes the content of the statement and classifies it into categories such as technical statements and business-related statements. The analysis unit can also classify the category of the statement by analyzing the user's past statement history and behavioral patterns. During analysis, the analysis unit applies different analysis algorithms depending on the category of the statement. For example, a specific algorithm can be applied to discriminatory statements for analysis. A different algorithm can be applied to offensive statements for analysis. Furthermore, an appropriate algorithm can be selected for analysis of other inappropriate statements. In this way, by applying different analysis algorithms depending on the category of the statement, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input statement data to a generation AI, which classifies the category of the statement, and apply different analysis algorithms based on the results.

[0043] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, uses a database to collect the user's past analysis results. For example, the analysis unit stores the user's past analysis results in the database and references them as needed. The analysis unit can also analyze the user's past statement history and behavioral patterns to improve the accuracy of the analysis. During analysis, the analysis unit improves the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis algorithm can be adjusted based on the user's past analysis results. The analysis accuracy can also be improved by referring to the user's past analysis results. The user's past analysis results can also be analyzed to select an optimal analysis method. In this way, the analysis accuracy can be improved by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past analysis result data into a generation AI, which analyzes the data and improves the accuracy of the analysis.

[0044] During analysis, the analysis unit can determine the analysis priority based on the time of comment submission. The analysis unit, for example, uses timestamp technology to obtain the time of comment submission. For example, the analysis unit records the date and time when a comment was submitted and stores it in a database. The analysis unit can also analyze a user's past comment history and behavioral patterns to evaluate the time of submission. During analysis, the analysis unit determines the analysis priority based on the time of comment submission. For example, recently submitted comments can be analyzed first. Also, comments submitted in the past can be analyzed later. The analysis priority can also be adjusted depending on the time of comment submission. In this way, by determining the analysis priority based on the time of comment submission, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input submission time data into a generation AI, which analyzes the data and determines the analysis priority.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the utterances during analysis. The analysis unit, for example, uses text analysis technology to evaluate the relevance of the utterances. For example, the analysis unit analyzes the content of the utterances and related keywords to evaluate the relevance. The analysis unit can also analyze the user's past utterance history and behavioral patterns to evaluate the relevance of the utterances during analysis. The analysis unit can adjust the order of analysis based on the relevance of the utterances during analysis. For example, highly relevant utterances can be analyzed preferentially. Less relevant utterances can also be analyzed later. The analysis order can also be adjusted according to the relevance of the utterances. In this way, by adjusting the analysis order based on the relevance of the utterances, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input utterance data to a generation AI, which evaluates the relevance of the utterances, and adjust the order of analysis based on the evaluation result.

[0046] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, the analysis unit analyzes the user's qualifications, years of experience, and past utterances to evaluate the user's level of expertise. For example, the analysis unit collects the user's qualifications and work history data to evaluate the user's level of expertise. The analysis unit can also analyze the user's past utterances to evaluate the frequency of use and level of understanding of technical terms. During analysis, the analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide analysis results that use a lot of technical terms. On the other hand, if the user does not have technical expertise, the analysis unit can provide analysis results in simpler language. The use of technical terms in the analysis can also be adjusted according to the user's level of expertise. In this way, by adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's qualifications and utterance data into a generation AI, which can evaluate the user's level of expertise and adjust the use of technical terms in the analysis based on the evaluation result.

[0047] When issuing a warning, the warning unit can adjust the level of detail of the warning based on the importance of the statement. The warning unit, for example, uses text analysis technology to evaluate the importance of the statement. For example, the warning unit analyzes the content and impact of the statement to evaluate the importance. The warning unit can also analyze the user's past statement history and behavioral patterns to evaluate the importance of the statement. When issuing a warning, the warning unit adjusts the level of detail of the warning based on the importance of the statement. For example, a detailed warning can be displayed for a statement with high importance. A simplified warning can be displayed for a statement with low importance. The level of detail of the warning can also be adjusted according to the importance of the statement. In this way, by adjusting the level of detail of the warning based on the importance of the statement, a more appropriate warning can be provided. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input statement data to a generation AI, which evaluates the importance of the statement, and adjust the level of detail of the warning based on the evaluation result.

[0048] When issuing a warning, the warning unit can apply different warning algorithms depending on the category of the statement. The warning unit, for example, uses text classification technology to classify the category of the statement. For example, the warning unit analyzes the content of the statement and classifies it into categories such as technical statements and business-related statements. The warning unit can also analyze the user's past statement history and behavioral patterns to classify the category of the statement. When issuing a warning, the warning unit applies different warning algorithms depending on the category of the statement. For example, a specific algorithm can be applied to issue a warning against discriminatory statements. A different algorithm can be applied to issue a warning against offensive statements. An appropriate algorithm can also be selected to issue a warning against other inappropriate statements. In this way, by applying different warning algorithms depending on the category of the statement, more appropriate warnings can be provided. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input statement data to a generation AI, which classifies the category of the statement, and apply different warning algorithms based on the results.

[0049] When issuing a warning, the warning unit can improve the accuracy of the warning by referring to the user's past warning results. The warning unit, for example, uses a database to collect the user's past warning results. For example, the warning unit stores the user's past warning results in the database and references them as needed. The warning unit can also analyze the user's past speech history and behavioral patterns to improve the accuracy of the warning. When issuing a warning, the warning unit can improve the accuracy of the warning by referring to the user's past warning results. For example, the warning algorithm can be adjusted based on the user's past warning results. The accuracy of the warning can also be improved by referring to the user's past warning results. The user's past warning results can also be analyzed to select an optimal warning method. In this way, the accuracy of the warning can be improved by referring to the user's past warning results. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input past warning result data into a generation AI, which analyzes the data and improves the accuracy of the warning.

[0050] When issuing a warning, the warning unit can determine the priority of the warning based on the time the comment was submitted. The warning unit, for example, uses timestamp technology to obtain the time the comment was submitted. For example, the warning unit records the date and time the comment was submitted and stores it in a database. The warning unit can also analyze the user's past comment history and behavioral patterns to evaluate the submission time. When issuing a warning, the warning unit determines the priority of the warning based on the time the comment was submitted. For example, a warning can be displayed preferentially for recently submitted comments. Also, a warning can be displayed later for previously submitted comments. The priority of the warning can also be adjusted depending on the time the comment was submitted. In this way, by determining the priority of the warning based on the time the comment was submitted, more appropriate warnings can be provided. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without AI. For example, the warning unit can input submission time data into a generation AI, which analyzes the data and determines the priority of the warning.

[0051] The warning unit can adjust the order of warnings based on the relevance of the utterances when issuing a warning. The warning unit uses, for example, text analysis technology to evaluate the relevance of the utterances. For example, the warning unit analyzes the content of the utterances and related keywords to evaluate the relevance. The warning unit can also analyze the user's past utterance history and behavioral patterns to evaluate the relevance of the utterances. When issuing a warning, the warning unit adjusts the order of warnings based on the relevance of the utterances. For example, a warning can be displayed preferentially for highly relevant utterances. Furthermore, a warning can be displayed later for less relevant utterances. The order of warnings can also be adjusted according to the relevance of the utterances. In this way, adjusting the order of warnings based on the relevance of the utterances makes it possible to provide more appropriate warnings. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input utterance data to a generation AI, which evaluates the relevance of the utterances, and adjust the order of warnings based on the evaluation result.

[0052] When issuing a warning, the warning unit can adjust the use of technical terms in the warning depending on the user's level of expertise. For example, the warning unit can analyze the user's qualifications, years of experience, and past utterances to evaluate the user's level of expertise. For example, the warning unit can collect the user's qualifications and work history data to evaluate the user's level of expertise. The warning unit can also analyze the user's past utterances to evaluate the frequency of use and level of understanding of technical terms. When issuing a warning, the warning unit can adjust the use of technical terms in the warning depending on the user's level of expertise. For example, if the user has technical expertise, the warning unit can display a warning that uses a lot of technical terms. On the other hand, if the user does not have technical expertise, the warning unit can display a warning in simple language. The use of technical terms in the warning can also be adjusted depending on the user's level of expertise. By adjusting the use of technical terms in the warning depending on the user's level of expertise, a more understandable warning can be provided. Some or all of the above-described processing in the warning unit can be performed using, for example, AI, or without AI. For example, the warning unit can input the user's qualifications and utterance data into a generation AI, which can evaluate the user's level of expertise and adjust the use of technical terms in the warning based on the evaluation result.

[0053] The suggestion unit can adjust the level of detail of the suggestion based on the importance of the utterance when making a suggestion. The suggestion unit uses, for example, text analysis technology to evaluate the importance of the utterance. For example, the suggestion unit analyzes the content and influence of the utterance to evaluate the importance. The suggestion unit can also analyze the user's past utterance history and behavioral patterns to evaluate the importance of the utterance. When making a suggestion, the suggestion unit adjusts the level of detail of the suggestion based on the importance of the utterance. For example, a detailed suggestion can be made for a utterance with high importance. A simplified suggestion can be made for a utterance with low importance. The level of detail of the suggestion can also be adjusted according to the importance of the utterance. In this way, by adjusting the level of detail of the suggestion based on the importance of the utterance, more appropriate suggestions can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input utterance data to a generation AI, which evaluates the importance of the utterance, and adjust the level of detail of the suggestion based on the evaluation result.

[0054] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the utterance. The suggestion unit, for example, uses text classification technology to classify the category of the utterance. For example, the suggestion unit analyzes the content of the utterance and classifies it into categories such as technical utterances and business-related utterances. The suggestion unit can also analyze a user's past utterance history and behavioral patterns to classify the category of the utterance. When making a suggestion, the suggestion unit applies different suggestion algorithms depending on the category of the utterance. For example, a specific algorithm can be applied to make a suggestion for discriminatory utterances. A different algorithm can be applied to make a suggestion for offensive utterances. An appropriate algorithm can also be selected to make a suggestion for other inappropriate utterances. In this way, by applying different suggestion algorithms depending on the category of the utterance, more appropriate suggestions can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input utterance data to a generation AI, which classifies the category of the utterance, and apply different suggestion algorithms based on the results.

[0055] When making a suggestion, the suggestion unit can improve the accuracy of the suggestion by referring to the user's past suggestion results. The suggestion unit, for example, uses a database to collect the user's past suggestion results. For example, the suggestion unit stores the user's past suggestion results in the database and references them as needed. The suggestion unit can also analyze the user's past speech history and behavioral patterns to improve the accuracy of the suggestion. When making a suggestion, the suggestion unit improves the accuracy of the suggestion by referring to the user's past suggestion results. For example, the suggestion unit adjusts the suggestion algorithm based on the user's past suggestion results. The suggestion unit can also improve the accuracy of the suggestion by referring to the user's past suggestion results. The suggestion unit can also analyze the user's past suggestion results and select an optimal suggestion method. In this way, the suggestion unit can improve the accuracy of the suggestion by referring to the user's past suggestion results. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input past suggestion result data into a generation AI, which analyzes the data and improves the accuracy of the suggestion.

[0056] The suggestion unit can determine the priority of the proposal based on the time of submission of the comment when making the proposal. The suggestion unit, for example, uses timestamp technology to obtain the time of submission of the comment. For example, the suggestion unit records the date and time when the comment was submitted and stores it in a database. The suggestion unit can also analyze the user's past comment history and behavioral patterns to evaluate the submission time. When making the proposal, the suggestion unit determines the priority of the proposal based on the time of submission of the comment. For example, a suggestion can be made preferentially for a recently submitted comment. Also, a suggestion can be made later for a comment submitted in the past. The priority of the proposal can also be adjusted depending on the time of submission of the comment. In this way, by determining the priority of the proposal based on the time of submission of the comment, more appropriate proposals can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input submission time data into a generation AI, which analyzes the data and determines the priority of the proposal.

[0057] The suggestion unit can adjust the order of suggestions based on the relevance of the utterances when making suggestions. The suggestion unit uses, for example, text analysis technology to evaluate the relevance of the utterances. For example, the suggestion unit analyzes the content of the utterances and related keywords to evaluate the relevance. The suggestion unit can also analyze the user's past utterance history and behavioral patterns to evaluate the relevance of the utterances. When making suggestions, the suggestion unit adjusts the order of suggestions based on the relevance of the utterances. For example, suggestions can be made preferentially for highly relevant utterances. Furthermore, suggestions can be made later for less relevant utterances. The order of suggestions can also be adjusted according to the relevance of the utterances. In this way, by adjusting the order of suggestions based on the relevance of the utterances, more appropriate suggestions can be provided. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input utterance data to a generation AI, which evaluates the relevance of the utterances, and adjust the order of suggestions based on the evaluation result.

[0058] When making a proposal, the suggestion unit can adjust the use of technical terms in the proposal according to the user's level of expertise. For example, the suggestion unit analyzes the user's qualifications, years of experience, and past utterances to evaluate the user's level of expertise. For example, the suggestion unit collects the user's qualification information and work history data to evaluate the user's level of expertise. The suggestion unit can also analyze the user's past utterances to evaluate the frequency of use and understanding of technical terms. When making a proposal, the suggestion unit adjusts the use of technical terms in the proposal according to the user's level of expertise. For example, if the user has technical expertise, the suggestion unit can make a proposal that uses a lot of technical terms. On the other hand, if the user does not have technical expertise, the suggestion unit can make a proposal in simple language. The use of technical terms in the proposal can also be adjusted according to the user's level of expertise. By adjusting the use of technical terms in the proposal according to the user's level of expertise, it is possible to provide a more understandable proposal. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without AI. For example, the suggestion unit can input the user's qualification information and utterance data into a generation AI, which can evaluate the user's level of expertise and adjust the use of technical terms in the proposal based on the evaluation result.

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

[0060] When accepting a user's comments, the acceptance unit can analyze the user's past comment history and detect specific patterns. For example, it can identify expressions and phrases that the user has frequently used in the past and optimize the acceptance of comments based on those expressions. Also, if the user has made inappropriate comments in the past, it can filter those expressions to limit the acceptance of comments. Furthermore, it can analyze speech patterns in specific time periods and situations based on the user's comment history and select the optimal timing for accepting comments. This makes it possible to utilize the user's past comment history to accept more appropriate comments.

[0061] The alert unit can customize the content of the alert based on the user's current situation and areas of interest. For example, if the user is at work, alerts related to work can be displayed preferentially. If the user is on vacation, alerts with relaxing content can be displayed. Furthermore, if the user is participating in a specific event, alerts related to the event can be displayed. This allows the alert content to be customized based on the user's current situation and areas of interest, thereby providing more relevant alerts.

[0062] The reception unit can select the optimal reception means depending on the user's input method. For example, if the user is using voice input, the utterance can be received using voice recognition technology. If the user is using text input, the utterance can be received using text analysis technology. Furthermore, if the user is using images, the utterance can be understood and received using image analysis technology. This allows for smoother utterance reception by selecting the optimal reception means depending on the user's input method.

[0063] The warning unit can improve the accuracy of the warning by referring to the user's past warning results. For example, the warning algorithm can be adjusted based on the user's past warning results. The warning accuracy can also be improved by referring to the user's past warning results. Furthermore, the warning unit can analyze the user's past warning results and select the optimal warning method. In this way, the accuracy of the warning can be improved by referring to the user's past warning results.

[0064] The reception unit can prioritize reception of highly relevant utterances by taking into consideration the user's geographical location information. For example, if the user is in a specific area, it can prioritize reception of utterances related to that area. Also, if the user is traveling, it can prioritize reception of utterances related to the travel destination. Furthermore, if the user is at home, it can also prioritize reception of utterances related to the home. In this way, it is possible to prioritize reception of more relevant utterances by taking into consideration the user's geographical location information.

[0065] The analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis algorithm can be adjusted based on the user's past analysis results. The analysis unit can also improve the accuracy of the analysis by referring to the user's past analysis results. Furthermore, the analysis unit can analyze the user's past analysis results and select the optimal analysis method. In this way, the analysis accuracy can be improved by referring to the user's past analysis results.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The reception unit receives a user's input. The input may be a verbal statement, a text message, or a social media post. The reception unit may receive the input via, for example, a chat application or a social networking platform. The reception unit may also receive the input via voice. Step 2: The analysis unit uses the generation AI to analyze the utterances entered by the reception unit. The analysis is performed using natural language processing technology. For example, the generation AI uses techniques such as morphological analysis, grammatical analysis, and semantic analysis to understand the content of the utterance. It also understands the context of the utterance and detects whether it contains inappropriate content. For example, it detects discriminatory expressions or offensive language. Step 3: The warning unit displays a warning to the user when the analysis unit detects an inappropriate comment. The warning is displayed as a message such as "This comment is inappropriate." For example, the warning can be displayed using a pop-up message or a voice alert. The warning can also be displayed using an email notification. Step 4: The suggestion unit makes suggestions for correcting statements that have been flagged by the warning unit. Suggestions are displayed in concrete terms, such as "Avoid using this expression." For example, they may suggest alternative expressions or provide specific examples of corrections. Suggestions can also include specific scenarios for use in educational settings or the workplace.

[0068] (Example 2) A tool according to an embodiment of the present invention is a system that detects unintentional inappropriate comments and prevents them by issuing warnings and suggesting corrections. In this system, a user inputs a comment, and a generation AI analyzes the comment to detect whether it contains inappropriate content. If so, a warning is displayed to the user and a suggestion for correction is made. For example, when a user inputs a comment via chat or social media, the comment is input to a generation AI. The generation AI uses natural language processing technology to understand the content of the comment and detect whether it contains inappropriate content. For example, it detects discriminatory or offensive language. If so, a warning message is displayed to the user, such as "This comment is inappropriate." Specific suggestions for correction, such as "Avoid using this expression," are also made. This allows users to recognize and correct their own inappropriate comments. Furthermore, this tool can be used in a variety of settings, including educational settings and the workplace. For example, it can prevent students from making inappropriate comments during class and prevent workplace harassment. This tool can improve the quality of communication by detecting unintentional inappropriate comments and issuing warnings and suggesting corrections. For example, communication on chat and social media will become smoother. It will also help maintain a healthy environment by preventing inappropriate comments in educational settings and the workplace.

[0069] An inappropriate remark prevention system according to an embodiment includes a receiving unit, an analysis unit, a warning unit, and a suggestion unit. The receiving unit receives a user's input of a remark. The remark may be, for example, a verbal remark, a text message, or a social media post, but is not limited to these examples. The receiving unit receives the remark through, for example, a chat application or a social networking platform. The receiving unit may also receive the remark using voice input. The analysis unit uses a generation AI to analyze the remark input. The analysis may be performed using, for example, natural language processing technology, but is not limited to these examples. For example, the generation AI understands the content of the remark using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The analysis unit may also use the generation AI to understand the context of the remark and detect whether the remark contains inappropriate content. For example, the generation AI detects discriminatory language or offensive language. The warning unit displays a warning to the user when the analysis unit detects an inappropriate remark. The warning may be, for example, a message such as "This remark is inappropriate," but is not limited to these examples. For example, the warning unit displays the warning using a pop-up message or a voice alert. The warning unit can also issue a warning using an email notification. The suggestion unit makes a suggestion for correcting a statement warned by the warning unit. The suggestion may be displayed with specific content such as, for example, "Avoid using this expression," but is not limited to such an example. For example, the suggestion unit presents alternative expressions or provides specific examples of correction. The suggestion unit can also make suggestions including specific use scenarios in educational settings or the workplace. For example, the suggestion unit makes suggestions for correcting statements made during class or meetings. In this way, the inappropriate remarks prevention system according to the embodiment can detect unintentional inappropriate remarks and prevent them in advance by issuing a warning or suggesting corrections. For example, the user can realize that their remarks are inappropriate and correct them. Furthermore, preventing inappropriate remarks in educational settings or the workplace can maintain a healthy environment.

[0070] The analysis unit can use natural language processing technology to understand the content of a utterance and detect whether it contains content deemed inappropriate based on specific criteria. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit can use morphological analysis to break down the words in a utterance and grammatical analysis to analyze the structure of the sentence. The analysis unit can also use semantic analysis to understand the meaning of the utterance. For example, the analysis unit can understand the context of the utterance and detect whether it contains content deemed inappropriate based on specific criteria. In this way, natural language processing technology can accurately understand the content of the utterance and detect inappropriate content. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input a utterance into a generation AI, which can analyze the content of the utterance and detect inappropriate content.

[0071] The warning unit can display a message such as "This comment has been determined to be inappropriate based on specific criteria." For example, the warning unit displays a pop-up message such as "This comment has been determined to be inappropriate based on specific criteria." The warning unit can also issue a warning using an audio alert. For example, the warning unit issues an audio warning such as "This comment is inappropriate." The warning unit can also issue a warning using an email notification. For example, the warning unit can send a warning message to the user by email. By doing so, the user can be warned of inappropriate comments and be prompted to correct the comment. Some or all of the above-described processing in the warning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the warning unit displays a warning message when the generation AI detects an inappropriate comment.

[0072] The suggestion unit can display specific suggestions such as, "This expression is determined to be inappropriate based on specific criteria, so please avoid using it." For example, the suggestion unit displays specific suggestions such as, "This expression is determined to be inappropriate based on specific criteria, so please avoid using it," in a pop-up. The suggestion unit can also present alternative expressions and provide specific correction examples. For example, the suggestion unit can make suggestions such as, "Instead of this expression, try using this expression." The suggestion unit can also make suggestions including specific usage scenarios in educational settings or the workplace. For example, the suggestion unit can make correction suggestions for comments made during class or meetings. This can encourage the user to use appropriate expressions by providing specific correction suggestions to the user. Some or all of the above-mentioned processing in the suggestion unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the suggestion unit can make correction suggestions when the generation AI detects inappropriate comments.

[0073] The analysis unit can detect expressions that are judged to be discriminatory or offensive based on specific criteria. The analysis unit, for example, uses a specific keyword list to detect discriminatory expressions or offensive language. For example, the analysis unit scans statements based on the keyword list and detects whether they contain discriminatory expressions or offensive language. The analysis unit can also use context analysis to understand the context of a statement and detect discriminatory expressions or offensive language. For example, the analysis unit analyzes the context before and after a statement to determine whether it contains discriminatory expressions or offensive language. This detection of discriminatory expressions or offensive language enables more specific prevention of inappropriate statements. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input statements into a generation AI, which then detects discriminatory expressions or offensive language.

[0074] The suggestion unit may include specific usage scenarios in educational settings or the workplace (e.g., utterances made during class, utterances made during meetings). The suggestion unit makes suggestions including specific usage scenarios in educational settings or the workplace. For example, the suggestion unit may make a suggestion such as "This expression is not appropriate for use during class" in response to a utterance made during class. The suggestion unit may also make a suggestion such as "This expression is not appropriate for use during meetings" in response to a utterance made during a meeting. By including specific usage scenarios in educational settings or the workplace, suggestions tailored to actual usage scenarios are possible. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI, for example. For example, when the generation AI detects an inappropriate utterance, the suggestion unit makes a suggestion including a specific usage scenario in educational settings or the workplace.

[0075] The reception unit can estimate the user's emotions and adjust the timing of utterance acceptance based on the estimated user emotions. The reception unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the reception unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The reception unit can also estimate the user's emotions using voice analysis technology. For example, the reception unit analyzes the tone and speed of the user's voice to estimate the emotions. The reception unit can also estimate the user's emotions using text analysis technology. For example, the reception unit analyzes the content of the user's utterances to estimate the emotions. The reception unit adjusts the timing of utterance acceptance based on the estimated user emotions. For example, if the user is excited, the reception unit can temporarily delay the acceptance of utterances to give the user time to calm down. If the user is relaxed, the reception unit can immediately accept utterances, promoting smooth communication. If the user is stressed, the reception unit can slightly delay the acceptance of utterances to provide an opportunity for reconsideration. In this way, by adjusting the timing of utterance acceptance according to the user's emotions, utterances can be accepted at a more appropriate time. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit inputs the user's facial expression data into the generation AI, which then estimates the emotion, and adjusts the timing of receiving the utterance based on the result.

[0076] The reception unit can analyze the user's past speech history and select the optimal reception method. The reception unit, for example, uses data mining technology to analyze the user's past speech history. For example, the reception unit collects the user's past speech data and identifies frequently used expressions and patterns. Furthermore, if the user has made inappropriate statements in the past, the reception unit can filter out those expressions and restrict reception. For example, the reception unit filters out specific keywords and phrases based on the user's past speech history. Furthermore, the reception unit can analyze the user's past speech patterns and receive messages at an appropriate time. For example, the reception unit selects the optimal reception method by taking into account the time period and circumstances in which the user made past statements. Thus, by analyzing the user's past speech history, a more appropriate reception method can be selected. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input the user's speech history data into a generation AI, which can select the optimal reception method.

[0077] When receiving a comment, the reception unit can filter the comment based on the user's current situation and areas of interest. The reception unit, for example, uses sensor technology to grasp the user's current situation. For example, the reception unit detects the user's location information and activity status using a sensor to grasp the current situation. The reception unit can also analyze social media data to grasp the user's areas of interest. For example, the reception unit analyzes the topics the user follows and the content of posts to identify the user's areas of interest. When receiving a comment, the reception unit filters the comment based on the user's current situation and areas of interest. For example, if the user is at work, only work-related comments can be preferentially accepted. Also, if the user is on vacation, relaxing comments can be preferentially accepted. Also, if the user is participating in a specific event, comments related to the event can be preferentially accepted. In this way, by filtering comments based on the user's current situation and areas of interest, more relevant comments can be accepted. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's location information data into the generation AI, which can then analyze the current situation and filter comments.

[0078] When receiving a utterance, the reception unit can select the optimal reception means depending on the user's input method. The reception unit, for example, acquires information about the input device to detect the user's input method. For example, the reception unit acquires information from an input device such as a microphone, keyboard, or touch screen and identifies the user's input method. When receiving a utterance, the reception unit selects the optimal reception means depending on the user's input method. For example, if the user uses voice input, the reception unit can accept the utterance using voice recognition technology. Also, if the user uses text input, the reception unit can accept the utterance using text analysis technology. Also, if the user uses images, the reception unit can understand and accept the content of the utterance using image analysis technology. This enables smoother utterance reception by selecting the optimal reception means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input information from the input device to a generation AI, which can select the optimal reception means.

[0079] The reception unit can estimate the user's emotions and determine the priority of utterances to be received based on the estimated user's emotions. The reception unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the reception unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The reception unit can also estimate the user's emotions using voice analysis technology. For example, the reception unit analyzes the tone and speed of the user's voice to estimate the emotions. The reception unit can also estimate the user's emotions using text analysis technology. For example, the reception unit analyzes the content of the user's utterances to estimate the emotions. The reception unit determines the priority of utterances to be received based on the estimated user's emotions. For example, if the user is angry, the priority of the utterance can be set low to give the user time to calm down. If the user is relaxed, the priority of the utterance can be set high to promote smooth communication. If the user is sad, the priority of the utterance can be set medium to encourage an appropriate response. In this way, by determining the priority of utterances according to the user's emotions, more appropriate utterances can be preferentially received. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit inputs the user's facial expression data into the generation AI, which then estimates the emotion and determines the priority of the utterances based on the result.

[0080] When receiving a utterance, the reception unit can prioritize receiving highly relevant utterances by taking into account the user's geographical location information. The reception unit, for example, uses GPS technology to acquire the user's geographical location information. For example, the reception unit acquires GPS data from the user's smartphone or device to identify the user's current location. The reception unit can also acquire the user's geographical location information using an IP address. For example, the reception unit analyzes the user's IP address to identify the user's geographical location. When receiving a utterance, the reception unit prioritizes receiving highly relevant utterances by taking into account the user's geographical location information. For example, if the user is in a specific area, the reception unit prioritizes receiving utterances related to that area. Also, if the user is traveling, the reception unit can prioritize receiving utterances related to the user's travel destination. Also, if the user is at home, the reception unit can prioritize receiving utterances related to the user's home. In this way, by taking into account the user's geographical location information, it is possible to prioritize receiving more relevant utterances. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's GPS data into the generation AI, which can then analyze the geographical location information and determine the priority of the comments.

[0081] The reception unit can analyze the user's social media activity and receive related comments when receiving a comment. The reception unit, for example, uses data mining technology to analyze the user's social media activity. For example, the reception unit collects and analyzes data such as the content of posts, the number of followers, and the number of likes from the user's social media account. The reception unit can also analyze the topics and hashtags the user follows to identify areas of interest. When receiving a comment, the reception unit analyzes the user's social media activity and receives related comments. For example, the reception unit can prioritize expressions frequently used by the user on social media. The reception unit can also prioritize posts related to topics the user follows on social media. The reception unit can also analyze the user's social media activity history and receive related comments. In this way, by analyzing the user's social media activity, more relevant comments can be received. Some or all of the above-described processing by the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input the user's social media data into a generation AI, which analyzes the data and receives related comments.

[0082] When receiving a comment, the reception unit can customize the reception method by reflecting the user's past feedback. The reception unit, for example, uses a feedback form or a questionnaire to collect the user's past feedback. For example, the reception unit collects ratings and comments provided by the user and stores them in a database. The reception unit can also analyze the user's past comment history and behavioral patterns and reflect the feedback. When receiving a comment, the reception unit customizes the reception method by reflecting the user's past feedback. For example, the reception unit adjusts the reception method for comments based on feedback provided by the user in the past. If the user has made inappropriate comments in the past, the reception unit can filter those expressions to limit reception. The reception unit can also analyze the user's past feedback and suggest an optimal reception method. In this way, a more appropriate reception method can be customized by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input the user's feedback data into a generation AI, which analyzes the data and customizes the optimal reception method.

[0083] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated user's emotions. The analysis unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the analysis unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The analysis unit can also estimate the user's emotions using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the user's voice to estimate the emotions. The analysis unit can also estimate the user's emotions using text analysis technology. For example, the analysis unit analyzes the content of the user's speech to estimate the emotions. Based on the estimated user's emotions, the analysis unit adjusts the presentation of the analysis. For example, if the user is angry, the analysis results can be presented in a calm manner. If the user is relaxed, detailed analysis results can be provided. If the user is sad, the analysis results can be presented in a gentle manner. By adjusting the presentation of the analysis based on the user's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit may input the user's facial expression data into the generation AI, which may infer the emotion and adjust the method of expression of the analysis based on the result.

[0084] The analysis unit can adjust the level of detail of the analysis based on the importance of the statement during analysis. The analysis unit, for example, uses text analysis technology to evaluate the importance of the statement. For example, the analysis unit analyzes the content and influence of the statement and evaluates the importance. The analysis unit can also analyze the user's past statement history and behavioral patterns to evaluate the importance of the statement. During analysis, the analysis unit adjusts the level of detail of the analysis based on the importance of the statement. For example, a detailed analysis can be performed for statements with high importance. A simplified analysis can be performed for statements with low importance. The depth of the analysis can also be adjusted depending on the importance of the statement. In this way, by adjusting the level of detail of the analysis based on the importance of the statement, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input statement data to a generation AI, which evaluates the importance of the statement, and adjust the level of detail of the analysis based on the evaluation result.

[0085] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the statement. The analysis unit, for example, uses text classification technology to classify the category of the statement. For example, the analysis unit analyzes the content of the statement and classifies it into categories such as technical statements and business-related statements. The analysis unit can also classify the category of the statement by analyzing the user's past statement history and behavioral patterns. During analysis, the analysis unit applies different analysis algorithms depending on the category of the statement. For example, a specific algorithm can be applied to discriminatory statements for analysis. A different algorithm can be applied to offensive statements for analysis. Furthermore, an appropriate algorithm can be selected for analysis of other inappropriate statements. In this way, by applying different analysis algorithms depending on the category of the statement, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input statement data to a generation AI, which classifies the category of the statement, and apply different analysis algorithms based on the results.

[0086] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, uses a database to collect the user's past analysis results. For example, the analysis unit stores the user's past analysis results in the database and references them as needed. The analysis unit can also analyze the user's past statement history and behavioral patterns to improve the accuracy of the analysis. During analysis, the analysis unit improves the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis algorithm can be adjusted based on the user's past analysis results. The analysis accuracy can also be improved by referring to the user's past analysis results. The user's past analysis results can also be analyzed to select an optimal analysis method. In this way, the analysis accuracy can be improved by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past analysis result data into a generation AI, which analyzes the data and improves the accuracy of the analysis.

[0087] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. The analysis unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the analysis unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The analysis unit can also estimate the user's emotions using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the user's voice to estimate the emotions. The analysis unit can also estimate the user's emotions using text analysis technology. For example, the analysis unit analyzes the content of the user's speech to estimate the emotions. The analysis unit adjusts the length of the analysis based on the estimated user emotions. For example, if the user is in a hurry, the analysis unit can provide a short and concise analysis result. If the user is relaxed, the analysis unit can provide a detailed analysis result. If the user is excited, the analysis unit can provide an analysis result with visually stimulating effects. By adjusting the length of the analysis according to the user's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the user's facial expression data into the generation AI, which may infer the emotion and adjust the length of the analysis based on the result.

[0088] During analysis, the analysis unit can determine the analysis priority based on the time of comment submission. The analysis unit, for example, uses timestamp technology to obtain the time of comment submission. For example, the analysis unit records the date and time when a comment was submitted and stores it in a database. The analysis unit can also analyze a user's past comment history and behavioral patterns to evaluate the time of submission. During analysis, the analysis unit determines the analysis priority based on the time of comment submission. For example, recently submitted comments can be analyzed first. Also, comments submitted in the past can be analyzed later. The analysis priority can also be adjusted depending on the time of comment submission. In this way, by determining the analysis priority based on the time of comment submission, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input submission time data into a generation AI, which analyzes the data and determines the analysis priority.

[0089] The analysis unit can adjust the order of analysis based on the relevance of the utterances during analysis. The analysis unit, for example, uses text analysis technology to evaluate the relevance of the utterances. For example, the analysis unit analyzes the content of the utterances and related keywords to evaluate the relevance. The analysis unit can also analyze the user's past utterance history and behavioral patterns to evaluate the relevance of the utterances during analysis. The analysis unit can adjust the order of analysis based on the relevance of the utterances during analysis. For example, highly relevant utterances can be analyzed preferentially. Less relevant utterances can also be analyzed later. The analysis order can also be adjusted according to the relevance of the utterances. In this way, by adjusting the analysis order based on the relevance of the utterances, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input utterance data to a generation AI, which evaluates the relevance of the utterances, and adjust the order of analysis based on the evaluation result.

[0090] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, the analysis unit analyzes the user's qualifications, years of experience, and past utterances to evaluate the user's level of expertise. For example, the analysis unit collects the user's qualifications and work history data to evaluate the user's level of expertise. The analysis unit can also analyze the user's past utterances to evaluate the frequency of use and level of understanding of technical terms. During analysis, the analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide analysis results that use a lot of technical terms. On the other hand, if the user does not have technical expertise, the analysis unit can provide analysis results in simpler language. The use of technical terms in the analysis can also be adjusted according to the user's level of expertise. In this way, by adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's qualifications and utterance data into a generation AI, which can evaluate the user's level of expertise and adjust the use of technical terms in the analysis based on the evaluation result.

[0091] The warning unit can estimate the user's emotions and adjust the display method of the warning based on the estimated user's emotions. The warning unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the warning unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The warning unit can also estimate the user's emotions using voice analysis technology. For example, the warning unit can analyze the tone and speed of the user's voice to estimate the emotions. The warning unit can also estimate the user's emotions using text analysis technology. For example, the warning unit can analyze the content of the user's speech to estimate the emotions. Based on the estimated user's emotions, the warning unit adjusts the display method of the warning. For example, if the user is angry, the warning can be displayed with calm expression. If the user is relaxed, the warning can be displayed with detailed expression. If the user is sad, the warning can be displayed with gentle expression. This allows for more appropriate warnings to be provided by adjusting the display method of the warning according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit may input the user's facial expression data into the generation AI, which may infer the user's emotion and adjust the warning display method based on the result.

[0092] When issuing a warning, the warning unit can adjust the level of detail of the warning based on the importance of the statement. The warning unit, for example, uses text analysis technology to evaluate the importance of the statement. For example, the warning unit analyzes the content and impact of the statement to evaluate the importance. The warning unit can also analyze the user's past statement history and behavioral patterns to evaluate the importance of the statement. When issuing a warning, the warning unit adjusts the level of detail of the warning based on the importance of the statement. For example, a detailed warning can be displayed for a statement with high importance. A simplified warning can be displayed for a statement with low importance. The level of detail of the warning can also be adjusted according to the importance of the statement. In this way, by adjusting the level of detail of the warning based on the importance of the statement, a more appropriate warning can be provided. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input statement data to a generation AI, which evaluates the importance of the statement, and adjust the level of detail of the warning based on the evaluation result.

[0093] When issuing a warning, the warning unit can apply different warning algorithms depending on the category of the statement. The warning unit, for example, uses text classification technology to classify the category of the statement. For example, the warning unit analyzes the content of the statement and classifies it into categories such as technical statements and business-related statements. The warning unit can also analyze the user's past statement history and behavioral patterns to classify the category of the statement. When issuing a warning, the warning unit applies different warning algorithms depending on the category of the statement. For example, a specific algorithm can be applied to issue a warning against discriminatory statements. A different algorithm can be applied to issue a warning against offensive statements. An appropriate algorithm can also be selected to issue a warning against other inappropriate statements. In this way, by applying different warning algorithms depending on the category of the statement, more appropriate warnings can be provided. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input statement data to a generation AI, which classifies the category of the statement, and apply different warning algorithms based on the results.

[0094] When issuing a warning, the warning unit can improve the accuracy of the warning by referring to the user's past warning results. The warning unit, for example, uses a database to collect the user's past warning results. For example, the warning unit stores the user's past warning results in the database and references them as needed. The warning unit can also analyze the user's past speech history and behavioral patterns to improve the accuracy of the warning. When issuing a warning, the warning unit can improve the accuracy of the warning by referring to the user's past warning results. For example, the warning algorithm can be adjusted based on the user's past warning results. The accuracy of the warning can also be improved by referring to the user's past warning results. The user's past warning results can also be analyzed to select an optimal warning method. In this way, the accuracy of the warning can be improved by referring to the user's past warning results. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input past warning result data into a generation AI, which analyzes the data and improves the accuracy of the warning.

[0095] The warning unit can estimate the user's emotions and adjust the length of the warning based on the estimated user's emotions. The warning unit can, for example, use facial expression recognition technology to estimate the user's emotions. For example, the warning unit can capture the user's facial expressions with a camera and estimate the emotions using a facial expression recognition algorithm. The warning unit can also estimate the user's emotions using voice analysis technology. For example, the warning unit can analyze the tone and speed of the user's voice to estimate the emotions. The warning unit can also estimate the user's emotions using text analysis technology. For example, the warning unit can analyze the content of the user's speech to estimate the emotions. The warning unit adjusts the length of the warning based on the estimated user's emotions. For example, if the user is in a hurry, a short and to-the-point warning can be displayed. If the user is relaxed, a detailed warning can be displayed. If the user is excited, a warning with a visually stimulating effect can be displayed. This allows the length of the warning to be adjusted according to the user's emotions, thereby providing more appropriate warnings. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the warning unit may be performed using AI, or may be performed without using AI. For example, the warning unit may input the user's facial expression data into the generation AI, which may infer the emotion and adjust the length of the warning based on the result.

[0096] When issuing a warning, the warning unit can determine the priority of the warning based on the time the comment was submitted. The warning unit, for example, uses timestamp technology to obtain the time the comment was submitted. For example, the warning unit records the date and time the comment was submitted and stores it in a database. The warning unit can also analyze the user's past comment history and behavioral patterns to evaluate the submission time. When issuing a warning, the warning unit determines the priority of the warning based on the time the comment was submitted. For example, a warning can be displayed preferentially for recently submitted comments. Also, a warning can be displayed later for previously submitted comments. The priority of the warning can also be adjusted depending on the time the comment was submitted. In this way, by determining the priority of the warning based on the time the comment was submitted, more appropriate warnings can be provided. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without AI. For example, the warning unit can input submission time data into a generation AI, which analyzes the data and determines the priority of the warning.

[0097] The warning unit can adjust the order of warnings based on the relevance of the utterances when issuing a warning. The warning unit uses, for example, text analysis technology to evaluate the relevance of the utterances. For example, the warning unit analyzes the content of the utterances and related keywords to evaluate the relevance. The warning unit can also analyze the user's past utterance history and behavioral patterns to evaluate the relevance of the utterances. When issuing a warning, the warning unit adjusts the order of warnings based on the relevance of the utterances. For example, a warning can be displayed preferentially for highly relevant utterances. Furthermore, a warning can be displayed later for less relevant utterances. The order of warnings can also be adjusted according to the relevance of the utterances. In this way, adjusting the order of warnings based on the relevance of the utterances makes it possible to provide more appropriate warnings. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input utterance data to a generation AI, which evaluates the relevance of the utterances, and adjust the order of warnings based on the evaluation result.

[0098] When issuing a warning, the warning unit can adjust the use of technical terms in the warning depending on the user's level of expertise. For example, the warning unit can analyze the user's qualifications, years of experience, and past utterances to evaluate the user's level of expertise. For example, the warning unit can collect the user's qualifications and work history data to evaluate the user's level of expertise. The warning unit can also analyze the user's past utterances to evaluate the frequency of use and level of understanding of technical terms. When issuing a warning, the warning unit can adjust the use of technical terms in the warning depending on the user's level of expertise. For example, if the user has technical expertise, the warning unit can display a warning that uses a lot of technical terms. On the other hand, if the user does not have technical expertise, the warning unit can display a warning in simple language. The use of technical terms in the warning can also be adjusted depending on the user's level of expertise. By adjusting the use of technical terms in the warning depending on the user's level of expertise, a more understandable warning can be provided. Some or all of the above-described processing in the warning unit can be performed using, for example, AI, or without AI. For example, the warning unit can input the user's qualifications and utterance data into a generation AI, which can evaluate the user's level of expertise and adjust the use of technical terms in the warning based on the evaluation result.

[0099] The suggestion unit can estimate the user's emotions and adjust the way suggestions are expressed based on the estimated user's emotions. The suggestion unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the suggestion unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The suggestion unit can also estimate the user's emotions using voice analysis technology. For example, the suggestion unit analyzes the tone and speed of the user's voice to estimate the emotions. The suggestion unit can also estimate the user's emotions using text analysis technology. For example, the suggestion unit analyzes the content of the user's speech to estimate the emotions. Based on the estimated user's emotions, the suggestion unit adjusts the way suggestions are expressed. For example, if the user is angry, the suggestion unit can make a calm suggestion. If the user is relaxed, the suggestion unit can make a detailed suggestion. If the user is sad, the suggestion unit can make a gentle suggestion. This allows the suggestion unit to provide more appropriate suggestions by adjusting the way suggestions are expressed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input the user's facial expression data into the generation AI, which may infer the emotion and adjust the way the suggestion is presented based on the result.

[0100] The suggestion unit can adjust the level of detail of the suggestion based on the importance of the utterance when making a suggestion. The suggestion unit uses, for example, text analysis technology to evaluate the importance of the utterance. For example, the suggestion unit analyzes the content and influence of the utterance to evaluate the importance. The suggestion unit can also analyze the user's past utterance history and behavioral patterns to evaluate the importance of the utterance. When making a suggestion, the suggestion unit adjusts the level of detail of the suggestion based on the importance of the utterance. For example, a detailed suggestion can be made for a utterance with high importance. A simplified suggestion can be made for a utterance with low importance. The level of detail of the suggestion can also be adjusted according to the importance of the utterance. In this way, by adjusting the level of detail of the suggestion based on the importance of the utterance, more appropriate suggestions can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input utterance data to a generation AI, which evaluates the importance of the utterance, and adjust the level of detail of the suggestion based on the evaluation result.

[0101] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the utterance. The suggestion unit, for example, uses text classification technology to classify the category of the utterance. For example, the suggestion unit analyzes the content of the utterance and classifies it into categories such as technical utterances and business-related utterances. The suggestion unit can also analyze a user's past utterance history and behavioral patterns to classify the category of the utterance. When making a suggestion, the suggestion unit applies different suggestion algorithms depending on the category of the utterance. For example, a specific algorithm can be applied to make a suggestion for discriminatory utterances. A different algorithm can be applied to make a suggestion for offensive utterances. An appropriate algorithm can also be selected to make a suggestion for other inappropriate utterances. In this way, by applying different suggestion algorithms depending on the category of the utterance, more appropriate suggestions can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input utterance data to a generation AI, which classifies the category of the utterance, and apply different suggestion algorithms based on the results.

[0102] When making a suggestion, the suggestion unit can improve the accuracy of the suggestion by referring to the user's past suggestion results. The suggestion unit, for example, uses a database to collect the user's past suggestion results. For example, the suggestion unit stores the user's past suggestion results in the database and references them as needed. The suggestion unit can also analyze the user's past speech history and behavioral patterns to improve the accuracy of the suggestion. When making a suggestion, the suggestion unit improves the accuracy of the suggestion by referring to the user's past suggestion results. For example, the suggestion unit adjusts the suggestion algorithm based on the user's past suggestion results. The suggestion unit can also improve the accuracy of the suggestion by referring to the user's past suggestion results. The suggestion unit can also analyze the user's past suggestion results and select an optimal suggestion method. In this way, the suggestion unit can improve the accuracy of the suggestion by referring to the user's past suggestion results. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input past suggestion result data into a generation AI, which analyzes the data and improves the accuracy of the suggestion.

[0103] The suggestion unit can estimate the user's emotion and adjust the length of the suggestion based on the estimated user's emotion. The suggestion unit, for example, uses facial expression recognition technology to estimate the user's emotion. For example, the suggestion unit captures the user's facial expression with a camera and estimates the emotion using a facial expression recognition algorithm. The suggestion unit can also estimate the user's emotion using voice analysis technology. For example, the suggestion unit can analyze the tone and speed of the user's voice to estimate the emotion. The suggestion unit can also estimate the user's emotion using text analysis technology. For example, the suggestion unit can analyze the content of the user's speech to estimate the emotion. The suggestion unit adjusts the length of the suggestion based on the estimated user's emotion. For example, if the user is in a hurry, the suggestion unit can provide a short and to-the-point suggestion. If the user is relaxed, the suggestion unit can provide a detailed suggestion. If the user is excited, the suggestion unit can provide a suggestion with a visually stimulating effect. This allows the suggestion unit to provide more appropriate suggestions by adjusting the length of the suggestion based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input the user's facial expression data into the generation AI, which may infer the emotion and adjust the length of the suggestion based on the result.

[0104] The suggestion unit can determine the priority of the proposal based on the time of submission of the comment when making the proposal. The suggestion unit, for example, uses timestamp technology to obtain the time of submission of the comment. For example, the suggestion unit records the date and time when the comment was submitted and stores it in a database. The suggestion unit can also analyze the user's past comment history and behavioral patterns to evaluate the submission time. When making the proposal, the suggestion unit determines the priority of the proposal based on the time of submission of the comment. For example, a suggestion can be made preferentially for a recently submitted comment. Also, a suggestion can be made later for a comment submitted in the past. The priority of the proposal can also be adjusted depending on the time of submission of the comment. In this way, by determining the priority of the proposal based on the time of submission of the comment, more appropriate proposals can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input submission time data into a generation AI, which analyzes the data and determines the priority of the proposal.

[0105] The suggestion unit can adjust the order of suggestions based on the relevance of the utterances when making suggestions. The suggestion unit uses, for example, text analysis technology to evaluate the relevance of the utterances. For example, the suggestion unit analyzes the content of the utterances and related keywords to evaluate the relevance. The suggestion unit can also analyze the user's past utterance history and behavioral patterns to evaluate the relevance of the utterances. When making suggestions, the suggestion unit adjusts the order of suggestions based on the relevance of the utterances. For example, suggestions can be made preferentially for highly relevant utterances. Furthermore, suggestions can be made later for less relevant utterances. The order of suggestions can also be adjusted according to the relevance of the utterances. In this way, by adjusting the order of suggestions based on the relevance of the utterances, more appropriate suggestions can be provided. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input utterance data to a generation AI, which evaluates the relevance of the utterances, and adjust the order of suggestions based on the evaluation result.

[0106] When making a proposal, the suggestion unit can adjust the use of technical terms in the proposal according to the user's level of expertise. For example, the suggestion unit analyzes the user's qualifications, years of experience, and past utterances to evaluate the user's level of expertise. For example, the suggestion unit collects the user's qualification information and work history data to evaluate the user's level of expertise. The suggestion unit can also analyze the user's past utterances to evaluate the frequency of use and understanding of technical terms. When making a proposal, the suggestion unit adjusts the use of technical terms in the proposal according to the user's level of expertise. For example, if the user has technical expertise, the suggestion unit can make a proposal that uses a lot of technical terms. On the other hand, if the user does not have technical expertise, the suggestion unit can make a proposal in simple language. The use of technical terms in the proposal can also be adjusted according to the user's level of expertise. By adjusting the use of technical terms in the proposal according to the user's level of expertise, it is possible to provide a more understandable proposal. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without AI. For example, the suggestion unit can input the user's qualification information and utterance data into a generation AI, which can evaluate the user's level of expertise and adjust the use of technical terms in the proposal based on the evaluation result. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, warning unit, and suggestion unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14 and receives a user's utterance. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the utterance using a generation AI. The warning unit is realized, for example, by the output device 40 of the smart device 14 and displays a warning to the user. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suggests corrections. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, warning unit, and suggestion unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the smart glasses 214 and receives a user's utterance. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the utterance using a generation AI. The warning unit is realized, for example, by the speaker 240 of the smart glasses 214 and displays a warning to the user. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suggests corrections. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, warning unit, and suggestion unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the headset-type terminal 314 and receives utterances from the user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the utterances using a generation AI. The warning unit is realized, for example, by the speaker 240 of the headset-type terminal 314 and displays a warning to the user. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suggests corrections. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, warning unit, and suggestion unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the robot 414 and receives utterances from the user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the utterances using a generation AI. The warning unit is realized, for example, by the speaker 240 of the robot 414 and displays a warning to the user. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suggests corrections.

[0107] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0108] When accepting a user's comments, the acceptance unit can analyze the user's past comment history and detect specific patterns. For example, it can identify expressions and phrases that the user has frequently used in the past and optimize the acceptance of comments based on those expressions. Also, if the user has made inappropriate comments in the past, it can filter those expressions to limit the acceptance of comments. Furthermore, it can analyze speech patterns in specific time periods and situations based on the user's comment history and select the optimal timing for accepting comments. This makes it possible to utilize the user's past comment history to accept more appropriate comments.

[0109] The analysis unit can estimate the user's emotions and adjust the level of analysis detail based on the estimated emotions. For example, if the user is angry, a concise and to-the-point analysis result can be provided. If the user is relaxed, a detailed analysis result can be provided. Furthermore, if the user is sad, the analysis result can be presented in a gentler manner. In this way, by adjusting the level of analysis detail according to the user's emotions, more appropriate analysis results can be provided.

[0110] The alert unit can customize the content of the alert based on the user's current situation and areas of interest. For example, if the user is at work, alerts related to work can be displayed preferentially. If the user is on vacation, alerts with relaxing content can be displayed. Furthermore, if the user is participating in a specific event, alerts related to the event can be displayed. This allows the alert content to be customized based on the user's current situation and areas of interest, thereby providing more relevant alerts.

[0111] The suggestion unit can estimate the user's emotions and adjust the way suggestions are expressed based on the estimated emotions. For example, if the user is angry, the suggestion unit can make a calm suggestion. If the user is relaxed, the suggestion unit can make a detailed suggestion. Furthermore, if the user is sad, the suggestion unit can make a gentle suggestion. In this way, by adjusting the way suggestions are expressed according to the user's emotions, more appropriate suggestions can be provided.

[0112] The reception unit can select the optimal reception means depending on the user's input method. For example, if the user is using voice input, the utterance can be received using voice recognition technology. If the user is using text input, the utterance can be received using text analysis technology. Furthermore, if the user is using images, the utterance can be understood and received using image analysis technology. This allows for smoother utterance reception by selecting the optimal reception means depending on the user's input method.

[0113] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated emotions. For example, if the user is angry, the analysis results can be presented in a calm manner. If the user is relaxed, detailed analysis results can be provided. Furthermore, if the user is sad, the analysis results can be presented in a gentle manner. In this way, by adjusting the way the analysis is presented according to the user's emotions, more appropriate analysis results can be provided.

[0114] The warning unit can improve the accuracy of the warning by referring to the user's past warning results. For example, the warning algorithm can be adjusted based on the user's past warning results. The warning accuracy can also be improved by referring to the user's past warning results. Furthermore, the warning unit can analyze the user's past warning results and select the optimal warning method. In this way, the accuracy of the warning can be improved by referring to the user's past warning results.

[0115] The suggestion unit can estimate the user's emotions and adjust the length of the suggestions based on the estimated emotions. For example, if the user is in a hurry, a short and to-the-point suggestion can be made. If the user is relaxed, a detailed suggestion can be made. Furthermore, if the user is excited, a suggestion with a visually stimulating effect can be made. In this way, by adjusting the length of the suggestion according to the user's emotions, more appropriate suggestions can be provided.

[0116] The reception unit can prioritize reception of highly relevant utterances by taking into consideration the user's geographical location information. For example, if the user is in a specific area, it can prioritize reception of utterances related to that area. Also, if the user is traveling, it can prioritize reception of utterances related to the travel destination. Furthermore, if the user is at home, it can also prioritize reception of utterances related to the home. In this way, it is possible to prioritize reception of more relevant utterances by taking into consideration the user's geographical location information.

[0117] The analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis algorithm can be adjusted based on the user's past analysis results. The analysis unit can also improve the accuracy of the analysis by referring to the user's past analysis results. Furthermore, the analysis unit can analyze the user's past analysis results and select the optimal analysis method. In this way, the analysis accuracy can be improved by referring to the user's past analysis results.

[0118] The processing flow of the second embodiment will be briefly explained below.

[0119] Step 1: The reception unit receives a user's input. The input may be a verbal statement, a text message, or a social media post. The reception unit may receive the input via, for example, a chat application or a social networking platform. The reception unit may also receive the input via voice. Step 2: The analysis unit uses the generation AI to analyze the utterances entered by the reception unit. The analysis is performed using natural language processing technology. For example, the generation AI uses techniques such as morphological analysis, grammatical analysis, and semantic analysis to understand the content of the utterance. It also understands the context of the utterance and detects whether it contains inappropriate content. For example, it detects discriminatory expressions or offensive language. Step 3: The warning unit displays a warning to the user when the analysis unit detects an inappropriate comment. The warning is displayed as a message such as "This comment is inappropriate." For example, the warning can be displayed using a pop-up message or a voice alert. The warning can also be displayed using an email notification. Step 4: The suggestion unit makes suggestions for correcting statements that have been flagged by the warning unit. Suggestions are displayed in concrete terms, such as "Avoid using this expression." For example, they may suggest alternative expressions or provide specific examples of corrections. Suggestions can also include specific scenarios for use in educational settings or the workplace.

[0120] 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.

[0121] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of 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.

[0122] 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.

[0123] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0124] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0125] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0140] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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."

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] [Explanation of symbols]

[0192] 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 reception unit for inputting comments; an analysis unit that analyzes the comments input by the reception unit; a warning unit that displays a warning when a statement that is determined to be inappropriate based on specific criteria by the analysis unit is detected; a suggestion unit that suggests corrections to the statements warned by the warning unit; Equipped with A system characterized by:

2. The analysis unit It uses natural language processing technology to understand the content of speech and detect whether it contains content that is deemed inappropriate based on specific criteria.

2. The system of claim 1.

3. The analysis unit Detecting expressions that are deemed discriminatory or offensive based on specific criteria 2. The system of claim 1.

4. The proposal unit Includes specific usage scenarios for educational and workplace settings 2. The system of claim 1.

5. The reception unit Estimates the user's emotions and adjusts the timing of speech acceptance based on the estimated user emotions.

2. The system of claim 1.

6. The reception unit Analyze the user's past speech history and select the optimal reception method 2. The system of claim 1.

Images