System

Abstract

An object of the system according to the embodiment is to detect a statement with a high risk of harassment in real time and prevent the statement in advance.SOLUTION: A system includes an analysis unit, a detection unit, and a warning unit. The analysis unit analyzes the conversation content in real time. The detection unit detects a speech with a high risk of harassment on the basis of a result of the analysis by the analysis unit. The warning unit issues a warning to the user on the basis of the speech detected by the detection 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 technology has the problem of not being able to adequately detect statements that pose a high risk of harassment in real time and prevent them from happening.

[0005] The system according to the embodiment aims to detect statements that pose a high risk of harassment in real time and prevent them from happening. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a detection unit, and a warning unit. The analysis unit analyzes the content of the conversation in real time. The detection unit detects statements that pose a high risk of harassment based on the results of the analysis by the analysis unit. The warning unit issues a warning to the user based on the statements detected by the detection unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect statements that pose a high risk of harassment in real time and prevent them from happening. [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 harassment prevention system according to an embodiment of the present invention prevents the three major forms of harassment (sexual harassment, power harassment, and moral harassment) by incorporating an "AI checker" into everyday communication tools and requesting AI to provide guidance and judgment. In the harassment prevention system, the AI ​​checker analyzes conversation content in real time while a user is using a communication tool, detects potentially harassing statements, and issues a warning to the user. For example, in the harassment prevention system, the AI ​​checker analyzes conversation content in real time while the user is using a communication tool. The AI ​​checker uses natural language processing technology to understand the content and context of the statements. For example, the AI ​​checker analyzes statements made during a Zoom meeting and identifies statements that may be harassing. Next, the harassment prevention system detects potentially harassing statements based on the analysis results. For example, it detects statements that may be sexual harassment or statements that show signs of power harassment. The AI ​​checker evaluates the risk of the statements based on past data and case studies. Furthermore, the harassment prevention system issues a warning to users if the AI ​​checker detects potentially harassing statements. For example, it displays a warning message such as, "This statement may be sexual harassment." This allows users to review their own statements and prevent harassment before it occurs. The harassment prevention system allows users to be aware of their own statements on a daily basis, preventing the three major forms of harassment (sexual harassment, power harassment, and moral harassment). The harassment prevention system is also provided as a plug-in for communication tools and target services such as Zoom, making it easy to implement. For example, by implementing the harassment prevention system in a company's online meetings, employees can prevent harassment before it occurs. Furthermore, by using the harassment prevention system in personal chat tools, harassment can be prevented in everyday communication. This allows the harassment prevention system to automatically analyze users' statements and prevent harassment before it occurs.For example, while a user is using a communication tool, an AI checker can analyze the content of the conversation in real time, detect potentially harassing remarks, and issue a warning to the user, preventing harassment before it occurs. Furthermore, the harassment prevention system is provided as a plug-in for communication tools and target services such as Zoom, making it easy to implement. This makes it possible to prevent harassment before it occurs in corporate online meetings and personal chat tools.

[0029] A harassment prevention system according to an embodiment includes an analysis unit, a detection unit, and a warning unit. The analysis unit analyzes conversation content in real time. The analysis unit understands the content and context of utterances using, for example, natural language processing technology. For example, the analysis unit can break down utterances into words using morphological analysis and analyze sentence structure using grammatical analysis. The analysis unit can also understand the meaning of utterances using semantic analysis. The analysis unit can also analyze utterances made during a Zoom conference. For example, the analysis unit can analyze audio data made during a Zoom conference in real time to understand the content of utterances. The detection unit detects utterances that pose a high risk of harassment based on the results of the analysis by the analysis unit. The detection unit evaluates the risk of utterances based on, for example, past data and case studies. For example, the detection unit can refer to past conversation logs to evaluate whether specific words or phrases pose a high risk of harassment. The detection unit can also evaluate the risk of utterances based on existing cases of harassment. The detection unit can also detect utterances that pose a high risk of sexual harassment or utterances that show signs of power harassment. For example, the detection unit can evaluate whether a specific word or phrase poses a high risk of sexual harassment. The warning unit issues a warning to the user based on the utterance detected by the detection unit. The warning unit, for example, issues a pop-up message or a voice notification. For example, the warning unit can display a warning message such as "This utterance may be sexual harassment." The warning unit can also issue a voice notification and immediately warn the user. As a result, the harassment prevention system according to the embodiment can analyze user utterances in real time, detect utterances that may be harassment, and issue a warning, thereby preventing harassment acts before they occur.

[0030] The analysis unit can understand the content and context of a statement using natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit can break down the words of a statement using morphological analysis and analyze the structure of the sentence using grammatical analysis. The analysis unit can also understand the meaning of a statement using semantic analysis. For example, the analysis unit can refer to surrounding sentences and related topics to understand the context of a statement. In this way, the use of natural language processing technology allows the content and context of a statement to be accurately understood, improving analysis accuracy.

[0031] The detection unit can assess the risk of a statement based on past data or cases. Past data and cases include, for example, past conversation logs and existing cases of harassment. The detection unit can, for example, refer to past conversation logs to assess whether specific words or phrases pose a high risk of harassment. The detection unit can also assess the risk of a statement based on existing cases of harassment. For example, the detection unit can use past data to assess whether specific words or phrases pose a high risk of harassment. In this way, risk assessment based on past data and cases can accurately detect statements that may be harassment.

[0032] The warning unit can issue a pop-up message or a voice notification. The pop-up message can include, for example, a display position, a message length, and the like. The warning unit can display a warning message such as, for example, "This comment may be sexual harassment." The warning unit can also issue a voice notification to immediately warn the user. For example, the warning unit can adjust the type of voice and the timing of the notification. This allows the user to be immediately warned by issuing a pop-up message or a voice notification.

[0033] The analysis unit can analyze the content of statements made during a Zoom meeting. Zoom meetings include, for example, the use of a specific version or features. The analysis unit can, for example, analyze audio data during a Zoom meeting in real time to understand the content of statements made. For example, the analysis unit can analyze statements made during a Zoom meeting in real time to detect statements that pose a high risk of harassment. This makes it possible to prevent harassment in online meetings by analyzing the content of statements made during a Zoom meeting.

[0034] The detection unit can detect statements that pose a high risk of sexual harassment or statements that show signs of power harassment. Statements that pose a high risk of sexual harassment include, for example, specific words, phrases, contexts, etc. The detection unit can, for example, evaluate whether specific words or phrases pose a high risk of sexual harassment. The detection unit can also detect statements that show signs of power harassment. For example, the detection unit can evaluate whether specific words or phrases show signs of power harassment. In this way, by detecting statements that show signs of sexual harassment or power harassment, these acts of harassment can be prevented before they occur.

[0035] During analysis, the analysis unit can correct the analysis results based on the tone or volume of the speech. For example, if the user speaks loudly, the analysis unit can analyze the speech as emphasized and perform a risk assessment. Also, if the user speaks softly, the analysis unit can have the AI ​​carefully analyze the speech and emphasize the context to avoid misunderstandings. Furthermore, if the user speaks in a tone that differs from normal speech, the analysis unit can incorporate the change in tone into the analysis and perform a risk assessment. This improves the accuracy of the analysis results by taking into account the tone and volume of the speech. Analysis of the tone of the speech includes, for example, the pitch and intonation of the voice. Analysis of the volume of the speech includes, for example, the decibel value and sound pressure level.

[0036] During analysis, the analysis unit can optimize the analysis algorithm by referring to the user's past speech history. For example, the analysis unit allows the AI ​​to perform a risk assessment of a specific phrase based on the phrase's past use. The analysis unit can also extract specific patterns from the user's past speech history and allow the AI ​​to perform analysis based on those patterns. Furthermore, the analysis unit can analyze the user's past speech history and allow the AI ​​to adjust the analysis algorithm based on that history. In this way, by referring to the user's past speech history, the analysis algorithm can be optimized and the analysis accuracy improved. The user's past speech history may include, for example, a specific period of time or specific conversation content.

[0037] The analysis unit can improve the accuracy of analysis by filtering background and environmental sounds during analysis. For example, if the background sound is loud, the analysis unit's AI can filter that sound to clearly analyze the content of the speech. In addition, if there is a lot of environmental sound, the analysis unit can also remove that sound and accurately analyze the context of the speech. Furthermore, if the background sound fluctuates, the analysis unit can also correct the fluctuations and consistently analyze the content of the speech. In this way, filtering background and environmental sounds improves the accuracy of analysis. Background sounds include, for example, environmental sounds and noise. Environmental sounds include, for example, the sound of wind and the sound of cars.

[0038] The analysis unit can perform analysis based on the user's geographical or cultural background during analysis. For example, if the user is in a different cultural sphere, the analysis unit allows the AI ​​to analyze the utterances taking into account the cultural background. In addition, if the user is in a specific region, the analysis unit can allow the AI ​​to analyze the utterances taking into account the characteristics of that region. Furthermore, if the user is in a multicultural environment, the analysis unit can allow the AI ​​to analyze the utterances taking into account the environment. This improves the accuracy of the analysis results by taking into account the user's geographical and cultural backgrounds. Geographical backgrounds include, for example, countries, regions, and cities. Cultural backgrounds include, for example, religion, customs, and language.

[0039] During analysis, the analysis unit can analyze the user's social media activity and complement the context of the comments. For example, the analysis unit uses AI to complement the context of the comments based on the content of the user's social media posts. The analysis unit can also analyze the user's social media activity history and use AI to understand the background of the comments. Furthermore, the analysis unit can use AI to complement the context of the comments based on the user's friendships on social media. In this way, by analyzing the user's social media activity, the context of the comments can be complemented and the accuracy of the analysis can be improved. Social media activity includes, for example, the content of posts, comments, and the number of likes.

[0040] During analysis, the analysis unit can customize the analysis algorithm based on the user's occupation or job title. For example, if the user is a manager, the analysis unit applies an analysis algorithm according to the AI's job title. Furthermore, if the user is engaged in a specific occupation, the analysis unit can also apply an analysis algorithm according to the AI's job title. Furthermore, if the user holds a different job title, the analysis unit can also apply an analysis algorithm according to the AI's job title. In this way, customizing the analysis algorithm based on the user's occupation or job title improves the accuracy of the analysis. Occupations include, for example, industry and job type. Job titles include, for example, managerial position and general employee.

[0041] Upon detection, the detection unit can perform risk assessment based on the frequency or pattern of the utterance. For example, if a user frequently uses a specific phrase, the detection unit can have the AI ​​perform risk assessment of that phrase. The detection unit can also analyze the user's utterance pattern, and have the AI ​​perform risk assessment based on that pattern. Furthermore, the detection unit can also take into account the frequency of the user's utterances, and have the AI ​​perform risk assessment based on that frequency. In this way, the accuracy of risk assessment is improved by taking into account the frequency and pattern of the utterances. The frequency of the utterances includes, for example, the number of utterances within a certain period of time. The pattern of the utterances includes, for example, the repetition of a specific phrase.

[0042] The detection unit can apply different detection algorithms depending on the category of the statement during detection. For example, in the case of a work-related statement, the detection unit has the AI ​​apply a detection algorithm depending on the category. In addition, in the case of a private statement, the detection unit can also have the AI ​​apply a detection algorithm depending on the category. Furthermore, the detection unit can automatically classify the user's statement category and have the AI ​​apply a detection algorithm depending on the category. In this way, by applying different detection algorithms depending on the category of the statement, detection accuracy is improved. Statement categories include, for example, work-related and private-related.

[0043] During detection, the detection unit can improve detection accuracy by referring to the user's past utterance data. For example, the detection unit uses AI to improve detection accuracy based on the user's past utterance data. The detection unit can also analyze the user's past utterance patterns, and the AI ​​can improve detection accuracy based on those patterns. Furthermore, the detection unit can also refer to the user's past utterance history, and the AI ​​can improve detection accuracy based on that history. In this way, by referring to the user's past utterance data, detection accuracy is improved. The user's past utterance data includes, for example, a specific period of time or specific conversation content.

[0044] The detection unit can perform risk assessment based on the user's geographical or cultural background during detection. For example, if the user is in a different cultural sphere, the detection unit allows the AI ​​to perform risk assessment by taking into account the cultural background. Furthermore, if the user is in a specific region, the detection unit can allow the AI ​​to perform risk assessment by taking into account the characteristics of the region. Furthermore, if the user is in a multicultural environment, the detection unit can allow the AI ​​to perform risk assessment by taking into account the environment. This improves the accuracy of risk assessment by taking into account the user's geographical and cultural background. Geographical backgrounds include, for example, countries, regions, cities, etc. Cultural backgrounds include, for example, religion, customs, and language, etc.

[0045] At the time of detection, the detection unit can analyze the user's social media activity and complement the risk of the statement. For example, the detection unit uses AI to complement the risk of the statement based on the content of the user's social media posts. The detection unit can also analyze the user's social media activity history and use AI to evaluate the risk of the statement. Furthermore, the detection unit can also use AI to complement the risk of the statement based on the user's friendships on social media. In this way, by analyzing the user's social media activity, the risk of the statement can be complemented and detection accuracy improved. Social media activity includes, for example, the content of posts, comments, the number of likes, etc.

[0046] During detection, the detection unit can customize the detection algorithm based on the user's occupation or job title. For example, if the user is a manager, the detection unit causes the AI ​​to apply a detection algorithm according to the job title. Furthermore, if the user is engaged in a specific occupation, the detection unit can also cause the AI ​​to apply a detection algorithm according to the occupation. Furthermore, if the user holds a different job title, the detection unit can also cause the AI ​​to apply a detection algorithm according to the job title. In this way, customizing the detection algorithm based on the user's occupation or job title improves detection accuracy. Occupations include, for example, industry and job type. Job titles include, for example, managerial position and general employee.

[0047] When issuing a warning, the warning unit can display different warning messages depending on the risk of the statement. For example, if the risk level is high, the AI ​​can display a strong warning message. Furthermore, if the risk level is medium, the warning unit can also display a warning message. Furthermore, if the risk level is low, the AI ​​can also display a light warning message. In this way, by displaying different warning messages depending on the risk level of the statement, it is possible to issue an appropriate warning to the user. The risk of the statement includes, for example, the definition of the risk level and the evaluation method.

[0048] When issuing a warning, the warning unit can adjust the frequency of warnings by referring to the user's past warning history. For example, if the user has received frequent warnings in the past, the AI ​​can increase the frequency of warnings. In addition, if the user has not received many warnings in the past, the AI ​​can set the frequency of warnings to normal mode. Furthermore, the warning unit can analyze the user's past warning history and adjust the frequency of warnings based on that history. In this way, by referring to the user's past warning history, the frequency of warnings can be appropriately adjusted, reducing the burden on the user. The user's past warning history can include, for example, specific periods and specific warning contents.

[0049] The warning unit can improve the warning message by reflecting user feedback when issuing a warning. For example, if a user provides feedback on a warning message, the warning unit allows the AI ​​to improve the warning message based on that feedback. The warning unit can also analyze the user feedback and have the AI ​​adjust the content of the warning message. Furthermore, the warning unit can also improve the way the AI ​​expresses the warning message by taking user feedback into consideration. In this way, the content of the warning message can be improved by reflecting user feedback, helping the user understand it better. User feedback includes, for example, surveys and direct comments.

[0050] The warning unit can customize the warning message based on the user's geographical and cultural background when issuing a warning. For example, if the user is in a different cultural sphere, the AI ​​customizes the warning message by taking into account the cultural background. In addition, if the user is in a specific region, the AI ​​can customize the warning message by taking into account the characteristics of the region. Furthermore, if the user is in a multicultural environment, the AI ​​can customize the warning message by taking into account the environment. This allows the content of the warning message to be appropriately customized by taking into account the user's geographical and cultural background. Geographical backgrounds include, for example, countries, regions, and cities. Cultural backgrounds include, for example, religion, customs, and language.

[0051] When issuing a warning, the warning unit can analyze the user's social media activity and complement the content of the warning. For example, the warning unit uses AI to complement the content of the warning based on the content of the user's social media posts. The warning unit can also analyze the user's social media activity history and use AI to adjust the content of the warning. Furthermore, the warning unit can also use AI to complement the content of the warning based on the user's friendships on social media. In this way, by analyzing the user's social media activity, the content of the warning can be complemented and the accuracy of the warning can be improved. Social media activity includes, for example, the content of posts, comments, the number of likes, etc.

[0052] When issuing a warning, the warning unit can customize the warning message based on the user's occupation or job title. For example, if the user is a manager, the warning unit causes the AI ​​to display a warning message according to that job title. Furthermore, if the user is engaged in a specific occupation, the warning unit can also cause the AI ​​to display a warning message according to that job title. Furthermore, if the user holds a different job title, the warning unit can also cause the AI ​​to display a warning message according to that job title. In this way, customizing the warning message based on the user's occupation or job title makes the content of the warning more appropriate. Occupations include, for example, industry and job type. Job titles include, for example, managerial position and general position.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The analysis unit can estimate the intention behind a user's remarks and correct the analysis results based on that intention. For example, the analysis unit can detect content that the user has said as a joke and perform risk assessment taking that intention into account. In addition, if a user makes a statement that could be misunderstood, the analysis unit can estimate the intention and place emphasis on the context to avoid misunderstanding. Furthermore, if a user makes an emotional statement, the analysis unit can understand the intention and correct the analysis results by taking the emotional background into account. In this way, the accuracy of the analysis results is improved by taking into account the intention of the statement.

[0055] The detection unit can perform risk assessment based on the tone and volume of a user's speech. For example, if a user speaks loudly, the risk assessment can be performed assuming that the speech is emphasized. Also, if a user speaks softly, the speech can be carefully analyzed, emphasizing the context to avoid misunderstanding. Furthermore, if the user's speech is in a tone different from normal, the change in tone can be reflected in the analysis and used to perform risk assessment. In this way, the accuracy of risk assessment can be improved by taking into account the tone and volume of speech.

[0056] The analysis unit can optimize the analysis algorithm by referring to the user's past speech history. For example, it can perform a risk assessment of a particular phrase based on the phrase's past use. It can also extract a particular pattern from the user's past speech history and perform analysis based on that pattern. It can also analyze the user's past speech history and adjust the analysis algorithm based on that history. In this way, by referring to the user's past speech history, the analysis algorithm can be optimized and the analysis accuracy improved.

[0057] The detection unit can perform risk assessment based on the frequency and patterns of a user's utterances. For example, if a user frequently uses a specific phrase, the detection unit can perform a risk assessment of that phrase. The detection unit can also analyze the user's utterance patterns and perform risk assessment based on those patterns. Furthermore, the detection unit can also take into account the frequency of a user's utterances and perform risk assessment based on that frequency. In this way, by taking into account the frequency and patterns of utterances, the accuracy of risk assessment can be improved.

[0058] The analysis unit can perform analysis based on the user's geographical and cultural background. For example, if the user is in a different cultural sphere, the utterances can be analyzed taking into account that cultural background. Also, if the user is in a specific region, the utterances can be analyzed taking into account the characteristics of that region. Furthermore, if the user is in a multicultural environment, the utterances can be analyzed taking into account that environment. In this way, by taking into account the user's geographical and cultural background, the accuracy of the analysis results can be improved.

[0059] The analysis unit can analyze the user's social media activity and complement the context of the comment. For example, the analysis unit can complement the context of the comment based on the content of the user's social media posts. It can also analyze the user's social media activity history to understand the background of the comment. It can also complement the context of the comment by referring to the user's friendships on social media. In this way, by analyzing the user's social media activity, the context of the comment can be complemented and the accuracy of the analysis can be improved.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The analysis unit analyzes the conversation content in real time. The analysis unit uses natural language processing technology to understand the content and context of what is being said. For example, it can use morphological analysis to break down the words in a speech, grammatical analysis to analyze the structure of the sentence, and semantic analysis to understand the meaning of what is being said. It can also analyze audio data during Zoom meetings in real time to understand the content of what is being said. Step 2: The detection unit detects statements that pose a high risk of harassment based on the results of the analysis by the analysis unit. The detection unit evaluates the risk of statements based on past data and examples. For example, it can refer to past conversation logs to evaluate whether specific words or phrases pose a high risk of harassment. It can also evaluate the risk of statements based on existing harassment examples. It can also detect statements that pose a high risk of sexual harassment or statements that show signs of power harassment. Step 3: The warning unit issues a warning to the user based on the remark detected by the detection unit. The warning unit issues a pop-up message or a voice notification. For example, the warning unit can display a warning message such as "This remark may be sexual harassment." It can also issue a voice notification to immediately warn the user.

[0062] (Example 2) A harassment prevention system according to an embodiment of the present invention prevents the three major forms of harassment (sexual harassment, power harassment, and moral harassment) by incorporating an "AI checker" into everyday communication tools and requesting AI to provide guidance and judgment. In the harassment prevention system, the AI ​​checker analyzes conversation content in real time while a user is using a communication tool, detects potentially harassing statements, and issues a warning to the user. For example, in the harassment prevention system, the AI ​​checker analyzes conversation content in real time while the user is using a communication tool. The AI ​​checker uses natural language processing technology to understand the content and context of the statements. For example, the AI ​​checker analyzes statements made during a Zoom meeting and identifies statements that may be harassing. Next, the harassment prevention system detects potentially harassing statements based on the analysis results. For example, it detects statements that may be sexual harassment or statements that show signs of power harassment. The AI ​​checker evaluates the risk of the statements based on past data and case studies. Furthermore, the harassment prevention system issues a warning to users if the AI ​​checker detects potentially harassing statements. For example, it displays a warning message such as, "This statement may be sexual harassment." This allows users to review their own statements and prevent harassment before it occurs. The harassment prevention system allows users to be aware of their own statements on a daily basis, preventing the three major forms of harassment (sexual harassment, power harassment, and moral harassment). The harassment prevention system is also provided as a plug-in for communication tools and target services such as Zoom, making it easy to implement. For example, by implementing the harassment prevention system in a company's online meetings, employees can prevent harassment before it occurs. Furthermore, by using the harassment prevention system in personal chat tools, harassment can be prevented in everyday communication. This allows the harassment prevention system to automatically analyze users' statements and prevent harassment before it occurs.For example, while a user is using a communication tool, an AI checker can analyze the content of the conversation in real time, detect potentially harassing remarks, and issue a warning to the user, preventing harassment before it occurs. Furthermore, the harassment prevention system is provided as a plug-in for communication tools and target services such as Zoom, making it easy to implement. This makes it possible to prevent harassment before it occurs in corporate online meetings and personal chat tools.

[0063] A harassment prevention system according to an embodiment includes an analysis unit, a detection unit, and a warning unit. The analysis unit analyzes conversation content in real time. The analysis unit understands the content and context of utterances using, for example, natural language processing technology. For example, the analysis unit can break down utterances into words using morphological analysis and analyze sentence structure using grammatical analysis. The analysis unit can also understand the meaning of utterances using semantic analysis. The analysis unit can also analyze utterances made during a Zoom conference. For example, the analysis unit can analyze audio data made during a Zoom conference in real time to understand the content of utterances. The detection unit detects utterances that pose a high risk of harassment based on the results of the analysis by the analysis unit. The detection unit evaluates the risk of utterances based on, for example, past data and case studies. For example, the detection unit can refer to past conversation logs to evaluate whether specific words or phrases pose a high risk of harassment. The detection unit can also evaluate the risk of utterances based on existing cases of harassment. The detection unit can also detect utterances that pose a high risk of sexual harassment or utterances that show signs of power harassment. For example, the detection unit can evaluate whether a specific word or phrase poses a high risk of sexual harassment. The warning unit issues a warning to the user based on the utterance detected by the detection unit. The warning unit, for example, issues a pop-up message or a voice notification. For example, the warning unit can display a warning message such as "This utterance may be sexual harassment." The warning unit can also issue a voice notification and immediately warn the user. As a result, the harassment prevention system according to the embodiment can analyze user utterances in real time, detect utterances that may be harassment, and issue a warning, thereby preventing harassment acts before they occur.

[0064] The analysis unit can understand the content and context of a statement using natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit can break down the words of a statement using morphological analysis and analyze the structure of the sentence using grammatical analysis. The analysis unit can also understand the meaning of a statement using semantic analysis. For example, the analysis unit can refer to surrounding sentences and related topics to understand the context of a statement. In this way, the use of natural language processing technology allows the content and context of a statement to be accurately understood, improving analysis accuracy.

[0065] The detection unit can assess the risk of a statement based on past data or cases. Past data and cases include, for example, past conversation logs and existing cases of harassment. The detection unit can, for example, refer to past conversation logs to assess whether specific words or phrases pose a high risk of harassment. The detection unit can also assess the risk of a statement based on existing cases of harassment. For example, the detection unit can use past data to assess whether specific words or phrases pose a high risk of harassment. In this way, risk assessment based on past data and cases can accurately detect statements that may be harassment.

[0066] The warning unit can issue a pop-up message or a voice notification. The pop-up message can include, for example, a display position, a message length, and the like. The warning unit can display a warning message such as, for example, "This comment may be sexual harassment." The warning unit can also issue a voice notification to immediately warn the user. For example, the warning unit can adjust the type of voice and the timing of the notification. This allows the user to be immediately warned by issuing a pop-up message or a voice notification.

[0067] The analysis unit can analyze the content of statements made during a Zoom meeting. Zoom meetings include, for example, the use of a specific version or features. The analysis unit can, for example, analyze audio data during a Zoom meeting in real time to understand the content of statements made. For example, the analysis unit can analyze statements made during a Zoom meeting in real time to detect statements that pose a high risk of harassment. This makes it possible to prevent harassment in online meetings by analyzing the content of statements made during a Zoom meeting.

[0068] The detection unit can detect statements that pose a high risk of sexual harassment or statements that show signs of power harassment. Statements that pose a high risk of sexual harassment include, for example, specific words, phrases, contexts, etc. The detection unit can, for example, evaluate whether specific words or phrases pose a high risk of sexual harassment. The detection unit can also detect statements that show signs of power harassment. For example, the detection unit can evaluate whether specific words or phrases show signs of power harassment. In this way, by detecting statements that show signs of sexual harassment or power harassment, these acts of harassment can be prevented before they occur.

[0069] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions. For example, if the user is nervous, the analysis unit can increase the accuracy of the analysis and perform the analysis carefully to prevent false positives. Furthermore, if the user is relaxed, the analysis unit can set the analysis accuracy to normal mode and perform the analysis quickly. Furthermore, if the user is excited, the analysis unit can increase the accuracy of the analysis and carefully analyze emotional statements. This improves the accuracy of the analysis results by adjusting the analysis accuracy based on the user's emotions. The user's emotions are estimated using technologies such as facial expression recognition and voice analysis. For example, the analysis unit can analyze the user's facial expression data to estimate the user's emotions. Furthermore, the analysis unit can analyze the user's voice data to estimate the user's emotions.

[0070] During analysis, the analysis unit can correct the analysis results based on the tone or volume of the speech. For example, if the user speaks loudly, the analysis unit can analyze the speech as emphasized and perform a risk assessment. Also, if the user speaks softly, the analysis unit can have the AI ​​carefully analyze the speech and emphasize the context to avoid misunderstandings. Furthermore, if the user speaks in a tone that differs from normal speech, the analysis unit can incorporate the change in tone into the analysis and perform a risk assessment. This improves the accuracy of the analysis results by taking into account the tone and volume of the speech. Analysis of the tone of the speech includes, for example, the pitch and intonation of the voice. Analysis of the volume of the speech includes, for example, the decibel value and sound pressure level.

[0071] During analysis, the analysis unit can optimize the analysis algorithm by referring to the user's past speech history. For example, the analysis unit allows the AI ​​to perform a risk assessment of a specific phrase based on the phrase's past use. The analysis unit can also extract specific patterns from the user's past speech history and allow the AI ​​to perform analysis based on those patterns. Furthermore, the analysis unit can analyze the user's past speech history and allow the AI ​​to adjust the analysis algorithm based on that history. In this way, by referring to the user's past speech history, the analysis algorithm can be optimized and the analysis accuracy improved. The user's past speech history may include, for example, a specific period of time or specific conversation content.

[0072] The analysis unit can improve the accuracy of analysis by filtering background and environmental sounds during analysis. For example, if the background sound is loud, the analysis unit's AI can filter that sound to clearly analyze the content of the speech. In addition, if there is a lot of environmental sound, the analysis unit can also remove that sound and accurately analyze the context of the speech. Furthermore, if the background sound fluctuates, the analysis unit can also correct the fluctuations and consistently analyze the content of the speech. In this way, filtering background and environmental sounds improves the accuracy of analysis. Background sounds include, for example, environmental sounds and noise. Environmental sounds include, for example, the sound of wind and the sound of cars.

[0073] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit can have the AI ​​display the analysis results simply, reducing the user's burden. Furthermore, if the user is relaxed, the analysis unit can have the AI ​​display the analysis results in detail, providing the user with more information. Furthermore, if the user is excited, the analysis unit can display the analysis results in a visually easy-to-understand manner, helping the user understand. This reduces the user's burden by adjusting the display method of the analysis results based on the user's emotions. The user's emotions are estimated using technologies such as facial expression recognition and voice analysis. For example, the analysis unit can analyze the user's facial expression data to estimate the user's emotions. Furthermore, the analysis unit can analyze the user's voice data to estimate the user's emotions.

[0074] The analysis unit can perform analysis based on the user's geographical or cultural background during analysis. For example, if the user is in a different cultural sphere, the analysis unit allows the AI ​​to analyze the utterances taking into account the cultural background. In addition, if the user is in a specific region, the analysis unit can allow the AI ​​to analyze the utterances taking into account the characteristics of that region. Furthermore, if the user is in a multicultural environment, the analysis unit can allow the AI ​​to analyze the utterances taking into account the environment. This improves the accuracy of the analysis results by taking into account the user's geographical and cultural backgrounds. Geographical backgrounds include, for example, countries, regions, and cities. Cultural backgrounds include, for example, religion, customs, and language.

[0075] During analysis, the analysis unit can analyze the user's social media activity and complement the context of the comments. For example, the analysis unit uses AI to complement the context of the comments based on the content of the user's social media posts. The analysis unit can also analyze the user's social media activity history and use AI to understand the background of the comments. Furthermore, the analysis unit can use AI to complement the context of the comments based on the user's friendships on social media. In this way, by analyzing the user's social media activity, the context of the comments can be complemented and the accuracy of the analysis can be improved. Social media activity includes, for example, the content of posts, comments, and the number of likes.

[0076] During analysis, the analysis unit can customize the analysis algorithm based on the user's occupation or job title. For example, if the user is a manager, the analysis unit applies an analysis algorithm according to the AI's job title. Furthermore, if the user is engaged in a specific occupation, the analysis unit can also apply an analysis algorithm according to the AI's job title. Furthermore, if the user holds a different job title, the analysis unit can also apply an analysis algorithm according to the AI's job title. In this way, customizing the analysis algorithm based on the user's occupation or job title improves the accuracy of the analysis. Occupations include, for example, industry and job type. Job titles include, for example, managerial position and general employee.

[0077] The detection unit can estimate the user's emotions and adjust the detection criteria based on the estimated user emotions. For example, if the user is nervous, the AI ​​can tighten the detection criteria to prevent false detection. Furthermore, if the user is relaxed, the AI ​​can set the detection criteria to normal mode and perform detection quickly. Furthermore, if the user is excited, the AI ​​can tighten the detection criteria to carefully detect emotional statements. This improves detection accuracy by adjusting the detection criteria based on the user's emotions. The user's emotions are estimated using technologies such as facial expression recognition and voice analysis. For example, the detection unit can analyze the user's facial expression data to estimate the user's emotions. Furthermore, the detection unit can analyze the user's voice data to estimate the user's emotions.

[0078] Upon detection, the detection unit can perform risk assessment based on the frequency or pattern of the utterance. For example, if a user frequently uses a specific phrase, the detection unit can have the AI ​​perform risk assessment of that phrase. The detection unit can also analyze the user's utterance pattern, and have the AI ​​perform risk assessment based on that pattern. Furthermore, the detection unit can also take into account the frequency of the user's utterances, and have the AI ​​perform risk assessment based on that frequency. In this way, the accuracy of risk assessment is improved by taking into account the frequency and pattern of the utterances. The frequency of the utterances includes, for example, the number of utterances within a certain period of time. The pattern of the utterances includes, for example, the repetition of a specific phrase.

[0079] The detection unit can apply different detection algorithms depending on the category of the statement during detection. For example, in the case of a work-related statement, the detection unit has the AI ​​apply a detection algorithm depending on the category. In addition, in the case of a private statement, the detection unit can also have the AI ​​apply a detection algorithm depending on the category. Furthermore, the detection unit can automatically classify the user's statement category and have the AI ​​apply a detection algorithm depending on the category. In this way, by applying different detection algorithms depending on the category of the statement, detection accuracy is improved. Statement categories include, for example, work-related and private-related.

[0080] During detection, the detection unit can improve detection accuracy by referring to the user's past utterance data. For example, the detection unit uses AI to improve detection accuracy based on the user's past utterance data. The detection unit can also analyze the user's past utterance patterns, and the AI ​​can improve detection accuracy based on those patterns. Furthermore, the detection unit can also refer to the user's past utterance history, and the AI ​​can improve detection accuracy based on that history. In this way, by referring to the user's past utterance data, detection accuracy is improved. The user's past utterance data includes, for example, a specific period of time or specific conversation content.

[0081] The detection unit can estimate the user's emotions and adjust the display method of the detection results based on the estimated user emotions. For example, if the user is nervous, the AI ​​can display the detection results simply, reducing the user's burden. Furthermore, if the user is relaxed, the AI ​​can display the detection results in detail, providing the user with more information. Furthermore, if the user is excited, the AI ​​can display the detection results in a visually easy-to-understand manner, helping the user understand. This reduces the user's burden by adjusting the display method of the detection results based on the user's emotions. The user's emotions are estimated using technologies such as facial expression recognition and voice analysis. For example, the detection unit can analyze the user's facial expression data to estimate the user's emotions. Furthermore, the detection unit can analyze the user's voice data to estimate the user's emotions.

[0082] The detection unit can perform risk assessment based on the user's geographical or cultural background during detection. For example, if the user is in a different cultural sphere, the detection unit allows the AI ​​to perform risk assessment by taking into account the cultural background. Furthermore, if the user is in a specific region, the detection unit can allow the AI ​​to perform risk assessment by taking into account the characteristics of the region. Furthermore, if the user is in a multicultural environment, the detection unit can allow the AI ​​to perform risk assessment by taking into account the environment. This improves the accuracy of risk assessment by taking into account the user's geographical and cultural background. Geographical backgrounds include, for example, countries, regions, cities, etc. Cultural backgrounds include, for example, religion, customs, and language, etc.

[0083] At the time of detection, the detection unit can analyze the user's social media activity and complement the risk of the statement. For example, the detection unit uses AI to complement the risk of the statement based on the content of the user's social media posts. The detection unit can also analyze the user's social media activity history and use AI to evaluate the risk of the statement. Furthermore, the detection unit can also use AI to complement the risk of the statement based on the user's friendships on social media. In this way, by analyzing the user's social media activity, the risk of the statement can be complemented and detection accuracy improved. Social media activity includes, for example, the content of posts, comments, the number of likes, etc.

[0084] During detection, the detection unit can customize the detection algorithm based on the user's occupation or job title. For example, if the user is a manager, the detection unit causes the AI ​​to apply a detection algorithm according to the job title. Furthermore, if the user is engaged in a specific occupation, the detection unit can also cause the AI ​​to apply a detection algorithm according to the occupation. Furthermore, if the user holds a different job title, the detection unit can also cause the AI ​​to apply a detection algorithm according to the job title. In this way, customizing the detection algorithm based on the user's occupation or job title improves detection accuracy. Occupations include, for example, industry and job type. Job titles include, for example, managerial position and general employee.

[0085] The warning unit can estimate the user's emotions and adjust the way the warning is expressed based on the estimated user's emotions. For example, if the user is nervous, the AI ​​can express the warning calmly, reducing the user's burden. Furthermore, if the user is relaxed, the AI ​​can express the warning in detail, providing the user with more information. Furthermore, if the user is excited, the AI ​​can express the warning in a visually easy-to-understand manner, helping the user understand. This reduces the user's burden by adjusting the way the warning is expressed based on the user's emotions. The user's emotions are estimated using technologies such as facial expression recognition and voice analysis. For example, the warning unit can analyze the user's facial expression data to estimate the user's emotions. The warning unit can also analyze the user's voice data to estimate the user's emotions.

[0086] When issuing a warning, the warning unit can display different warning messages depending on the risk of the statement. For example, if the risk level is high, the AI ​​can display a strong warning message. Furthermore, if the risk level is medium, the warning unit can also display a warning message. Furthermore, if the risk level is low, the AI ​​can also display a light warning message. In this way, by displaying different warning messages depending on the risk level of the statement, it is possible to issue an appropriate warning to the user. The risk of the statement includes, for example, the definition of the risk level and the evaluation method.

[0087] When issuing a warning, the warning unit can adjust the frequency of warnings by referring to the user's past warning history. For example, if the user has received frequent warnings in the past, the AI ​​can increase the frequency of warnings. In addition, if the user has not received many warnings in the past, the AI ​​can set the frequency of warnings to normal mode. Furthermore, the warning unit can analyze the user's past warning history and adjust the frequency of warnings based on that history. In this way, by referring to the user's past warning history, the frequency of warnings can be appropriately adjusted, reducing the burden on the user. The user's past warning history can include, for example, specific periods and specific warning contents.

[0088] The warning unit can improve the warning message by reflecting user feedback when issuing a warning. For example, if a user provides feedback on a warning message, the warning unit allows the AI ​​to improve the warning message based on that feedback. The warning unit can also analyze the user feedback and have the AI ​​adjust the content of the warning message. Furthermore, the warning unit can also improve the way the AI ​​expresses the warning message by taking user feedback into consideration. In this way, the content of the warning message can be improved by reflecting user feedback, helping the user understand it better. User feedback includes, for example, surveys and direct comments.

[0089] The warning unit can estimate the user's emotions and adjust the timing of the warning based on the estimated user emotions. For example, if the user is nervous, the AI ​​in the warning unit can delay the timing of the warning, thereby reducing the burden on the user. Furthermore, if the user is relaxed, the AI ​​can set the timing of the warning to normal mode. Furthermore, if the user is excited, the AI ​​can advance the timing of the warning and issue a prompt warning. In this way, the burden on the user is reduced by adjusting the timing of the warning based on the user's emotions. The user's emotions are estimated using technologies such as facial expression recognition and voice analysis. For example, the warning unit can analyze the user's facial expression data to estimate the user's emotions. The warning unit can also analyze the user's voice data to estimate the user's emotions.

[0090] The warning unit can customize the warning message based on the user's geographical and cultural background when issuing a warning. For example, if the user is in a different cultural sphere, the AI ​​customizes the warning message by taking into account the cultural background. In addition, if the user is in a specific region, the AI ​​can customize the warning message by taking into account the characteristics of the region. Furthermore, if the user is in a multicultural environment, the AI ​​can customize the warning message by taking into account the environment. This allows the content of the warning message to be appropriately customized by taking into account the user's geographical and cultural background. Geographical backgrounds include, for example, countries, regions, and cities. Cultural backgrounds include, for example, religion, customs, and language.

[0091] When issuing a warning, the warning unit can analyze the user's social media activity and complement the content of the warning. For example, the warning unit uses AI to complement the content of the warning based on the content of the user's social media posts. The warning unit can also analyze the user's social media activity history and use AI to adjust the content of the warning. Furthermore, the warning unit can also use AI to complement the content of the warning based on the user's friendships on social media. In this way, by analyzing the user's social media activity, the content of the warning can be complemented and the accuracy of the warning can be improved. Social media activity includes, for example, the content of posts, comments, the number of likes, etc.

[0092] When issuing a warning, the warning unit can customize the warning message based on the user's occupation or job title. For example, if the user is a manager, the warning unit causes the AI ​​to display a warning message according to that job title. Furthermore, if the user is engaged in a specific occupation, the warning unit can also cause the AI ​​to display a warning message according to that job title. Furthermore, if the user holds a different job title, the warning unit can also cause the AI ​​to display a warning message according to that job title. In this way, customizing the warning message based on the user's occupation or job title makes the content of the warning more appropriate. Occupations include, for example, industry and job type. Job titles include, for example, managerial position and general position. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, detection unit, and warning unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14 or the processor 28 of the data processing device 12. For example, the detection unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the warning unit is realized by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, detection unit, and warning unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 or the processor 28 of the data processing device 12. For example, the detection unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the warning unit is realized by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, detection unit, and warning unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset type terminal 314 or the processor 28 of the data processing device 12. For example, the detection unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the warning unit is realized by the display 343 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, detection unit, and warning unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 or the processor 28 of the data processing device 12. For example, the detection unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the warning unit is realized by the speaker 240 of the robot 414 or the specific processing unit 290 of the data processing device 12.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The analysis unit can estimate the intention behind a user's remarks and correct the analysis results based on that intention. For example, the analysis unit can detect content that the user has said as a joke and perform risk assessment taking that intention into account. In addition, if a user makes a statement that could be misunderstood, the analysis unit can estimate the intention and place emphasis on the context to avoid misunderstanding. Furthermore, if a user makes an emotional statement, the analysis unit can understand the intention and correct the analysis results by taking the emotional background into account. In this way, the accuracy of the analysis results is improved by taking into account the intention of the statement.

[0095] The detection unit can perform risk assessment based on the tone and volume of a user's speech. For example, if a user speaks loudly, the risk assessment can be performed assuming that the speech is emphasized. Also, if a user speaks softly, the speech can be carefully analyzed, emphasizing the context to avoid misunderstanding. Furthermore, if the user's speech is in a tone different from normal, the change in tone can be reflected in the analysis and used to perform risk assessment. In this way, the accuracy of risk assessment can be improved by taking into account the tone and volume of speech.

[0096] The warning unit can estimate the user's emotions and adjust the way the warning is expressed based on the estimated user's emotions. For example, if the user is nervous, the warning can be expressed calmly, reducing the burden on the user. Also, if the user is relaxed, the warning can be expressed in detail, providing the user with more information. Furthermore, if the user is excited, the warning can be expressed in a visually easy-to-understand manner, helping the user understand. In this way, the burden on the user can be reduced by adjusting the way the warning is expressed based on the user's emotions.

[0097] The analysis unit can optimize the analysis algorithm by referring to the user's past speech history. For example, it can perform a risk assessment of a particular phrase based on the phrase's past use. It can also extract a particular pattern from the user's past speech history and perform analysis based on that pattern. It can also analyze the user's past speech history and adjust the analysis algorithm based on that history. In this way, by referring to the user's past speech history, the analysis algorithm can be optimized and the analysis accuracy improved.

[0098] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions. For example, if the user is nervous, the analysis accuracy can be increased and the analysis can be performed carefully to prevent false positives. Also, if the user is relaxed, the analysis accuracy can be set to normal mode and the analysis can be performed quickly. Furthermore, if the user is excited, the analysis accuracy can be increased and emotional statements can be analyzed carefully. In this way, adjusting the analysis accuracy based on the user's emotions improves the accuracy of the analysis results.

[0099] The detection unit can perform risk assessment based on the frequency and patterns of a user's utterances. For example, if a user frequently uses a specific phrase, the detection unit can perform a risk assessment of that phrase. The detection unit can also analyze the user's utterance patterns and perform risk assessment based on those patterns. Furthermore, the detection unit can also take into account the frequency of a user's utterances and perform risk assessment based on that frequency. In this way, by taking into account the frequency and patterns of utterances, the accuracy of risk assessment can be improved.

[0100] The warning unit can estimate the user's emotions and adjust the timing of the warning based on the estimated user emotions. For example, if the user is nervous, the warning timing can be delayed to reduce the burden on the user. Also, if the user is relaxed, the warning timing can be set to normal mode. Furthermore, if the user is excited, the warning timing can be advanced to provide a prompt warning. In this way, the burden on the user can be reduced by adjusting the warning timing based on the user's emotions.

[0101] The analysis unit can perform analysis based on the user's geographical and cultural background. For example, if the user is in a different cultural sphere, the utterances can be analyzed taking into account that cultural background. Also, if the user is in a specific region, the utterances can be analyzed taking into account the characteristics of that region. Furthermore, if the user is in a multicultural environment, the utterances can be analyzed taking into account that environment. In this way, by taking into account the user's geographical and cultural background, the accuracy of the analysis results can be improved.

[0102] The warning unit can estimate the user's emotions and adjust the content of the warning based on the estimated user's emotions. For example, if the user is nervous, the warning content can be made gentler, thereby reducing the burden on the user. Also, if the user is relaxed, the warning content can be made more detailed, thereby providing the user with more information. Furthermore, if the user is excited, the warning content can be made visually easier to understand, thereby helping the user to understand. In this way, the burden on the user can be reduced by adjusting the content of the warning based on the user's emotions.

[0103] The analysis unit can analyze the user's social media activity and complement the context of the comment. For example, the analysis unit can complement the context of the comment based on the content of the user's social media posts. It can also analyze the user's social media activity history to understand the background of the comment. It can also complement the context of the comment by referring to the user's friendships on social media. In this way, by analyzing the user's social media activity, the context of the comment can be complemented and the accuracy of the analysis can be improved.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The analysis unit analyzes the conversation content in real time. The analysis unit uses natural language processing technology to understand the content and context of what is being said. For example, it can use morphological analysis to break down the words in a speech, grammatical analysis to analyze the structure of the sentence, and semantic analysis to understand the meaning of what is being said. It can also analyze audio data during Zoom meetings in real time to understand the content of what is being said. Step 2: The detection unit detects statements that pose a high risk of harassment based on the results of the analysis by the analysis unit. The detection unit evaluates the risk of statements based on past data and examples. For example, it can refer to past conversation logs to evaluate whether specific words or phrases pose a high risk of harassment. It can also evaluate the risk of statements based on existing harassment examples. It can also detect statements that pose a high risk of sexual harassment or statements that show signs of power harassment. Step 3: The warning unit issues a warning to the user based on the remark detected by the detection unit. The warning unit issues a pop-up message or a voice notification. For example, the warning unit can display a warning message such as "This remark may be sexual harassment." It can also issue a voice notification to immediately warn the user.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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 AI 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.

[0124] 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.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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 AI 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.

[0140] 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.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0164] 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."

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. An analysis unit that analyzes the conversation content in real time, a detection unit that detects statements that pose a high risk of harassment based on the results of the analysis by the analysis unit; a warning unit that issues a warning to a user based on the utterance detected by the detection unit. A system characterized by:

2. The analysis unit Using natural language processing technology to understand the content and context of statements The system of claim 1 .

3. The detection unit Evaluate the risk of statements based on past data or examples The system of claim 1 .

4. The warning unit Pop-up message or sound notification The system of claim 1 .

5. The analysis unit Analyze what is said during a Zoom meeting The system of claim 1 .

6. The detection unit Detect statements that pose a high risk of sexual harassment or show signs of power harassment The system of claim 1 .

7. The analysis unit Estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions. The system of claim 1 .

8. The analysis unit During analysis, the analysis results are adjusted based on the tone or volume of speech. The system of claim 1 .

Images