System

Abstract

An object of the system according to the embodiment is to detect a wording having a possibility of power harassment in real time and to immediately respond to the wording.SOLUTION: A system according to an embodiment includes a monitoring unit, a detection unit, an alert unit, and a recording unit. The monitoring unit monitors the conversation in real time. The detection unit detects a wording having a possibility of power harassment from the conversation monitored by the monitoring unit. The alert unit issues an alert based on the wording detected by the detection unit. The recording unit records the word 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 making it difficult to detect occurrences of power harassment in real time and respond immediately.

[0005] The system according to the embodiment aims to detect potentially power harassment statements in real time and respond immediately. [Means for solving the problem]

[0006] The system according to the embodiment includes a monitoring unit, a detection unit, an alert unit, and a recording unit. The monitoring unit monitors conversations in real time. The detection unit detects words that may be power harassment from the conversations monitored by the monitoring unit. The alert unit issues an alert based on the words detected by the detection unit. The recording unit records the words detected by the detection unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect potentially power harassment statements in real time and respond immediately. [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 power harassment detection system according to an embodiment of the present invention is a system that monitors conversations in real time, and a generation AI detects language that may constitute power harassment, issues an alert, and records the information. The power harassment detection system monitors conversations in real time, and the generation AI compares the information with past cases of power harassment to detect language that may constitute power harassment. For example, the power harassment detection system monitors conversations in real time. For example, the power harassment detection system converts the conversation into text data using speech recognition technology. Next, the power harassment detection system compares the information with past cases of power harassment using a generation AI to detect language that may constitute power harassment. For example, the generation AI detects language such as "You're useless" or "Quit." Next, the power harassment detection system issues an alert based on the detected language. For example, the alert may be displayed on a screen, sent by voice, or sent by email. Next, the power harassment detection system records the detected language. For example, the recording may be stored in the cloud or locally. This allows the power harassment detection system to monitor conversations in real time, detect any potentially harassing language, issue an alert, and record the information. This allows the power harassment detection system to prevent power harassment from occurring and contribute to improving the work environment. For example, if potentially harassing language is detected, a notification will be sent to the employee's supervisor or the human resources department, and appropriate action will be taken. In this way, the system can prevent power harassment from occurring and contribute to improving the work environment.

[0029] A power harassment detection system according to an embodiment includes a monitoring unit, a detection unit, an alert unit, and a recording unit. The monitoring unit monitors conversations in real time. The monitoring unit converts the conversations into text data using, for example, voice recognition technology. The monitoring unit can also use a generation AI to analyze the speed and tone of the conversation and detect abnormal patterns. For example, the monitoring unit detects a sudden change in the speed of the conversation as an abnormal pattern. The monitoring unit can also detect a sudden change in the tone of the conversation as an abnormal pattern. The monitoring unit can also analyze a combination of the speed and tone of the conversation to detect abnormal patterns. The detection unit uses the generation AI to detect phrases that may be power harassment from the conversations monitored by the monitoring unit. The detection unit, for example, compares past cases of power harassment to detect phrases that may be power harassment. For example, the detection unit detects phrases such as "You're useless" or "Quit." The detection unit can also evaluate the possibility of power harassment by taking into account the context of the conversation. For example, the detection unit analyzes the context of a conversation to evaluate whether a specific phrase constitutes power harassment. The detection unit can also interpret the meaning of words used in a conversation based on the context and evaluate the possibility of power harassment. The detection unit can also evaluate whether a specific phrase constitutes power harassment by taking into account the tone and emotion of the conversation. The alert unit issues an alert based on the phrase detected by the detection unit. The alert unit issues the alert by, for example, a screen display, an audio notification, an email notification, or the like. For example, the alert unit displays a message such as "Power harassment may be occurring. Please be careful" on the screen. The alert unit can also issue an audio notification such as "Power harassment may be occurring. Please be careful." The alert unit can also issue an email notification such as "Power harassment may be occurring. Please be careful." The recording unit records the phrase detected by the detection unit. The recording unit records the phrase by, for example, storing it on the cloud or locally.For example, the recording unit may use cloud services such as AWS (registered trademark) or Google (registered trademark) Cloud to store data in the cloud. Alternatively, the recording unit may use a recording medium such as a hard disk or SSD to store data locally. This allows the power harassment detection system according to the embodiment to monitor conversations in real time, detect potentially power harassment statements, issue an alert, and record them. This allows the power harassment detection system according to the embodiment to prevent power harassment from occurring and contribute to improving the work environment.

[0030] The alert unit can issue an alert by means of a screen display, a voice notification, or an email notification. The alert unit issues an alert by means of, for example, a pop-up notification or a banner display as a screen display. For example, the alert unit can display a message such as "Power harassment may be occurring. Please be careful" as a pop-up notification as a screen display. The alert unit can also display a message such as "Power harassment may be occurring. Please be careful" as a banner display as a screen display. The alert unit can also issue an alert by means of a voice message or an alarm sound as a voice notification. For example, the alert unit can issue an alert by means of a voice message such as "Power harassment may be occurring. Please be careful" as a voice notification. The alert unit can also issue an alert by sounding an alarm sound as a voice notification. The alert unit can also issue an alert by means of an email notification such as a text email or an HTML email. For example, the alert unit can issue an email notification such as "Power harassment may be occurring. Please be careful" as a text email. The alert unit can also issue an email notification such as "Power harassment may be occurring. Please be careful" as an HTML email. This allows for a variety of alert generation methods, making it possible to notify the user effectively.

[0031] The recording unit can record the text by storing it in the cloud or by storing it locally. For example, the recording unit uses cloud services such as AWS or Google Cloud as a method of storing it in the cloud. The recording unit can also use recording media such as a hard disk or SSD as a method of storing it locally. For example, the recording unit can store the text using an S3 bucket from AWS as a method of storing it in the cloud. The recording unit can also store the text using Cloud Storage from Google Cloud. The recording unit can also store the text on a hard disk as a method of storing it locally. The recording unit can also store the text on an SSD. This diversifies the methods of storing the text, thereby improving the security and accessibility of the records.

[0032] The monitoring unit can convert the conversation into text data using speech recognition technology. The monitoring unit can convert the conversation into text data using, for example, deep learning-based speech recognition technology. The monitoring unit can also convert the conversation into text data using HMM (hidden Markov model)-based speech recognition technology. For example, the monitoring unit can convert the conversation into text data in real time using deep learning-based speech recognition technology. The monitoring unit can also convert the conversation into text data in real time using HMM-based speech recognition technology. The monitoring unit can also analyze the speed and tone of the conversation using generative AI to detect abnormal patterns. For example, the monitoring unit can detect a sudden change in the speed of the conversation as an abnormal pattern. The monitoring unit can also detect a sudden change in the tone of the conversation as an abnormal pattern. The monitoring unit can also analyze the combination of the speed and tone of the conversation to detect abnormal patterns. As a result, the conversation can be treated as text data using speech recognition technology.

[0033] The detection unit can compare many past cases of power harassment to detect language that may constitute power harassment. For example, the detection unit compares past cases of power harassment with court precedents and internal company reports. The detection unit can also use generation AI to compare past cases of power harassment to detect language that may constitute power harassment. For example, the detection unit detects language that may constitute power harassment based on court precedents. The detection unit can also detect language that may constitute power harassment based on internal company reports. The detection unit can also use generation AI to compare past cases of power harassment to detect language that may constitute power harassment. For example, the detection unit uses generation AI to detect language such as "You're useless" or "Quit." The detection unit can also evaluate the possibility of power harassment by taking into account the context of the conversation. For example, the detection unit analyzes the context before and after the conversation to evaluate whether specific language constitutes power harassment. The detection unit can also interpret the meaning of words used in conversations based on the context and assess the possibility of power harassment.The detection unit can also take into account the tone and emotion of the conversation to evaluate whether specific words constitute power harassment.This allows for highly accurate detection of words that may be power harassment by comparing them with past cases.

[0034] The monitoring unit can filter background sounds during conversations and environmental sounds to remove noise. For example, the monitoring unit can analyze background sounds during conversations in real time and remove them using noise-canceling technology. The monitoring unit can also detect environmental sounds and filter specific frequency bands to improve the clarity of the conversation. The monitoring unit can also learn specific noise patterns during conversations, and the generation AI can automatically remove the noise. For example, the monitoring unit can analyze background sounds during conversations in real time and remove them using noise-canceling technology. The monitoring unit can also detect environmental sounds and filter specific frequency bands to improve the clarity of the conversation. The monitoring unit can also learn specific noise patterns during conversations, and the generation AI can automatically remove the noise. This makes it possible to improve the clarity of the conversation by removing noise.

[0035] The monitoring unit can detect abnormal patterns by analyzing the speed and tone of speech. For example, if the speed of speech changes suddenly, the generation AI detects this as an abnormal pattern. The monitoring unit can also detect a sudden change in the tone of speech as a abnormal pattern by the generation AI. The monitoring unit can also analyze the combination of speed and tone of speech to detect abnormal patterns. For example, if the speed of speech changes suddenly, the generation AI detects this as an abnormal pattern. The monitoring unit can also detect a sudden change in the tone of speech as a abnormal pattern by the generation AI. The monitoring unit can also analyze the combination of speed and tone of speech to detect abnormal patterns. This allows for early detection of abnormal conversation patterns by detecting abnormalities in speed and tone of speech.

[0036] The monitoring unit can be set to respond preferentially to specific keywords or phrases. The monitoring unit preferentially detects specific keywords, such as "quit" or "useless," for example. The monitoring unit can also preferentially monitor conversations containing specific phrases. The monitoring unit can also perform monitoring based on custom keywords set by the user. For example, the monitoring unit preferentially detects specific keywords, such as "quit" or "useless." The monitoring unit can also preferentially monitor conversations containing specific phrases. The monitoring unit can also perform monitoring based on custom keywords set by the user. In this way, by responding preferentially to specific keywords or phrases, important conversations can be quickly detected.

[0037] The monitoring unit can prioritize monitoring highly relevant conversations by taking into account the geographical location information of the user. For example, when the user is in a specific location, the monitoring unit prioritizes monitoring conversations related to the location. Furthermore, when the user is on the move, the monitoring unit can also prioritize monitoring conversations related to the destination. Furthermore, when the user is in a specific region, the monitoring unit can also prioritize monitoring conversations related to the region. For example, when the user is in a specific location, the monitoring unit prioritizes monitoring conversations related to the location. Furthermore, when the user is on the move, the monitoring unit can also prioritize monitoring conversations related to the destination. Furthermore, when the user is in a specific region, the monitoring unit can also prioritize monitoring conversations related to the region. In this way, highly relevant conversations can be prioritized by taking into account the geographical location information.

[0038] The monitoring unit can analyze the user's social media activity and monitor related conversations. For example, the monitoring unit monitors related conversations based on content posted by the user on social media. The monitoring unit can also monitor related conversations with reference to the activities of the user's friends on social media. The monitoring unit can also monitor related conversations based on the user's check-in information on social media. For example, the monitoring unit monitors related conversations based on content posted by the user on social media. The monitoring unit can also monitor related conversations with reference to the activities of the user's friends on social media. The monitoring unit can also monitor related conversations with reference to the user's check-in information on social media. In this way, related conversations can be effectively monitored by analyzing social media activity.

[0039] The monitoring unit can customize the monitoring method by reflecting the user's past feedback. The monitoring unit, for example, adjusts the monitoring sensitivity based on feedback provided by the user in the past. The monitoring unit can also customize the response to specific keywords or phrases by referring to the user's past feedback. The monitoring unit can also adjust the monitoring frequency and method based on the user's past feedback. For example, the monitoring unit adjusts the monitoring sensitivity based on feedback provided by the user in the past. The monitoring unit can also customize the response to specific keywords or phrases by referring to the user's past feedback. The monitoring unit can also adjust the monitoring frequency and method based on the user's past feedback. In this way, the monitoring method can be optimized for the user by reflecting the past feedback.

[0040] The detection unit can evaluate the possibility of power harassment by taking into account the context of the conversation. For example, the detection unit analyzes the context before and after the conversation to evaluate whether specific words constitute power harassment. The detection unit can also interpret the meaning of words used in the conversation based on the context to evaluate the possibility of power harassment. The detection unit can also evaluate whether specific words constitute power harassment by taking into account the tone and emotions of the conversation. For example, the detection unit analyzes the context before and after the conversation to evaluate whether specific words constitute power harassment. The detection unit can also interpret the meaning of words used in the conversation based on the context to evaluate the possibility of power harassment. The detection unit can also evaluate whether specific words constitute power harassment by taking into account the tone and emotions of the conversation. In this way, by taking into account the context of the conversation, the possibility of power harassment can be evaluated more accurately.

[0041] The detection unit can improve the accuracy of detection by taking into account attribute information of the participants in the conversation. The detection unit evaluates the possibility of power harassment by taking into account, for example, the job titles and relationships of the participants in the conversation. The detection unit can also evaluate the possibility of power harassment by referring to the past behavioral history of the participants in the conversation. The detection unit can also evaluate whether specific words constitute power harassment based on the attribute information of the participants in the conversation. For example, the detection unit evaluates the possibility of power harassment by taking into account the job titles and relationships of the participants in the conversation. The detection unit can also evaluate the possibility of power harassment by referring to the past behavioral history of the participants in the conversation. The detection unit can also evaluate whether specific words constitute power harassment based on the attribute information of the participants in the conversation. In this way, by taking into account the attribute information of the participants in the conversation, the accuracy of detection can be improved.

[0042] The detection unit can optimize the detection algorithm by referring to past detection results. The detection unit, for example, analyzes past detection results and improves the accuracy of the detection algorithm. The detection unit can also learn specific words or patterns based on past detection results and optimize the detection algorithm. The detection unit can also adjust the parameters of the detection algorithm by referring to past detection results. For example, the detection unit analyzes past detection results and improves the accuracy of the detection algorithm. The detection unit can also learn specific words or patterns based on past detection results and optimize the detection algorithm. The detection unit can also adjust the parameters of the detection algorithm by referring to past detection results. In this way, the accuracy of the detection algorithm can be improved by referring to past detection results.

[0043] The detection unit can perform detection taking into account the geographical distribution of conversations. For example, the detection unit can prioritize detecting conversations in a specific region. The detection unit can also analyze the geographical distribution of conversations and evaluate the possibility of power harassment in a specific region. The detection unit can also prioritize detecting conversations in a specific region by taking geographical factors into account. For example, the detection unit can prioritize detecting conversations in a specific region. The detection unit can also analyze the geographical distribution of conversations and evaluate the possibility of power harassment in a specific region. The detection unit can also prioritize detecting conversations in a specific region by taking geographical factors into account. In this way, the possibility of power harassment in a specific region can be evaluated by taking geographical distribution into account.

[0044] The detection unit can improve the accuracy of detection by referring to related literature and data. The detection unit, for example, refers to related literature to evaluate the possibility of power harassment. The detection unit can also improve the accuracy of detection by learning specific phrases and patterns based on past data. The detection unit can also optimize the detection algorithm by referring to related research results. For example, the detection unit can evaluate the possibility of power harassment by referring to related literature. The detection unit can also improve the accuracy of detection by learning specific phrases and patterns based on past data. The detection unit can also optimize the detection algorithm by referring to related research results. In this way, the accuracy of detection can be improved by referring to related literature and data.

[0045] The detection unit can perform detection taking into account the market value of a conversation. For example, the detection unit prioritizes detection when the content of a conversation has an impact on the market value. The detection unit can also evaluate the market value of a conversation and determine whether specific words constitute power harassment. The detection unit can also prioritize detection of specific conversations taking into account market value. For example, the detection unit prioritizes detection when the content of a conversation has an impact on the market value. The detection unit can also evaluate the market value of a conversation and determine whether specific words constitute power harassment. The detection unit can also prioritize detection of specific conversations taking into account market value. In this way, specific conversations can be detected with priority by taking market value into account.

[0046] When an alert occurs, the alert unit can select a notification method based on the importance of the alert. For example, the alert unit notifies a high-importance alert by both audio notification and on-screen display. The alert unit can also notify a medium-importance alert only by on-screen display. The alert unit can also notify a low-importance alert only by email notification. For example, the alert unit notifies a high-importance alert by both audio notification and on-screen display. The alert unit can also notify a medium-importance alert only by on-screen display. The alert unit can also notify a low-importance alert only by email notification. In this way, by selecting a notification method based on the importance of the alert, appropriate notifications are possible.

[0047] When an alert occurs, the alert unit can select the optimal notification method by referring to the user's past alert history. For example, the alert unit prioritizes selecting a notification method that the user has used preferentially in the past. The alert unit can also customize the optimal notification method based on the user's past alert history. The alert unit can also analyze the user's past alert history and select the most effective notification method. For example, the alert unit prioritizes selecting a notification method that the user has used preferentially in the past. The alert unit can also customize the optimal notification method based on the user's past alert history. The alert unit can also analyze the user's past alert history and select the most effective notification method. In this way, the optimal notification method can be selected by referring to the past alert history.

[0048] When an alert occurs, the alert unit can customize the content of the alert according to the user's current situation. For example, when the user is in a meeting, the alert unit selects a quiet notification method and makes the alert content simple. Furthermore, when the user is on the move, the alert unit can prioritize audio notification and make the alert content detailed. Furthermore, when the user is relaxed, the alert unit can use both screen display and audio notification and make the alert content detailed. For example, when the user is in a meeting, the alert unit selects a quiet notification method and makes the alert content simple. Furthermore, when the user is on the move, the alert unit can prioritize audio notification and make the alert content detailed. Furthermore, when the user is relaxed, the alert unit can use both screen display and audio notification and make the alert content detailed. This allows the content of the alert to be customized according to the user's current situation, enabling more appropriate notifications.

[0049] When an alert occurs, the alert unit can select the optimal notification method in consideration of the user's device information. For example, if the user is using a smartphone, the alert unit selects a notification method that combines a screen display and a voice notification. Furthermore, if the user is using a PC, the alert unit can also select a notification method that combines a screen display and an email notification. Furthermore, if the user is using a smartwatch, the alert unit can also select a notification method that combines a vibration notification and a screen display. For example, if the user is using a smartphone, the alert unit selects a notification method that combines a screen display and a voice notification. Furthermore, if the user is using a PC, the alert unit can also select a notification method that combines a screen display and an email notification. Furthermore, if the user is using a smartwatch, the alert unit can also select a notification method that combines a vibration notification and a screen display. In this way, the optimal notification method can be selected by considering the device information.

[0050] When an alert occurs, the alert unit can make the alert content multilingual in accordance with the user's language setting. The alert unit, for example, automatically translates the alert content based on the language setting of the user's device. The alert unit can also provide a language switching function when the user uses multiple languages. The alert unit can also provide the alert content in a specific language when the user selects that language. For example, the alert unit can automatically translate the alert content based on the language setting of the user's device. The alert unit can also provide a language switching function when the user uses multiple languages. The alert unit can also provide the alert content in a specific language when the user selects that language. This makes it possible to provide appropriate notifications to the user by making the alert content multilingual in accordance with the language setting.

[0051] When an alert occurs, the alert unit can customize the alert content based on the user's occupation and lifestyle. For example, if the user is a businessman, the alert unit can provide alert content related to work. Furthermore, if the user is a student, the alert unit can also provide alert content related to schoolwork. Furthermore, if the user is a housewife, the alert unit can also provide alert content related to homework. For example, if the user is a businessman, the alert unit can provide alert content related to work. Furthermore, if the user is a student, the alert unit can also provide alert content related to schoolwork. Furthermore, if the user is a housewife, the alert unit can also provide alert content related to homework. In this way, customizing the alert content based on the user's occupation and lifestyle enables more appropriate notifications.

[0052] The recording unit can adjust the level of detail of the recording based on the importance of the conversation when recording. For example, the recording unit can perform detailed recording of a conversation of high importance and save all utterances. The recording unit can also record only the main points of a conversation of medium importance and save important utterances. The recording unit can also perform concise recording of a conversation of low importance and save only necessary information. For example, the recording unit can perform detailed recording of a conversation of high importance and save all utterances. The recording unit can also record only the main points of a conversation of medium importance and save important utterances. The recording unit can also perform concise recording of a conversation of low importance and save only necessary information. In this way, by adjusting the level of detail of the recording based on the importance of the conversation, necessary information can be appropriately saved.

[0053] The recording unit can apply different recording algorithms depending on the category of the conversation when recording. For example, in the case of a business conversation, the recording unit can perform detailed recording and save all utterances. In addition, in the case of a private conversation, the recording unit can perform concise recording and save only important utterances. In addition, in the case of an academic conversation, the recording unit can perform detailed recording including technical terms and save all utterances. For example, in the case of a business conversation, the recording unit can perform detailed recording and save all utterances. In addition, in the case of a private conversation, the recording unit can perform concise recording and save only important utterances. In addition, in the case of an academic conversation, the recording unit can perform detailed recording including technical terms and save all utterances. In this way, by applying a recording algorithm depending on the category of the conversation, appropriate recording is possible.

[0054] The recording unit can improve the accuracy of recording by referring to the user's past recording results when recording. For example, the recording unit analyzes the user's past recording results and improves the accuracy of the recording algorithm. The recording unit can also learn a specific pattern based on the user's past recording results and improve the accuracy of recording. The recording unit can also adjust the parameters of the recording algorithm by referring to the user's past recording results. For example, the recording unit analyzes the user's past recording results and improves the accuracy of the recording algorithm. The recording unit can also learn a specific pattern based on the user's past recording results and improve the accuracy of recording. The recording unit can also adjust the parameters of the recording algorithm by referring to the user's past recording results. In this way, the accuracy of recording can be improved by referring to the past recording results.

[0055] The recording unit can determine the priority of recording when recording based on the submission time of the conversation. For example, the recording unit gives priority to recording a conversation with a high urgency and saves it immediately. The recording unit can also give priority to recording a conversation with an approaching submission deadline and save it early. The recording unit can also postpone recording a conversation with a distant submission deadline and save only the necessary information. For example, the recording unit gives priority to recording a conversation with a high urgency and saves it immediately. The recording unit can also give priority to recording a conversation with an approaching submission deadline and save it early. The recording unit can also postpone recording a conversation with a distant submission deadline and save only the necessary information. In this way, by determining the priority of recording based on the submission time, it is possible to preferentially record a conversation with a high urgency.

[0056] The recording unit can adjust the order of recording based on the relevance of the conversations when recording. For example, the recording unit can prioritize recording and immediately save conversations with high relevance. The recording unit can also record only the main points of conversations with medium relevance and save important information. The recording unit can also postpone recording conversations with low relevance and save only necessary information. For example, the recording unit can prioritize recording and immediately save conversations with high relevance. The recording unit can also record only the main points of conversations with medium relevance and save important information. The recording unit can also postpone recording conversations with low relevance and save only necessary information. In this way, by adjusting the order of recording based on relevance, important conversations can be recorded with priority.

[0057] During recording, the recording unit can adjust the use of technical terms in the recording according to the user's level of expertise. For example, if the user has technical expertise, the recording unit can perform detailed recording including technical terms. Furthermore, if the user does not have technical expertise, the recording unit can perform concise recording and avoid technical terms. Furthermore, the recording unit can adjust the level of detail in the recording according to the user's level of expertise. For example, if the user has technical expertise, the recording unit can perform detailed recording including technical terms. Furthermore, if the user does not have technical expertise, the recording unit can perform concise recording and avoid technical terms. Furthermore, the recording unit can adjust the level of detail in the recording according to the user's level of expertise. This allows for appropriate recording by adjusting the use of technical terms in the recording according to the level of expertise.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The monitoring unit can refer to the user's calendar information and adjust the monitoring sensitivity for important meetings and events. For example, if an important meeting is scheduled, the monitoring unit increases the sensitivity to detect details of the conversation. Also, if the user is on vacation, the monitoring unit can decrease the sensitivity to detect only important conversations. Furthermore, if the user is traveling, the monitoring unit can set the sensitivity to medium to detect only necessary information. This allows the monitoring sensitivity to be adjusted according to the user's schedule, making it possible to detect more appropriate conversation content.

[0060] The monitoring unit can adjust the monitoring sensitivity taking into account the user's device usage status. For example, if the user is using a smartphone, the monitoring unit increases the sensitivity and detects conversations in real time. If the user is using a PC, the monitoring unit can set the sensitivity to medium and detect only necessary information. Furthermore, if the user is using a smartwatch, the monitoring unit can decrease the sensitivity and detect only important conversations. This allows the detection of more appropriate conversation content by adjusting the monitoring sensitivity according to the device usage status.

[0061] The monitoring unit can prioritize monitoring highly relevant conversations by taking into account the geographical location information of the user. For example, when the user is in a specific location, the monitoring unit prioritizes monitoring conversations related to that location. In addition, when the user is traveling, the monitoring unit can prioritize monitoring conversations related to the user's destination. Furthermore, when the user is in a specific region, the monitoring unit can prioritize monitoring conversations related to that region. In this way, highly relevant conversations can be prioritized by taking into account the geographical location information.

[0062] The monitoring unit can analyze the user's social media activity and monitor related conversations. For example, the monitoring unit can monitor related conversations based on the content posted by the user on social media. The monitoring unit can also monitor related conversations based on the activities of the user's friends on social media. Furthermore, the monitoring unit can monitor related conversations based on the user's check-in information on social media. This allows for effective monitoring of related conversations by analyzing social media activity.

[0063] The monitoring unit can customize the monitoring method by reflecting the user's past feedback. For example, the monitoring unit can adjust the monitoring sensitivity based on feedback provided by the user in the past. The monitoring unit can also customize the response to specific keywords or phrases by referring to the user's past feedback. Furthermore, the monitoring unit can adjust the frequency and method of monitoring based on the user's past feedback. In this way, the monitoring method can be optimized for the user by reflecting past feedback.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The monitoring unit monitors the conversation in real time. The monitoring unit uses voice recognition technology to convert the conversation into text data, and uses generative AI to analyze the speed and tone of the conversation to detect abnormal patterns. For example, a sudden change in the speed of the conversation or a sudden change in tone will be detected as an abnormal pattern. Step 2: The detection unit detects phrases that may be considered power harassment from the conversations monitored by the monitoring unit. The detection unit uses generative AI to compare past cases of power harassment and detect phrases such as "You're useless" or "Quit." The detection unit also takes into account the context, tone, and emotions of the conversation to assess the possibility of power harassment. Step 3: The alert unit issues an alert based on the text detected by the detection unit. The alert unit notifies the user by displaying a message on the screen, making a sound, sending an email, or otherwise sending a message such as "There is a possibility of power harassment. Please be careful." Step 4: The recording unit records the text detected by the detection unit. The recording unit records the text by saving it in the cloud or locally. For example, the recording unit can use cloud services such as AWS or Google Cloud, or can use recording media such as a hard disk or SSD.

[0066] (Example 2) A power harassment detection system according to an embodiment of the present invention is a system that monitors conversations in real time, and a generation AI detects language that may constitute power harassment, issues an alert, and records the information. The power harassment detection system monitors conversations in real time, and the generation AI compares the information with past cases of power harassment to detect language that may constitute power harassment. For example, the power harassment detection system monitors conversations in real time. For example, the power harassment detection system converts the conversation into text data using speech recognition technology. Next, the power harassment detection system compares the information with past cases of power harassment using a generation AI to detect language that may constitute power harassment. For example, the generation AI detects language such as "You're useless" or "Quit." Next, the power harassment detection system issues an alert based on the detected language. For example, the alert may be displayed on a screen, sent by voice, or sent by email. Next, the power harassment detection system records the detected language. For example, the recording may be stored in the cloud or locally. This allows the power harassment detection system to monitor conversations in real time, detect any potentially harassing language, issue an alert, and record the information. This allows the power harassment detection system to prevent power harassment from occurring and contribute to improving the work environment. For example, if potentially harassing language is detected, a notification will be sent to the employee's supervisor or the human resources department, and appropriate action will be taken. In this way, the system can prevent power harassment from occurring and contribute to improving the work environment.

[0067] A power harassment detection system according to an embodiment includes a monitoring unit, a detection unit, an alert unit, and a recording unit. The monitoring unit monitors conversations in real time. The monitoring unit converts the conversations into text data using, for example, voice recognition technology. The monitoring unit can also use a generation AI to analyze the speed and tone of the conversation and detect abnormal patterns. For example, the monitoring unit detects a sudden change in the speed of the conversation as an abnormal pattern. The monitoring unit can also detect a sudden change in the tone of the conversation as an abnormal pattern. The monitoring unit can also analyze a combination of the speed and tone of the conversation to detect abnormal patterns. The detection unit uses the generation AI to detect phrases that may be power harassment from the conversations monitored by the monitoring unit. The detection unit, for example, compares past cases of power harassment to detect phrases that may be power harassment. For example, the detection unit detects phrases such as "You're useless" or "Quit." The detection unit can also evaluate the possibility of power harassment by taking into account the context of the conversation. For example, the detection unit analyzes the context of a conversation to evaluate whether a specific phrase constitutes power harassment. The detection unit can also interpret the meaning of words used in a conversation based on the context and evaluate the possibility of power harassment. The detection unit can also evaluate whether a specific phrase constitutes power harassment by taking into account the tone and emotion of the conversation. The alert unit issues an alert based on the phrase detected by the detection unit. The alert unit issues the alert by, for example, a screen display, an audio notification, an email notification, or the like. For example, the alert unit displays a message such as "Power harassment may be occurring. Please be careful" on the screen. The alert unit can also issue an audio notification such as "Power harassment may be occurring. Please be careful." The alert unit can also issue an email notification such as "Power harassment may be occurring. Please be careful." The recording unit records the phrase detected by the detection unit. The recording unit records the phrase by, for example, storing it on the cloud or locally.For example, the recording unit may use a cloud service such as AWS or Google Cloud to store data in the cloud. Alternatively, the recording unit may use a recording medium such as a hard disk or SSD to store data locally. This allows the power harassment detection system according to the embodiment to monitor conversations in real time, detect potentially harassing language, issue an alert, and record the conversation. This allows the power harassment detection system according to the embodiment to prevent power harassment from occurring and contribute to improving the work environment.

[0068] The alert unit can issue an alert by means of a screen display, a voice notification, or an email notification. The alert unit issues an alert by means of, for example, a pop-up notification or a banner display as a screen display. For example, the alert unit can display a message such as "Power harassment may be occurring. Please be careful" as a pop-up notification as a screen display. The alert unit can also display a message such as "Power harassment may be occurring. Please be careful" as a banner display as a screen display. The alert unit can also issue an alert by means of a voice message or an alarm sound as a voice notification. For example, the alert unit can issue an alert by means of a voice message such as "Power harassment may be occurring. Please be careful" as a voice notification. The alert unit can also issue an alert by sounding an alarm sound as a voice notification. The alert unit can also issue an alert by means of an email notification such as a text email or an HTML email. For example, the alert unit can issue an email notification such as "Power harassment may be occurring. Please be careful" as a text email. The alert unit can also issue an email notification such as "Power harassment may be occurring. Please be careful" as an HTML email. This allows for a variety of alert generation methods, making it possible to notify the user effectively.

[0069] The recording unit can record the text by storing it in the cloud or by storing it locally. For example, the recording unit uses cloud services such as AWS or Google Cloud as a method of storing it in the cloud. The recording unit can also use recording media such as a hard disk or SSD as a method of storing it locally. For example, the recording unit can store the text using an S3 bucket from AWS as a method of storing it in the cloud. The recording unit can also store the text using Cloud Storage from Google Cloud. The recording unit can also store the text on a hard disk as a method of storing it locally. The recording unit can also store the text on an SSD. This diversifies the methods of storing the text, thereby improving the security and accessibility of the records.

[0070] The monitoring unit can convert the conversation into text data using speech recognition technology. The monitoring unit can convert the conversation into text data using, for example, deep learning-based speech recognition technology. The monitoring unit can also convert the conversation into text data using HMM (hidden Markov model)-based speech recognition technology. For example, the monitoring unit can convert the conversation into text data in real time using deep learning-based speech recognition technology. The monitoring unit can also convert the conversation into text data in real time using HMM-based speech recognition technology. The monitoring unit can also analyze the speed and tone of the conversation using generative AI to detect abnormal patterns. For example, the monitoring unit can detect a sudden change in the speed of the conversation as an abnormal pattern. The monitoring unit can also detect a sudden change in the tone of the conversation as an abnormal pattern. The monitoring unit can also analyze the combination of the speed and tone of the conversation to detect abnormal patterns. As a result, the conversation can be treated as text data using speech recognition technology.

[0071] The detection unit can compare many past cases of power harassment to detect language that may constitute power harassment. For example, the detection unit compares past cases of power harassment with court precedents and internal company reports. The detection unit can also use generation AI to compare past cases of power harassment to detect language that may constitute power harassment. For example, the detection unit detects language that may constitute power harassment based on court precedents. The detection unit can also detect language that may constitute power harassment based on internal company reports. The detection unit can also use generation AI to compare past cases of power harassment to detect language that may constitute power harassment. For example, the detection unit uses generation AI to detect language such as "You're useless" or "Quit." The detection unit can also evaluate the possibility of power harassment by taking into account the context of the conversation. For example, the detection unit analyzes the context before and after the conversation to evaluate whether specific language constitutes power harassment. The detection unit can also interpret the meaning of words used in conversations based on the context and assess the possibility of power harassment.The detection unit can also take into account the tone and emotion of the conversation to evaluate whether specific words constitute power harassment.This allows for highly accurate detection of words that may be power harassment by comparing them with past cases.

[0072] The monitoring unit can estimate the user's emotions and adjust the monitoring sensitivity based on the estimated user's emotions. For example, when the user is feeling stressed, the monitoring unit increases the monitoring sensitivity to detect more detailed conversation content. Furthermore, when the user is relaxed, the monitoring unit can decrease the monitoring sensitivity to detect only important conversations. Furthermore, when the user is in a hurry, the monitoring unit can set the monitoring sensitivity to a medium level to detect only necessary information. For example, when the user is feeling stressed, the monitoring unit increases the monitoring sensitivity to detect more detailed conversation content. Furthermore, when the user is relaxed, the monitoring unit can decrease the monitoring sensitivity to detect only important conversations. Furthermore, when the user is in a hurry, the monitoring unit can set the monitoring sensitivity to a medium level to detect only necessary information. In this way, by adjusting the monitoring sensitivity according to the user's emotions, more appropriate conversation content can be detected.

[0073] The monitoring unit can filter background sounds during conversations and environmental sounds to remove noise. For example, the monitoring unit can analyze background sounds during conversations in real time and remove them using noise-canceling technology. The monitoring unit can also detect environmental sounds and filter specific frequency bands to improve the clarity of the conversation. The monitoring unit can also learn specific noise patterns during conversations, and the generation AI can automatically remove the noise. For example, the monitoring unit can analyze background sounds during conversations in real time and remove them using noise-canceling technology. The monitoring unit can also detect environmental sounds and filter specific frequency bands to improve the clarity of the conversation. The monitoring unit can also learn specific noise patterns during conversations, and the generation AI can automatically remove the noise. This makes it possible to improve the clarity of the conversation by removing noise.

[0074] The monitoring unit can detect abnormal patterns by analyzing the speed and tone of speech. For example, if the speed of speech changes suddenly, the generation AI detects this as an abnormal pattern. The monitoring unit can also detect a sudden change in the tone of speech as a abnormal pattern by the generation AI. The monitoring unit can also analyze the combination of speed and tone of speech to detect abnormal patterns. For example, if the speed of speech changes suddenly, the generation AI detects this as an abnormal pattern. The monitoring unit can also detect a sudden change in the tone of speech as a abnormal pattern by the generation AI. The monitoring unit can also analyze the combination of speed and tone of speech to detect abnormal patterns. This allows for early detection of abnormal conversation patterns by detecting abnormalities in speed and tone of speech.

[0075] The monitoring unit can be set to respond preferentially to specific keywords or phrases. The monitoring unit preferentially detects specific keywords, such as "quit" or "useless," for example. The monitoring unit can also preferentially monitor conversations containing specific phrases. The monitoring unit can also perform monitoring based on custom keywords set by the user. For example, the monitoring unit preferentially detects specific keywords, such as "quit" or "useless." The monitoring unit can also preferentially monitor conversations containing specific phrases. The monitoring unit can also perform monitoring based on custom keywords set by the user. In this way, by responding preferentially to specific keywords or phrases, important conversations can be quickly detected.

[0076] The monitoring unit can estimate the user's emotions and adjust the monitoring frequency based on the estimated user's emotions. For example, when the user is feeling stressed, the monitoring unit can increase the monitoring frequency and detect conversations more frequently. Furthermore, when the user is relaxed, the monitoring unit can decrease the monitoring frequency and detect only important conversations. Furthermore, when the user is in a hurry, the monitoring unit can set the monitoring frequency to a medium level and detect only necessary information. For example, when the user is feeling stressed, the monitoring unit can increase the monitoring frequency and detect conversations more frequently. Furthermore, when the user is relaxed, the monitoring unit can decrease the monitoring frequency and detect only important conversations. Furthermore, when the user is in a hurry, the monitoring unit can set the monitoring frequency to a medium level and detect only necessary information. In this way, by adjusting the monitoring frequency according to the user's emotions, more appropriate conversation content can be detected.

[0077] The monitoring unit can prioritize monitoring highly relevant conversations by taking into account the geographical location information of the user. For example, when the user is in a specific location, the monitoring unit prioritizes monitoring conversations related to the location. Furthermore, when the user is on the move, the monitoring unit can also prioritize monitoring conversations related to the destination. Furthermore, when the user is in a specific region, the monitoring unit can also prioritize monitoring conversations related to the region. For example, when the user is in a specific location, the monitoring unit prioritizes monitoring conversations related to the location. Furthermore, when the user is on the move, the monitoring unit can also prioritize monitoring conversations related to the destination. Furthermore, when the user is in a specific region, the monitoring unit can also prioritize monitoring conversations related to the region. In this way, highly relevant conversations can be prioritized by taking into account the geographical location information.

[0078] The monitoring unit can analyze the user's social media activity and monitor related conversations. For example, the monitoring unit monitors related conversations based on content posted by the user on social media. The monitoring unit can also monitor related conversations with reference to the activities of the user's friends on social media. The monitoring unit can also monitor related conversations based on the user's check-in information on social media. For example, the monitoring unit monitors related conversations based on content posted by the user on social media. The monitoring unit can also monitor related conversations with reference to the activities of the user's friends on social media. The monitoring unit can also monitor related conversations with reference to the user's check-in information on social media. In this way, related conversations can be effectively monitored by analyzing social media activity.

[0079] The monitoring unit can customize the monitoring method by reflecting the user's past feedback. The monitoring unit, for example, adjusts the monitoring sensitivity based on feedback provided by the user in the past. The monitoring unit can also customize the response to specific keywords or phrases by referring to the user's past feedback. The monitoring unit can also adjust the monitoring frequency and method based on the user's past feedback. For example, the monitoring unit adjusts the monitoring sensitivity based on feedback provided by the user in the past. The monitoring unit can also customize the response to specific keywords or phrases by referring to the user's past feedback. The monitoring unit can also adjust the monitoring frequency and method based on the user's past feedback. In this way, the monitoring method can be optimized for the user by reflecting the past feedback.

[0080] The detection unit can estimate the user's emotions and adjust the detection criteria based on the estimated user's emotions. For example, when the user is feeling stressed, the detection unit can tighten the detection criteria to detect more cases of potential power harassment. Furthermore, when the user is relaxed, the detection unit can loosen the detection criteria to detect only serious cases of potential power harassment. Furthermore, when the user is in a hurry, the detection unit can set the detection criteria to a moderate level to detect only cases of potential power harassment that are necessary. For example, when the user is feeling stressed, the detection unit can tighten the detection criteria to detect more cases of potential power harassment. Furthermore, when the user is relaxed, the detection unit can loosen the detection criteria to detect only serious cases of potential power harassment. Furthermore, when the user is in a hurry, the detection unit can set the detection criteria to a moderate level to detect only cases of potential power harassment that are necessary. In this way, by adjusting the detection criteria according to the user's emotions, it is possible to more appropriately detect cases of potential power harassment.

[0081] The detection unit can evaluate the possibility of power harassment by taking into account the context of the conversation. For example, the detection unit analyzes the context before and after the conversation to evaluate whether specific words constitute power harassment. The detection unit can also interpret the meaning of words used in the conversation based on the context to evaluate the possibility of power harassment. The detection unit can also evaluate whether specific words constitute power harassment by taking into account the tone and emotions of the conversation. For example, the detection unit analyzes the context before and after the conversation to evaluate whether specific words constitute power harassment. The detection unit can also interpret the meaning of words used in the conversation based on the context to evaluate the possibility of power harassment. The detection unit can also evaluate whether specific words constitute power harassment by taking into account the tone and emotions of the conversation. In this way, by taking into account the context of the conversation, the possibility of power harassment can be evaluated more accurately.

[0082] The detection unit can improve the accuracy of detection by taking into account attribute information of the participants in the conversation. The detection unit evaluates the possibility of power harassment by taking into account, for example, the job titles and relationships of the participants in the conversation. The detection unit can also evaluate the possibility of power harassment by referring to the past behavioral history of the participants in the conversation. The detection unit can also evaluate whether specific words constitute power harassment based on the attribute information of the participants in the conversation. For example, the detection unit evaluates the possibility of power harassment by taking into account the job titles and relationships of the participants in the conversation. The detection unit can also evaluate the possibility of power harassment by referring to the past behavioral history of the participants in the conversation. The detection unit can also evaluate whether specific words constitute power harassment based on the attribute information of the participants in the conversation. In this way, by taking into account the attribute information of the participants in the conversation, the accuracy of detection can be improved.

[0083] The detection unit can optimize the detection algorithm by referring to past detection results. The detection unit, for example, analyzes past detection results and improves the accuracy of the detection algorithm. The detection unit can also learn specific words or patterns based on past detection results and optimize the detection algorithm. The detection unit can also adjust the parameters of the detection algorithm by referring to past detection results. For example, the detection unit analyzes past detection results and improves the accuracy of the detection algorithm. The detection unit can also learn specific words or patterns based on past detection results and optimize the detection algorithm. The detection unit can also adjust the parameters of the detection algorithm by referring to past detection results. In this way, the accuracy of the detection algorithm can be improved by referring to past detection results.

[0084] The detection unit can estimate the user's emotions and determine a detection priority based on the estimated user's emotions. For example, when the user is feeling stressed, the detection unit can increase the detection priority and detect more cases of possible power harassment. Furthermore, when the user is relaxed, the detection unit can lower the detection priority and detect only serious cases of possible power harassment. Furthermore, when the user is in a hurry, the detection unit can set the detection priority to medium and detect only serious cases of possible power harassment. For example, when the user is feeling stressed, the detection unit can increase the detection priority and detect more cases of possible power harassment. Furthermore, when the user is relaxed, the detection unit can lower the detection priority and detect only serious cases of possible power harassment. Furthermore, when the user is in a hurry, the detection unit can set the detection priority to medium and detect only serious cases of possible power harassment. In this way, by determining the detection priority according to the user's emotions, it is possible to preferentially detect more serious cases of possible power harassment.

[0085] The detection unit can perform detection taking into account the geographical distribution of conversations. For example, the detection unit can prioritize detecting conversations in a specific region. The detection unit can also analyze the geographical distribution of conversations and evaluate the possibility of power harassment in a specific region. The detection unit can also prioritize detecting conversations in a specific region by taking geographical factors into account. For example, the detection unit can prioritize detecting conversations in a specific region. The detection unit can also analyze the geographical distribution of conversations and evaluate the possibility of power harassment in a specific region. The detection unit can also prioritize detecting conversations in a specific region by taking geographical factors into account. In this way, the possibility of power harassment in a specific region can be evaluated by taking geographical distribution into account.

[0086] The detection unit can improve the accuracy of detection by referring to related literature and data. The detection unit, for example, refers to related literature to evaluate the possibility of power harassment. The detection unit can also improve the accuracy of detection by learning specific phrases and patterns based on past data. The detection unit can also optimize the detection algorithm by referring to related research results. For example, the detection unit can evaluate the possibility of power harassment by referring to related literature. The detection unit can also improve the accuracy of detection by learning specific phrases and patterns based on past data. The detection unit can also optimize the detection algorithm by referring to related research results. In this way, the accuracy of detection can be improved by referring to related literature and data.

[0087] The detection unit can perform detection taking into account the market value of a conversation. For example, the detection unit prioritizes detection when the content of a conversation has an impact on the market value. The detection unit can also evaluate the market value of a conversation and determine whether specific words constitute power harassment. The detection unit can also prioritize detection of specific conversations taking into account market value. For example, the detection unit prioritizes detection when the content of a conversation has an impact on the market value. The detection unit can also evaluate the market value of a conversation and determine whether specific words constitute power harassment. The detection unit can also prioritize detection of specific conversations taking into account market value. In this way, specific conversations can be detected with priority by taking market value into account.

[0088] The alert unit can estimate the user's emotions and adjust the way the alert is expressed based on the estimated user's emotions. For example, if the user is nervous, the alert unit issues an alert in a calm tone. Furthermore, if the user is relaxed, the alert unit can also issue an alert in a bright tone. Furthermore, if the user is in a hurry, the alert unit can also issue a quick and concise alert. For example, if the user is nervous, the alert unit can issue an alert in a calm tone. Furthermore, if the user is relaxed, the alert unit can also issue an alert in a bright tone. Furthermore, if the user is in a hurry, the alert unit can also issue a quick and concise alert. This allows for more effective notification by adjusting the way the alert is expressed based on the user's emotions.

[0089] When an alert occurs, the alert unit can select a notification method based on the importance of the alert. For example, the alert unit notifies a high-importance alert by both audio notification and on-screen display. The alert unit can also notify a medium-importance alert only by on-screen display. The alert unit can also notify a low-importance alert only by email notification. For example, the alert unit notifies a high-importance alert by both audio notification and on-screen display. The alert unit can also notify a medium-importance alert only by on-screen display. The alert unit can also notify a low-importance alert only by email notification. In this way, by selecting a notification method based on the importance of the alert, appropriate notifications are possible.

[0090] When an alert occurs, the alert unit can select the optimal notification method by referring to the user's past alert history. For example, the alert unit prioritizes selecting a notification method that the user has used preferentially in the past. The alert unit can also customize the optimal notification method based on the user's past alert history. The alert unit can also analyze the user's past alert history and select the most effective notification method. For example, the alert unit prioritizes selecting a notification method that the user has used preferentially in the past. The alert unit can also customize the optimal notification method based on the user's past alert history. The alert unit can also analyze the user's past alert history and select the most effective notification method. In this way, the optimal notification method can be selected by referring to the past alert history.

[0091] When an alert occurs, the alert unit can customize the content of the alert according to the user's current situation. For example, when the user is in a meeting, the alert unit selects a quiet notification method and makes the alert content simple. Furthermore, when the user is on the move, the alert unit can prioritize audio notification and make the alert content detailed. Furthermore, when the user is relaxed, the alert unit can use both screen display and audio notification and make the alert content detailed. For example, when the user is in a meeting, the alert unit selects a quiet notification method and makes the alert content simple. Furthermore, when the user is on the move, the alert unit can prioritize audio notification and make the alert content detailed. Furthermore, when the user is relaxed, the alert unit can use both screen display and audio notification and make the alert content detailed. This allows the content of the alert to be customized according to the user's current situation, enabling more appropriate notifications.

[0092] The alert unit can estimate the user's emotions and adjust the frequency of alerts based on the estimated user's emotions. For example, if the user is feeling stressed, the alert unit can increase the frequency of alerts and provide more notifications. Furthermore, if the user is relaxed, the alert unit can decrease the frequency of alerts and provide only important notifications. Furthermore, if the user is in a hurry, the alert unit can set the frequency of alerts to a medium level and provide only necessary notifications. For example, if the user is feeling stressed, the alert unit can increase the frequency of alerts and provide more notifications. Furthermore, if the user is relaxed, the alert unit can decrease the frequency of alerts and provide only important notifications. Furthermore, if the user is in a hurry, the alert unit can set the frequency of alerts to a medium level and provide only necessary notifications. In this way, adjusting the frequency of alerts according to the user's emotions enables more appropriate notifications.

[0093] When an alert occurs, the alert unit can select the optimal notification method in consideration of the user's device information. For example, if the user is using a smartphone, the alert unit selects a notification method that combines a screen display and a voice notification. Furthermore, if the user is using a PC, the alert unit can also select a notification method that combines a screen display and an email notification. Furthermore, if the user is using a smartwatch, the alert unit can also select a notification method that combines a vibration notification and a screen display. For example, if the user is using a smartphone, the alert unit selects a notification method that combines a screen display and a voice notification. Furthermore, if the user is using a PC, the alert unit can also select a notification method that combines a screen display and an email notification. Furthermore, if the user is using a smartwatch, the alert unit can also select a notification method that combines a vibration notification and a screen display. In this way, the optimal notification method can be selected by considering the device information.

[0094] When an alert occurs, the alert unit can make the alert content multilingual in accordance with the user's language setting. The alert unit, for example, automatically translates the alert content based on the language setting of the user's device. The alert unit can also provide a language switching function when the user uses multiple languages. The alert unit can also provide the alert content in a specific language when the user selects that language. For example, the alert unit can automatically translate the alert content based on the language setting of the user's device. The alert unit can also provide a language switching function when the user uses multiple languages. The alert unit can also provide the alert content in a specific language when the user selects that language. This makes it possible to provide appropriate notifications to the user by making the alert content multilingual in accordance with the language setting.

[0095] When an alert occurs, the alert unit can customize the alert content based on the user's occupation and lifestyle. For example, if the user is a businessman, the alert unit can provide alert content related to work. Furthermore, if the user is a student, the alert unit can also provide alert content related to schoolwork. Furthermore, if the user is a housewife, the alert unit can also provide alert content related to homework. For example, if the user is a businessman, the alert unit can provide alert content related to work. Furthermore, if the user is a student, the alert unit can also provide alert content related to schoolwork. Furthermore, if the user is a housewife, the alert unit can also provide alert content related to homework. In this way, customizing the alert content based on the user's occupation and lifestyle enables more appropriate notifications.

[0096] The recording unit can estimate the user's emotions and adjust the recording method based on the estimated user's emotions. For example, if the user is feeling stressed, the recording unit can record in detail and allow the user to review the information later. Furthermore, if the user is relaxed, the recording unit can record in brief and save only important information. Furthermore, if the user is in a hurry, the recording unit can record only necessary information and allow the user to add details later. For example, if the user is feeling stressed, the recording unit can record in detail and allow the user to review the information later. Furthermore, if the user is relaxed, the recording unit can record in brief and save only important information. Furthermore, if the user is in a hurry, the recording unit can record only necessary information and allow the user to add details later. In this way, by adjusting the recording method according to the user's emotions, more appropriate recording is possible.

[0097] The recording unit can adjust the level of detail of the recording based on the importance of the conversation when recording. For example, the recording unit can perform detailed recording of a conversation of high importance and save all utterances. The recording unit can also record only the main points of a conversation of medium importance and save important utterances. The recording unit can also perform concise recording of a conversation of low importance and save only necessary information. For example, the recording unit can perform detailed recording of a conversation of high importance and save all utterances. The recording unit can also record only the main points of a conversation of medium importance and save important utterances. The recording unit can also perform concise recording of a conversation of low importance and save only necessary information. In this way, by adjusting the level of detail of the recording based on the importance of the conversation, necessary information can be appropriately saved.

[0098] The recording unit can apply different recording algorithms depending on the category of the conversation when recording. For example, in the case of a business conversation, the recording unit can perform detailed recording and save all utterances. In addition, in the case of a private conversation, the recording unit can perform concise recording and save only important utterances. In addition, in the case of an academic conversation, the recording unit can perform detailed recording including technical terms and save all utterances. For example, in the case of a business conversation, the recording unit can perform detailed recording and save all utterances. In addition, in the case of a private conversation, the recording unit can perform concise recording and save only important utterances. In addition, in the case of an academic conversation, the recording unit can perform detailed recording including technical terms and save all utterances. In this way, by applying a recording algorithm depending on the category of the conversation, appropriate recording is possible.

[0099] The recording unit can improve the accuracy of recording by referring to the user's past recording results when recording. For example, the recording unit analyzes the user's past recording results and improves the accuracy of the recording algorithm. The recording unit can also learn a specific pattern based on the user's past recording results and improve the accuracy of recording. The recording unit can also adjust the parameters of the recording algorithm by referring to the user's past recording results. For example, the recording unit analyzes the user's past recording results and improves the accuracy of the recording algorithm. The recording unit can also learn a specific pattern based on the user's past recording results and improve the accuracy of recording. The recording unit can also adjust the parameters of the recording algorithm by referring to the user's past recording results. In this way, the accuracy of recording can be improved by referring to the past recording results.

[0100] The recording unit can estimate the user's emotions and determine a recording priority based on the estimated user's emotions. For example, when the user is feeling stressed, the recording unit can increase the recording priority and record more conversations. Furthermore, when the user is relaxed, the recording unit can decrease the recording priority and record only important conversations. Furthermore, when the user is in a hurry, the recording unit can set the recording priority to medium and record only necessary conversations. For example, when the user is feeling stressed, the recording unit can increase the recording priority and record more conversations. Furthermore, when the user is relaxed, the recording unit can decrease the recording priority and record only important conversations. Furthermore, when the user is in a hurry, the recording unit can set the recording priority to medium and record only necessary conversations. In this way, by determining the recording priority according to the user's emotions, important conversations can be preferentially recorded.

[0101] The recording unit can determine the priority of recording when recording based on the submission time of the conversation. For example, the recording unit gives priority to recording a conversation with a high urgency and saves it immediately. The recording unit can also give priority to recording a conversation with an approaching submission deadline and save it early. The recording unit can also postpone recording a conversation with a distant submission deadline and save only the necessary information. For example, the recording unit gives priority to recording a conversation with a high urgency and saves it immediately. The recording unit can also give priority to recording a conversation with an approaching submission deadline and save it early. The recording unit can also postpone recording a conversation with a distant submission deadline and save only the necessary information. In this way, by determining the priority of recording based on the submission time, it is possible to preferentially record a conversation with a high urgency.

[0102] The recording unit can adjust the order of recording based on the relevance of the conversations when recording. For example, the recording unit can prioritize recording and immediately save conversations with high relevance. The recording unit can also record only the main points of conversations with medium relevance and save important information. The recording unit can also postpone recording conversations with low relevance and save only necessary information. For example, the recording unit can prioritize recording and immediately save conversations with high relevance. The recording unit can also record only the main points of conversations with medium relevance and save important information. The recording unit can also postpone recording conversations with low relevance and save only necessary information. In this way, by adjusting the order of recording based on relevance, important conversations can be recorded with priority.

[0103] During recording, the recording unit can adjust the use of technical terms in the recording according to the user's level of expertise. For example, if the user has technical expertise, the recording unit can perform detailed recording including technical terms. Furthermore, if the user does not have technical expertise, the recording unit can perform concise recording and avoid technical terms. Furthermore, the recording unit can adjust the level of detail in the recording according to the user's level of expertise. For example, if the user has technical expertise, the recording unit can perform detailed recording including technical terms. Furthermore, if the user does not have technical expertise, the recording unit can perform concise recording and avoid technical terms. Furthermore, the recording unit can adjust the level of detail in the recording according to the user's level of expertise. This allows for appropriate recording by adjusting the use of technical terms in the recording according to the level of expertise. === Hard Collateral 1-1 === Each of the multiple elements, including the monitoring unit, detection unit, alert unit, and recording unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the monitoring unit monitors conversations in real time using the camera 42 and microphone 38B of the smart device 14 and converts the voice data into text data using the control unit 46A. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and uses a generation AI to compare past cases of power harassment and detect phrases that may be considered power harassment. The alert unit, for example, displays a message on the screen or provides a voice notification using the output device 40 of the smart device 14, and sends an email notification using the specific processing unit 290 of the data processing device 12. The recording unit, for example, records the detected phrases in the database 24 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the monitoring unit, detection unit, alert unit, and recording unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the monitoring unit monitors conversations in real time using the camera 42 and microphone 238 of the smart glasses 214 and converts the voice into text data using the control unit 46A. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and uses a generation AI to compare past cases of power harassment and detect phrases that may be considered power harassment. The alert unit issues a voice notification using the speaker 240 of the smart glasses 214 and an email notification using the specific processing unit 290 of the data processing device 12. The recording unit records the detected phrases in the database 24 of the data processing device 12, for example. === Hard Collateral 1-3 === Each of the multiple elements including the monitoring unit, detection unit, alert unit, and recording unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the monitoring unit monitors conversations in real time using the camera 42 and microphone 238 of the headset-type terminal 314 and converts the voice into text data using the control unit 46A. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and uses a generation AI to compare past cases of power harassment and detect words that may be considered power harassment. The alert unit issues a voice notification using the speaker 240 of the headset-type terminal 314, and issues an email notification using the specific processing unit 290 of the data processing device 12. The recording unit records the detected words in the database 24 of the data processing device 12, for example. === Hard Collateral 1-4 === Each of the multiple elements including the monitoring unit, detection unit, alert unit, and recording unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the monitoring unit monitors conversations in real time using the camera 42 and microphone 238 of the robot 414 and converts the voice into text data using the control unit 46A. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and uses a generation AI to compare past cases of power harassment and detect words that may be considered power harassment. The alert unit issues a voice notification using the speaker 240 of the robot 414 and an email notification using the specific processing unit 290 of the data processing device 12. The recording unit records the detected words in the database 24 of the data processing device 12, for example.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] The monitoring unit acquires the user's biometric information and can adjust the monitoring sensitivity of the conversation based on data such as stress level and heart rate. For example, if the user's heart rate suddenly rises, the monitoring unit increases the sensitivity and detects more detailed conversation content. Also, if the user's stress level is high, the monitoring unit can increase the sensitivity and prioritize detection of words that may be considered power harassment. Furthermore, if the user's biometric information is stable, the monitoring unit can lower the sensitivity and detect only important conversations. In this way, by adjusting the monitoring sensitivity based on the user's biometric information, more appropriate conversation content can be detected.

[0106] The monitoring unit can refer to the user's calendar information and adjust the monitoring sensitivity for important meetings and events. For example, if an important meeting is scheduled, the monitoring unit increases the sensitivity to detect details of the conversation. Also, if the user is on vacation, the monitoring unit can decrease the sensitivity to detect only important conversations. Furthermore, if the user is traveling, the monitoring unit can set the sensitivity to medium to detect only necessary information. This allows the monitoring sensitivity to be adjusted according to the user's schedule, making it possible to detect more appropriate conversation content.

[0107] The monitoring unit can learn the user's voice patterns and monitor conversations based on individual voice features. For example, it can learn the user's tone and rhythm of voice and detect abnormal changes. It can also learn the user's specific phrases and expressions and evaluate the importance of the conversation based on them. Furthermore, it can estimate a specific emotional state based on the user's voice patterns and adjust the monitoring sensitivity. This makes it possible to detect conversation content with greater accuracy by monitoring based on the user's voice patterns.

[0108] The monitoring unit can analyze the user's past conversation history and learn specific patterns to improve the accuracy of monitoring. For example, it can extract frequently used phrases and keywords from the past conversation history and perform monitoring based on them. It can also learn changes in conversation tone and speed in specific situations based on the past conversation history to detect abnormal patterns. Furthermore, it can also estimate specific emotional states by referring to the past conversation history and adjust the sensitivity of monitoring. In this way, it is possible to improve the accuracy of monitoring by utilizing the past conversation history.

[0109] The monitoring unit can adjust the monitoring sensitivity taking into account the user's device usage status. For example, if the user is using a smartphone, the monitoring unit increases the sensitivity and detects conversations in real time. If the user is using a PC, the monitoring unit can set the sensitivity to medium and detect only necessary information. Furthermore, if the user is using a smartwatch, the monitoring unit can decrease the sensitivity and detect only important conversations. This allows the detection of more appropriate conversation content by adjusting the monitoring sensitivity according to the device usage status.

[0110] The monitoring unit can estimate the user's emotions and adjust the monitoring frequency based on the estimated user's emotions. For example, if the user is feeling stressed, the monitoring frequency can be increased to detect conversations more frequently. Also, if the user is relaxed, the monitoring frequency can be reduced to detect only important conversations. Furthermore, if the user is in a hurry, the monitoring frequency can be set to a medium level to detect only necessary information. In this way, by adjusting the monitoring frequency according to the user's emotions, more appropriate conversation content can be detected.

[0111] The monitoring unit can prioritize monitoring highly relevant conversations by taking into account the geographical location information of the user. For example, when the user is in a specific location, the monitoring unit prioritizes monitoring conversations related to that location. In addition, when the user is traveling, the monitoring unit can prioritize monitoring conversations related to the user's destination. Furthermore, when the user is in a specific region, the monitoring unit can prioritize monitoring conversations related to that region. In this way, highly relevant conversations can be prioritized by taking into account the geographical location information.

[0112] The monitoring unit can analyze the user's social media activity and monitor related conversations. For example, the monitoring unit can monitor related conversations based on the content posted by the user on social media. The monitoring unit can also monitor related conversations based on the activities of the user's friends on social media. Furthermore, the monitoring unit can monitor related conversations based on the user's check-in information on social media. This allows for effective monitoring of related conversations by analyzing social media activity.

[0113] The monitoring unit can customize the monitoring method by reflecting the user's past feedback. For example, the monitoring unit can adjust the monitoring sensitivity based on feedback provided by the user in the past. The monitoring unit can also customize the response to specific keywords or phrases by referring to the user's past feedback. Furthermore, the monitoring unit can adjust the frequency and method of monitoring based on the user's past feedback. In this way, the monitoring method can be optimized for the user by reflecting past feedback.

[0114] The detection unit can estimate the user's emotions and adjust the detection criteria based on the estimated user emotions. For example, if the user is feeling stressed, the detection criteria can be set to be stricter, and more cases of possible power harassment can be detected. Also, if the user is relaxed, the detection criteria can be set to be looser, and only important cases of possible power harassment can be detected. Furthermore, if the user is in a hurry, the detection criteria can be set to be medium, and only necessary cases of possible power harassment can be detected. In this way, by adjusting the detection criteria according to the user's emotions, more appropriate cases of possible power harassment can be detected.

[0115] The processing flow of the second embodiment will be briefly explained below.

[0116] Step 1: The monitoring unit monitors the conversation in real time. The monitoring unit uses voice recognition technology to convert the conversation into text data, and uses generative AI to analyze the speed and tone of the conversation to detect abnormal patterns. For example, a sudden change in the speed of the conversation or a sudden change in tone will be detected as an abnormal pattern. Step 2: The detection unit detects phrases that may be considered power harassment from the conversations monitored by the monitoring unit. The detection unit uses generative AI to compare past cases of power harassment and detect phrases such as "You're useless" or "Quit." The detection unit also takes into account the context, tone, and emotions of the conversation to assess the possibility of power harassment. Step 3: The alert unit issues an alert based on the text detected by the detection unit. The alert unit notifies the user by displaying a message on the screen, making a sound, sending an email, or otherwise sending a message such as "There is a possibility of power harassment. Please be careful." Step 4: The recording unit records the text detected by the detection unit. The recording unit records the text by saving it in the cloud or locally. For example, the recording unit can use cloud services such as AWS or Google Cloud, or can use recording media such as a hard disk or SSD.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0175] 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."

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] [Explanation of symbols]

[0189] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A monitoring unit that monitors conversations in real time; a detection unit that detects words that may be power harassment from the conversations monitored by the monitoring unit; an alert unit that issues an alert based on the text detected by the detection unit; a recording unit that records the text detected by the detection unit. A system characterized by:

2. The alert unit Alerts can be displayed on the screen, notified by voice, or sent via email.

2. The system of claim 1.

3. The recording unit Record your text using cloud or local storage 2. The system of claim 1.

4. The monitoring unit Converting conversations into text data using voice recognition technology 2. The system of claim 1.

5. The detection unit Collating a large number of past cases of power harassment to detect phrases that may be considered power harassment 2. The system of claim 1.

6. The monitoring unit Estimate the user's emotions and adjust the monitoring sensitivity based on the estimated user emotions.

2. The system of claim 1.

7. The monitoring unit Filters background noise from conversations and environmental sounds to remove noise 2. The system of claim 1.

8. The monitoring unit Analyzes speech rate and tone to detect unusual patterns 2. The system of claim 1.

9. The monitoring unit Set preferences for specific keywords or phrases 2. The system of claim 1.

Images