System

Abstract

An object of a system according to an embodiment is to detect a sign of power harassment at an early stage and automatically take appropriate measures.SOLUTION: A system includes a voice analysis unit, a text analysis unit, a warning unit, and a notification unit. The voice analysis unit analyzes the voice data and identifies an utterance that may be power harassment. The text analysis unit analyzes the text data and identifies a message that may be power harassment. The warning unit issues a warning based on the sign of power harassment identified by the voice analysis unit and the text analysis unit. The notification unit notifies a supervisor or a personnel department based on the warning issued by the warning unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem of making it difficult to detect signs of power harassment early and automatically take appropriate action.

[0005] The system according to the embodiment aims to detect signs of power harassment early and automatically take appropriate measures. [Means for solving the problem]

[0006] The system according to the embodiment includes a voice analysis unit, a text analysis unit, a warning unit, and a notification unit. The voice analysis unit analyzes voice data and identifies statements that may constitute power harassment. The text analysis unit analyzes text data and identifies messages that may constitute power harassment. The warning unit issues a warning based on the signs of power harassment identified by the voice analysis unit and the text analysis unit. The notification unit notifies a supervisor or the human resources department based on the warning issued by the warning unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect signs of power harassment early and automatically take appropriate measures. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The power harassment detection tool according to an embodiment of the present invention is a tool that detects power harassment in the workplace and takes immediate measures. This tool uses generative AI to detect signs of power harassment and automatically take appropriate measures. As a result, the power harassment detection tool can detect signs of power harassment in the workplace in real time and take prompt and appropriate measures.

[0029] A power harassment detection tool according to an embodiment includes a voice analysis unit, a text analysis unit, a warning unit, and a notification unit. The voice analysis unit analyzes voice data and identifies statements that may constitute power harassment. For example, the voice analysis unit records statements made during meetings or everyday conversations and inputs the recorded voice data into a generation AI. The generation AI analyzes specific keywords, tone, and context to identify statements that may constitute power harassment. For example, if aggressive statements such as "You're useless" or "How many times do I have to tell you?" are detected, the generation AI recognizes them as signs of power harassment. The text analysis unit analyzes text data and identifies messages that may constitute power harassment. For example, the content of internal chats or emails is input into the generation AI. The generation AI analyzes specific keywords and context to identify messages that may constitute power harassment. For example, if aggressive messages such as "incompetent" or "quit already" are detected, the generation AI recognizes them as signs of power harassment. The warning unit issues a warning based on the signs of power harassment identified by the voice analysis unit and the text analysis unit. For example, when a remark or message that may be power harassment is detected, a warning message is sent to the relevant parties. Specifically, the warning is issued with the content, "This remark may be power harassment. Please be careful." The notification unit notifies a superior or the human resources department based on the warning issued by the warning unit. For example, when a remark or message that may be power harassment is detected, a detailed report is made to the superior or the human resources department. Specifically, a notification is made with the content, "Mr. / Ms. XX made an aggressive remark to Mr. / Ms. △△. Details are as follows." This enables the power harassment detection tool to detect signs of power harassment in real time and automatically take appropriate action.

[0030] The voice analysis unit can refer to past conversation history to understand the context of a conversation and analyze whether specific statements are being repeated. For example, the voice analysis unit stores past conversation history in a database and analyzes whether specific offensive statements are being repeated. For example, if words such as "incompetent" or "useless" are frequently used. The voice analysis unit also analyzes the context of the conversation and evaluates the relevance of past conversations with the current conversation. For example, if an offensive statement was made in the past, it checks whether that statement is being repeated in the current conversation. The voice analysis unit also refers to past conversation history and identifies repeated specific statements as a sign of power harassment. For example, if the same speaker repeatedly makes aggressive statements. This makes it possible to refer to past conversation history and analyze whether specific statements are being repeated.

[0031] The audio analysis unit also analyzes background sounds of conversations and environmental sounds, and can identify the tendency for power harassment to occur in a particular environment. The audio analysis unit, for example, analyzes background sounds of conversations to identify whether specific environmental sounds are associated with the occurrence of power harassment. For example, conversations in a noisy office environment are associated with the occurrence of power harassment. The audio analysis unit also analyzes environmental sounds to identify whether specific sounds are associated with the occurrence of power harassment. For example, the sound of a conference room door opening and closing or the sound of a telephone ringing is associated with the occurrence of power harassment. The audio analysis unit also analyzes background sounds of conversations in real time to identify the tendency for power harassment to occur in a particular environment. For example, conversations at a particular time or place are associated with the occurrence of power harassment. In this way, the background sounds of conversations and environmental sounds can be analyzed to identify the tendency for power harassment to occur in a particular environment.

[0032] The voice analysis unit can analyze voice data in different languages ​​and build a multilingual power harassment detection system. The voice analysis unit, for example, analyzes voice data in different languages ​​and identifies signs of power harassment based on specific keywords or tones. For example, it supports multiple languages ​​such as English and Chinese. The voice analysis unit also builds a multilingual voice analysis system and analyzes conversations in different languages ​​in real time. For example, it supports multiple languages ​​used by international companies. The voice analysis unit also analyzes voice data in different languages ​​and identifies signs of power harassment in specific languages. For example, it performs analysis taking into account the cultural background of each language. This makes it possible to analyze voice data in different languages ​​and build a multilingual power harassment detection system.

[0033] The text analysis unit can refer to past email and chat history and analyze the frequency of specific keywords. For example, the text analysis unit stores past email and chat history in a database and analyzes the frequency of specific keywords. For example, if aggressive language such as "incompetent" or "quit already" is frequently used, the text analysis unit also analyzes the context of the text data and evaluates the relevance of past messages with current messages. For example, if there was an aggressive message in the past, it checks whether that message is being repeated in the current conversation. The text analysis unit also refers to past email and chat history and identifies repeated occurrences of specific keywords as a sign of power harassment. For example, if the same person repeatedly sends aggressive messages. This makes it possible to refer to past email and chat history and analyze the frequency of specific keywords.

[0034] The text analysis unit can also analyze non-verbal elements such as images and emojis to identify signs of power harassment. For example, the text analysis unit analyzes images and emojis included in a message to identify non-verbal elements with aggressive meanings. For example, when an emoji of an angry face or an aggressive image is included. The text analysis unit also analyzes non-verbal elements to identify whether specific emojis or images are used as signs of power harassment. For example, when aggressive emojis or images are used repeatedly. The text analysis unit also analyzes non-verbal elements included in a message in real time to identify signs of power harassment. For example, when specific emojis or images are used frequently. This makes it possible to analyze non-verbal elements such as images and emojis and identify signs of power harassment.

[0035] The text analysis unit can analyze text data in different languages ​​and build a multilingual power harassment detection system. The text analysis unit, for example, analyzes text data in different languages ​​and identifies signs of power harassment based on specific keywords and context. For example, it supports multiple languages ​​such as English and Chinese. The text analysis unit also builds a multilingual text analysis system and analyzes messages in different languages ​​in real time. For example, it supports multiple languages ​​used by international companies. The text analysis unit also analyzes text data in different languages ​​and identifies signs of power harassment in specific languages. For example, it performs analysis taking into account the cultural background of each language. This makes it possible to analyze text data in different languages ​​and build a multilingual power harassment detection system.

[0036] The warning unit can customize the content of the warning message based on past cases of power harassment and provide more specific advice. The warning unit, for example, stores past cases of power harassment in a database and customizes the content of the warning message. For example, it provides specific advice based on a specific case. The warning unit also analyzes data on power harassment cases and optimizes the content of the warning message. For example, it creates a warning message based on lessons learned from past cases. The warning unit also references past cases of power harassment and builds a system that customizes the content of the warning message. For example, it provides specific advice according to a specific situation. This makes it possible to customize the content of the warning message based on past cases of power harassment and provide more specific advice.

[0037] The warning unit can issue the warning message in different formats, such as audio and visual notes, to facilitate understanding by the recipient. For example, the warning unit can issue the warning message in audio format to build a system that facilitates understanding by the recipient. For example, the warning message can be generated using speech synthesis technology. The warning unit can also issue the warning message in visual note format to facilitate understanding by the recipient. For example, the warning content can be visually displayed using diagrams or illustrations. The warning unit can also issue the warning message in different formats to develop a system that facilitates understanding by the recipient. For example, the warning message can be issued by combining audio and visual notes. This makes it possible to issue the warning message in different formats, such as audio and visual notes, to facilitate understanding by the recipient.

[0038] The warning unit can build a warning system that is compatible with different devices (smartphones, PCs, tablets). The warning unit builds a warning system that is compatible with different devices, such as smartphones, PCs, and tablets. For example, it issues a warning message optimized for each device. The warning unit also develops a warning system that is compatible with different devices, allowing users to receive warnings on any device. For example, it provides a smartphone app or PC software. The warning unit also builds a system that makes warning messages compatible with different devices. For example, it issues warning messages in different formats for each device. This makes it possible to build a warning system that is compatible with different devices.

[0039] The notification unit can customize the notification content based on past cases of power harassment and provide more specific advice. The notification unit, for example, stores past cases of power harassment in a database and customizes the notification content. For example, it provides specific advice based on specific cases. The notification unit also analyzes data on power harassment cases and optimizes the notification content. For example, it creates notification content based on lessons learned from past cases. The notification unit also builds a system that references past cases of power harassment and customizes the notification content. For example, it provides specific advice according to specific situations. This makes it possible to customize the notification content based on past cases of power harassment and provide more specific advice.

[0040] The notification unit can issue the notification content in different formats, such as audio and visual notes, to facilitate understanding by the recipient. The notification unit, for example, builds a system that issues the notification content in audio format to facilitate understanding by the recipient. For example, the notification content is generated using speech synthesis technology. The notification unit also issues the notification content in visual note format to facilitate understanding by the recipient. For example, the notification content is visually displayed using diagrams and illustrations. The notification unit also develops a system that issues the notification content in different formats to facilitate understanding by the recipient. For example, the notification content is issued by combining audio and visual notes. This makes it possible to issue the notification content in different formats, such as audio and visual notes, to facilitate understanding by the recipient.

[0041] The notification unit can build a notification system that is compatible with different devices (smartphones, PCs, tablets). The notification unit builds a notification system that is compatible with different devices, such as smartphones, PCs, and tablets. For example, it issues notification content that is optimized for each device. The notification unit also develops a notification system that is compatible with different devices, allowing users to receive notifications on any device. For example, it provides smartphone apps and PC software. The notification unit also builds a system that makes notification content compatible with different devices. For example, it issues notification content in different formats for each device. This makes it possible to build a notification system that is compatible with different devices.

[0042] The system records detected signs of power harassment and builds a database for later analysis. The system, for example, records detected signs of power harassment and builds a database for later analysis. For example, it records information such as the content of remarks or messages, the date and time, and the parties involved. The system also builds a database for recording signs of power harassment and develops a system for later analysis. For example, it collects data for analyzing trends and frequency of power harassment. The system also develops a system for recording detected signs of power harassment and builds a database for later analysis. For example, it collects data for visualizing the occurrence of power harassment. This makes it possible to record detected signs of power harassment and build a database for later analysis.

[0043] The system can analyze the trends and frequency of power harassment based on the recorded data and take appropriate measures. For example, the system builds a system that analyzes the trends and frequency of power harassment based on the recorded data. For example, it identifies trends in the occurrence of power harassment at specific times or locations. The system also analyzes the trends and frequency of power harassment and develops a system for taking appropriate measures. For example, it takes special measures for departments where power harassment occurs frequently. The system also builds a system that analyzes the trends and frequency of power harassment based on the recorded data and takes appropriate measures. For example, it visualizes the occurrence status of power harassment and provides data for taking measures. This makes it possible to analyze the trends and frequency of power harassment based on the recorded data and take appropriate measures.

[0044] The system can identify the causes of power harassment based on the recorded data and propose preventive measures. For example, the system builds a system that identifies the causes of power harassment based on the recorded data. For example, it analyzes whether specific remarks or actions are related to the occurrence of power harassment. The system also develops a system for identifying the causes of power harassment and proposing preventive measures. For example, it analyzes whether specific situations or environments influence the occurrence of power harassment. The system also builds a system that identifies the causes of power harassment based on the recorded data and proposes preventive measures. For example, it proposes specific measures to prevent power harassment from occurring in the first place. In this way, it is possible to identify the causes of power harassment based on the recorded data and propose preventive measures.

[0045] The system can visualize the occurrence of power harassment based on the recorded data and share it with relevant parties. The system, for example, builds a system that visualizes the occurrence of power harassment based on the recorded data. For example, the system visually displays the occurrence of power harassment using graphs and charts. The system also develops a system for visualizing the occurrence of power harassment and sharing it with relevant parties. For example, the system periodically generates reports and distributes them to relevant parties. The system also builds a system that visualizes the occurrence of power harassment based on the recorded data and shares it with relevant parties. For example, the system shares the occurrence of power harassment in real time using an online platform. This makes it possible to visualize the occurrence of power harassment based on the recorded data and share it with relevant parties.

[0046] The system can predict the risk of power harassment based on the recorded data and take measures in advance. For example, the system builds a system that predicts the risk of power harassment based on the recorded data. For example, it analyzes past data and identifies high-risk situations and environments. The system also predicts the risk of power harassment and develops a system for taking measures in advance. For example, it takes special measures for high-risk departments or time periods. The system also predicts the risk of power harassment based on the recorded data and builds a system for taking measures in advance. For example, it suggests preventive measures for high-risk situations and environments. In this way, the system can predict the risk of power harassment based on the recorded data and take measures in advance.

[0047] The system can analyze trends in the occurrence of power harassment based on the recorded data and take long-term countermeasures. For example, the system builds a system that analyzes trends in the occurrence of power harassment based on the recorded data. For example, it identifies trends in the occurrence of power harassment during specific periods or locations. The system also analyzes trends in the occurrence of power harassment and develops a system for taking long-term countermeasures. For example, it takes special measures for departments where power harassment occurs frequently. The system also builds a system that analyzes trends in the occurrence of power harassment based on the recorded data and takes long-term countermeasures. For example, it visualizes the occurrence status of power harassment and provides data for taking countermeasures. This makes it possible to analyze trends in the occurrence of power harassment based on the recorded data and take long-term countermeasures.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The power harassment detection tool can further include a biometrics analysis unit. The biometrics analysis unit, for example, monitors the speaker's heart rate and electrodermal response in real time to detect signs of stress or tension. For example, a sudden increase in heart rate or an increase in electrodermal response is identified as a sign of power harassment. The biometrics analysis unit also analyzes the speaker's physiological data and issues a warning if the stress level is high. For example, if a high stress level continues for a long period of time. The biometrics analysis unit can also identify signs of power harassment based on the speaker's physiological data and take appropriate action. This makes it possible to analyze the speaker's physiological data and detect signs of power harassment.

[0050] The power harassment detection tool may further include a behavior analysis unit. The behavior analysis unit, for example, analyzes the speaker's body movements and gestures to identify aggressive behavior. For example, when a waving hand or pointing gesture is detected. The behavior analysis unit also analyzes the speaker's posture and facial expression to identify any signs of negative emotion as a sign of power harassment. For example, a furrowed brow or a posture with crossed arms. The behavior analysis unit also analyzes the speaker's behavior in real time and issues a warning if aggressive behavior is continuously displayed. For example, when repeated aggressive gestures are detected. This makes it possible to analyze the speaker's behavior and detect signs of power harassment.

[0051] The power harassment detection tool may further include a context analysis unit. The context analysis unit, for example, analyzes background information and circumstances of a conversation to identify trends in the occurrence of power harassment under specific circumstances. For example, when the progress of a specific project or task is related to the occurrence of power harassment. The context analysis unit also analyzes background information of a conversation to identify whether specific events or occurrences influence the occurrence of power harassment. For example, when the timing of performance evaluations or promotions is related to the occurrence of power harassment. The context analysis unit also analyzes background information of a conversation in real time to identify trends in the occurrence of power harassment under specific circumstances. For example, when relationships with specific superiors or colleagues influence the occurrence of power harassment. In this way, background information of a conversation can be analyzed to identify trends in the occurrence of power harassment under specific circumstances.

[0052] The power harassment detection tool can further include a social network analysis unit. The social network analysis unit, for example, analyzes human relationships and communication patterns within a company to identify relationships with a high risk of power harassment. For example, it analyzes the frequency and content of communication within a specific group. The social network analysis unit also analyzes human relationships within a company to identify relationships with a high risk of power harassment when a specific person is isolated. For example, when a specific person rarely communicates with other members. The social network analysis unit also analyzes human relationships within a company in real time to identify relationships with a high risk of power harassment. For example, when the relationship between a specific superior and a subordinate is tense. This makes it possible to analyze human relationships within a company and identify relationships with a high risk of power harassment.

[0053] The power harassment detection tool may further include a feedback providing unit. The feedback providing unit provides real-time feedback to the speaker based on, for example, detected signs of power harassment. For example, the feedback providing unit may provide the speaker with feedback such as, "That comment is aggressive. Try to use more gentle language." The feedback providing unit may also suggest specific improvement measures to the speaker based on the detected signs of power harassment. For example, the feedback providing unit may provide feedback such as, "In the next meeting, try to respect the other person's opinion." The feedback providing unit may also provide feedback to the speaker encouraging positive behavior based on the detected signs of power harassment. For example, the feedback providing unit may provide feedback such as, "That comment was constructive. Let's keep it up." In this way, feedback may be provided to the speaker in real time, making it possible to prevent power harassment from occurring.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The voice analysis unit analyzes the voice data and identifies statements that may be considered power harassment. For example, statements made during meetings or everyday conversations are recorded and the audio data is input into the generation AI. The generation AI analyzes specific keywords, tone, and context, and recognizes aggressive statements such as "You're useless" and "How many times do I have to tell you" as signs of power harassment. Step 2: The text analysis unit analyzes the text data and identifies messages that may be considered power harassment. For example, the contents of internal chats or emails are input into the generation AI. The generation AI analyzes specific keywords and contexts, and recognizes aggressive messages such as "incompetent" or "quit immediately" as signs of power harassment. Step 3: The warning unit issues a warning based on the signs of power harassment identified by the voice analysis unit and text analysis unit. For example, when a statement or message that may be power harassment is detected, a warning message such as "This statement may be power harassment. Please be careful" is sent to the relevant person. Step 4: The Notification Department notifies the superior or the human resources department based on the warning issued by the Warning Department. For example, if a remark or message that may be power harassment is detected, the notification will be sent to the superior or the human resources department with a message such as, "Mr. / Ms. XX made an offensive remark to Mr. / Ms. △△. Details are as follows."

[0056] (Example 2) The power harassment detection tool according to an embodiment of the present invention is a tool that detects power harassment in the workplace and takes immediate measures. This tool uses generative AI to detect signs of power harassment and automatically take appropriate measures. As a result, the power harassment detection tool can detect signs of power harassment in the workplace in real time and take prompt and appropriate measures.

[0057] A power harassment detection tool according to an embodiment includes a voice analysis unit, a text analysis unit, a warning unit, and a notification unit. The voice analysis unit analyzes voice data and identifies statements that may constitute power harassment. For example, the voice analysis unit records statements made during meetings or everyday conversations and inputs the recorded voice data into a generation AI. The generation AI analyzes specific keywords, tone, and context to identify statements that may constitute power harassment. For example, if aggressive statements such as "You're useless" or "How many times do I have to tell you?" are detected, the generation AI recognizes them as signs of power harassment. The text analysis unit analyzes text data and identifies messages that may constitute power harassment. For example, the content of internal chats or emails is input into the generation AI. The generation AI analyzes specific keywords and context to identify messages that may constitute power harassment. For example, if aggressive messages such as "incompetent" or "quit already" are detected, the generation AI recognizes them as signs of power harassment. The warning unit issues a warning based on the signs of power harassment identified by the voice analysis unit and the text analysis unit. For example, when a remark or message that may be power harassment is detected, a warning message is sent to the relevant parties. Specifically, the warning is issued with the content, "This remark may be power harassment. Please be careful." The notification unit notifies a superior or the human resources department based on the warning issued by the warning unit. For example, when a remark or message that may be power harassment is detected, a detailed report is made to the superior or the human resources department. Specifically, a notification is made with the content, "Mr. / Ms. XX made an aggressive remark to Mr. / Ms. △△. Details are as follows." This enables the power harassment detection tool to detect signs of power harassment in real time and automatically take appropriate action.

[0058] The voice analysis unit analyzes the speaker's tone of voice or emotion in real time, and can identify signs of power harassment based on changes in emotion. The voice analysis unit, for example, analyzes the speaker's tone of voice and identifies strong negative emotions such as anger or irritation as signs of power harassment. For example, it detects changes in voice pitch or volume. The voice analysis unit also identifies signs of power harassment based on sudden changes in the speaker's emotion during a conversation. For example, a sudden change from a calm tone to an aggressive tone. The voice analysis unit also analyzes the speaker's emotion in real time, and identifies signs of power harassment when negative emotions are continuously expressed. For example, a repeated angry tone is detected during a conversation. This makes it possible to identify signs of power harassment based on changes in the speaker's emotion.

[0059] The voice analysis unit can refer to past conversation history to understand the context of a conversation and analyze whether specific statements are being repeated. For example, the voice analysis unit stores past conversation history in a database and analyzes whether specific offensive statements are being repeated. For example, if words such as "incompetent" or "useless" are frequently used. The voice analysis unit also analyzes the context of the conversation and evaluates the relevance of past conversations with the current conversation. For example, if an offensive statement was made in the past, it checks whether that statement is being repeated in the current conversation. The voice analysis unit also refers to past conversation history and identifies repeated specific statements as a sign of power harassment. For example, if the same speaker repeatedly makes aggressive statements. This makes it possible to refer to past conversation history and analyze whether specific statements are being repeated.

[0060] The voice analysis unit uses an emotion estimation function to simultaneously analyze the emotions of the speaker and the receiver, and the warning unit can issue a warning if a mismatch between their emotions is detected as a sign of power harassment. For example, the voice analysis unit can simultaneously analyze the emotions of the speaker and the receiver, and identify a sign of power harassment if the speaker feels anger while the receiver feels fear or anxiety. The voice analysis unit can also identify signs of power harassment based on a significant difference in the emotions of the speaker and the receiver during a conversation. For example, if the speaker speaks in an aggressive tone while the receiver is silent. The voice analysis unit can also analyze the emotions of the speaker and the receiver in real time, and identify a continuous mismatch in emotions as a sign of power harassment. For example, if the speaker repeatedly speaks in an angry tone while the receiver feels anxious. This allows the system to detect signs of power harassment based on a mismatch between the emotions of the speaker and the receiver and issue a warning.

[0061] The audio analysis unit also analyzes background sounds of conversations and environmental sounds, and can identify the tendency for power harassment to occur in a particular environment. The audio analysis unit, for example, analyzes background sounds of conversations to identify whether specific environmental sounds are associated with the occurrence of power harassment. For example, conversations in a noisy office environment are associated with the occurrence of power harassment. The audio analysis unit also analyzes environmental sounds to identify whether specific sounds are associated with the occurrence of power harassment. For example, the sound of a conference room door opening and closing or the sound of a telephone ringing is associated with the occurrence of power harassment. The audio analysis unit also analyzes background sounds of conversations in real time to identify the tendency for power harassment to occur in a particular environment. For example, conversations at a particular time or place are associated with the occurrence of power harassment. In this way, the background sounds of conversations and environmental sounds can be analyzed to identify the tendency for power harassment to occur in a particular environment.

[0062] The voice analysis unit can analyze voice data in different languages ​​and build a multilingual power harassment detection system. The voice analysis unit, for example, analyzes voice data in different languages ​​and identifies signs of power harassment based on specific keywords or tones. For example, it supports multiple languages ​​such as English and Chinese. The voice analysis unit also builds a multilingual voice analysis system and analyzes conversations in different languages ​​in real time. For example, it supports multiple languages ​​used by international companies. The voice analysis unit also analyzes voice data in different languages ​​and identifies signs of power harassment in specific languages. For example, it performs analysis taking into account the cultural background of each language. This makes it possible to analyze voice data in different languages ​​and build a multilingual power harassment detection system.

[0063] The voice analysis unit can use the emotion estimation function to display the emotion of a speaker during a conversation in real time and provide feedback to elicit positive emotions. The voice analysis unit, for example, builds a system that analyzes the emotion of a speaker in real time and displays the results. For example, the emotion score of the speaker is displayed on a screen. The voice analysis unit also analyzes the emotion of the speaker and provides feedback to elicit positive emotions. For example, if the speaker has negative emotions, it suggests positive words. The voice analysis unit also uses the emotion estimation function to display the emotion of a speaker during a conversation in real time and provide advice to elicit positive emotions. For example, if the speaker is feeling angry, it urges the speaker to stay calm. This makes it possible to display the emotion of the speaker in real time and provide feedback to elicit positive emotions.

[0064] The text analysis unit can refer to past email and chat history and analyze the frequency of specific keywords. For example, the text analysis unit stores past email and chat history in a database and analyzes the frequency of specific keywords. For example, if aggressive language such as "incompetent" or "quit already" is frequently used, the text analysis unit also analyzes the context of the text data and evaluates the relevance of past messages with current messages. For example, if there was an aggressive message in the past, it checks whether that message is being repeated in the current conversation. The text analysis unit also refers to past email and chat history and identifies repeated occurrences of specific keywords as a sign of power harassment. For example, if the same person repeatedly sends aggressive messages. This makes it possible to refer to past email and chat history and analyze the frequency of specific keywords.

[0065] The text analysis unit performs sentiment analysis of text data and is able to preferentially detect messages with strong negative emotions. The text analysis unit, for example, performs sentiment analysis of text data and builds a system that preferentially detects messages with strong negative emotions. For example, it identifies messages with high sentiment scores for "anger" or "sadness." The text analysis unit also analyzes the sentiment scores of messages and preferentially detects messages with strong negative emotions. For example, if aggressive messages such as "incompetent" or "quit quickly" are detected. The text analysis unit also uses sentiment analysis to develop a system that preferentially detects messages with strong negative emotions. For example, it identifies messages with sentiment scores above a certain level as signs of power harassment. This makes it possible to perform sentiment analysis of text data and preferentially detect messages with strong negative emotions.

[0066] The text analysis unit uses an emotion estimation function to simultaneously analyze the emotions of the sender and receiver of a message, and the warning unit can issue a warning if a mismatch in emotions is detected as a sign of power harassment. For example, the text analysis unit can simultaneously analyze the emotions of the sender and receiver of a message, and identify a sign of power harassment if the sender feels anger while the receiver feels fear or anxiety. The text analysis unit also analyzes the context of a message and identifies signs of power harassment based on a significant difference in emotions between the sender and receiver. For example, if the sender sends aggressive messages while the receiver remains silent. The text analysis unit also analyzes the emotions of the sender and receiver of a message in real time, and identifies a continuous mismatch in emotions as a sign of power harassment. For example, if the sender repeatedly sends angry messages while the receiver feels anxious. This allows signs of power harassment to be detected based on a mismatch in emotions between the sender and receiver of a message, and a warning can be issued.

[0067] The text analysis unit can also analyze non-verbal elements such as images and emojis to identify signs of power harassment. For example, the text analysis unit analyzes images and emojis included in a message to identify non-verbal elements with aggressive meanings. For example, when an emoji of an angry face or an aggressive image is included. The text analysis unit also analyzes non-verbal elements to identify whether specific emojis or images are used as signs of power harassment. For example, when aggressive emojis or images are used repeatedly. The text analysis unit also analyzes non-verbal elements included in a message in real time to identify signs of power harassment. For example, when specific emojis or images are used frequently. This makes it possible to analyze non-verbal elements such as images and emojis and identify signs of power harassment.

[0068] The text analysis unit can analyze text data in different languages ​​and build a multilingual power harassment detection system. The text analysis unit, for example, analyzes text data in different languages ​​and identifies signs of power harassment based on specific keywords and context. For example, it supports multiple languages ​​such as English and Chinese. The text analysis unit also builds a multilingual text analysis system and analyzes messages in different languages ​​in real time. For example, it supports multiple languages ​​used by international companies. The text analysis unit also analyzes text data in different languages ​​and identifies signs of power harassment in specific languages. For example, it performs analysis taking into account the cultural background of each language. This makes it possible to analyze text data in different languages ​​and build a multilingual power harassment detection system.

[0069] The text analysis unit can use the emotion estimation function to display the emotion of the message sender in real time and provide feedback to elicit positive emotions. The text analysis unit, for example, builds a system that analyzes the emotion of the message sender in real time and displays the results. For example, the sender's emotion score is displayed on a screen. The text analysis unit also analyzes the emotion of the message sender and provides feedback to elicit positive emotions. For example, if the sender has negative emotions, it suggests positive words. The text analysis unit also uses the emotion estimation function to display the emotion of the message sender in real time and provide advice to elicit positive emotions. For example, if the sender has angry emotions, it urges the sender to stay calm. This makes it possible to display the emotion of the message sender in real time and provide feedback to elicit positive emotions.

[0070] The warning unit can customize the content of the warning message based on past cases of power harassment and provide more specific advice. The warning unit, for example, stores past cases of power harassment in a database and customizes the content of the warning message. For example, it provides specific advice based on a specific case. The warning unit also analyzes data on power harassment cases and optimizes the content of the warning message. For example, it creates a warning message based on lessons learned from past cases. The warning unit also references past cases of power harassment and builds a system that customizes the content of the warning message. For example, it provides specific advice according to a specific situation. This makes it possible to customize the content of the warning message based on past cases of power harassment and provide more specific advice.

[0071] The warning unit can optimize the timing of issuing a warning based on changes in the emotions in remarks and messages. The warning unit, for example, analyzes changes in the emotions in remarks and messages in real time and builds a system that issues a warning at the optimal timing. For example, a warning is issued when there is a sudden change in emotion. The warning unit also optimizes the timing of issuing a warning based on changes in emotion. For example, a warning is issued immediately when negative emotions become stronger. The warning unit also develops a system that analyzes changes in the emotions in remarks and messages and optimizes the timing of issuing a warning. For example, a warning is issued when changes in emotion are continuously observed. This makes it possible to optimize the timing of issuing a warning based on changes in the emotions in remarks and messages.

[0072] The warning unit uses the emotion estimation function to analyze the emotions of the recipient of the warning message and adjust the message so that the recipient receives it positively. The warning unit, for example, builds a system that analyzes the emotions of the recipient of the warning message in real time and adjusts the message based on the results. For example, if the recipient has negative emotions, it adds positive words. The warning unit also analyzes the recipient's emotions and optimizes the content of the warning message. For example, if the recipient is feeling angry, it adds a message urging the recipient to stay calm. The warning unit also uses the emotion estimation function to develop a system that analyzes the emotions of the recipient of the warning message and adjusts the message so that the recipient receives it positively. For example, if the recipient is feeling anxious, it adds reassuring words. In this way, it is possible to analyze the emotions of the recipient of the warning message and adjust the message so that the recipient receives it positively.

[0073] The warning unit can issue the warning message in different formats, such as audio and visual notes, to facilitate understanding by the recipient. For example, the warning unit can issue the warning message in audio format to build a system that facilitates understanding by the recipient. For example, the warning message can be generated using speech synthesis technology. The warning unit can also issue the warning message in visual note format to facilitate understanding by the recipient. For example, the warning content can be visually displayed using diagrams or illustrations. The warning unit can also issue the warning message in different formats to develop a system that facilitates understanding by the recipient. For example, the warning message can be issued by combining audio and visual notes. This makes it possible to issue the warning message in different formats, such as audio and visual notes, to facilitate understanding by the recipient.

[0074] The warning unit can build a warning system that is compatible with different devices (smartphones, PCs, tablets). The warning unit builds a warning system that is compatible with different devices, such as smartphones, PCs, and tablets. For example, it issues a warning message optimized for each device. The warning unit also develops a warning system that is compatible with different devices, allowing users to receive warnings on any device. For example, it provides a smartphone app or PC software. The warning unit also builds a system that makes warning messages compatible with different devices. For example, it issues warning messages in different formats for each device. This makes it possible to build a warning system that is compatible with different devices.

[0075] The warning unit can use the emotion estimation function to monitor the recipient's emotions after the issuance of a warning message and send a follow-up message as necessary. The warning unit, for example, builds a system that monitors the recipient's emotions in real time after the issuance of a warning message and sends a follow-up message as necessary. For example, if the recipient is feeling anxious, it sends a reassuring message. The warning unit also analyzes the recipient's emotions and sends a follow-up message after the issuance of a warning message. For example, if the recipient is feeling angry, it sends a message urging the recipient to stay calm. The warning unit also uses the emotion estimation function to develop a system that monitors the recipient's emotions after the issuance of a warning message and sends a follow-up message as necessary. For example, if the recipient is feeling anxious, it adds reassuring words. This makes it possible to monitor the recipient's emotions after the issuance of a warning message and send a follow-up message as necessary.

[0076] The notification unit can customize the notification content based on past cases of power harassment and provide more specific advice. The notification unit, for example, stores past cases of power harassment in a database and customizes the notification content. For example, it provides specific advice based on specific cases. The notification unit also analyzes data on power harassment cases and optimizes the notification content. For example, it creates notification content based on lessons learned from past cases. The notification unit also builds a system that references past cases of power harassment and customizes the notification content. For example, it provides specific advice according to specific situations. This makes it possible to customize the notification content based on past cases of power harassment and provide more specific advice.

[0077] The notification unit can optimize the timing of notifications based on changes in the emotions in comments and messages. The notification unit, for example, analyzes changes in the emotions in comments and messages in real time, and builds a system that issues notifications at optimal timing. For example, a notification is issued when emotions change suddenly. The notification unit also optimizes the timing of issuing notifications based on changes in emotions. For example, a notification is issued immediately when negative emotions become stronger. The notification unit also develops a system that analyzes changes in the emotions in comments and messages, and optimizes the timing of issuing notifications. For example, a notification is issued when changes in emotions are continuously observed. This makes it possible to optimize the timing of notifications based on changes in emotions in comments and messages.

[0078] The notification unit uses the emotion estimation function to analyze the emotions of the superior and human resources department receiving the notification, and can adjust the message so that the recipient receives it positively. The notification unit, for example, builds a system that analyzes the emotions of the superior and human resources department receiving the notification in real time, and adjusts the message based on the results. For example, if the recipient has negative emotions, it adds positive words. The notification unit also analyzes the recipient's emotions and optimizes the notification content. For example, if the recipient is feeling angry, it adds a message urging the recipient to stay calm. The notification unit also uses the emotion estimation function to develop a system that analyzes the emotions of the superior and human resources department receiving the notification, and adjusts the message so that the recipient receives it positively. For example, if the recipient is feeling anxious, it adds reassuring words. In this way, it is possible to analyze the emotions of the superior and human resources department receiving the notification, and adjust the message so that the recipient receives it positively.

[0079] The notification unit can issue the notification content in different formats, such as audio and visual notes, to facilitate understanding by the recipient. The notification unit, for example, builds a system that issues the notification content in audio format to facilitate understanding by the recipient. For example, the notification content is generated using speech synthesis technology. The notification unit also issues the notification content in visual note format to facilitate understanding by the recipient. For example, the notification content is visually displayed using diagrams and illustrations. The notification unit also develops a system that issues the notification content in different formats to facilitate understanding by the recipient. For example, the notification content is issued by combining audio and visual notes. This makes it possible to issue the notification content in different formats, such as audio and visual notes, to facilitate understanding by the recipient.

[0080] The notification unit can build a notification system that is compatible with different devices (smartphones, PCs, tablets). The notification unit builds a notification system that is compatible with different devices, such as smartphones, PCs, and tablets. For example, it issues notification content that is optimized for each device. The notification unit also develops a notification system that is compatible with different devices, allowing users to receive notifications on any device. For example, it provides smartphone apps and PC software. The notification unit also builds a system that makes notification content compatible with different devices. For example, it issues notification content in different formats for each device. This makes it possible to build a notification system that is compatible with different devices.

[0081] The notification unit can use the emotion estimation function to monitor the emotions of the superior or the human resources department after receiving the notification and send a follow-up message as necessary. For example, the notification unit builds a system that monitors the emotions of the superior or the human resources department in real time after receiving the notification and sends a follow-up message as necessary. For example, if the recipient is feeling anxious, it sends a reassuring message. The notification unit also analyzes the recipient's emotions and sends a follow-up message after receiving the notification. For example, if the recipient is feeling angry, it sends a message urging the recipient to stay calm. The notification unit also uses the emotion estimation function to develop a system that monitors the emotions of the superior or the human resources department after receiving the notification and sends a follow-up message as necessary. For example, if the recipient is feeling anxious, it adds reassuring words. This makes it possible to monitor the emotions of the superior or the human resources department after receiving the notification and send a follow-up message as necessary.

[0082] The system records detected signs of power harassment and builds a database for later analysis. The system, for example, records detected signs of power harassment and builds a database for later analysis. For example, it records information such as the content of remarks or messages, the date and time, and the parties involved. The system also builds a database for recording signs of power harassment and develops a system for later analysis. For example, it collects data for analyzing trends and frequency of power harassment. The system also develops a system for recording detected signs of power harassment and builds a database for later analysis. For example, it collects data for visualizing the occurrence of power harassment. This makes it possible to record detected signs of power harassment and build a database for later analysis.

[0083] The system can analyze the trends and frequency of power harassment based on the recorded data and take appropriate measures. For example, the system builds a system that analyzes the trends and frequency of power harassment based on the recorded data. For example, it identifies trends in the occurrence of power harassment at specific times or locations. The system also analyzes the trends and frequency of power harassment and develops a system for taking appropriate measures. For example, it takes special measures for departments where power harassment occurs frequently. The system also builds a system that analyzes the trends and frequency of power harassment based on the recorded data and takes appropriate measures. For example, it visualizes the occurrence status of power harassment and provides data for taking measures. This makes it possible to analyze the trends and frequency of power harassment based on the recorded data and take appropriate measures.

[0084] The system can identify the causes of power harassment based on the recorded data and propose preventive measures. For example, the system builds a system that identifies the causes of power harassment based on the recorded data. For example, it analyzes whether specific remarks or actions are related to the occurrence of power harassment. The system also develops a system for identifying the causes of power harassment and proposing preventive measures. For example, it analyzes whether specific situations or environments influence the occurrence of power harassment. The system also builds a system that identifies the causes of power harassment based on the recorded data and proposes preventive measures. For example, it proposes specific measures to prevent power harassment from occurring in the first place. In this way, it is possible to identify the causes of power harassment based on the recorded data and propose preventive measures.

[0085] The system can visualize the occurrence of power harassment based on the recorded data and share it with relevant parties. The system, for example, builds a system that visualizes the occurrence of power harassment based on the recorded data. For example, the system visually displays the occurrence of power harassment using graphs and charts. The system also develops a system for visualizing the occurrence of power harassment and sharing it with relevant parties. For example, the system periodically generates reports and distributes them to relevant parties. The system also builds a system that visualizes the occurrence of power harassment based on the recorded data and shares it with relevant parties. For example, the system shares the occurrence of power harassment in real time using an online platform. This makes it possible to visualize the occurrence of power harassment based on the recorded data and share it with relevant parties.

[0086] The system can predict the risk of power harassment based on the recorded data and take measures in advance. For example, the system builds a system that predicts the risk of power harassment based on the recorded data. For example, it analyzes past data and identifies high-risk situations and environments. The system also predicts the risk of power harassment and develops a system for taking measures in advance. For example, it takes special measures for high-risk departments or time periods. The system also predicts the risk of power harassment based on the recorded data and builds a system for taking measures in advance. For example, it suggests preventive measures for high-risk situations and environments. In this way, the system can predict the risk of power harassment based on the recorded data and take measures in advance.

[0087] The system can analyze trends in the occurrence of power harassment based on the recorded data and take long-term countermeasures. For example, the system builds a system that analyzes trends in the occurrence of power harassment based on the recorded data. For example, it identifies trends in the occurrence of power harassment during specific periods or locations. The system also analyzes trends in the occurrence of power harassment and develops a system for taking long-term countermeasures. For example, it takes special measures for departments where power harassment occurs frequently. The system also builds a system that analyzes trends in the occurrence of power harassment based on the recorded data and takes long-term countermeasures. For example, it visualizes the occurrence status of power harassment and provides data for taking countermeasures. This makes it possible to analyze trends in the occurrence of power harassment based on the recorded data and take long-term countermeasures.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The power harassment detection tool can further include a biometrics analysis unit. The biometrics analysis unit, for example, monitors the speaker's heart rate and electrodermal response in real time to detect signs of stress or tension. For example, a sudden increase in heart rate or an increase in electrodermal response is identified as a sign of power harassment. The biometrics analysis unit also analyzes the speaker's physiological data and issues a warning if the stress level is high. For example, if a high stress level continues for a long period of time. The biometrics analysis unit can also identify signs of power harassment based on the speaker's physiological data and take appropriate action. This makes it possible to analyze the speaker's physiological data and detect signs of power harassment.

[0090] The power harassment detection tool may further include a behavior analysis unit. The behavior analysis unit, for example, analyzes the speaker's body movements and gestures to identify aggressive behavior. For example, when a waving hand or pointing gesture is detected. The behavior analysis unit also analyzes the speaker's posture and facial expression to identify any signs of negative emotion as a sign of power harassment. For example, a furrowed brow or a posture with crossed arms. The behavior analysis unit also analyzes the speaker's behavior in real time and issues a warning if aggressive behavior is continuously displayed. For example, when repeated aggressive gestures are detected. This makes it possible to analyze the speaker's behavior and detect signs of power harassment.

[0091] The power harassment detection tool may further include a context analysis unit. The context analysis unit, for example, analyzes background information and circumstances of a conversation to identify trends in the occurrence of power harassment under specific circumstances. For example, when the progress of a specific project or task is related to the occurrence of power harassment. The context analysis unit also analyzes background information of a conversation to identify whether specific events or occurrences influence the occurrence of power harassment. For example, when the timing of performance evaluations or promotions is related to the occurrence of power harassment. The context analysis unit also analyzes background information of a conversation in real time to identify trends in the occurrence of power harassment under specific circumstances. For example, when relationships with specific superiors or colleagues influence the occurrence of power harassment. In this way, background information of a conversation can be analyzed to identify trends in the occurrence of power harassment under specific circumstances.

[0092] The power harassment detection tool can further include a social network analysis unit. The social network analysis unit, for example, analyzes human relationships and communication patterns within a company to identify relationships with a high risk of power harassment. For example, it analyzes the frequency and content of communication within a specific group. The social network analysis unit also analyzes human relationships within a company to identify relationships with a high risk of power harassment when a specific person is isolated. For example, when a specific person rarely communicates with other members. The social network analysis unit also analyzes human relationships within a company in real time to identify relationships with a high risk of power harassment. For example, when the relationship between a specific superior and a subordinate is tense. This makes it possible to analyze human relationships within a company and identify relationships with a high risk of power harassment.

[0093] The power harassment detection tool may further include a feedback providing unit. The feedback providing unit provides real-time feedback to the speaker based on, for example, detected signs of power harassment. For example, the feedback providing unit may provide the speaker with feedback such as, "That comment is aggressive. Try to use more gentle language." The feedback providing unit may also suggest specific improvement measures to the speaker based on the detected signs of power harassment. For example, the feedback providing unit may provide feedback such as, "In the next meeting, try to respect the other person's opinion." The feedback providing unit may also provide feedback to the speaker encouraging positive behavior based on the detected signs of power harassment. For example, the feedback providing unit may provide feedback such as, "That comment was constructive. Let's keep it up." In this way, feedback may be provided to the speaker in real time, making it possible to prevent power harassment from occurring.

[0094] The power harassment detection tool can also use an emotion estimation function to analyze the speaker's emotions and identify signs of power harassment based on changes in emotion. For example, if a speaker suddenly shows anger, this change can be identified as a sign of power harassment. The emotion estimation function can also be used to identify signs of power harassment when the speaker's emotions are continuously negative. For example, if emotions of anger or irritation are repeatedly detected in a conversation. The emotion estimation function can also be used to identify signs of power harassment when the speaker's emotions suddenly change. For example, if a tone suddenly changes from calm to aggressive. This makes it possible to identify signs of power harassment based on changes in the speaker's emotions.

[0095] The power harassment detection tool also uses an emotion estimation function to analyze the recipient's emotions and identify signs of power harassment if the recipient is feeling negative emotions. For example, if the recipient is feeling fear or anxiety, it can identify signs of power harassment based on those emotions. The emotion estimation function can also be used to identify signs of power harassment if the recipient's emotions are continuously negative. For example, if emotions of fear or anxiety are repeatedly detected during a conversation. The emotion estimation function can also be used to identify signs of power harassment if the recipient's emotions change suddenly. For example, if a tone changes suddenly from a calm tone to one of fear or anxiety. This makes it possible to identify signs of power harassment based on changes in the recipient's emotions.

[0096] The power harassment detection tool also uses an emotion estimation function to analyze the degree of agreement between the emotions of the speaker and the receiver, and can issue a warning if a mismatch in emotions is detected as a sign of power harassment. For example, if the speaker is feeling anger while the receiver is feeling fear or anxiety, this can be identified as a sign of power harassment. The emotion estimation function can also be used to identify a significant difference in the emotions of the speaker and the receiver based on this mismatch as a sign of power harassment. For example, if the speaker speaks in an aggressive tone while the receiver is silent. The emotion estimation function can also be used to identify a persistent mismatch in emotions between the speaker and the receiver as a sign of power harassment. For example, if the speaker repeatedly speaks in an angry tone while the receiver is feeling anxious. This makes it possible to detect signs of power harassment based on a mismatch in emotions between the speaker and the receiver, and issue a warning.

[0097] The power harassment detection tool can further use an emotion estimation function to display the speaker's emotions in real time and provide feedback to elicit positive emotions. For example, a system can be built that analyzes the speaker's emotions in real time and displays the results. For example, the speaker's emotion score can be displayed on a screen. The emotion estimation function can also be used to analyze the speaker's emotions and provide feedback to elicit positive emotions. For example, positive words can be suggested if the speaker is feeling negative emotions. The emotion estimation function can also be used to display the speaker's emotions in real time and provide advice to elicit positive emotions. For example, if the speaker is feeling angry, the tool can urge them to stay calm. This makes it possible to display the speaker's emotions in real time and provide feedback to elicit positive emotions.

[0098] The power harassment detection tool also uses an emotion estimation function to simultaneously analyze the emotions of the message sender and receiver, and can issue a warning if a mismatch in emotions is detected as a sign of power harassment. For example, by simultaneously analyzing the emotions of the message sender and receiver, if the sender feels anger while the receiver feels fear or anxiety, this can be identified as a sign of power harassment. The emotion estimation function also analyzes the context of a message and, if there is a significant difference in the emotions of the sender and receiver, this can be identified as a sign of power harassment based on the mismatch. For example, if the sender sends aggressive messages while the receiver is silent. The emotion estimation function also analyzes the emotions of the message sender and receiver in real time, and if there is a continuous mismatch in emotions, this can be identified as a sign of power harassment. For example, if the sender repeatedly sends angry messages while the receiver feels anxious. This allows the tool to detect signs of power harassment based on the mismatch in emotions between the message sender and receiver, and issue a warning.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The voice analysis unit analyzes the voice data and identifies statements that may be considered power harassment. For example, statements made during meetings or everyday conversations are recorded and the audio data is input into the generation AI. The generation AI analyzes specific keywords, tone, and context, and recognizes aggressive statements such as "You're useless" and "How many times do I have to tell you" as signs of power harassment. Step 2: The text analysis unit analyzes the text data and identifies messages that may be considered power harassment. For example, the contents of internal chats or emails are input into the generation AI. The generation AI analyzes specific keywords and contexts, and recognizes aggressive messages such as "incompetent" or "quit immediately" as signs of power harassment. Step 3: The warning unit issues a warning based on the signs of power harassment identified by the voice analysis unit and text analysis unit. For example, when a statement or message that may be power harassment is detected, a warning message such as "This statement may be power harassment. Please be careful" is sent to the relevant person. Step 4: The Notification Department notifies the superior or the human resources department based on the warning issued by the Warning Department. For example, if a remark or message that may be power harassment is detected, the notification will be sent to the superior or the human resources department with a message such as, "Mr. / Ms. XX made an offensive remark to Mr. / Ms. △△. Details are as follows."

[0101] 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.

[0102] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0103] 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.

[0104] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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).

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0114] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0120] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0129] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0135] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0145] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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."

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0168] 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 system that uses generative AI to detect signs of power harassment and automatically take appropriate action. a voice analysis unit that analyzes the voice data and identifies the remarks that may be power harassment; a text analysis unit that analyzes text data and identifies messages that may be power harassment; a warning unit that issues a warning based on the signs of power harassment identified by the voice analysis unit and the text analysis unit; a notification unit that notifies a superior or a human resources department based on the warning issued by the warning unit. A system characterized by:

2. The voice analysis unit Analyze the speaker's tone of voice or emotion in real time and identify signs of power harassment based on changes in emotion.

2. The system of claim 1.

3. The voice analysis unit The background sounds of conversations and environmental sounds are also analyzed to identify the tendency for the power harassment to occur in specific environments.

2. The system of claim 1.

4. The text analysis unit View past email and chat history to analyze the frequency of specific keywords 2. The system of claim 1.

5. The warning unit The warning message content is customized based on past cases of power harassment, providing more specific advice.

2. The system of claim 1.

6. The notification unit Customize notifications based on past cases of power harassment to provide more specific advice 2. The system of claim 1.

7. The text analysis unit Sentiment analysis of the text data is performed, and messages with strong negative sentiment are preferentially detected.

2. The system of claim 1.

8. The warning unit Optimizing the timing of issuing the warning based on changes in the sentiment of the utterance and the message.

2. The system of claim 1.

Images